Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b8098c4096
|
@@ -105,11 +105,6 @@ jobs:
|
||||
echo "commit_timestamp=${COMMIT_TIMESTAMP}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- id: changes
|
||||
env:
|
||||
# The push's own range. Empty on workflow_dispatch and all
|
||||
# zeroes for a new branch; `decide` treats both as unusable and
|
||||
# falls back to the full gate.
|
||||
PUSH_BEFORE: ${{ github.event.before }}
|
||||
run: |
|
||||
set -ux
|
||||
# Default: build everything. Detection only ever narrows
|
||||
@@ -194,30 +189,9 @@ jobs:
|
||||
BUILD_TOOLS=$(decide "$TOOLS_BASE" "$TOOLS_RE")
|
||||
BUILD_ANGELS=$(decide "$ANGELS_BASE" "$ANGELS_RE")
|
||||
if [ "$BUILD_CORTEX" = "true" ] || [ "$BUILD_NEURON" = "true" ] || [ "$BUILD_BENCH" = "true" ] || [ "$BUILD_UPSTREAM" = "true" ] || [ "$BUILD_ROUTER" = "true" ] || [ "$BUILD_TOOLS" = "true" ] || [ "$BUILD_ANGELS" = "true" ]; then
|
||||
# Anything we are about to build gets linted and tested.
|
||||
# This is the invariant that matters: no artefact reaches
|
||||
# the fleet unchecked, however the branch below behaves.
|
||||
CHECK_RUST=true
|
||||
else
|
||||
# Nothing is being built, so nothing will be published.
|
||||
# The only question left is whether THIS PUSH touched
|
||||
# Rust — and the honest base for that is the push's own
|
||||
# range, not a package's publication lag.
|
||||
#
|
||||
# This used to ask "has anything Rust changed since
|
||||
# cortex was last published". Cortex is only rebuilt when
|
||||
# cortex paths change, so after a run of neuron-only work
|
||||
# its base sits days behind and the diff from it sweeps in
|
||||
# every unrelated Rust commit since. A one-character
|
||||
# whitespace fix to a doc then re-ran fmt, clippy and the
|
||||
# full test suite over a delta that had already been
|
||||
# linted on the branch that introduced it (2026-08-18,
|
||||
# base fec5b33).
|
||||
#
|
||||
# `decide` returns true for an unusable base, so a new
|
||||
# branch (all-zero before-sha) or a force-push still gets
|
||||
# the full gate.
|
||||
CHECK_RUST=$(decide "$PUSH_BEFORE" "$RUST_RE")
|
||||
CHECK_RUST=$(decide "$CORTEX_BASE" "$RUST_RE")
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
@@ -262,7 +236,7 @@ jobs:
|
||||
# fast instead of triggering a slower uncached rebuild; only a real
|
||||
# sccache fault drops the cache. See script/ci-cargo-escalate.sh.
|
||||
- name: Clippy (sccache escalation)
|
||||
run: script/ci-cargo-escalate.sh cargo clippy --workspace --all-targets -- -D warnings
|
||||
run: script/ci-cargo-escalate.sh cargo clippy --workspace -- -D warnings
|
||||
|
||||
test:
|
||||
name: Test
|
||||
|
||||
+10
-105
@@ -39,34 +39,24 @@ env:
|
||||
CARGO_TARGET_DIR: target-${{ github.job }}
|
||||
|
||||
jobs:
|
||||
# Two independent questions: does this change need the Rust gate, and
|
||||
# does it need the web gate.
|
||||
#
|
||||
# The SPA under helexa.ai/ is built and shipped by its own deploy job and
|
||||
# is not read by any crate, build script or spec file — so a change
|
||||
# confined to it cannot alter a Rust result. Waiting up to 70 minutes for
|
||||
# a CUDA type-check to prove that is pure latency, and the wait is what
|
||||
# tempts people to merge front-end work unchecked. Documentation is inert
|
||||
# the same way, and more obviously: no crate `include_str!`s a markdown
|
||||
# file, no spec packages `doc/`, no build script reads one.
|
||||
# tempts people to merge front-end work unchecked.
|
||||
#
|
||||
# Conversely a Rust-only change cannot break the SPA, so it need not
|
||||
# spend three minutes on `npm ci` + lint + typecheck + build.
|
||||
#
|
||||
# The classification stays deliberately one-directional: it only ever
|
||||
# narrows the gate when *every* changed path is known-inert, and every
|
||||
# The classification is deliberately one-directional: it only ever
|
||||
# narrows the gate when *every* changed path is front-end, and every
|
||||
# other outcome — a tag, an unknown base, an empty diff, a mixed
|
||||
# changeset — falls through to the full gate. A new top-level directory
|
||||
# is therefore covered on the day it appears, without anyone
|
||||
# remembering to add it here. Adding an inert pattern is the only way to
|
||||
# widen what gets skipped, which is the property worth keeping.
|
||||
# remembering to add it here.
|
||||
changes:
|
||||
name: Classify changes
|
||||
timeout-minutes: 10
|
||||
runs-on: fedora-43
|
||||
outputs:
|
||||
rust: ${{ steps.classify.outputs.rust }}
|
||||
web: ${{ steps.classify.outputs.web }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
@@ -74,12 +64,7 @@ jobs:
|
||||
- id: classify
|
||||
run: |
|
||||
set -u
|
||||
full() {
|
||||
echo "→ full gate: $1"
|
||||
echo "rust=true" >> "$GITHUB_OUTPUT"
|
||||
echo "web=true" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
}
|
||||
full() { echo "→ full gate: $1"; echo "rust=true" >> "$GITHUB_OUTPUT"; exit 0; }
|
||||
|
||||
# Tags build the SRPMs from the whole tree, and the srpm jobs
|
||||
# gate on fmt/clippy/test/cuda-check. Never narrow there.
|
||||
@@ -101,51 +86,11 @@ jobs:
|
||||
echo "changed files:"
|
||||
printf '%s\n' "${files}" | sed 's/^/ /'
|
||||
|
||||
# Inert for Rust: the SPA, documentation, and fleet config.
|
||||
# Markdown is matched only at the repo root and under doc/ — a
|
||||
# .md inside crates/ is left to fall through, since
|
||||
# `include_str!` could make one load-bearing without this file
|
||||
# knowing.
|
||||
#
|
||||
# Fleet config (models.toml, asset/neuron/<host>.toml,
|
||||
# asset/helexa-bench/<host>.toml) is read by a *running*
|
||||
# daemon, never by a build script or an `include_str!`, so it
|
||||
# cannot change a Rust result. Deploying one is a config rsync
|
||||
# plus a service restart — neuron re-reads it and reloads the
|
||||
# model — so spending ~25 minutes on fmt, clippy, test and a
|
||||
# CUDA type-check to prove a one-line TOML edit compiles is
|
||||
# pure latency (#291).
|
||||
#
|
||||
# The `config` job below stays ungated and still validates
|
||||
# these files, so narrowing here removes the meritless work
|
||||
# without removing the check that matters. build-prerelease
|
||||
# already reaches the same conclusion on main: none of its
|
||||
# per-package path regexes match these files, so a config-only
|
||||
# push builds no binaries.
|
||||
rust_relevant="$(printf '%s\n' "${files}" \
|
||||
| grep -v '^helexa\.ai/' \
|
||||
| grep -v '^doc/' \
|
||||
| grep -vE '^[^/]+\.md$' \
|
||||
| grep -vE '^asset/neuron/[^/]+\.toml$' \
|
||||
| grep -vE '^asset/helexa-bench/[^/]+\.toml$' \
|
||||
| grep -vE '^models\.toml$' \
|
||||
|| true)"
|
||||
if [ -n "${rust_relevant}" ]; then
|
||||
echo "rust=true" >> "$GITHUB_OUTPUT"
|
||||
echo "→ Rust gate: required"
|
||||
else
|
||||
echo "rust=false" >> "$GITHUB_OUTPUT"
|
||||
echo "→ Rust gate: skipped (front-end and/or docs only)"
|
||||
fi
|
||||
other="$(printf '%s\n' "${files}" | grep -v '^helexa\.ai/' || true)"
|
||||
[ -z "${other}" ] || full "changes outside helexa.ai/"
|
||||
|
||||
# The web gate is needed only when the SPA itself changed.
|
||||
if printf '%s\n' "${files}" | grep -q '^helexa\.ai/'; then
|
||||
echo "web=true" >> "$GITHUB_OUTPUT"
|
||||
echo "→ web gate: required"
|
||||
else
|
||||
echo "web=false" >> "$GITHUB_OUTPUT"
|
||||
echo "→ web gate: skipped (nothing under helexa.ai/)"
|
||||
fi
|
||||
echo "→ front-end only: skipping the Rust gate"
|
||||
echo "rust=false" >> "$GITHUB_OUTPUT"
|
||||
|
||||
fmt:
|
||||
name: Format
|
||||
@@ -157,39 +102,10 @@ jobs:
|
||||
- uses: actions/checkout@v4
|
||||
- run: cargo fmt --check --all
|
||||
|
||||
# models.toml and asset/neuron/<host>.toml both describe how a model is
|
||||
# served, and until #283 nothing forced them to agree. #252 is the bill
|
||||
# for that: models.toml omitted `quant`, so a cortex cold-load served
|
||||
# bf16 and could not prefill, while the same model was fine when the
|
||||
# host loaded it from its own config. The sampling override (#283) is a
|
||||
# second field with the same hazard, so the gate lands with it.
|
||||
#
|
||||
# Deliberately ungated by the `changes` classifier: it is a
|
||||
# sub-second Python run with no build, and the whole point is that it
|
||||
# cannot be skipped on the push that introduces the drift. A config
|
||||
# change is neither `rust` nor `web`, so gating it on either would let
|
||||
# a pure-TOML push through unchecked — precisely the push that breaks
|
||||
# this.
|
||||
config:
|
||||
name: Config consistency
|
||||
timeout-minutes: 5
|
||||
runs-on: fedora-43
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- run: python3 script/check-config-consistency.py
|
||||
# Two files describe one routing decision and nothing forced them
|
||||
# to agree. On 2026-08-27 the router still aliased
|
||||
# `helexa/balanced` to a model retired from the catalogue, so
|
||||
# every web-chat turn evicted beast's resident flagship to
|
||||
# cold-load it. Same shape as the check above (#252/#287).
|
||||
- run: python3 script/check-alias-targets.py
|
||||
|
||||
web:
|
||||
name: Web (lint + typecheck + i18n + build)
|
||||
timeout-minutes: 20
|
||||
runs-on: fedora-43
|
||||
needs: changes
|
||||
if: needs.changes.outputs.web == 'true'
|
||||
defaults:
|
||||
run:
|
||||
working-directory: helexa.ai
|
||||
@@ -205,12 +121,6 @@ jobs:
|
||||
# reached main exactly that way.
|
||||
- run: npm run lint
|
||||
- run: npm run typecheck
|
||||
# Behaviour, not just types. Gating from the first commit was the
|
||||
# deliberate call (#304): with no existing suite there is nothing to
|
||||
# stabilise, so a warn-first period would only create a window in
|
||||
# which a vacuous test lands and gets normalised — and a suite
|
||||
# nobody trusts is worse than none, because it gets cited.
|
||||
- run: npm test
|
||||
# 42 locales with strict key parity is a promise that breaks
|
||||
# quietly. Adding an English string without translating it must fail
|
||||
# here, not in review, and certainly not in front of somebody
|
||||
@@ -232,13 +142,8 @@ jobs:
|
||||
# in sync with build-prerelease.yml): a signal death (rustc SIGSEGV
|
||||
# / OOM-kill) keeps the cache and fails fast instead of an uncached
|
||||
# rebuild; only a real sccache fault drops the cache.
|
||||
# --all-targets so `#[cfg(test)]` modules, tests/, benches/ and
|
||||
# examples/ are linted too (#286). Without it clippy sees only lib
|
||||
# and bin targets, so `-D warnings` never gated a single line of
|
||||
# test code — which is how two tests lost their `#[test]` attribute
|
||||
# and stopped running unnoticed.
|
||||
- name: Clippy (sccache escalation)
|
||||
run: script/ci-cargo-escalate.sh cargo clippy --workspace --all-targets -- -D warnings
|
||||
run: script/ci-cargo-escalate.sh cargo clippy --workspace -- -D warnings
|
||||
|
||||
test:
|
||||
name: Test
|
||||
|
||||
+18
-426
@@ -37,37 +37,7 @@ env:
|
||||
${{ secrets.RSYNC_SSH_KEY }}
|
||||
|
||||
jobs:
|
||||
# Gate the whole rollout on the two config files agreeing about every
|
||||
# model they both describe. models.toml (cortex, cold loads) and
|
||||
# asset/neuron/<host>.toml (resident models) each say how a model is
|
||||
# served — quant, and since #283 the sampling override. When they
|
||||
# disagree the model is served one way cold and another way resident,
|
||||
# which is #252.
|
||||
#
|
||||
# Deliberately a *gate*, not a step inside deploy-cortex: an
|
||||
# inconsistent pair must stop the neuron rollout too, and stopping it
|
||||
# before anything restarts is much cheaper than after (a beast restart
|
||||
# costs ~5-6 min of 27B cold-load).
|
||||
config-check:
|
||||
name: Config consistency
|
||||
runs-on: fedora-43
|
||||
if: >-
|
||||
${{
|
||||
github.event_name == 'workflow_dispatch'
|
||||
|| github.event.workflow_run.conclusion == 'success'
|
||||
}}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- run: python3 script/check-config-consistency.py
|
||||
# Two files describe one routing decision and nothing forced them
|
||||
# to agree. On 2026-08-27 the router still aliased
|
||||
# `helexa/balanced` to a model retired from the catalogue, so
|
||||
# every web-chat turn evicted beast's resident flagship to
|
||||
# cold-load it. Same shape as the check above (#252/#287).
|
||||
- run: python3 script/check-alias-targets.py
|
||||
|
||||
deploy-cortex:
|
||||
needs: [config-check]
|
||||
runs-on: fedora-43
|
||||
# Two trigger paths: manual dispatch always runs; workflow_run
|
||||
# only runs if the upstream `build-prerelease` actually succeeded.
|
||||
@@ -77,7 +47,6 @@ jobs:
|
||||
|| github.event.workflow_run.conclusion == 'success'
|
||||
}}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: SSH init
|
||||
run: |
|
||||
mkdir -p ~/.ssh
|
||||
@@ -96,33 +65,6 @@ jobs:
|
||||
echo "inv=$(ssh gitea_ci@hanzalova.internal \
|
||||
'systemctl show -P InvocationID cortex.service' || true)" >> "$GITHUB_OUTPUT"
|
||||
|
||||
# The catalogue is tracked (#283) precisely so it can be rolled out
|
||||
# here rather than hand-copied. Sync it *before* the package step,
|
||||
# so the restart that step performs is the one that picks it up —
|
||||
# and report whether it changed, because a catalogue edit with no
|
||||
# new RPM must still restart cortex or the change never takes
|
||||
# effect.
|
||||
#
|
||||
# Compared by digest rather than rsync's own change detection so the
|
||||
# answer is available to the shell that decides on the restart.
|
||||
- name: Sync gateway catalogue (models.toml)
|
||||
id: catalogue
|
||||
run: |
|
||||
local_sum=$(sha256sum models.toml | cut -d' ' -f1)
|
||||
remote_sum=$(ssh gitea_ci@hanzalova.internal \
|
||||
'sha256sum /etc/cortex/models.toml 2>/dev/null | cut -d" " -f1' || true)
|
||||
if [ "${local_sum}" = "${remote_sum}" ]; then
|
||||
echo "changed=0" >> "$GITHUB_OUTPUT"
|
||||
echo "models.toml unchanged (${local_sum})"
|
||||
else
|
||||
rsync --archive --compress \
|
||||
--chown root:root --chmod 0644 \
|
||||
--rsync-path 'sudo rsync' \
|
||||
models.toml gitea_ci@hanzalova.internal:/etc/cortex/models.toml
|
||||
echo "changed=1" >> "$GITHUB_OUTPUT"
|
||||
echo "models.toml updated: ${remote_sum:-<absent>} -> ${local_sum}"
|
||||
fi
|
||||
|
||||
# Gating compares `rpm -q` against the packages.json manifest the
|
||||
# publish job maintains — NOT unprivileged `dnf check-update`,
|
||||
# which proved unreliable as the gitea_ci user (hung on metadata
|
||||
@@ -133,11 +75,6 @@ jobs:
|
||||
ssh gitea_ci@hanzalova.internal 'bash -s' <<'DEPLOY'
|
||||
set -eu
|
||||
pkg=cortex
|
||||
# Default to 0 if the sync step somehow produced no output:
|
||||
# `set -u` plus `[ "" -eq 0 ]` would abort the deploy on an
|
||||
# arithmetic error rather than on anything meaningful.
|
||||
config_changed="${{ steps.catalogue.outputs.changed }}"
|
||||
config_changed="${config_changed:-0}"
|
||||
# `rpm -q` prints "package X is not installed" on STDOUT and exits
|
||||
# 1, so `|| echo not-installed` never fires — it captures the
|
||||
# message text instead. Test the exit code.
|
||||
@@ -153,31 +90,18 @@ jobs:
|
||||
p = max(cands, key=lambda p: p.get("buildTime", 0))
|
||||
print(p["version"] + "-" + p["release"])
|
||||
' "${pkg}" 2>/dev/null || true)
|
||||
# Skip only when BOTH the package and the catalogue are
|
||||
# unchanged — a models.toml edit (a new sampling override, a
|
||||
# corrected quant) must restart cortex even with no new RPM,
|
||||
# exactly as the neuron drop-in does below.
|
||||
if [ -n "${latest}" ] && [ "${latest}" = "${installed}" ] \
|
||||
&& [ "${config_changed}" -eq 0 ]; then
|
||||
echo "${pkg}-${installed} already current; models.toml unchanged — leaving service untouched"
|
||||
if [ -n "${latest}" ] && [ "${latest}" = "${installed}" ]; then
|
||||
echo "${pkg}-${installed} already current — leaving service untouched"
|
||||
exit 0
|
||||
fi
|
||||
pkg_changed=1
|
||||
if [ -n "${latest}" ] && [ "${latest}" = "${installed}" ]; then
|
||||
pkg_changed=0
|
||||
fi
|
||||
echo "installed=${installed} published=${latest:-unknown} pkg_changed=${pkg_changed} config_changed=${config_changed} — deploying"
|
||||
echo "installed=${installed} published=${latest:-unknown} — deploying"
|
||||
if systemctl is-active --quiet cortex.service; then
|
||||
sudo /usr/bin/systemctl stop cortex.service
|
||||
fi
|
||||
# A catalogue-only change still restarts, but must not spend a
|
||||
# dnf metadata refresh proving the package is already current.
|
||||
if [ "${pkg_changed}" -eq 1 ]; then
|
||||
if rpm -q "${pkg}" >/dev/null 2>&1; then
|
||||
sudo /usr/bin/dnf upgrade --refresh --allowerasing -y cortex
|
||||
else
|
||||
sudo /usr/bin/dnf install --refresh --allowerasing -y cortex
|
||||
fi
|
||||
if rpm -q "${pkg}" >/dev/null 2>&1; then
|
||||
sudo /usr/bin/dnf upgrade --refresh --allowerasing -y cortex
|
||||
else
|
||||
sudo /usr/bin/dnf install --refresh --allowerasing -y cortex
|
||||
fi
|
||||
sudo /usr/bin/systemctl daemon-reload
|
||||
# enable --now: start the service AND enable it for boot so the
|
||||
@@ -218,7 +142,7 @@ jobs:
|
||||
CAPTURE
|
||||
|
||||
deploy-neurons:
|
||||
needs: [config-check, deploy-cortex]
|
||||
needs: [deploy-cortex]
|
||||
runs-on: fedora-43
|
||||
strategy:
|
||||
# One neuron failing must not cancel the others. Cortex is up
|
||||
@@ -253,7 +177,6 @@ jobs:
|
||||
load_timeout: 300
|
||||
max_prompt_tokens: 16384
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: SSH init
|
||||
run: |
|
||||
mkdir -p ~/.ssh
|
||||
@@ -269,42 +192,6 @@ jobs:
|
||||
echo "inv=$(ssh gitea_ci@${{ matrix.host }} \
|
||||
'systemctl show -P InvocationID neuron.service' || true)" >> "$GITHUB_OUTPUT"
|
||||
|
||||
# asset/neuron/<short>.toml is this host's neuron.toml. It carries
|
||||
# the resident-model specs — including the #283 sampling override,
|
||||
# which is inert until the daemon reloads the model, so a change
|
||||
# here has to restart the neuron the same way the context-cap
|
||||
# drop-in does.
|
||||
#
|
||||
# Synced before the package step so the restart that step performs
|
||||
# is the one that picks it up. Digest-compared rather than trusting
|
||||
# rsync's own change detection, because the restart decision needs
|
||||
# the answer and a needless neuron restart costs ~5-6 min of 27B
|
||||
# cold-load (#1).
|
||||
- name: Sync neuron config (${{ matrix.host }})
|
||||
id: neuronconf
|
||||
run: |
|
||||
short="${{ matrix.host }}"; short="${short%%.*}"
|
||||
src="asset/neuron/${short}.toml"
|
||||
if [ ! -f "${src}" ]; then
|
||||
echo "changed=0" >> "$GITHUB_OUTPUT"
|
||||
echo "no ${src} in the repo — leaving this host's config alone"
|
||||
exit 0
|
||||
fi
|
||||
local_sum=$(sha256sum "${src}" | cut -d' ' -f1)
|
||||
remote_sum=$(ssh gitea_ci@${{ matrix.host }} \
|
||||
'sha256sum /etc/neuron/neuron.toml 2>/dev/null | cut -d" " -f1' || true)
|
||||
if [ "${local_sum}" = "${remote_sum}" ]; then
|
||||
echo "changed=0" >> "$GITHUB_OUTPUT"
|
||||
echo "${src} unchanged (${local_sum})"
|
||||
else
|
||||
rsync --archive --compress \
|
||||
--chown root:root --chmod 0644 \
|
||||
--rsync-path 'sudo rsync' \
|
||||
"${src}" gitea_ci@${{ matrix.host }}:/etc/neuron/neuron.toml
|
||||
echo "changed=1" >> "$GITHUB_OUTPUT"
|
||||
echo "${src} updated: ${remote_sum:-<absent>} -> ${local_sum}"
|
||||
fi
|
||||
|
||||
# See deploy-cortex for why gating uses the publish manifest and
|
||||
# not unprivileged `dnf check-update`.
|
||||
- name: Deploy helexa-neuron-${{ matrix.flavour }} (skips when already current)
|
||||
@@ -313,9 +200,6 @@ jobs:
|
||||
set -eu
|
||||
pkg=helexa-neuron-${{ matrix.flavour }}
|
||||
max_prompt_tokens="${{ matrix.max_prompt_tokens }}"
|
||||
# A neuron.toml change counts as a config change for the
|
||||
# restart decision below, exactly like the drop-in.
|
||||
neuron_toml_changed="${{ steps.neuronconf.outputs.changed }}"
|
||||
|
||||
# ── Desired per-model systemd drop-in ─────────────────────────
|
||||
# model.conf carries NEURON_MAX_PROMPT_TOKENS so the context cap
|
||||
@@ -324,7 +208,7 @@ jobs:
|
||||
# deploy-managed value wins over any manual local override of the
|
||||
# same variable. See doc/context-limits.md.
|
||||
conf=/etc/systemd/system/neuron.service.d/model.conf
|
||||
config_changed=${neuron_toml_changed:-0}
|
||||
config_changed=0
|
||||
if [ -n "${max_prompt_tokens}" ]; then
|
||||
desired=$(printf '%s\n%s\n%s\n%s' \
|
||||
"# Managed by .gitea/workflows/deploy.yml - do not edit by hand." \
|
||||
@@ -358,17 +242,13 @@ jobs:
|
||||
# Skip only when BOTH the package and the drop-in are unchanged —
|
||||
# a context-cap change must restart the neuron even with no new RPM.
|
||||
if [ "${pkg_changed}" -eq 0 ] && [ "${config_changed}" -eq 0 ]; then
|
||||
echo "${pkg}-${installed} current; NEURON_MAX_PROMPT_TOKENS=${max_prompt_tokens:-<unset>} and neuron.toml unchanged — leaving service untouched"
|
||||
echo "${pkg}-${installed} current; NEURON_MAX_PROMPT_TOKENS=${max_prompt_tokens:-<unset>} unchanged — leaving service untouched"
|
||||
exit 0
|
||||
fi
|
||||
echo "installed=${installed} published=${latest:-unknown} pkg_changed=${pkg_changed} config_changed=${config_changed} — deploying"
|
||||
|
||||
# Write the drop-in (staged in gitea_ci's dir, installed root-owned).
|
||||
# Guarded on max_prompt_tokens as well as config_changed: since
|
||||
# a neuron.toml change also sets config_changed, an entry with
|
||||
# no max_prompt_tokens would otherwise reach this with `desired`
|
||||
# unset.
|
||||
if [ "${config_changed}" -eq 1 ] && [ -n "${max_prompt_tokens}" ]; then
|
||||
if [ "${config_changed}" -eq 1 ]; then
|
||||
printf '%s\n' "${desired}" > /var/lib/gitea_ci/model.conf
|
||||
sudo /usr/bin/install -o root -g root -m 0644 -D /var/lib/gitea_ci/model.conf "${conf}"
|
||||
rm -f /var/lib/gitea_ci/model.conf
|
||||
@@ -532,161 +412,6 @@ jobs:
|
||||
# dependency on cortex or the neurons (the sweep loop is version-aware
|
||||
# and picks up whatever each neuron reports whenever). So it runs
|
||||
# alongside the cortex→neurons chain rather than after it.
|
||||
# The vhost sync gets its own job, with NO `needs`, because it is not
|
||||
# part of deploying the gateway binary and must not be able to stop
|
||||
# one.
|
||||
#
|
||||
# It was briefly a step inside deploy-cortex, and that broke the fleet
|
||||
# on its first run (2026-08-27, run 1284): the step hard-fails until an
|
||||
# operator has run script/infra-setup.sh to install its sudoers grant,
|
||||
# a failed step fails the job, and `deploy-neurons` has
|
||||
# `needs: [deploy-cortex]` — so a missing nginx permission silently
|
||||
# skipped the rollout of all three neuron flavours. The fleet stayed
|
||||
# two commits behind while the run reported only "deploy-cortex:
|
||||
# failure".
|
||||
#
|
||||
# #287 names this ordering trap. The lesson is narrower than "order the
|
||||
# steps": a step whose prerequisite is installed by hand does not
|
||||
# belong in a job that something else depends on, because its failure
|
||||
# is not a statement about that job. Moving it later within
|
||||
# deploy-cortex would not have helped — the job still ends red and the
|
||||
# dependents still skip.
|
||||
#
|
||||
# Failing hard here is still right: drift between the repo and the live
|
||||
# file is a real defect, and this job going red says that and nothing
|
||||
# else.
|
||||
deploy-nginx:
|
||||
runs-on: fedora-43
|
||||
if: >-
|
||||
${{
|
||||
github.event_name == 'workflow_dispatch'
|
||||
|| github.event.workflow_run.conclusion == 'success'
|
||||
}}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: SSH init
|
||||
run: |
|
||||
mkdir -p ~/.ssh
|
||||
echo "${DEPLOY_KEY}" > ~/.ssh/id_ed25519
|
||||
chmod 600 ~/.ssh/id_ed25519
|
||||
ssh -o ConnectTimeout=5 -o StrictHostKeyChecking=accept-new \
|
||||
gitea_ci@hanzalova.internal 'hostname -f'
|
||||
|
||||
# nginx vhost config for the internal site. Version-controlled in
|
||||
# `asset/nginx/` since the beginning, but until now only ever
|
||||
# installed by `script/infra-setup.sh` — a one-time, run-by-hand
|
||||
# script. So the repo copy and the live file could diverge with
|
||||
# nothing to detect it, which is the #252 shape: two sources of
|
||||
# truth for one thing and nothing forcing agreement.
|
||||
#
|
||||
# Writes to sites-available and (re)points sites-enabled at it as
|
||||
# a symlink. On this host sites-enabled was a *regular file*, not a
|
||||
# symlink — two independent copies, of which nginx reads one. An
|
||||
# operator editing "the config" would reasonably edit
|
||||
# sites-available, watch `nginx -t` pass, reload, and see nothing
|
||||
# change. Making the link canonical is part of the sync rather
|
||||
# than a separate chore, so the layout cannot drift back.
|
||||
#
|
||||
# `nginx -t` gates the reload: a config that fails validation is
|
||||
# left un-reloaded with the previous one still serving.
|
||||
- name: Sync internal nginx vhost
|
||||
run: |
|
||||
src="asset/nginx/helexa.internal.conf"
|
||||
|
||||
# The sudoers drop-in that permits this is installed by
|
||||
# script/infra-setup.sh, which is run by hand, so the live copy
|
||||
# can lag the repo by however long it has been since anyone ran
|
||||
# it. Check EVERY grant the step needs, not a representative
|
||||
# one: the first version of this preflight tested `nginx -t`
|
||||
# alone, which had existed for ages, so it passed and the job
|
||||
# then died on the two helexa-ratelimit.conf grants added in the
|
||||
# same commit as the check. A preflight that names a remedy
|
||||
# while probing the wrong permission is worse than none — it
|
||||
# tells you the sudoers are fine seconds before they are not.
|
||||
#
|
||||
# Each probe runs the command in a harmless form that still
|
||||
# matches its sudoers pattern (sha256sum reads; nginx -t and
|
||||
# `systemctl show` do not mutate). rsync and ln have no such
|
||||
# form, so they are checked with `sudo -nl`, which reports
|
||||
# whether a command is permitted without running it.
|
||||
missing=""
|
||||
probe() { # probe <description> <command...>
|
||||
local what="$1"; shift
|
||||
ssh gitea_ci@hanzalova.internal "$@" >/dev/null 2>&1 \
|
||||
|| missing="${missing}
|
||||
- ${what}"
|
||||
}
|
||||
probe "nginx -t" \
|
||||
'sudo -n /usr/sbin/nginx -t'
|
||||
probe "sha256sum /etc/nginx/sites-available/helexa.internal.conf" \
|
||||
'sudo -n /usr/bin/sha256sum /etc/nginx/sites-available/helexa.internal.conf'
|
||||
probe "sha256sum /etc/nginx/conf.d/helexa-ratelimit.conf" \
|
||||
'sudo -n /usr/bin/sha256sum /etc/nginx/conf.d/helexa-ratelimit.conf'
|
||||
probe "rsync -> /etc/nginx/sites-available/helexa.internal.conf" \
|
||||
'sudo -nl /usr/bin/rsync -a x /etc/nginx/sites-available/helexa.internal.conf'
|
||||
probe "rsync -> /etc/nginx/conf.d/helexa-ratelimit.conf" \
|
||||
'sudo -nl /usr/bin/rsync -a x /etc/nginx/conf.d/helexa-ratelimit.conf'
|
||||
probe "ln -sfn sites-available -> sites-enabled" \
|
||||
'sudo -nl /usr/bin/ln -sfn /etc/nginx/sites-available/helexa.internal.conf /etc/nginx/sites-enabled/helexa.internal.conf'
|
||||
probe "systemctl reload nginx" \
|
||||
'sudo -nl /usr/bin/systemctl reload nginx'
|
||||
|
||||
if [ -n "${missing}" ]; then
|
||||
echo "FAIL: gitea_ci is missing nginx sudoers grants on hanzalova:${missing}" >&2
|
||||
echo "" >&2
|
||||
echo " Re-run 'script/infra-setup.sh' once from an operator shell to" >&2
|
||||
echo " install the current asset/sudoers.d/cortex-host.conf. Having run" >&2
|
||||
echo " it before is not enough — grants are added to that file as deploy" >&2
|
||||
echo " steps grow, and the host keeps whatever revision it last saw." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
rl="asset/nginx/helexa-ratelimit.conf"
|
||||
local_sum=$(sha256sum "${src}" | cut -d' ' -f1)
|
||||
local_rl=$(sha256sum "${rl}" | cut -d' ' -f1)
|
||||
remote_sum=$(ssh gitea_ci@hanzalova.internal \
|
||||
'sudo sha256sum /etc/nginx/sites-available/helexa.internal.conf 2>/dev/null | cut -d" " -f1' || true)
|
||||
remote_rl=$(ssh gitea_ci@hanzalova.internal \
|
||||
'sudo sha256sum /etc/nginx/conf.d/helexa-ratelimit.conf 2>/dev/null | cut -d" " -f1' || true)
|
||||
link_ok=$(ssh gitea_ci@hanzalova.internal \
|
||||
'test -L /etc/nginx/sites-enabled/helexa.internal.conf && echo yes || echo no')
|
||||
|
||||
if [ "${local_sum}" = "${remote_sum}" ] \
|
||||
&& [ "${local_rl}" = "${remote_rl}" ] \
|
||||
&& [ "${link_ok}" = "yes" ]; then
|
||||
echo "nginx config unchanged, sites-enabled is a symlink — nothing to do"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Order matters: the vhost references names defined at http
|
||||
# context by helexa-ratelimit.conf (`limit_req_zone`s and the
|
||||
# `helexa_noquery` log format). Ship that first, or a vhost
|
||||
# referencing a not-yet-installed name fails `nginx -t` and the
|
||||
# deploy stops with the two files out of step.
|
||||
echo "syncing nginx rate-limit/log-format: ${remote_rl:-<absent>} -> ${local_rl}"
|
||||
rsync --archive --compress \
|
||||
--chown root:root --chmod 0644 \
|
||||
--rsync-path 'sudo rsync' \
|
||||
"${rl}" gitea_ci@hanzalova.internal:/etc/nginx/conf.d/helexa-ratelimit.conf
|
||||
|
||||
echo "syncing nginx vhost: ${remote_sum:-<absent>} -> ${local_sum} (symlink=${link_ok})"
|
||||
rsync --archive --compress \
|
||||
--chown root:root --chmod 0644 \
|
||||
--rsync-path 'sudo rsync' \
|
||||
"${src}" gitea_ci@hanzalova.internal:/etc/nginx/sites-available/helexa.internal.conf
|
||||
|
||||
ssh gitea_ci@hanzalova.internal 'bash -s' <<'NGINX'
|
||||
set -eu
|
||||
sudo /usr/bin/ln -sfn /etc/nginx/sites-available/helexa.internal.conf \
|
||||
/etc/nginx/sites-enabled/helexa.internal.conf
|
||||
if ! sudo /usr/sbin/nginx -t; then
|
||||
echo "FAIL: nginx -t rejected the synced config; not reloading" >&2
|
||||
exit 1
|
||||
fi
|
||||
sudo /usr/bin/systemctl reload nginx
|
||||
echo "nginx reloaded"
|
||||
NGINX
|
||||
|
||||
# Roll helexa-router + helexa-upstream onto the federation service host
|
||||
# (gallumbits). Same manifest-gated dnf pattern as deploy-cortex; the
|
||||
# two services are independent daemons on one host, so one job handles
|
||||
@@ -700,10 +425,6 @@ jobs:
|
||||
|| github.event.workflow_run.conclusion == 'success'
|
||||
}}
|
||||
steps:
|
||||
# Needed since "Sync router config" reads helexa-router.toml out of
|
||||
# the tree. This job managed without a checkout while it only ran
|
||||
# package upgrades over ssh.
|
||||
- uses: actions/checkout@v4
|
||||
- name: SSH init
|
||||
run: |
|
||||
mkdir -p ~/.ssh
|
||||
@@ -771,96 +492,6 @@ jobs:
|
||||
done
|
||||
DEPLOY
|
||||
|
||||
# Router config (#287). Tracked because it holds no secrets, and
|
||||
# synced here because being untracked is what let its
|
||||
# `helexa/balanced` alias keep pointing at a retired model until
|
||||
# beast fell over on 2026-08-27.
|
||||
#
|
||||
# After the package step, deliberately: this needs a sudoers grant
|
||||
# installed by the hand-run script/infra-setup.sh, so on a host that
|
||||
# has not seen the current grants it fails — and a step that fails
|
||||
# before the package work would hold the service binaries hostage to
|
||||
# an unrelated permission. deploy-gallumbits has no dependent jobs,
|
||||
# so the blast radius stops here either way.
|
||||
#
|
||||
# Restarts only on a digest change: the router re-reads its aliases
|
||||
# at startup, and a needless restart drops in-flight federation
|
||||
# requests.
|
||||
- name: Sync router config
|
||||
run: |
|
||||
missing=""
|
||||
probe() {
|
||||
local what="$1"; shift
|
||||
ssh gitea_ci@gallumbits.kosherinata.internal "$@" >/dev/null 2>&1 \
|
||||
|| missing="${missing}
|
||||
- ${what}"
|
||||
}
|
||||
probe "sha256sum /etc/helexa-router/helexa-router.toml" \
|
||||
'sudo -n /usr/bin/sha256sum /etc/helexa-router/helexa-router.toml'
|
||||
probe "rsync -> /etc/helexa-router/helexa-router.toml" \
|
||||
'sudo -nl /usr/bin/rsync -a x /etc/helexa-router/helexa-router.toml'
|
||||
probe "systemctl restart helexa-router.service" \
|
||||
'sudo -nl /usr/bin/systemctl restart helexa-router.service'
|
||||
if [ -n "${missing}" ]; then
|
||||
echo "FAIL: gitea_ci is missing sudoers grants on gallumbits:${missing}" >&2
|
||||
echo "" >&2
|
||||
echo " Re-run 'script/infra-setup.sh' once from an operator shell to" >&2
|
||||
echo " install the current asset/sudoers.d/gallumbits-host.conf." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
local_sum=$(sha256sum helexa-router.toml | cut -d' ' -f1)
|
||||
remote_sum=$(ssh gitea_ci@gallumbits.kosherinata.internal \
|
||||
'sudo -n /usr/bin/sha256sum /etc/helexa-router/helexa-router.toml 2>/dev/null | cut -d" " -f1' || true)
|
||||
|
||||
if [ "${local_sum}" = "${remote_sum}" ]; then
|
||||
echo "router config unchanged (${local_sum})"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Two questions, not one. The bytes decide whether to SYNC; the
|
||||
# parsed settings decide whether to RESTART. The first run of
|
||||
# this step proved why they differ: the only change was a
|
||||
# comment header, and it bounced the router anyway, dropping
|
||||
# whatever federation requests were in flight. The router reads
|
||||
# its aliases at startup, so a comment is not a reason to
|
||||
# interrupt anyone.
|
||||
#
|
||||
# Reading the remote copy into CI is safe here precisely because
|
||||
# this file holds no secrets — the same property that lets it be
|
||||
# tracked at all.
|
||||
#
|
||||
# The `cat` grant is deliberately NOT in the preflight above: if
|
||||
# it is missing the read yields nothing, the comparison reports
|
||||
# "changed", and the step restarts on any byte difference. That
|
||||
# is the old behaviour, not a broken one, so a host mid-way
|
||||
# through a sudoers rollout degrades instead of failing.
|
||||
remote_copy="$(mktemp)"
|
||||
trap 'rm -f "${remote_copy}"' EXIT
|
||||
ssh gitea_ci@gallumbits.kosherinata.internal \
|
||||
'sudo -n /usr/bin/cat /etc/helexa-router/helexa-router.toml' \
|
||||
> "${remote_copy}" 2>/dev/null || true
|
||||
|
||||
settings_changed=yes
|
||||
if python3 script/toml-settings-equal.py "${remote_copy}" helexa-router.toml; then
|
||||
settings_changed=no
|
||||
fi
|
||||
|
||||
echo "syncing helexa-router.toml: ${remote_sum:-<absent>} -> ${local_sum}"
|
||||
rsync --archive --compress \
|
||||
--chown root:root --chmod 0644 \
|
||||
--rsync-path 'sudo rsync' \
|
||||
helexa-router.toml \
|
||||
gitea_ci@gallumbits.kosherinata.internal:/etc/helexa-router/helexa-router.toml
|
||||
|
||||
if [ "${settings_changed}" = yes ]; then
|
||||
ssh gitea_ci@gallumbits.kosherinata.internal \
|
||||
'sudo -n /usr/bin/systemctl restart helexa-router.service'
|
||||
echo "helexa-router restarted: settings changed"
|
||||
else
|
||||
echo "helexa-router left running: only comments or formatting changed"
|
||||
fi
|
||||
|
||||
- name: Ensure firewalld allows helexa-router + helexa-upstream + helexa-tools + helexa-angels
|
||||
run: |
|
||||
ssh gitea_ci@gallumbits.kosherinata.internal '
|
||||
@@ -903,7 +534,6 @@ jobs:
|
||||
CAPTURE
|
||||
|
||||
deploy-bench:
|
||||
needs: [config-check]
|
||||
runs-on: fedora-43
|
||||
if: >-
|
||||
${{
|
||||
@@ -911,7 +541,6 @@ jobs:
|
||||
|| github.event.workflow_run.conclusion == 'success'
|
||||
}}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: SSH init
|
||||
run: |
|
||||
mkdir -p ~/.ssh
|
||||
@@ -927,28 +556,6 @@ jobs:
|
||||
echo "inv=$(ssh gitea_ci@bob.hanzalova.internal \
|
||||
'systemctl show -P InvocationID helexa-bench.service' || true)" >> "$GITHUB_OUTPUT"
|
||||
|
||||
# Same contract as the gateway and neuron configs: the repo is the
|
||||
# only writer, so a config edit must reach the host and restart the
|
||||
# service even when no new RPM landed.
|
||||
- name: Sync bench config
|
||||
id: benchconf
|
||||
run: |
|
||||
src="asset/helexa-bench/bob.toml"
|
||||
local_sum=$(sha256sum "${src}" | cut -d' ' -f1)
|
||||
remote_sum=$(ssh gitea_ci@bob.hanzalova.internal \
|
||||
'sha256sum /etc/helexa-bench/helexa-bench.toml 2>/dev/null | cut -d" " -f1' || true)
|
||||
if [ "${local_sum}" = "${remote_sum}" ]; then
|
||||
echo "changed=0" >> "$GITHUB_OUTPUT"
|
||||
echo "${src} unchanged (${local_sum})"
|
||||
else
|
||||
rsync --archive --compress \
|
||||
--chown root:root --chmod 0644 \
|
||||
--rsync-path 'sudo rsync' \
|
||||
"${src}" gitea_ci@bob.hanzalova.internal:/etc/helexa-bench/helexa-bench.toml
|
||||
echo "changed=1" >> "$GITHUB_OUTPUT"
|
||||
echo "${src} updated: ${remote_sum:-<absent>} -> ${local_sum}"
|
||||
fi
|
||||
|
||||
# See deploy-cortex for why gating uses the publish manifest and
|
||||
# not unprivileged `dnf check-update`.
|
||||
- name: Deploy helexa-bench (skips when already current)
|
||||
@@ -956,8 +563,6 @@ jobs:
|
||||
ssh gitea_ci@bob.hanzalova.internal 'bash -s' <<'DEPLOY'
|
||||
set -eu
|
||||
pkg=helexa-bench
|
||||
config_changed="${{ steps.benchconf.outputs.changed }}"
|
||||
config_changed="${config_changed:-0}"
|
||||
# `rpm -q` prints "package X is not installed" on STDOUT and exits
|
||||
# 1, so `|| echo not-installed` never fires — it captures the
|
||||
# message text instead. Test the exit code.
|
||||
@@ -973,25 +578,18 @@ jobs:
|
||||
p = max(cands, key=lambda p: p.get("buildTime", 0))
|
||||
print(p["version"] + "-" + p["release"])
|
||||
' "${pkg}" 2>/dev/null || true)
|
||||
if [ -n "${latest}" ] && [ "${latest}" = "${installed}" ] \
|
||||
&& [ "${config_changed}" -eq 0 ]; then
|
||||
echo "${pkg}-${installed} already current; config unchanged — leaving service untouched"
|
||||
if [ -n "${latest}" ] && [ "${latest}" = "${installed}" ]; then
|
||||
echo "${pkg}-${installed} already current — leaving service untouched"
|
||||
exit 0
|
||||
fi
|
||||
pkg_changed=1
|
||||
if [ -n "${latest}" ] && [ "${latest}" = "${installed}" ]; then
|
||||
pkg_changed=0
|
||||
fi
|
||||
echo "installed=${installed} published=${latest:-unknown} pkg_changed=${pkg_changed} config_changed=${config_changed} — deploying"
|
||||
echo "installed=${installed} published=${latest:-unknown} — deploying"
|
||||
if systemctl is-active --quiet helexa-bench.service; then
|
||||
sudo /usr/bin/systemctl stop helexa-bench.service
|
||||
fi
|
||||
if [ "${pkg_changed}" -eq 1 ]; then
|
||||
if rpm -q "${pkg}" >/dev/null 2>&1; then
|
||||
sudo /usr/bin/dnf upgrade --refresh --allowerasing -y helexa-bench
|
||||
else
|
||||
sudo /usr/bin/dnf install --refresh --allowerasing -y helexa-bench
|
||||
fi
|
||||
if rpm -q "${pkg}" >/dev/null 2>&1; then
|
||||
sudo /usr/bin/dnf upgrade --refresh --allowerasing -y helexa-bench
|
||||
else
|
||||
sudo /usr/bin/dnf install --refresh --allowerasing -y helexa-bench
|
||||
fi
|
||||
sudo /usr/bin/systemctl daemon-reload
|
||||
# enable --now: start the service AND enable it for boot so the
|
||||
@@ -1125,12 +723,6 @@ jobs:
|
||||
cd helexa.ai
|
||||
npm ci
|
||||
npm run i18n:check
|
||||
# Also run here, not just in ci.yml, for the same reason
|
||||
# i18n:check is: pushes to main skip ci.yml, so this is the only
|
||||
# gate a merge itself passes through. Cheap, and it is the exact
|
||||
# case the web CI comment describes — a defect reaching main and
|
||||
# surfacing as a broken deploy afterwards.
|
||||
npm test
|
||||
npm run build
|
||||
|
||||
- name: SSH init
|
||||
|
||||
+2
-14
@@ -8,23 +8,11 @@ helexa.ai/.env.local
|
||||
*.swo
|
||||
.idea/
|
||||
.vscode/
|
||||
# Secret-bearing service configs. These carry API keys, a JWT secret, DB
|
||||
# passwords and SMTP credentials, so they are hand-synced by
|
||||
# script/infra-setup.sh rather than shipped by CI (#287 Gap 1).
|
||||
#
|
||||
# helexa-router.toml is deliberately NOT here: it holds no secrets, only
|
||||
# a listen address, the product-tier aliases and a mesh endpoint. It was
|
||||
# ignored by association, and that is precisely how its `helexa/balanced`
|
||||
# alias came to point at a retired model for long enough to take beast
|
||||
# down (2026-08-27). A file nothing can diff is a file nothing can catch.
|
||||
# Operator-owned credential layer, merged after the CI-deployed config
|
||||
# by cortex / helexa-upstream / helexa-angels. Must never be committed.
|
||||
secrets.toml
|
||||
**/secrets.toml
|
||||
|
||||
cortex.toml
|
||||
models.toml
|
||||
doc/plan/*
|
||||
/target-cuda/
|
||||
.claude/
|
||||
helexa-router.toml
|
||||
helexa-upstream.toml
|
||||
helexa-angels.toml
|
||||
|
||||
@@ -167,7 +167,7 @@ doc-comment; touch points (the `Job` enum, the dispatch handlers, the
|
||||
cargo build --release # build all crates
|
||||
cargo run -p cortex-cli -- serve # run the gateway
|
||||
cargo test # run all tests
|
||||
cargo clippy --workspace --all-targets # lint (test code included)
|
||||
cargo clippy --workspace # lint
|
||||
```
|
||||
|
||||
## CI
|
||||
@@ -177,7 +177,7 @@ pass before merging:
|
||||
|
||||
```sh
|
||||
cargo fmt --check --all # formatting
|
||||
cargo clippy --workspace --all-targets -- -D warnings # lint (warnings are errors)
|
||||
cargo clippy --workspace -- -D warnings # lint (warnings are errors)
|
||||
cargo test --workspace # tests
|
||||
```
|
||||
|
||||
@@ -191,8 +191,7 @@ Work each change on its own branch; `main` stays releasable.
|
||||
|
||||
1. Implement on a feature branch (`fix/<issue>-…`, `feat/<issue>-…`).
|
||||
2. Run the CI triad locally (`cargo fmt --check --all`,
|
||||
`cargo clippy --workspace --all-targets -- -D warnings`,
|
||||
`cargo test --workspace`).
|
||||
`cargo clippy --workspace -- -D warnings`, `cargo test --workspace`).
|
||||
Local builds are **CPU-only** — the `#[cfg(feature = "cuda")]` neuron/TP
|
||||
paths do NOT compile locally. The branch CI's **CUDA type-check** job is
|
||||
the only thing that validates them, so for any neuron change the push to
|
||||
|
||||
@@ -1,10 +1,3 @@
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# MANAGED BY CI — .gitea/workflows/deploy.yml is the only writer.
|
||||
#
|
||||
# Edits made directly to the deployed copy on the host are reverted by
|
||||
# the next deploy, and until then the fleet runs something no commit
|
||||
# describes. Change it here, commit, let the pipeline ship it.
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# helexa-bench config for bob.hanzalova.internal.
|
||||
#
|
||||
# Synced to /etc/helexa-bench/helexa-bench.toml by script/infra-setup.sh
|
||||
@@ -22,20 +15,6 @@ iteration_pause_secs = 2
|
||||
request_timeout_secs = 600
|
||||
db_path = "/var/lib/helexa-bench/bench.sqlite"
|
||||
|
||||
# Identity bench presents to neurons (#288). Without it bench is
|
||||
# anonymous, and since #262 anonymous callers are served only from
|
||||
# leftover capacity — capped below max_in_flight and parked at the class
|
||||
# gate. That moved beast's concurrency:8 from 168.9 tok/s / 0.53s
|
||||
# ttft_p95 to 104.6 / 11.77s the day #262 landed and held there, so every
|
||||
# number since measured the yield policy, not serving capacity.
|
||||
#
|
||||
# A dedicated pair, not a borrowed one: bench then holds its own
|
||||
# fair-share allocation (#54) and cannot starve interactive traffic —
|
||||
# the failure #262 existed to fix.
|
||||
[bench.principal]
|
||||
account_id = "helexa-bench"
|
||||
key_id = "fleet-benchmark"
|
||||
|
||||
[scenarios]
|
||||
prompt_sizes = [128, 4096]
|
||||
max_tokens = 256
|
||||
@@ -43,10 +22,6 @@ max_tokens = 256
|
||||
# carries p95-under-concurrency data before the F3 A/B gate (#94) needs
|
||||
# it for comparison. Levels mirror the real a0/hermes/opencode fan-out.
|
||||
concurrency_levels = [2, 4, 8]
|
||||
# Non-streaming bursts (#285/#288). Kept to the top level: it is where
|
||||
# serialization shows most starkly and each level costs a full burst per
|
||||
# sample per build.
|
||||
concurrency_nonstreaming_levels = [8]
|
||||
concurrency_prompt_tokens = 512
|
||||
|
||||
# Capability probes (#91) — the reasoning/planning axis the speed
|
||||
|
||||
+8
-92
@@ -1,16 +1,9 @@
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# MANAGED BY CI — .gitea/workflows/deploy.yml is the only writer.
|
||||
#
|
||||
# Edits made directly to the deployed copy on the host are reverted by
|
||||
# the next deploy, and until then the fleet runs something no commit
|
||||
# describes. Change it here, commit, let the pipeline ship it.
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# neuron.toml for beast.hanzalova.internal
|
||||
#
|
||||
# 2x RTX 5090 (32 GB each) — TP-2 capable. Pre-warms Qwen3.8-27B with
|
||||
# q6k ISQ across both GPUs at activation, matching the validate-neuron
|
||||
# 2x RTX 5090 (32 GB each) — TP-2 capable. Pre-warms Qwen3.6-27B with
|
||||
# q5k ISQ across both GPUs at activation, matching the validate-neuron
|
||||
# invocation: `validate-neuron.sh beast.hanzalova.internal
|
||||
# Qwen/Qwen3.8-27B q6k 2`.
|
||||
# Qwen/Qwen3.6-27B q5k 2`.
|
||||
#
|
||||
# Synced to /etc/neuron/neuron.toml by script/infra-setup.sh. Edits
|
||||
# take effect after the next deploy workflow run restarts the service
|
||||
@@ -29,93 +22,16 @@ name = "candle"
|
||||
# count. NEURON_BATCHING=0 (systemd drop-in) is the kill switch;
|
||||
# removing this section reverts to batch-1 serialization.
|
||||
[harness.candle.admission]
|
||||
# 8. max_in_flight bounds how many requests run concurrently. It does
|
||||
# NOT partition the KV budget: since #257 (`eca42510`, 2026-08-15) KV is
|
||||
# a shared pool and each request reserves what its own prompt needs via
|
||||
# `enter_with_kv(principal, kv_reservation_mb(prompt_len, ...))`. A
|
||||
# request too big for what is free waits for bytes to come back rather
|
||||
# than being handed a fixed 1/N slice.
|
||||
#
|
||||
# This value was briefly set to 2 (#291) on the stated grounds that "the
|
||||
# KV budget is divided by it at load, so 8 gives each slot 18,852
|
||||
# tokens". That was true before #257 and false after it, and #291 was
|
||||
# filed and actioned after that landed. Nothing in the tree divides the
|
||||
# budget by the slot count — `kv_budget` is a semaphore of MiB permits
|
||||
# and the engine's `max_slots` is only the batch width.
|
||||
#
|
||||
# The concurrency measurement in #291 stands as data (89.6% of busy time
|
||||
# at one request in flight, 4.9% utilisation over seven days) but the
|
||||
# conclusion drawn from it does not, and the traffic it described has
|
||||
# changed: while it was taken, the router's `helexa/balanced` alias
|
||||
# pointed web chat at a second 27B, so per-model concurrency was split
|
||||
# across two models that were evicting each other. With both tiers now
|
||||
# resolving to this model, chat concurrency lands here.
|
||||
#
|
||||
# What actually bounds a busy moment is the pool: 3,689 MiB at
|
||||
# 32 KiB/token/card is ~118k tokens of KV to share. Eight ordinary chat
|
||||
# turns fit easily; a few very long agentic sessions will queue on bytes,
|
||||
# which is the correct behaviour and is what #257 built.
|
||||
max_in_flight = 8
|
||||
|
||||
# Snapshot budget for the cross-request prefix cache (#292).
|
||||
#
|
||||
# 3 GiB, not the 1 GiB default. At the measured 32 KiB/token/card, a
|
||||
# 1 GiB budget cannot hold a snapshot beyond ~32k tokens of K/V alone —
|
||||
# less once the GatedDeltaNet conv/recurrent state is deep-copied on top,
|
||||
# which on this arch is 48 of 64 layers in f32. Agentic sessions here run
|
||||
# well past that: `cached_tokens` was observed pinned at 2,016 for ten
|
||||
# consecutive turns while the prompt grew to 52,869, so every turn
|
||||
# re-prefilled ~50k tokens — 37 s each, against ~20 s of actual decode.
|
||||
# The cache was not missing; the snapshot would not fit.
|
||||
#
|
||||
# The snapshot budget is reserved BEFORE the KV budget, not from what is
|
||||
# left over: measured on this host, kv_budget_mb = 5737 - budget_mb,
|
||||
# exactly 1:1. So this number is a direct trade against how long a
|
||||
# single session can get, and both sides have a floor:
|
||||
#
|
||||
# budget_mb kv_budget tokens/slot (2 slots) holds a 52.9k snapshot
|
||||
# 1024 4713 75,400 no ← the #292 symptom
|
||||
# 3072 2665 42,600 yes, but sessions
|
||||
# cannot reach 52.9k
|
||||
# 2048 3689 59,000 yes
|
||||
#
|
||||
# 2 GiB is the value that satisfies both: a 52,869-token snapshot is
|
||||
# ~1,652 MB of K/V plus the GatedDeltaNet state (~1.73 GB total), and
|
||||
# per-slot KV still covers sessions comfortably past the deepest
|
||||
# observed. 3 GiB was tried first and starved KV — a session could no
|
||||
# longer reach the size whose snapshot the cache was being enlarged to
|
||||
# hold, which is self-defeating.
|
||||
#
|
||||
# max_entries stays at the default 8: the byte budget binds first here,
|
||||
# so the count cap is not what is forcing snapshots to be small.
|
||||
[harness.candle.prefix_cache]
|
||||
budget_mb = 2048
|
||||
|
||||
[[default_models]]
|
||||
# Qwen3.8-27B is the resident flagship (#251). It replaced the
|
||||
# 3.6-27B — architecturally identical, same model_type, layer counts and
|
||||
# vision tower — so the load spec is unchanged.
|
||||
#
|
||||
# The 3.6-27B is no longer catalogued (retired 2026-08-27). While both
|
||||
# were listed at the same residency class they could displace each other
|
||||
# in either direction, which is what let a stale `helexa/balanced` alias
|
||||
# evict this model on every authenticated web-chat turn. See models.toml
|
||||
# for the incident that ended the arrangement.
|
||||
# Qwen3.8-27B is the resident flagship (#251). Architecturally identical
|
||||
# to the 3.6-27B it replaced — same model_type, layer counts and vision
|
||||
# tower — so the load spec is unchanged. The 3.6-27B stays catalogued at
|
||||
# the same residency class, so it can still be cold-loaded on demand and
|
||||
# the two displace each other in either direction.
|
||||
model_id = "Qwen/Qwen3.8-27B"
|
||||
harness = "candle"
|
||||
quant = "q6k"
|
||||
tensor_parallel = 2
|
||||
devices = [0, 1]
|
||||
|
||||
# Sampling override (#283) — MUST match the `[models.sampling]` block on
|
||||
# this model in models.toml. Two files describe one model; only
|
||||
# script/check-config-consistency.py forces them to agree, and #252 is
|
||||
# what happens when nothing does.
|
||||
#
|
||||
# The model's own generation_config.json says temperature = 1.0, which
|
||||
# measured a 20% structural-defect rate on ~2k-token code generation
|
||||
# against 0/60 at <= 0.6 (Fisher exact one-sided p = 0.0031). Precedence
|
||||
# is request > operator > model, so a caller naming a temperature still
|
||||
# gets what it asked for.
|
||||
[default_models.sampling]
|
||||
temperature = 0.6
|
||||
|
||||
@@ -1,10 +1,3 @@
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# MANAGED BY CI — .gitea/workflows/deploy.yml is the only writer.
|
||||
#
|
||||
# Edits made directly to the deployed copy on the host are reverted by
|
||||
# the next deploy, and until then the fleet runs something no commit
|
||||
# describes. Change it here, commit, let the pipeline ship it.
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# neuron.toml for benjy.hanzalova.internal
|
||||
#
|
||||
# 1x RTX 4090 (24 GB) — largest single-GPU host on the fleet. Pre-warms
|
||||
|
||||
@@ -1,10 +1,3 @@
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# MANAGED BY CI — .gitea/workflows/deploy.yml is the only writer.
|
||||
#
|
||||
# Edits made directly to the deployed copy on the host are reverted by
|
||||
# the next deploy, and until then the fleet runs something no commit
|
||||
# describes. Change it here, commit, let the pipeline ship it.
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# neuron.toml for quadbrat.hanzalova.internal
|
||||
#
|
||||
# 1x RTX 3060 (12 GB) — small / quantised tier. Pre-warms Qwen3-1.7B
|
||||
|
||||
@@ -24,24 +24,3 @@ limit_req_zone $binary_remote_addr zone=helexa_tools:10m rate=30r/m;
|
||||
limit_req_zone $binary_remote_addr zone=angels_invite:1m rate=20r/m;
|
||||
limit_req_zone $binary_remote_addr zone=angels_auth:1m rate=12r/m;
|
||||
limit_req_status 429;
|
||||
|
||||
# Access-log format for the search locations, which must not record what
|
||||
# people searched for.
|
||||
#
|
||||
# The default `main` format logs `$request` — method, full URI *and
|
||||
# query string*. For a search proxy that means every query a user types
|
||||
# is written to /var/log/nginx/access.log next to their IP, for
|
||||
# authenticated and anonymous visitors alike. SearXNG's own web UI
|
||||
# defaults to POST partly to avoid exactly this.
|
||||
#
|
||||
# `$uri` is the path with the query stripped, so the operational signal
|
||||
# survives — who called, when, which endpoint, what status, how big, how
|
||||
# long — and the query itself does not. `$request_method` is kept
|
||||
# explicit since `$uri` drops it.
|
||||
#
|
||||
# Rate-limit debugging and abuse detection both work from this: they
|
||||
# need counts, statuses and client addresses, never the search terms.
|
||||
log_format helexa_noquery '$remote_addr - $remote_user [$time_local] '
|
||||
'"$request_method $uri $server_protocol" '
|
||||
'$status $body_bytes_sent "$http_referer" '
|
||||
'"$http_user_agent" $request_time';
|
||||
|
||||
@@ -73,9 +73,6 @@ server {
|
||||
location = /tools/fetch {
|
||||
limit_req zone=helexa_tools burst=10 nodelay;
|
||||
limit_except GET { deny all; }
|
||||
# The `url=` parameter is as revealing as a search query: it is
|
||||
# the page a user is having read to them. Same treatment.
|
||||
access_log /var/log/nginx/access.log helexa_noquery;
|
||||
proxy_pass http://gallumbits.kosherinata.internal:8889/fetch;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
@@ -86,40 +83,7 @@ server {
|
||||
# federation service host. GET only; the SPA requests format=json.
|
||||
location = /tools/web_search {
|
||||
limit_req zone=helexa_tools burst=10 nodelay;
|
||||
# GET and POST: SearXNG accepts both, and a client that POSTs
|
||||
# keeps its query out of any intermediary's request line. Other
|
||||
# methods have no meaning here.
|
||||
limit_except GET POST { deny all; }
|
||||
# A search query is small. Bounding the body stops this becoming
|
||||
# a way to push arbitrary bytes at the upstream.
|
||||
client_max_body_size 8k;
|
||||
# Never log the query — see helexa_noquery in
|
||||
# conf.d/helexa-ratelimit.conf.
|
||||
access_log /var/log/nginx/access.log helexa_noquery;
|
||||
proxy_pass http://gallumbits.kosherinata.internal:8888/search;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_read_timeout 30s;
|
||||
}
|
||||
|
||||
# The same upstream under SearXNG's own path, for clients that speak
|
||||
# the SearXNG API rather than our app's.
|
||||
#
|
||||
# `/tools/web_search` is our name for it, and a generic SearXNG
|
||||
# client cannot guess it: they take a base URL and append `/search`,
|
||||
# because that is what every SearXNG instance serves. Without this
|
||||
# block such a request falls through to `location /` and is answered
|
||||
# by the SPA — HTTP 200, `text/html`, and a JSON parse error at the
|
||||
# client. A 404 would at least be honest; 200-with-HTML sends people
|
||||
# looking for a bug in their own parser.
|
||||
#
|
||||
# Same upstream, same rate-limit zone, same GET-only restriction:
|
||||
# this is an alias, not a second, laxer door.
|
||||
location = /search {
|
||||
limit_req zone=helexa_tools burst=10 nodelay;
|
||||
limit_except GET POST { deny all; }
|
||||
client_max_body_size 8k;
|
||||
access_log /var/log/nginx/access.log helexa_noquery;
|
||||
limit_except GET { deny all; }
|
||||
proxy_pass http://gallumbits.kosherinata.internal:8888/search;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
|
||||
@@ -13,18 +13,6 @@ gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/cortex/models.toml
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /var/www/bench.helexa.ai/
|
||||
# deploy-website rsyncs the built helexa.ai SPA into the nginx webroot.
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /var/www/helexa.ai/
|
||||
# deploy.yml's "Sync internal nginx vhost" step: write the vhost, make
|
||||
# sites-enabled a symlink to it, validate, reload. Scoped to the one
|
||||
# file and the one service — `nginx -t` is included because a reload
|
||||
# must never happen on a config nginx has rejected.
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/nginx/sites-available/helexa.internal.conf
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/nginx/conf.d/helexa-ratelimit.conf
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/sha256sum /etc/nginx/conf.d/helexa-ratelimit.conf
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/sha256sum /etc/nginx/sites-available/helexa.internal.conf
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/ln -sfn /etc/nginx/sites-available/helexa.internal.conf /etc/nginx/sites-enabled/helexa.internal.conf
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/sbin/nginx -t
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl reload nginx
|
||||
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl start cortex.service
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl stop cortex.service
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl enable --now cortex.service
|
||||
|
||||
@@ -4,17 +4,9 @@
|
||||
# rolls out helexa-router (data plane), helexa-upstream (account/budget
|
||||
# authority), helexa-tools (grounding fetcher) and helexa-angels (the
|
||||
# confidential investor portal) package upgrades.
|
||||
# The SECRET-BEARING configs are not synced by CI — helexa-upstream.toml
|
||||
# and helexa-angels.toml carry a DB password, a JWT secret and SMTP
|
||||
# credentials, and ride in script/infra-setup.sh under the operator's own
|
||||
# sudo instead (#287 Gap 1, still open).
|
||||
#
|
||||
# helexa-router.toml is different and IS synced here: it holds no secrets,
|
||||
# only a listen address, the product-tier aliases and a mesh endpoint. It
|
||||
# was excluded by association with its neighbours, which is how its
|
||||
# `helexa/balanced` alias came to point at a model retired from the
|
||||
# catalogue and took beast down on 2026-08-27. A config CI cannot write is
|
||||
# a config no check can defend.
|
||||
# Configs are NOT synced by CI — they carry secrets (DB password, JWT
|
||||
# secret, operator tokens) and ride in script/infra-setup.sh under the
|
||||
# operator's own sudo instead.
|
||||
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl start helexa-router.service
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl stop helexa-router.service
|
||||
@@ -29,20 +21,6 @@ gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl start helexa-angels.service
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl stop helexa-angels.service
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl enable --now helexa-angels.service
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl daemon-reload
|
||||
|
||||
# deploy-gallumbits' "Sync router config" step. Scoped to the one file:
|
||||
# the neighbouring service configs stay operator-only until #287 Gap 1
|
||||
# gives them a render-from-secrets path.
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/rsync * /etc/helexa-router/helexa-router.toml
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/sha256sum /etc/helexa-router/helexa-router.toml
|
||||
# Read-back, so the sync can tell a settings change from a comment
|
||||
# change and restart only for the former. Safe to grant and safe to read
|
||||
# into CI because this file holds no secrets — the same property that
|
||||
# lets it be tracked. If this grant is absent the step degrades to
|
||||
# restarting on any byte change, which is why it is not in the step's
|
||||
# fail-hard preflight.
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/cat /etc/helexa-router/helexa-router.toml
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/systemctl restart helexa-router.service
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/dnf install --refresh --allowerasing -y helexa-router
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/dnf upgrade --refresh --allowerasing -y helexa-router
|
||||
gitea_ci ALL=(root) NOPASSWD: /usr/bin/dnf install --refresh --allowerasing -y helexa-upstream
|
||||
|
||||
+1
-8
@@ -1,10 +1,4 @@
|
||||
import type {
|
||||
Dimensions,
|
||||
MeasurementRegime,
|
||||
ReportRow,
|
||||
RunRow,
|
||||
SeriesPoint,
|
||||
} from "./types";
|
||||
import type { Dimensions, ReportRow, RunRow, SeriesPoint } from "./types";
|
||||
|
||||
// Empty default → `fetch('/api/...')` hits the dev proxy (vite.config.ts)
|
||||
// or the same origin. For a separately-hosted build, set VITE_API_BASE to
|
||||
@@ -21,7 +15,6 @@ async function getJson<T>(path: string): Promise<T> {
|
||||
|
||||
export const getDimensions = () => getJson<Dimensions>("/api/dimensions");
|
||||
export const getSummary = () => getJson<ReportRow[]>("/api/summary");
|
||||
export const getRegimes = () => getJson<MeasurementRegime[]>("/api/regimes");
|
||||
|
||||
// host is resolved server-side (each model maps to one host today), so the
|
||||
// public UI selects by model + scenario alone.
|
||||
|
||||
+86
-288
@@ -11,8 +11,8 @@ import {
|
||||
XAxis,
|
||||
YAxis,
|
||||
} from "recharts";
|
||||
import { getDimensions, getRegimes, getSeries } from "../api";
|
||||
import type { Dimensions, MeasurementRegime, SeriesPoint } from "../types";
|
||||
import { getDimensions, getSeries } from "../api";
|
||||
import type { Dimensions, SeriesPoint } from "../types";
|
||||
import { BASELINE_SOURCE, baselineFor } from "../baseline";
|
||||
|
||||
function Picker({
|
||||
@@ -40,95 +40,11 @@ function Picker({
|
||||
);
|
||||
}
|
||||
|
||||
type SeriesDef = {
|
||||
key: string;
|
||||
name: string;
|
||||
stroke: string;
|
||||
dashed?: boolean;
|
||||
};
|
||||
|
||||
/** One titled chart over the shared build timeline.
|
||||
*
|
||||
* Every panel draws the same x-axis and the same regime divider, so a
|
||||
* reader can line a change up across metrics — which is the whole point
|
||||
* of having more than two of them. */
|
||||
/** A vertical rule at a build where the metric changed meaning. */
|
||||
type Rule = { at: string; label: string; detail?: string };
|
||||
|
||||
function MetricChart({
|
||||
title,
|
||||
hint,
|
||||
data,
|
||||
lines,
|
||||
rules,
|
||||
unit,
|
||||
}: {
|
||||
title: string;
|
||||
hint?: string;
|
||||
data: Record<string, unknown>[];
|
||||
lines: SeriesDef[];
|
||||
rules?: Rule[];
|
||||
unit?: string;
|
||||
}) {
|
||||
const hasAny = data.some((d) => lines.some((l) => d[l.key] != null));
|
||||
if (!hasAny) return null;
|
||||
return (
|
||||
<>
|
||||
<h5 className="mt-4">
|
||||
{title}
|
||||
{unit ? <span className="text-muted fw-normal"> ({unit})</span> : null}
|
||||
</h5>
|
||||
{hint && <p className="text-muted small mb-2">{hint}</p>}
|
||||
<ResponsiveContainer width="100%" height={260}>
|
||||
<LineChart data={data} margin={{ top: 8, right: 24, bottom: 8, left: 0 }}>
|
||||
<CartesianGrid strokeDasharray="3 3" />
|
||||
<XAxis dataKey="label" />
|
||||
<YAxis />
|
||||
<Tooltip />
|
||||
<Legend />
|
||||
{(rules ?? [])
|
||||
// Only draw a rule whose build is actually on this x-axis;
|
||||
// recharts would otherwise place it at the origin and imply
|
||||
// the boundary sits before all the data.
|
||||
.filter((r) => data.some((d) => d.label === r.at))
|
||||
.map((r) => (
|
||||
<ReferenceLine
|
||||
key={`${r.at}-${r.label}`}
|
||||
x={r.at}
|
||||
stroke="#bbb"
|
||||
strokeDasharray="3 3"
|
||||
label={{
|
||||
value: r.label,
|
||||
position: "top",
|
||||
fill: "#999",
|
||||
fontSize: 11,
|
||||
}}
|
||||
/>
|
||||
))}
|
||||
{lines.map((l) => (
|
||||
<Line
|
||||
key={l.key}
|
||||
type="monotone"
|
||||
dataKey={l.key}
|
||||
name={l.name}
|
||||
stroke={l.stroke}
|
||||
strokeDasharray={l.dashed ? "5 5" : undefined}
|
||||
connectNulls
|
||||
dot={false}
|
||||
/>
|
||||
))}
|
||||
</LineChart>
|
||||
</ResponsiveContainer>
|
||||
</>
|
||||
);
|
||||
}
|
||||
|
||||
export default function Trends() {
|
||||
const [dims, setDims] = useState<Dimensions | null>(null);
|
||||
const [model, setModel] = useState("");
|
||||
const [scenario, setScenario] = useState("");
|
||||
const [series, setSeries] = useState<SeriesPoint[]>([]);
|
||||
const [regimes, setRegimes] = useState<MeasurementRegime[]>([]);
|
||||
const [err, setErr] = useState<string | null>(null);
|
||||
|
||||
useEffect(() => {
|
||||
@@ -139,10 +55,6 @@ export default function Trends() {
|
||||
if (d.scenarios[0]) setScenario(d.scenarios[0]);
|
||||
})
|
||||
.catch((e) => setErr(String(e)));
|
||||
// A missing/older API just means no rules — not a page failure.
|
||||
getRegimes()
|
||||
.then(setRegimes)
|
||||
.catch(() => setRegimes([]));
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
@@ -156,7 +68,10 @@ export default function Trends() {
|
||||
// Prepend the pre-helexa-bench baseline (dashed, separate keys) so it
|
||||
// anchors the timeline without being merged into the live line. Different
|
||||
// measurement regime — see baseline.ts / doc/benchmarks.md.
|
||||
const base = useMemo(() => baselineFor(model, scenario), [model, scenario]);
|
||||
const base = useMemo(
|
||||
() => baselineFor(model, scenario),
|
||||
[model, scenario],
|
||||
);
|
||||
const data = useMemo(
|
||||
() => [
|
||||
...base.map((p) => ({
|
||||
@@ -170,14 +85,6 @@ export default function Trends() {
|
||||
ttft: p.ttft_s_median,
|
||||
decode: p.decode_tps_median,
|
||||
total: p.total_s_median,
|
||||
ttftP95: p.ttft_p95_s_median,
|
||||
queueWait: p.queue_wait_ms_median,
|
||||
rejected: p.rejected_median,
|
||||
prefillTps: p.prefill_tps_median,
|
||||
reasoning: p.reasoning_tokens_median,
|
||||
cached: p.cached_tokens_median,
|
||||
completion: p.completion_tokens_median,
|
||||
tpot: p.tpot_p95_ms_median,
|
||||
})),
|
||||
],
|
||||
[series, base],
|
||||
@@ -188,55 +95,6 @@ export default function Trends() {
|
||||
const firstLive = series[0]?.git_sha;
|
||||
const showDivider = base.length > 0 && series.length > 0;
|
||||
|
||||
// The build where the measuring identity changed, derived from the
|
||||
// data rather than declared — a constant would go stale the moment
|
||||
// the principal is reconfigured (#288).
|
||||
const identityShift = useMemo(() => {
|
||||
for (let i = 1; i < series.length; i++) {
|
||||
const prev = series[i - 1].principal ?? "anonymous";
|
||||
const cur = series[i].principal ?? "anonymous";
|
||||
if (prev !== cur) {
|
||||
return {
|
||||
at: series[i].git_sha,
|
||||
label: `measured as ${cur === "anonymous" ? "anonymous" : "identified"}`,
|
||||
detail:
|
||||
"The identity bench measured under changed here. Anonymous " +
|
||||
"samples are subject to the #262 yield policy and understate " +
|
||||
"capacity, so points either side are not comparable (#288).",
|
||||
} as Rule;
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}, [series]);
|
||||
|
||||
/** Declared boundaries touching `metric`, plus the regime-independent
|
||||
* ones that apply to every panel. */
|
||||
const rulesFor = (metric: string): Rule[] => {
|
||||
const out: Rule[] = [];
|
||||
if (showDivider && firstLive) {
|
||||
out.push({ at: firstLive, label: "bench.py → helexa-bench" });
|
||||
}
|
||||
for (const r of regimes) {
|
||||
if (r.affects.includes(metric)) {
|
||||
out.push({ at: r.first_sha, label: r.label, detail: r.detail });
|
||||
}
|
||||
}
|
||||
if (identityShift) out.push(identityShift);
|
||||
return out;
|
||||
};
|
||||
|
||||
// Anonymous and identified samples are not comparable once #262 is in
|
||||
// the build: an anonymous caller is capped below max_in_flight and
|
||||
// parked at the class gate, so it characterises the yield policy
|
||||
// rather than serving capacity. Say so rather than letting someone
|
||||
// read a step change as an engine regression (#288).
|
||||
const identities = useMemo(
|
||||
() => new Set(series.map((p) => p.principal ?? "anonymous")),
|
||||
[series],
|
||||
);
|
||||
const mixedIdentity = identities.size > 1;
|
||||
const anyAnonymous = identities.has("anonymous");
|
||||
|
||||
if (err) return <Alert variant="danger">{err}</Alert>;
|
||||
if (!dims) return <Spinner animation="border" />;
|
||||
|
||||
@@ -264,25 +122,6 @@ export default function Trends() {
|
||||
</p>
|
||||
)}
|
||||
|
||||
{mixedIdentity && (
|
||||
<Alert variant="warning" className="py-2">
|
||||
<strong>Mixed measurement identity.</strong> Some builds were
|
||||
sampled anonymously and some under a principal. Since{" "}
|
||||
<code>#262</code> an anonymous caller is capped below{" "}
|
||||
<code>max_in_flight</code> and yields to identified traffic, so
|
||||
those points measure the admission policy rather than serving
|
||||
capacity. A step change across that boundary is the instrument,
|
||||
not the engine — see <code>#288</code>.
|
||||
</Alert>
|
||||
)}
|
||||
{!mixedIdentity && anyAnonymous && (
|
||||
<Alert variant="secondary" className="py-2 small">
|
||||
Sampled anonymously. Since <code>#262</code> anonymous callers are
|
||||
served from leftover capacity, so these numbers understate what an
|
||||
authenticated caller gets (<code>#288</code>).
|
||||
</Alert>
|
||||
)}
|
||||
|
||||
{data.length === 0 ? (
|
||||
<Alert variant="info">No data for this selection yet.</Alert>
|
||||
) : (
|
||||
@@ -294,128 +133,87 @@ export default function Trends() {
|
||||
see <code>doc/benchmarks.md</code>.
|
||||
</p>
|
||||
)}
|
||||
<h5 className="mt-3">decode tok/s (higher is better)</h5>
|
||||
<ResponsiveContainer width="100%" height={280}>
|
||||
<LineChart data={data} margin={{ top: 8, right: 24, bottom: 8, left: 0 }}>
|
||||
<CartesianGrid strokeDasharray="3 3" />
|
||||
<XAxis dataKey="label" />
|
||||
<YAxis />
|
||||
<Tooltip />
|
||||
<Legend />
|
||||
{showDivider && firstLive && (
|
||||
<ReferenceLine
|
||||
x={firstLive}
|
||||
stroke="#bbb"
|
||||
strokeDasharray="3 3"
|
||||
label={{
|
||||
value: "bench.py → helexa-bench",
|
||||
position: "top",
|
||||
fill: "#999",
|
||||
fontSize: 11,
|
||||
}}
|
||||
/>
|
||||
)}
|
||||
<Line
|
||||
type="monotone"
|
||||
dataKey="decode"
|
||||
name="decode tok/s"
|
||||
stroke="#0d6efd"
|
||||
connectNulls
|
||||
/>
|
||||
{base.length > 0 && (
|
||||
<Line
|
||||
type="monotone"
|
||||
dataKey="baseDecode"
|
||||
name="baseline (bench.py · gateway)"
|
||||
stroke="#888"
|
||||
strokeDasharray="5 5"
|
||||
connectNulls
|
||||
/>
|
||||
)}
|
||||
</LineChart>
|
||||
</ResponsiveContainer>
|
||||
|
||||
<MetricChart
|
||||
title="decode tok/s"
|
||||
unit="higher is better"
|
||||
data={data}
|
||||
rules={rulesFor("decode")}
|
||||
lines={[
|
||||
{ key: "decode", name: "decode tok/s", stroke: "#0d6efd" },
|
||||
...(base.length > 0
|
||||
? [
|
||||
{
|
||||
key: "baseDecode",
|
||||
name: "baseline (bench.py · gateway)",
|
||||
stroke: "#888",
|
||||
dashed: true,
|
||||
},
|
||||
]
|
||||
: []),
|
||||
]}
|
||||
/>
|
||||
|
||||
<MetricChart
|
||||
title="prefill tok/s"
|
||||
unit="higher is better"
|
||||
hint="The other half of serving speed, derived from prefill_tokens / prefill_ms. A prefix-cache hit shortens prefill_ms while the token count stays whole, so a high rate here is itself the cache-hit signal."
|
||||
data={data}
|
||||
rules={rulesFor("prefillTps")}
|
||||
lines={[
|
||||
{ key: "prefillTps", name: "prefill tok/s", stroke: "#20c997" },
|
||||
]}
|
||||
/>
|
||||
|
||||
<MetricChart
|
||||
title="TTFT"
|
||||
unit="seconds, lower is better"
|
||||
hint="Median and p95 together on purpose. Under concurrency the median is dominated by whichever streams were admitted immediately; the p95 is the one that moves when a caller is made to wait. Charting only the median is how a 0.53 s → 11.77 s tail went unnoticed for a week."
|
||||
data={data}
|
||||
rules={rulesFor("ttft")}
|
||||
lines={[
|
||||
{ key: "ttft", name: "TTFT median (s)", stroke: "#dc3545" },
|
||||
{ key: "ttftP95", name: "TTFT p95 (s)", stroke: "#fd7e14" },
|
||||
...(base.length > 0
|
||||
? [
|
||||
{
|
||||
key: "baseTtft",
|
||||
name: "baseline (bench.py · gateway)",
|
||||
stroke: "#888",
|
||||
dashed: true,
|
||||
},
|
||||
]
|
||||
: []),
|
||||
]}
|
||||
/>
|
||||
|
||||
<MetricChart
|
||||
title="inter-token gap p95"
|
||||
unit="ms, lower is better"
|
||||
hint="Stream smoothness. decode tok/s is a mean over the whole window, so a stream that stalls and then catches up is indistinguishable from one that never stalled — this is the number a user feels."
|
||||
data={data}
|
||||
rules={rulesFor("tpot")}
|
||||
lines={[
|
||||
{ key: "tpot", name: "inter-token p95 (ms)", stroke: "#6f42c1" },
|
||||
]}
|
||||
/>
|
||||
|
||||
<MetricChart
|
||||
title="admission"
|
||||
unit="queue wait ms · requests shed"
|
||||
hint="Separates “the server is slow” from “you were queued behind someone”. Queue wait is TTFT minus server-measured prefill; rejected counts honest backpressure rather than silent failures."
|
||||
data={data}
|
||||
rules={rulesFor("queueWait")}
|
||||
lines={[
|
||||
{ key: "queueWait", name: "queue wait (ms)", stroke: "#d63384" },
|
||||
{ key: "rejected", name: "rejected (count)", stroke: "#adb5bd" },
|
||||
]}
|
||||
/>
|
||||
|
||||
<MetricChart
|
||||
title="tokens per sample"
|
||||
unit="counts"
|
||||
hint="Cost, not speed. Reasoning tokens are the dominant driver on a reasoning model and move independently of every rate above — a template or sampling change can double what the model thinks before answering while the speed charts stay flat. Cached tokens are why prefill timing varies between otherwise identical samples."
|
||||
data={data}
|
||||
rules={rulesFor("completion")}
|
||||
lines={[
|
||||
{ key: "completion", name: "completion tokens", stroke: "#0dcaf0" },
|
||||
{ key: "reasoning", name: "reasoning tokens", stroke: "#ffc107" },
|
||||
{ key: "cached", name: "cached prompt tokens", stroke: "#198754" },
|
||||
]}
|
||||
/>
|
||||
|
||||
{(() => {
|
||||
// Explain every rule actually drawn for this selection. The
|
||||
// chart label is a name; without the reason, a reader still
|
||||
// has to go and rediscover what it meant — which is the cost
|
||||
// this whole feature exists to remove.
|
||||
const shown = [
|
||||
...regimes
|
||||
.filter((r) => series.some((p) => p.git_sha === r.first_sha))
|
||||
.map((r) => ({ at: r.first_sha, label: r.label, detail: r.detail })),
|
||||
...(identityShift ? [identityShift] : []),
|
||||
];
|
||||
if (shown.length === 0) return null;
|
||||
return (
|
||||
<div className="mt-4 pt-3 border-top">
|
||||
<p className="text-muted small mb-2">
|
||||
<strong>Dashed rules mark measurement-regime changes</strong> —
|
||||
builds where a number changed meaning rather than value. A step
|
||||
across one is the instrument, not the engine.
|
||||
</p>
|
||||
<dl className="row small text-muted mb-0">
|
||||
{shown.map((r) => (
|
||||
<div key={`${r.at}-${r.label}`} className="mb-2">
|
||||
<dt className="fw-semibold">
|
||||
<code>{r.at}</code> — {r.label}
|
||||
</dt>
|
||||
<dd className="mb-0">{r.detail}</dd>
|
||||
</div>
|
||||
))}
|
||||
</dl>
|
||||
</div>
|
||||
);
|
||||
})()}
|
||||
<h5 className="mt-4">TTFT seconds (lower is better)</h5>
|
||||
<ResponsiveContainer width="100%" height={280}>
|
||||
<LineChart data={data} margin={{ top: 8, right: 24, bottom: 8, left: 0 }}>
|
||||
<CartesianGrid strokeDasharray="3 3" />
|
||||
<XAxis dataKey="label" />
|
||||
<YAxis />
|
||||
<Tooltip />
|
||||
<Legend />
|
||||
{showDivider && firstLive && (
|
||||
<ReferenceLine
|
||||
x={firstLive}
|
||||
stroke="#bbb"
|
||||
strokeDasharray="3 3"
|
||||
label={{
|
||||
value: "bench.py → helexa-bench",
|
||||
position: "top",
|
||||
fill: "#999",
|
||||
fontSize: 11,
|
||||
}}
|
||||
/>
|
||||
)}
|
||||
<Line
|
||||
type="monotone"
|
||||
dataKey="ttft"
|
||||
name="TTFT (s)"
|
||||
stroke="#dc3545"
|
||||
connectNulls
|
||||
/>
|
||||
{base.length > 0 && (
|
||||
<Line
|
||||
type="monotone"
|
||||
dataKey="baseTtft"
|
||||
name="baseline (bench.py · gateway)"
|
||||
stroke="#888"
|
||||
strokeDasharray="5 5"
|
||||
connectNulls
|
||||
/>
|
||||
)}
|
||||
</LineChart>
|
||||
</ResponsiveContainer>
|
||||
</>
|
||||
)}
|
||||
</>
|
||||
|
||||
@@ -41,17 +41,6 @@ export interface SeriesPoint {
|
||||
ttft_s_median: number | null;
|
||||
decode_tps_median: number | null;
|
||||
total_s_median: number | null;
|
||||
ttft_p95_s_median: number | null;
|
||||
queue_wait_ms_median: number | null;
|
||||
rejected_median: number | null;
|
||||
prefill_tps_median: number | null;
|
||||
reasoning_tokens_median: number | null;
|
||||
cached_tokens_median: number | null;
|
||||
completion_tokens_median: number | null;
|
||||
tpot_p95_ms_median: number | null;
|
||||
/** Identity the samples were taken under, or null if anonymous.
|
||||
* Anonymous and identified points are not comparable (#288). */
|
||||
principal: string | null;
|
||||
samples: number;
|
||||
}
|
||||
|
||||
@@ -78,13 +67,3 @@ export interface RunRow {
|
||||
ok: boolean;
|
||||
error: string | null;
|
||||
}
|
||||
|
||||
/** A build at which a metric changed meaning rather than value (#288).
|
||||
* Served from the API so the UI and `report` cite one list. */
|
||||
export interface MeasurementRegime {
|
||||
first_sha: string;
|
||||
label: string;
|
||||
detail: string;
|
||||
/** Series keys this affects, as Trends.tsx names them. */
|
||||
affects: string[];
|
||||
}
|
||||
|
||||
@@ -20,11 +20,6 @@ pub struct MessagesRequest {
|
||||
pub temperature: Option<f64>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub top_p: Option<f64>,
|
||||
/// Anthropic's Messages API carries `top_k` natively, so it maps
|
||||
/// straight onto the OpenAI-side field rather than being dropped in
|
||||
/// translation (#272).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub top_k: Option<usize>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub stream: Option<bool>,
|
||||
#[serde(flatten)]
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
//! Model catalogue — profiles describing how to serve each model.
|
||||
|
||||
use crate::discovery::DeviceInfo;
|
||||
use crate::harness::{ModelCost, ModelLimit, SamplingOverride};
|
||||
use crate::harness::{ModelCost, ModelLimit};
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::collections::HashMap;
|
||||
use std::path::Path;
|
||||
@@ -57,23 +57,6 @@ pub struct ModelProfile {
|
||||
/// on this being explicit per model rather than implicit.
|
||||
#[serde(default)]
|
||||
pub source: Option<String>,
|
||||
/// Operator sampling override forwarded to neuron on cold load
|
||||
/// (#283). The counterpart to the same field in a host's
|
||||
/// `[[default_models]]` — a model that can be both cold-loaded by
|
||||
/// cortex and resident on a host must carry the same value in both,
|
||||
/// which `script/check-config-consistency.py` enforces in CI.
|
||||
///
|
||||
/// This is the #252 shape of hazard: two config files describing one
|
||||
/// model, with nothing forcing them to agree.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub sampling: Option<SamplingOverride>,
|
||||
/// The model's own `preserve_thinking` template control, forwarded
|
||||
/// on cold load so a model this gateway loads behaves the same as
|
||||
/// one the host was configured to hold resident. Two config files
|
||||
/// describing one model is how #252 happened; this rides along for
|
||||
/// the same reason `sampling` does.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub preserve_thinking: Option<bool>,
|
||||
|
||||
// ── Enrichment (issue #62) ────────────────────────────────
|
||||
/// Per-model token budget. When present, advertised in `/v1/models`
|
||||
@@ -257,8 +240,6 @@ mod tests {
|
||||
pinned_on: vec![],
|
||||
residency_priority: None,
|
||||
source: None,
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
limit: None,
|
||||
cost: None,
|
||||
capabilities: vec![],
|
||||
|
||||
@@ -143,48 +143,15 @@ pub struct NeuronEndpoint {
|
||||
impl GatewayConfig {
|
||||
/// Load configuration from a TOML file, with environment variable overrides.
|
||||
/// Env vars are prefixed with `CORTEX_` and use `__` as a separator.
|
||||
///
|
||||
/// A sibling `secrets.toml`, if present, is merged **after** the main
|
||||
/// file and therefore wins. It exists so the two have different
|
||||
/// owners: CI writes the main config, and only the operator writes
|
||||
/// the secrets — see [`secrets_path`].
|
||||
pub fn load(path: impl AsRef<Path>) -> Result<Self, Box<figment::Error>> {
|
||||
let path = path.as_ref();
|
||||
Figment::new()
|
||||
.merge(Toml::file(path))
|
||||
.merge(Toml::file(secrets_path(path)))
|
||||
.merge(Env::prefixed("CORTEX_").split("__"))
|
||||
.extract()
|
||||
.map_err(Box::new)
|
||||
}
|
||||
}
|
||||
|
||||
/// `secrets.toml` beside the main config.
|
||||
///
|
||||
/// The split exists to make a class of outage impossible rather than
|
||||
/// merely unlikely. Config that CI cannot write is config no check can
|
||||
/// defend: `helexa-router.toml` was excluded from git because it sat
|
||||
/// beside secret-bearing files, and its `helexa/balanced` alias then
|
||||
/// pointed at a retired model for long enough to take a node down
|
||||
/// (2026-08-27). The fix is not to hand CI the credentials — it is to
|
||||
/// stop mixing the two in one file.
|
||||
///
|
||||
/// So `cortex.toml` holds structure and is deployed by CI, while
|
||||
/// `secrets.toml` holds API keys and the upstream bearer, is written
|
||||
/// only by the operator, and is never read, written or diffed by the
|
||||
/// pipeline. Because it merges last it also wins, so a value present in
|
||||
/// both is the operator's.
|
||||
///
|
||||
/// A missing file is not an error — figment treats an absent
|
||||
/// `Toml::file` as an empty source — so a host that keeps everything in
|
||||
/// one file, and every existing deployment, keeps working unchanged.
|
||||
fn secrets_path(config: &Path) -> std::path::PathBuf {
|
||||
config
|
||||
.parent()
|
||||
.unwrap_or_else(|| Path::new("."))
|
||||
.join("secrets.toml")
|
||||
}
|
||||
|
||||
impl Default for GatewayConfig {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
@@ -203,111 +170,3 @@ impl Default for GatewayConfig {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod secrets_layer_tests {
|
||||
use super::*;
|
||||
use std::io::Write;
|
||||
|
||||
/// Write `main` (and optionally `secrets.toml`) into a fresh directory
|
||||
/// under the target dir, and load through the real code path.
|
||||
fn load_with(dir: &str, main: &str, secrets: Option<&str>) -> GatewayConfig {
|
||||
// `CARGO_TARGET_TMPDIR` is only set for integration tests, not for
|
||||
// unit tests inside src/, so derive a unique directory instead.
|
||||
let base = std::env::temp_dir().join(format!("helexa-cortex-config-{dir}"));
|
||||
let _ = std::fs::remove_dir_all(&base);
|
||||
std::fs::create_dir_all(&base).expect("create test dir");
|
||||
let cfg = base.join("cortex.toml");
|
||||
write!(
|
||||
std::fs::File::create(&cfg).expect("create config"),
|
||||
"{main}"
|
||||
)
|
||||
.expect("write");
|
||||
if let Some(s) = secrets {
|
||||
let p = base.join("secrets.toml");
|
||||
write!(std::fs::File::create(&p).expect("create secrets"), "{s}").expect("write");
|
||||
}
|
||||
GatewayConfig::load(&cfg).expect("config loads")
|
||||
}
|
||||
|
||||
const MAIN: &str = r#"
|
||||
[gateway]
|
||||
listen = "0.0.0.0:31313"
|
||||
metrics_listen = "0.0.0.0:31314"
|
||||
[eviction]
|
||||
strategy = "lru"
|
||||
defrag_after_cycles = 50
|
||||
[entitlements]
|
||||
require_auth = true
|
||||
|
||||
[[neurons]]
|
||||
name = "beast"
|
||||
endpoint = "http://beast.invalid:13131"
|
||||
"#;
|
||||
|
||||
/// The whole point: a host with no secrets.toml behaves exactly as
|
||||
/// before. Every current deployment is in this state, so if this
|
||||
/// regressed the change would take the fleet down on rollout rather
|
||||
/// than on adoption.
|
||||
#[test]
|
||||
fn an_absent_secrets_file_is_not_an_error() {
|
||||
let cfg = load_with("secrets_absent", MAIN, None);
|
||||
assert!(cfg.entitlements.require_auth);
|
||||
assert!(
|
||||
cfg.entitlements.keys.is_empty(),
|
||||
"no keys configured anywhere means no keys"
|
||||
);
|
||||
}
|
||||
|
||||
/// The array-of-tables case that ruled out env-var overrides:
|
||||
/// `[[entitlements.keys]]` cannot be expressed as `CORTEX_*` env vars,
|
||||
/// so the second TOML layer is what carries it.
|
||||
#[test]
|
||||
fn secrets_file_supplies_the_entitlement_keys() {
|
||||
let cfg = load_with(
|
||||
"secrets_keys",
|
||||
MAIN,
|
||||
Some(
|
||||
r#"
|
||||
[[entitlements.keys]]
|
||||
key = "sk-test-aaa"
|
||||
account_id = "acct-a"
|
||||
key_id = "a"
|
||||
[[entitlements.keys]]
|
||||
key = "sk-test-bbb"
|
||||
account_id = "acct-b"
|
||||
key_id = "b"
|
||||
"#,
|
||||
),
|
||||
);
|
||||
assert_eq!(cfg.entitlements.keys.len(), 2);
|
||||
assert_eq!(cfg.entitlements.keys[0].key, "sk-test-aaa");
|
||||
assert_eq!(cfg.entitlements.keys[1].account_id, "acct-b");
|
||||
assert!(
|
||||
cfg.entitlements.require_auth,
|
||||
"structure from the CI-owned file must survive the merge"
|
||||
);
|
||||
}
|
||||
|
||||
/// Ordering is the safety property. If CI ever ships a placeholder in
|
||||
/// the main file, the operator's real value must still win — otherwise
|
||||
/// a deploy silently swaps a live credential for a dummy.
|
||||
#[test]
|
||||
fn the_operators_value_wins_over_the_deployed_one() {
|
||||
let cfg = load_with(
|
||||
"secrets_precedence",
|
||||
&format!(
|
||||
"{MAIN}\n[upstream]\nenabled = true\nurl = \"https://example.invalid\"\nbearer = \"PLACEHOLDER\"\n"
|
||||
),
|
||||
Some("[upstream]\nbearer = \"real-token\"\n"),
|
||||
);
|
||||
assert_eq!(
|
||||
cfg.upstream.bearer, "real-token",
|
||||
"secrets.toml merges last, so it wins"
|
||||
);
|
||||
assert_eq!(
|
||||
cfg.upstream.url, "https://example.invalid",
|
||||
"fields the operator does not override keep the deployed value"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -109,23 +109,6 @@ pub struct ModelLoad {
|
||||
/// (#54/#137). `#[serde(default)]` for back-compat.
|
||||
#[serde(default)]
|
||||
pub rejected_per_principal: u64,
|
||||
/// Anonymous requests currently holding a seat (#262). Read against
|
||||
/// `in_flight` it says how much of this model's load is unattributable;
|
||||
/// against `anon_max_in_flight`, how close that traffic is to the
|
||||
/// ceiling that keeps it from starving identified callers.
|
||||
#[serde(default)]
|
||||
pub anon_in_flight: usize,
|
||||
/// Seats anonymous traffic may hold at once (#262); `0` = refused
|
||||
/// outright. `#[serde(default)]` (→ 0) for pre-#262 neurons, which
|
||||
/// applied no ceiling at all — cortex skips the gauge rather than
|
||||
/// publish a 0 that reads as the opposite of the truth.
|
||||
#[serde(default)]
|
||||
pub anon_max_in_flight: usize,
|
||||
/// Cumulative anonymous requests refused for want of leftover capacity
|
||||
/// (#262). Rising here with a flat `rejected_timeout` means the
|
||||
/// reservation is working, not that the model is overloaded.
|
||||
#[serde(default)]
|
||||
pub rejected_anon_yield: u64,
|
||||
/// Cumulative requests that waited for KV budget and never got it
|
||||
/// (#257) — the model is saturated by long-context sequences rather
|
||||
/// than by request count. `#[serde(default)]` for back-compat.
|
||||
@@ -188,9 +171,6 @@ mod health_load_tests {
|
||||
kv_available_mb: 0,
|
||||
rejected_timeout: 0,
|
||||
rejected_per_principal: 0,
|
||||
anon_in_flight: 2,
|
||||
anon_max_in_flight: 7,
|
||||
rejected_anon_yield: 0,
|
||||
tok_s_prefill: 0.0,
|
||||
tok_s_decode: 0.0,
|
||||
}],
|
||||
@@ -202,8 +182,6 @@ mod health_load_tests {
|
||||
assert_eq!(back.models[0].queue_depth, 3);
|
||||
assert_eq!(back.models[0].max_in_flight, 8);
|
||||
assert_eq!(back.models[0].max_queue_depth, 8);
|
||||
assert_eq!(back.models[0].anon_in_flight, 2);
|
||||
assert_eq!(back.models[0].anon_max_in_flight, 7);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -215,10 +193,6 @@ mod health_load_tests {
|
||||
assert_eq!(m.in_flight, 2);
|
||||
assert_eq!(m.max_in_flight, 0);
|
||||
assert_eq!(m.max_queue_depth, 0);
|
||||
// Likewise a pre-#262 neuron, which enforced no anonymous ceiling.
|
||||
assert_eq!(m.anon_in_flight, 0);
|
||||
assert_eq!(m.anon_max_in_flight, 0);
|
||||
assert_eq!(m.rejected_anon_yield, 0);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -26,115 +26,7 @@ pub struct HarnessHealth {
|
||||
pub uptime_secs: Option<u64>,
|
||||
}
|
||||
|
||||
/// Operator-set sampling defaults for one model (#283).
|
||||
///
|
||||
/// A model's `generation_config.json` is the model authors' statement of
|
||||
/// intent, and honouring it (#272) is right by default. It is not always
|
||||
/// right for the workload the operator serves: `Qwen/Qwen3.8-27B`
|
||||
/// publishes `temperature = 1.0`, which measured a 20% structural-defect
|
||||
/// rate on ~2k-token code generation against 0/60 at `<= 0.6`
|
||||
/// (#283, p = 0.0031).
|
||||
///
|
||||
/// This is the operator's explicit, visible correction to that default —
|
||||
/// deliberately *not* a heuristic that inspects the model and guesses.
|
||||
/// A temperature guesser is a footgun; a number in a config file the
|
||||
/// operator wrote is not.
|
||||
///
|
||||
/// Precedence is **request > operator > model > built-in fallback**: the
|
||||
/// override replaces what the model published, but a caller that names a
|
||||
/// value still wins, because an explicit API parameter that is silently
|
||||
/// ignored is a contract break.
|
||||
///
|
||||
/// Every field is optional and overlays independently — setting
|
||||
/// `temperature` alone leaves the model's `top_p`/`top_k` in force.
|
||||
#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
|
||||
pub struct SamplingOverride {
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub temperature: Option<f64>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub top_p: Option<f64>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub top_k: Option<usize>,
|
||||
/// Multiplier applied to recently-generated tokens before sampling.
|
||||
/// `1.0` disables it; above that, recently-emitted tokens get less
|
||||
/// likely.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub repeat_penalty: Option<f32>,
|
||||
/// How many recently-generated tokens the penalty considers.
|
||||
///
|
||||
/// The reason this is operator-settable at all: the built-in default
|
||||
/// is 64, inherited from candle's chat example, and a reasoning
|
||||
/// model's think block runs to tens of thousands of tokens. Anything
|
||||
/// restated more than 64 tokens later is invisible to the penalty,
|
||||
/// which is how a 28,672-token think block can contain the same
|
||||
/// derivation five times over.
|
||||
///
|
||||
/// Raising it is a real trade, not a free win: the penalty is
|
||||
/// token-level, and source code legitimately repeats tokens
|
||||
/// constantly (`const`, `function`, brace runs). A wide window at a
|
||||
/// meaningful penalty distorts exactly the output this fleet is for.
|
||||
/// Sequence-level repetition wants a sequence-level instrument
|
||||
/// (frequency/presence penalties, or a DRY-style sampler); this knob
|
||||
/// exists so the trade can be *measured* per model rather than
|
||||
/// guessed once and frozen into a constant.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub repeat_last_n: Option<usize>,
|
||||
/// Sequence-wide one-time penalty for already-seen tokens.
|
||||
///
|
||||
/// This, not `repeat_last_n`, is the remedy Qwen prescribe for the
|
||||
/// endless repetition their models fall into during long reasoning
|
||||
/// (0..2, 1.5 when severe). It is scored over everything generated
|
||||
/// so far, so a passage restated 5,000 tokens later is still
|
||||
/// penalised — the case a trailing window cannot see.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub presence_penalty: Option<f32>,
|
||||
/// Sequence-wide penalty proportional to a token's existing count.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub frequency_penalty: Option<f32>,
|
||||
/// Pin the sampler's RNG for every request to this model.
|
||||
///
|
||||
/// Exists because parameter search needs a control: comparing two
|
||||
/// `presence_penalty` values across unseeded runs cannot separate
|
||||
/// the parameter's effect from sampling variance, and the clients
|
||||
/// that would otherwise pin it cannot — pi's request builder sends
|
||||
/// no `seed` at all, so a caller-side seed is not available on the
|
||||
/// path that matters.
|
||||
///
|
||||
/// Note what this does and does not give. It removes sampling noise
|
||||
/// as a confounder; it does not make two runs comparable
|
||||
/// token-by-token, because changing a penalty changes the logits
|
||||
/// and the sequences diverge at the first step where a token choice
|
||||
/// flips.
|
||||
///
|
||||
/// Leaving this set is a product decision, not just a testing one:
|
||||
/// every identical prompt then yields an identical answer for every
|
||||
/// caller. That is defensible — predictable and cacheable — but it
|
||||
/// removes the variation a user may expect from retrying. A request
|
||||
/// that names its own seed still wins.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub seed: Option<u64>,
|
||||
}
|
||||
|
||||
impl SamplingOverride {
|
||||
/// True when the operator set nothing — an empty `[sampling]` table
|
||||
/// must behave exactly as no table at all.
|
||||
pub fn is_empty(&self) -> bool {
|
||||
self.temperature.is_none()
|
||||
&& self.top_p.is_none()
|
||||
&& self.top_k.is_none()
|
||||
&& self.repeat_penalty.is_none()
|
||||
&& self.repeat_last_n.is_none()
|
||||
&& self.presence_penalty.is_none()
|
||||
&& self.frequency_penalty.is_none()
|
||||
&& self.seed.is_none()
|
||||
}
|
||||
}
|
||||
|
||||
/// Specification for loading a model through a harness.
|
||||
///
|
||||
/// Doubles as the `[[default_models]]` entry shape in `neuron.toml`, so
|
||||
/// a field added here is available to both the load API and the
|
||||
/// operator's per-host config without a second type to keep in step.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ModelSpec {
|
||||
pub model_id: String,
|
||||
@@ -142,36 +34,6 @@ pub struct ModelSpec {
|
||||
pub quant: Option<String>,
|
||||
pub tensor_parallel: Option<u32>,
|
||||
pub devices: Option<Vec<u32>>,
|
||||
/// Operator sampling override (#283). Travels with the *model*, not
|
||||
/// the request: neuron is the only place sampling is resolved, so
|
||||
/// the override has to reach it whether the load came from cortex's
|
||||
/// catalogue or from this host's own `[[default_models]]`.
|
||||
///
|
||||
/// `#[serde(default)]` so a cortex or neuron predating this field
|
||||
/// still round-trips the spec.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub sampling: Option<SamplingOverride>,
|
||||
/// Whether prior assistant turns keep their reasoning when the chat
|
||||
/// template re-renders the conversation.
|
||||
///
|
||||
/// This is the model's own `preserve_thinking` template control, not
|
||||
/// an invention of ours. `Qwen/Qwen3.8-27B` defaults it to *true* —
|
||||
/// the whole transcript's think blocks are replayed — and `false`
|
||||
/// keeps reasoning only for turns after the last user query, i.e.
|
||||
/// the turn in progress.
|
||||
///
|
||||
/// `None` leaves the kwarg unset so the template's own default
|
||||
/// applies, which is the only safe default: the model's authors
|
||||
/// chose it, and overriding that fleet-wide on a hunch is how you
|
||||
/// ship a regression you cannot see.
|
||||
///
|
||||
/// Exposed as operator config so the premise can be A/B'd on a real
|
||||
/// workload — full replay is the larger prompt and pushes against
|
||||
/// the prefix-cache budget and the throughput-derived context
|
||||
/// ceiling, but whether it *helps* the model is a measurement, not
|
||||
/// a belief. A request's own `chat_template_kwargs` still wins.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub preserve_thinking: Option<bool>,
|
||||
}
|
||||
|
||||
/// Per-model token budget advertised by the catalogue or neuron.
|
||||
@@ -188,77 +50,8 @@ pub struct ModelLimit {
|
||||
/// back to `context − output`.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub input: Option<usize>,
|
||||
/// The generation budget a request gets when it names none, and the
|
||||
/// figure `input = context − output` is derived from.
|
||||
///
|
||||
/// A *reserve*, not a ceiling — a request may ask for more and be
|
||||
/// served it. Named `output` for the shape's history; the number a
|
||||
/// client should plan against is [`ModelLimit::output_ceiling`].
|
||||
/// Maximum number of generation tokens.
|
||||
pub output: usize,
|
||||
/// The largest output a request may name and be served (#278).
|
||||
///
|
||||
/// Distinct from `output`, which is the default and the KV-planning
|
||||
/// reserve. Publishing the reserve as the ceiling meant a client
|
||||
/// that trusted the advertisement asked for a fraction of what the
|
||||
/// model would happily generate — on a reasoning model, often less
|
||||
/// than its own think block costs.
|
||||
///
|
||||
/// `#[serde(default)]` so a neuron predating this field still
|
||||
/// deserializes; zero means "not advertised", and consumers fall
|
||||
/// back to `output`.
|
||||
#[serde(default, skip_serializing_if = "is_zero")]
|
||||
pub output_ceiling: usize,
|
||||
}
|
||||
|
||||
fn is_zero(v: &usize) -> bool {
|
||||
*v == 0
|
||||
}
|
||||
|
||||
/// What each reasoning effort level costs, in reasoning tokens (#223).
|
||||
///
|
||||
/// OpenAI-shaped clients can only send `minimal|low|medium|high` — the
|
||||
/// ladder is their entire vocabulary, and they cannot express a token
|
||||
/// count. So the server picks the numbers, and has to say what they are:
|
||||
/// a client choosing `low` with no idea whether that buys 2k tokens or
|
||||
/// 20k is guessing, which is the failure #274 exists to end.
|
||||
///
|
||||
/// Ordered rungs rather than a map, so the ladder reads in the order a
|
||||
/// client would climb it.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct ReasoningBudgetRung {
|
||||
/// The effort level as the caller spells it on the wire.
|
||||
///
|
||||
/// Since #290 these are the rungs the **model's own chat template**
|
||||
/// accepts, discovered by rendering it, rather than a ladder the
|
||||
/// operator invented. `Qwen/Qwen3.8-27B` accepts exactly `low`,
|
||||
/// `medium` and `xhigh` and raises on anything else; we previously
|
||||
/// advertised `minimal`/`low`/`medium`/`high`, two of which the
|
||||
/// template rejects and which omitted the model's own default.
|
||||
///
|
||||
/// Advertise only rungs the template accepts: an invented name is a
|
||||
/// name a caller can send and the model will reject. Note that a
|
||||
/// client need not read this at all — pi-ai takes its levels from a
|
||||
/// static `thinkingLevelMap` in the operator's config — so this is
|
||||
/// a statement of truth, not a control surface we can rely on.
|
||||
pub effort: String,
|
||||
/// Backstop reasoning-token cap for this rung, when the deployment
|
||||
/// sets one.
|
||||
///
|
||||
/// `None` is the normal case and means "named rung, no cap": effort
|
||||
/// is expressed to the model through its template, and the number of
|
||||
/// tokens it then spends is the model's business. A cap is a safety
|
||||
/// net against a runaway think block (#223), not the mechanism by
|
||||
/// which effort is selected — enforcing effort by truncation is what
|
||||
/// #290 fixed.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub tokens: Option<usize>,
|
||||
/// Whether the model applies this rung when the caller names none.
|
||||
///
|
||||
/// Taken from the template's own `|default(...)`. Without it a
|
||||
/// caller that says nothing cannot tell what it is getting — on
|
||||
/// Qwen3.8 that silently means `xhigh`.
|
||||
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
|
||||
pub default: bool,
|
||||
}
|
||||
|
||||
/// Operator-set pricing, **USD per 1,000,000 tokens, as JSON numbers**
|
||||
@@ -333,16 +126,6 @@ pub struct ModelInfo {
|
||||
/// marker tokens (`<think>` / `<\/think>` or similar).
|
||||
#[serde(default)]
|
||||
pub reasoning: bool,
|
||||
/// The operator's `preserve_thinking` for this loaded model, or
|
||||
/// `None` when unset and the template's own default applies.
|
||||
///
|
||||
/// Advertised so a run can be *stamped* with the value it ran
|
||||
/// under. This is an A/B knob whose whole purpose is comparison
|
||||
/// between runs, and a comparison whose arms cannot be told apart
|
||||
/// afterwards is not a comparison. Recovering it from deploy
|
||||
/// history is guesswork — a config sync can land mid-session.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub preserve_thinking: Option<bool>,
|
||||
|
||||
/// Whether this node can actually serve a request for this model
|
||||
/// right now (#245).
|
||||
@@ -361,11 +144,6 @@ pub struct ModelInfo {
|
||||
/// from its own routing table.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub servable: Option<ModelServability>,
|
||||
/// The reasoning-effort ladder this deployment honours (#223).
|
||||
/// Absent when the model does not reason, or the harness has no
|
||||
/// budget to offer.
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub reasoning_budget: Vec<ReasoningBudgetRung>,
|
||||
}
|
||||
|
||||
/// Why a loaded model can or cannot be served right now (#245).
|
||||
|
||||
@@ -44,12 +44,6 @@ pub struct NodeState {
|
||||
/// just one whose total topology could. Empty until the first
|
||||
/// /health poll.
|
||||
pub device_health: Vec<crate::discovery::DeviceHealth>,
|
||||
/// The reasoning-effort ladder this neuron honours (#223), copied
|
||||
/// from its `/models` reply at poll time. Per-node rather than
|
||||
/// per-model because it is host configuration — every model on a
|
||||
/// neuron reports the same rungs — and duplicating it onto each
|
||||
/// model entry would invite the two to disagree.
|
||||
pub reasoning_budget: Vec<crate::harness::ReasoningBudgetRung>,
|
||||
}
|
||||
|
||||
/// A model registered on a node, with its runtime status.
|
||||
@@ -193,35 +187,12 @@ pub struct CortexModelEntry {
|
||||
/// Served max-seq-len in tokens — mirrors `limit.context`.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub max_model_len: Option<usize>,
|
||||
/// The same window under the two names generic OpenAI clients look
|
||||
/// for (#278) — a client that probes for one of these rather than
|
||||
/// `max_model_len` would otherwise find no window at all and fall
|
||||
/// back to a number its operator had to invent by hand.
|
||||
///
|
||||
/// Publishing them is cheap and harmless; do not assume any
|
||||
/// *specific* client consumes them. An earlier version of this
|
||||
/// comment credited pi-ai's provider discovery, which was wrong:
|
||||
/// pi requires `contextWindow` as a static field on its model type
|
||||
/// and reads none of these keys at runtime (checked against 0.82.1
|
||||
/// and 0.84.3). The misattribution mattered — it made an operator's
|
||||
/// hand-set 80k window look like our advertisement failing to land,
|
||||
/// when in fact nothing was reading it and the number had to be
|
||||
/// maintained by hand regardless.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub context_window: Option<usize>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub context_length: Option<usize>,
|
||||
/// Usable input budget — mirrors `limit.input` when present.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub max_input_tokens: Option<usize>,
|
||||
/// The largest output a request may name — mirrors
|
||||
/// `limit.output_ceiling`, falling back to `limit.output` (#278).
|
||||
/// Maximum generation tokens — mirrors `limit.output`.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub max_output_tokens: Option<usize>,
|
||||
/// What each effort level buys, in reasoning tokens (#223) — so a
|
||||
/// client picking `low` knows what it asked for.
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub reasoning_budget: Vec<crate::harness::ReasoningBudgetRung>,
|
||||
}
|
||||
|
||||
impl CortexModelEntry {
|
||||
@@ -233,26 +204,8 @@ impl CortexModelEntry {
|
||||
/// dropped the limit.
|
||||
pub fn sync_flat_limit(&mut self) {
|
||||
self.max_model_len = self.limit.as_ref().map(|l| l.context);
|
||||
self.context_window = self.limit.as_ref().map(|l| l.context);
|
||||
self.context_length = self.limit.as_ref().map(|l| l.context);
|
||||
self.max_input_tokens = self.limit.as_ref().and_then(|l| l.input);
|
||||
// The ceiling, not the reserve (#278): a client that reads this
|
||||
// field turns it into the cap it sends on each request, so
|
||||
// advertising the reserve handed a reasoning model less budget
|
||||
// than its own think block needs. Falls back to the reserve for
|
||||
// a neuron too old to publish a ceiling.
|
||||
//
|
||||
// Observed with dsh. pi is *not* an example: its `maxTokens` is
|
||||
// a required static field in models.json and it reads nothing
|
||||
// from here — an operator has to copy this number across by
|
||||
// hand, and gets no error if they copy it wrong.
|
||||
self.max_output_tokens = self.limit.as_ref().map(|l| {
|
||||
if l.output_ceiling > 0 {
|
||||
l.output_ceiling
|
||||
} else {
|
||||
l.output
|
||||
}
|
||||
});
|
||||
self.max_output_tokens = self.limit.as_ref().map(|l| l.output);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -18,45 +18,6 @@ pub struct ChatCompletionRequest {
|
||||
pub temperature: Option<f64>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub top_p: Option<f64>,
|
||||
/// Truncate sampling to the `k` most likely tokens (#272).
|
||||
///
|
||||
/// Not in the OpenAI schema but universal among serving stacks
|
||||
/// (vLLM, SGLang, llama.cpp, Ollama), and required by models that
|
||||
/// publish it — Qwen3 specifies `top_k = 20`. A named field rather
|
||||
/// than `extra`, because a sampling parameter that lands in `extra`
|
||||
/// is accepted and silently discarded.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub top_k: Option<usize>,
|
||||
/// Pin the sampler's RNG for reproducible output (OpenAI core).
|
||||
///
|
||||
/// Previously ignored on every text path, which called
|
||||
/// `unix_subsec_nanos()` regardless — a caller asking for
|
||||
/// determinism got fresh randomness and a `200`.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub seed: Option<u64>,
|
||||
/// Penalty applied to recently-generated tokens; `1.0` disables.
|
||||
/// Defaults to 1.1 when absent (#272).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub repetition_penalty: Option<f32>,
|
||||
/// How many recent tokens `repetition_penalty` considers. Defaults
|
||||
/// to 64 — fine for chat, short for a long reasoning block, which is
|
||||
/// why it is a knob rather than a constant (#272).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub repeat_last_n: Option<usize>,
|
||||
/// OpenAI core, `-2.0..=2.0`. Subtracted once from any token that
|
||||
/// has already appeared, regardless of how often.
|
||||
///
|
||||
/// Unlike `repetition_penalty` this is scored over the **whole**
|
||||
/// generated sequence, not a trailing window — which is what a
|
||||
/// reasoning model needs, and what Qwen recommend (0..2, 1.5 for
|
||||
/// severe cases) for the endless-repetition failure their own
|
||||
/// models exhibit during long thinking.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub presence_penalty: Option<f32>,
|
||||
/// OpenAI core, `-2.0..=2.0`. Subtracted in proportion to how many
|
||||
/// times a token has already appeared.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub frequency_penalty: Option<f32>,
|
||||
/// The deprecated spelling of the output cap. Still what most
|
||||
/// clients send; see [`ChatCompletionRequest::effective_max_tokens`].
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
@@ -188,9 +149,8 @@ pub struct Usage {
|
||||
/// `completion_tokens`, never added into `total_tokens`).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub completion_tokens_details: Option<CompletionTokensDetails>,
|
||||
/// OpenAI-standard breakdown of `prompt_tokens`, carrying
|
||||
/// `cached_tokens` (#269). Omitted when nothing was reused, so
|
||||
/// "absent" stays distinguishable from "measured as zero".
|
||||
/// OpenAI-standard breakdown of `prompt_tokens`. Populated once
|
||||
/// prompt caching lands (#11); `None` until then.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub prompt_tokens_details: Option<PromptTokensDetails>,
|
||||
/// helexa extension (non-OpenAI): server-measured prefill/decode
|
||||
@@ -222,9 +182,8 @@ pub struct CompletionTokensDetails {
|
||||
/// Sub-counts of `Usage::prompt_tokens`.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct PromptTokensDetails {
|
||||
/// Prompt tokens served from neuron's prefix KV cache (#11), so a
|
||||
/// caller can see the saving rather than assume none (#269). A
|
||||
/// sub-count of `prompt_tokens`, never added into `total_tokens`.
|
||||
/// Prompt tokens served from cache (cache-read rate). Populated
|
||||
/// once prompt caching lands (#11).
|
||||
pub cached_tokens: u64,
|
||||
}
|
||||
|
||||
|
||||
@@ -55,26 +55,6 @@ pub struct ResponsesRequest {
|
||||
pub temperature: Option<f64>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub top_p: Option<f64>,
|
||||
/// Truncate sampling to the `k` most likely tokens (#272). Not in
|
||||
/// the Responses schema, but a sampling parameter that lands in
|
||||
/// `extra` is accepted and silently discarded, which is the defect
|
||||
/// this closes.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub top_k: Option<usize>,
|
||||
/// Pin the sampler's RNG for reproducible output (#272).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub seed: Option<u64>,
|
||||
/// Penalty on recently-generated tokens; `1.0` disables (#272).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub repetition_penalty: Option<f32>,
|
||||
/// Window `repetition_penalty` considers (#272).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub repeat_last_n: Option<usize>,
|
||||
/// OpenAI core; forwarded to the chat path unchanged.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub presence_penalty: Option<f32>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub frequency_penalty: Option<f32>,
|
||||
/// Chained-conversation identifier. We don't store responses
|
||||
/// server-side yet; if this is `Some`, the handler returns 400.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
@@ -150,22 +130,12 @@ pub enum ResponsesInputItem {
|
||||
/// string or an array of content parts; the translator renders
|
||||
/// either form to text rather than losing the tool result.
|
||||
FunctionCallOutput { call_id: String, output: Value },
|
||||
/// A reasoning item the model emitted on an earlier turn, replayed
|
||||
/// by the client so the model can continue its own train of thought.
|
||||
///
|
||||
/// Both spellings are modelled because both are in the wild and one
|
||||
/// of them is ours: OpenAI's o-series carries the text in `content`
|
||||
/// as `reasoning_text` parts, while neuron emits `summary` with a
|
||||
/// `summary_text` part. Clients round-trip the completed item
|
||||
/// verbatim — pi-ai stores our `response.output_item.done` payload
|
||||
/// and replays it unchanged — so whichever field we emit is the
|
||||
/// field we get back, and reading only one of them silently loses
|
||||
/// the turn's reasoning.
|
||||
/// Reasoning items emitted by o-series models. Accepted but
|
||||
/// not forwarded to the model — neuron's candle path doesn't
|
||||
/// surface reasoning separately yet.
|
||||
Reasoning {
|
||||
#[serde(default)]
|
||||
content: Vec<Value>,
|
||||
#[serde(default)]
|
||||
summary: Vec<Value>,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -220,46 +190,11 @@ pub struct ResponsesResponse {
|
||||
pub status: String,
|
||||
pub model: String,
|
||||
pub output: Vec<ResponsesOutputItem>,
|
||||
/// Why a `status: "incomplete"` response stopped short. Required in
|
||||
/// practice, not optional decoration: a client cannot tell an
|
||||
/// honest truncation from a protocol fault without it, and at least
|
||||
/// one treats the difference as fatal.
|
||||
///
|
||||
/// pi-ai's `mapStopReason` maps
|
||||
/// `incomplete` + `reason == "max_output_tokens"` to
|
||||
/// `stopReason: "length"`, and `incomplete` with no reason to
|
||||
/// `stopReason: "error"` ("Response incomplete without a provider
|
||||
/// reason"). Its agent loop then either continues — failing any
|
||||
/// truncated tool calls safely and letting the model recover on the
|
||||
/// next turn — or halts outright. Omitting this field cost a live
|
||||
/// agentic session its whole run.
|
||||
///
|
||||
/// `None` for `completed` and `in_progress`.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub incomplete_details: Option<IncompleteDetails>,
|
||||
/// Populated on completion; `None` while streaming.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub usage: Option<ResponsesUsage>,
|
||||
}
|
||||
|
||||
/// Why a response is `incomplete`.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
|
||||
pub struct IncompleteDetails {
|
||||
/// OpenAI spells the output-cap case `"max_output_tokens"`; that is
|
||||
/// the only reason we produce today. `content_filter` is the other
|
||||
/// value the upstream API defines.
|
||||
pub reason: String,
|
||||
}
|
||||
|
||||
impl IncompleteDetails {
|
||||
/// The response ran into the caller's output budget.
|
||||
pub fn max_output_tokens() -> Self {
|
||||
Self {
|
||||
reason: "max_output_tokens".into(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[serde(tag = "type", rename_all = "snake_case")]
|
||||
pub enum ResponsesOutputItem {
|
||||
@@ -276,15 +211,6 @@ pub enum ResponsesOutputItem {
|
||||
#[serde(default = "default_item_status")]
|
||||
status: String,
|
||||
},
|
||||
/// A think block, as its own output item ahead of the message —
|
||||
/// the same shape the streaming projector emits, so a client sees
|
||||
/// one contract whether or not it streams (#300).
|
||||
Reasoning {
|
||||
id: String,
|
||||
summary: Vec<ResponsesSummaryPart>,
|
||||
#[serde(default = "default_item_status")]
|
||||
status: String,
|
||||
},
|
||||
/// Reserved for the day tool-call extraction lands. The wire
|
||||
/// shape mirrors `ResponsesInputItem::FunctionCall`.
|
||||
FunctionCall {
|
||||
@@ -297,24 +223,6 @@ pub enum ResponsesOutputItem {
|
||||
},
|
||||
}
|
||||
|
||||
/// One `summary_text` part of a reasoning output item.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ResponsesSummaryPart {
|
||||
/// Always `"summary_text"`.
|
||||
#[serde(rename = "type")]
|
||||
pub part_type: String,
|
||||
pub text: String,
|
||||
}
|
||||
|
||||
impl ResponsesSummaryPart {
|
||||
pub fn summary_text(text: impl Into<String>) -> Self {
|
||||
Self {
|
||||
part_type: "summary_text".into(),
|
||||
text: text.into(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn default_item_status() -> String {
|
||||
"completed".into()
|
||||
}
|
||||
@@ -341,8 +249,8 @@ pub struct ResponsesUsage {
|
||||
/// sub-count of `output_tokens`, never added into `total_tokens`).
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub output_tokens_details: Option<OutputTokensDetails>,
|
||||
/// OpenAI-standard breakdown of `input_tokens`, carrying
|
||||
/// `cached_tokens` (#269). Omitted when nothing was reused.
|
||||
/// OpenAI-standard breakdown of `input_tokens`. Populated once
|
||||
/// prompt caching lands (#11); `None` until then.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub input_tokens_details: Option<InputTokensDetails>,
|
||||
}
|
||||
@@ -357,8 +265,8 @@ pub struct OutputTokensDetails {
|
||||
/// Sub-counts of `ResponsesUsage::input_tokens`.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct InputTokensDetails {
|
||||
/// Input tokens served from neuron's prefix KV cache (#11), so a
|
||||
/// caller can see the saving rather than assume none (#269).
|
||||
/// Input tokens served from cache (cache-read rate). Populated
|
||||
/// once prompt caching lands (#11).
|
||||
pub cached_tokens: u64,
|
||||
}
|
||||
|
||||
@@ -381,37 +289,9 @@ pub mod events {
|
||||
pub const OUTPUT_TEXT_DONE: &str = "response.output_text.done";
|
||||
pub const CONTENT_PART_DONE: &str = "response.content_part.done";
|
||||
pub const OUTPUT_ITEM_DONE: &str = "response.output_item.done";
|
||||
/// Reasoning-item event family. A reasoning model's think block is
|
||||
/// its own output item, emitted ahead of the message item, with a
|
||||
/// summary part carrying the text. Streaming these is what keeps the
|
||||
/// connection observably alive while a model thinks — clients time
|
||||
/// out on silence, and SSE comment keep-alives don't count because
|
||||
/// idle timers reset on parsed events, not comments.
|
||||
pub const REASONING_SUMMARY_PART_ADDED: &str = "response.reasoning_summary_part.added";
|
||||
pub const REASONING_SUMMARY_TEXT_DELTA: &str = "response.reasoning_summary_text.delta";
|
||||
pub const REASONING_SUMMARY_TEXT_DONE: &str = "response.reasoning_summary_text.done";
|
||||
pub const REASONING_SUMMARY_PART_DONE: &str = "response.reasoning_summary_part.done";
|
||||
pub const FUNCTION_CALL_ARGUMENTS_DELTA: &str = "response.function_call_arguments.delta";
|
||||
pub const FUNCTION_CALL_ARGUMENTS_DONE: &str = "response.function_call_arguments.done";
|
||||
pub const COMPLETED: &str = "response.completed";
|
||||
/// Terminal frame for a response that stopped short. Carries the
|
||||
/// same `response` payload as [`COMPLETED`], with
|
||||
/// `status: "incomplete"` and `incomplete_details.reason`.
|
||||
///
|
||||
/// A client keyed on the event name — rather than on
|
||||
/// `response.status` — sees no terminal event at all if a truncated
|
||||
/// response is announced as `response.completed`, and waits out its
|
||||
/// idle timeout.
|
||||
pub const INCOMPLETE: &str = "response.incomplete";
|
||||
/// Terminal frame for a response that did not finish because the
|
||||
/// server failed — a poisoned device, an OOM, a producer that died
|
||||
/// mid-stream. Carries `status: "failed"` and an `error` object.
|
||||
///
|
||||
/// The alternative is worse than it looks: defaulting a missing
|
||||
/// finish to a clean stop reports a crash as a complete answer, and
|
||||
/// the caller believes a truncated or empty reply was the model's
|
||||
/// considered response.
|
||||
pub const FAILED: &str = "response.failed";
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
@@ -616,7 +496,6 @@ mod tests {
|
||||
}],
|
||||
status: "completed".into(),
|
||||
}],
|
||||
incomplete_details: None,
|
||||
usage: Some(ResponsesUsage {
|
||||
input_tokens: 5,
|
||||
output_tokens: 3,
|
||||
@@ -629,36 +508,5 @@ mod tests {
|
||||
let parsed: ResponsesResponse = serde_json::from_str(&json).unwrap();
|
||||
assert_eq!(parsed.id, "resp_1");
|
||||
assert_eq!(parsed.output.len(), 1);
|
||||
assert!(
|
||||
!json.contains("incomplete_details"),
|
||||
"a completed response must not carry an incomplete reason"
|
||||
);
|
||||
}
|
||||
|
||||
/// The field pi-ai's `mapStopReason` keys on. Absent, it maps
|
||||
/// `incomplete` to `stopReason: "error"` and its agent loop halts;
|
||||
/// present with `max_output_tokens`, it maps to `"length"` and the
|
||||
/// loop continues.
|
||||
#[test]
|
||||
fn an_incomplete_response_serialises_its_reason() {
|
||||
let r = ResponsesResponse {
|
||||
id: "resp_2".into(),
|
||||
object: "response".into(),
|
||||
created_at: 1700,
|
||||
status: "incomplete".into(),
|
||||
model: "m".into(),
|
||||
output: vec![],
|
||||
incomplete_details: Some(IncompleteDetails::max_output_tokens()),
|
||||
usage: None,
|
||||
};
|
||||
let v: serde_json::Value = serde_json::to_value(&r).unwrap();
|
||||
assert_eq!(v["status"], "incomplete");
|
||||
assert_eq!(v["incomplete_details"]["reason"], "max_output_tokens");
|
||||
|
||||
let parsed: ResponsesResponse = serde_json::from_value(v).unwrap();
|
||||
assert_eq!(
|
||||
parsed.incomplete_details,
|
||||
Some(IncompleteDetails::max_output_tokens())
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -94,28 +94,6 @@ pub fn anthropic_to_openai(req: MessagesRequest) -> ChatCompletionRequest {
|
||||
if let Some(tc) = tool_choice {
|
||||
obj.insert("tool_choice".into(), tc);
|
||||
}
|
||||
// Anthropic's extended-thinking budget is the one quantitative
|
||||
// reasoning control any of our wire formats offers (#223).
|
||||
// Normalised onto `reasoning.max_tokens`, the shape the harness
|
||||
// resolves, so all three inlets converge on one field instead of
|
||||
// each generation loop learning three spellings.
|
||||
let budget = obj
|
||||
.get("thinking")
|
||||
.filter(|t| t.get("type").and_then(Value::as_str) != Some("disabled"))
|
||||
.and_then(|t| t.get("budget_tokens"))
|
||||
.and_then(Value::as_u64)
|
||||
.filter(|n| *n > 0);
|
||||
if let Some(budget) = budget {
|
||||
let reasoning = obj
|
||||
.entry("reasoning")
|
||||
.or_insert_with(|| Value::Object(Default::default()));
|
||||
if !reasoning.is_object() {
|
||||
*reasoning = Value::Object(Default::default());
|
||||
}
|
||||
if let Some(r) = reasoning.as_object_mut() {
|
||||
r.entry("max_tokens").or_insert_with(|| Value::from(budget));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
ChatCompletionRequest {
|
||||
@@ -123,15 +101,6 @@ pub fn anthropic_to_openai(req: MessagesRequest) -> ChatCompletionRequest {
|
||||
messages,
|
||||
temperature: req.temperature,
|
||||
top_p: req.top_p,
|
||||
// Anthropic models top_k too, so it survives the hop (#272).
|
||||
top_k: req.top_k,
|
||||
// Anthropic's Messages API has no seed or penalty knobs; absent
|
||||
// means the model's own generation_config decides.
|
||||
seed: None,
|
||||
repetition_penalty: None,
|
||||
repeat_last_n: None,
|
||||
presence_penalty: None,
|
||||
frequency_penalty: None,
|
||||
max_tokens: Some(req.max_tokens),
|
||||
// Anthropic has one spelling; it maps onto the legacy field.
|
||||
max_completion_tokens: None,
|
||||
@@ -415,26 +384,17 @@ fn anthropic_content_to_text(content: AnthropicContent) -> String {
|
||||
pub fn openai_to_anthropic(resp: ChatCompletionResponse) -> MessagesResponse {
|
||||
let choice = resp.choices.into_iter().next();
|
||||
|
||||
let (content_text, reasoning_text, stop_reason) = match choice {
|
||||
let (content_text, stop_reason) = match choice {
|
||||
Some(c) => {
|
||||
let text = match c.message.content {
|
||||
MessageContent::Text(t) => t,
|
||||
MessageContent::Parts(parts) => serde_json::to_string(&parts).unwrap_or_default(),
|
||||
MessageContent::Null => String::new(),
|
||||
};
|
||||
// The model's think block, which the harness returns on
|
||||
// `message.reasoning_content` (#300).
|
||||
let reasoning = c
|
||||
.message
|
||||
.extra
|
||||
.get("reasoning_content")
|
||||
.and_then(|v| v.as_str())
|
||||
.map(str::to_string)
|
||||
.filter(|t| !t.is_empty());
|
||||
let stop = c.finish_reason.map(|r| map_stop_reason(&r));
|
||||
(text, reasoning, stop)
|
||||
(text, stop)
|
||||
}
|
||||
None => (String::new(), None, None),
|
||||
None => (String::new(), None),
|
||||
};
|
||||
|
||||
let usage = resp.usage.unwrap_or(Usage {
|
||||
@@ -450,32 +410,10 @@ pub fn openai_to_anthropic(resp: ChatCompletionResponse) -> MessagesResponse {
|
||||
id: resp.id,
|
||||
response_type: "message".into(),
|
||||
role: "assistant".into(),
|
||||
// A `thinking` block ahead of the text, which is Anthropic's
|
||||
// own ordering. This path accepted `thinking.budget_tokens` on
|
||||
// the way in (see `anthropic_to_openai`) and returned nothing on
|
||||
// the way out: the caller spent the tokens, could not see them,
|
||||
// and could not replay the model's reasoning next turn (#300).
|
||||
//
|
||||
// Emitted without a `signature`. Anthropic signs its thinking
|
||||
// blocks and a client that round-trips one may expect the field;
|
||||
// we cannot mint a valid signature and inventing one would be
|
||||
// worse than omitting it. If a real client rejects an unsigned
|
||||
// block, the fix is to gate this behind a flag — not to go back
|
||||
// to silently deleting the model's work.
|
||||
content: {
|
||||
let mut blocks = Vec::with_capacity(2);
|
||||
if let Some(thinking) = reasoning_text {
|
||||
blocks.push(ContentBlock {
|
||||
block_type: "thinking".into(),
|
||||
data: json!({ "thinking": thinking }),
|
||||
});
|
||||
}
|
||||
blocks.push(ContentBlock {
|
||||
block_type: "text".into(),
|
||||
data: json!({ "text": content_text }),
|
||||
});
|
||||
blocks
|
||||
},
|
||||
content: vec![ContentBlock {
|
||||
block_type: "text".into(),
|
||||
data: json!({ "text": content_text }),
|
||||
}],
|
||||
model: resp.model,
|
||||
stop_reason,
|
||||
usage: AnthropicUsage {
|
||||
@@ -532,7 +470,6 @@ pub struct AnthropicStreamTranslator {
|
||||
enum OpenBlock {
|
||||
Text,
|
||||
ToolUse,
|
||||
Thinking,
|
||||
}
|
||||
|
||||
impl AnthropicStreamTranslator {
|
||||
@@ -572,32 +509,6 @@ impl AnthropicStreamTranslator {
|
||||
}
|
||||
|
||||
for choice in &chunk.choices {
|
||||
// The model's think block. Dropped entirely until #300: this
|
||||
// translator read `content` and `tool_calls` and nothing
|
||||
// else, so an Anthropic client asked for extended thinking
|
||||
// (`thinking.budget_tokens`, which `anthropic_to_openai`
|
||||
// accepts), was billed for the tokens, and received a stream
|
||||
// with no thinking in it — every turn, silently. Fixing only
|
||||
// the non-streaming translation would have missed this,
|
||||
// because the clients that ask for thinking stream.
|
||||
if let Some(text) = choice
|
||||
.delta
|
||||
.get("reasoning_content")
|
||||
.and_then(Value::as_str)
|
||||
&& !text.is_empty()
|
||||
{
|
||||
self.ensure_thinking_block(&mut out);
|
||||
let index = self.open_block.as_ref().map(|(i, _)| *i).unwrap_or(0);
|
||||
out.push((
|
||||
"content_block_delta".to_string(),
|
||||
json!({
|
||||
"type": "content_block_delta",
|
||||
"index": index,
|
||||
"delta": { "type": "thinking_delta", "thinking": text }
|
||||
}),
|
||||
));
|
||||
}
|
||||
|
||||
if let Some(text) = choice.delta.get("content").and_then(Value::as_str)
|
||||
&& !text.is_empty()
|
||||
{
|
||||
@@ -711,32 +622,6 @@ impl AnthropicStreamTranslator {
|
||||
out
|
||||
}
|
||||
|
||||
/// Open a `thinking` block, closing whatever preceded it.
|
||||
///
|
||||
/// Emitted without a `signature`. Anthropic signs its thinking
|
||||
/// blocks; we cannot mint a valid one, and inventing a value would
|
||||
/// be worse than omitting it. If a client rejects an unsigned block
|
||||
/// the fix is a flag — not a return to deleting the model's work.
|
||||
fn ensure_thinking_block(&mut self, out: &mut Vec<(String, Value)>) {
|
||||
match &self.open_block {
|
||||
Some((_, OpenBlock::Thinking)) => {}
|
||||
_ => {
|
||||
self.close_open_block(out);
|
||||
let index = self.next_index;
|
||||
self.next_index += 1;
|
||||
self.open_block = Some((index, OpenBlock::Thinking));
|
||||
out.push((
|
||||
"content_block_start".to_string(),
|
||||
json!({
|
||||
"type": "content_block_start",
|
||||
"index": index,
|
||||
"content_block": { "type": "thinking", "thinking": "" }
|
||||
}),
|
||||
));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn ensure_text_block(&mut self, out: &mut Vec<(String, Value)>) {
|
||||
match &self.open_block {
|
||||
Some((_, OpenBlock::Text)) => {}
|
||||
@@ -1146,115 +1031,4 @@ mod request_tests {
|
||||
let tools = openai.extra.get("tools").and_then(Value::as_array).unwrap();
|
||||
assert_eq!(tools[0]["function"]["name"], "x");
|
||||
}
|
||||
|
||||
/// The Anthropic path must return the model's thinking (#300).
|
||||
///
|
||||
/// It accepted `thinking.budget_tokens` on the way in and returned
|
||||
/// a bare text block on the way out: the caller spent the tokens,
|
||||
/// never saw them, and could not replay the model's reasoning on
|
||||
/// the next turn. Taking a parameter and silently discarding what
|
||||
/// it buys is the defect, not the missing field.
|
||||
#[test]
|
||||
fn anthropic_response_carries_a_thinking_block() {
|
||||
let mut extra = serde_json::Map::new();
|
||||
extra.insert("reasoning_content".into(), json!("weighing the options"));
|
||||
let resp = ChatCompletionResponse {
|
||||
id: "id".into(),
|
||||
object: "chat.completion".into(),
|
||||
created: 0,
|
||||
model: "m".into(),
|
||||
choices: vec![crate::openai::ChatCompletionChoice {
|
||||
index: 0,
|
||||
message: ChatMessage {
|
||||
role: "assistant".into(),
|
||||
content: MessageContent::Text("the answer".into()),
|
||||
extra: Value::Object(extra),
|
||||
},
|
||||
finish_reason: Some("stop".into()),
|
||||
extra: Value::Null,
|
||||
}],
|
||||
usage: None,
|
||||
extra: Value::Null,
|
||||
};
|
||||
let a = openai_to_anthropic(resp);
|
||||
assert_eq!(a.content.len(), 2, "expected thinking + text");
|
||||
assert_eq!(a.content[0].block_type, "thinking", "thinking comes first");
|
||||
assert_eq!(a.content[0].data["thinking"], "weighing the options");
|
||||
assert_eq!(a.content[1].block_type, "text");
|
||||
assert_eq!(a.content[1].data["text"], "the answer");
|
||||
}
|
||||
|
||||
/// No thinking means the unchanged single text block.
|
||||
#[test]
|
||||
fn anthropic_response_without_thinking_is_unchanged() {
|
||||
let resp = ChatCompletionResponse {
|
||||
id: "id".into(),
|
||||
object: "chat.completion".into(),
|
||||
created: 0,
|
||||
model: "m".into(),
|
||||
choices: vec![crate::openai::ChatCompletionChoice {
|
||||
index: 0,
|
||||
message: ChatMessage {
|
||||
role: "assistant".into(),
|
||||
content: MessageContent::Text("plain".into()),
|
||||
extra: Value::Object(Default::default()),
|
||||
},
|
||||
finish_reason: Some("stop".into()),
|
||||
extra: Value::Null,
|
||||
}],
|
||||
usage: None,
|
||||
extra: Value::Null,
|
||||
};
|
||||
let a = openai_to_anthropic(resp);
|
||||
assert_eq!(a.content.len(), 1);
|
||||
assert_eq!(a.content[0].block_type, "text");
|
||||
}
|
||||
|
||||
/// Streaming Anthropic must carry thinking too (#300).
|
||||
///
|
||||
/// Fixing only the non-streaming translation would have missed this
|
||||
/// entirely — and missed it for the clients that matter, since the
|
||||
/// ones asking for extended thinking stream.
|
||||
#[test]
|
||||
fn anthropic_stream_emits_thinking_deltas() {
|
||||
use crate::openai::{ChatCompletionChunk, ChunkChoice};
|
||||
let mut t = AnthropicStreamTranslator::new();
|
||||
let chunk = |delta: Value| ChatCompletionChunk {
|
||||
id: "c".into(),
|
||||
object: "chat.completion.chunk".into(),
|
||||
created: 0,
|
||||
model: "m".into(),
|
||||
choices: vec![ChunkChoice {
|
||||
index: 0,
|
||||
delta,
|
||||
finish_reason: None,
|
||||
extra: Value::Null,
|
||||
}],
|
||||
usage: None,
|
||||
extra: Value::Null,
|
||||
};
|
||||
|
||||
let ev = t.on_chunk(&chunk(json!({ "reasoning_content": "weighing it" })));
|
||||
let start = ev
|
||||
.iter()
|
||||
.find(|(n, _)| n == "content_block_start")
|
||||
.expect("a block must open");
|
||||
assert_eq!(start.1["content_block"]["type"], "thinking");
|
||||
let delta = ev
|
||||
.iter()
|
||||
.find(|(n, _)| n == "content_block_delta")
|
||||
.expect("a delta must follow");
|
||||
assert_eq!(delta.1["delta"]["type"], "thinking_delta");
|
||||
assert_eq!(delta.1["delta"]["thinking"], "weighing it");
|
||||
|
||||
// Visible text opens a separate block, after thinking closes.
|
||||
let ev = t.on_chunk(&chunk(json!({ "content": "the answer" })));
|
||||
let names: Vec<&str> = ev.iter().map(|(n, _)| n.as_str()).collect();
|
||||
assert!(
|
||||
names.contains(&"content_block_stop"),
|
||||
"the thinking block must close first: {names:?}"
|
||||
);
|
||||
let start = ev.iter().find(|(n, _)| n == "content_block_start").unwrap();
|
||||
assert_eq!(start.1["content_block"]["type"], "text");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -798,10 +798,6 @@ async fn list_models(State(fleet): State<Arc<CortexState>>) -> Json<Value> {
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
context_window: None,
|
||||
context_length: None,
|
||||
// Catalogue-seeded: no neuron has reported rungs yet.
|
||||
reasoning_budget: Vec::new(),
|
||||
},
|
||||
);
|
||||
}
|
||||
@@ -843,13 +839,6 @@ async fn list_models(State(fleet): State<Arc<CortexState>>) -> Json<Value> {
|
||||
// so a client never overflows the most-constrained
|
||||
// deployment that might serve it.
|
||||
e.limit = tightest_limit(e.limit.take(), entry.limit.clone());
|
||||
// The reasoning ladder this neuron honours (#223).
|
||||
// First non-empty wins: a catalogue-seeded entry
|
||||
// starts with none, and neurons serving the same
|
||||
// model are configured alike.
|
||||
if e.reasoning_budget.is_empty() {
|
||||
e.reasoning_budget = node.reasoning_budget.clone();
|
||||
}
|
||||
})
|
||||
.or_insert_with(|| CortexModelEntry {
|
||||
id: model_id.clone(),
|
||||
@@ -869,10 +858,6 @@ async fn list_models(State(fleet): State<Arc<CortexState>>) -> Json<Value> {
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
context_window: None,
|
||||
context_length: None,
|
||||
// What this neuron says each effort level buys (#223).
|
||||
reasoning_budget: node.reasoning_budget.clone(),
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -934,10 +919,6 @@ async fn list_models(State(fleet): State<Arc<CortexState>>) -> Json<Value> {
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
context_window: None,
|
||||
context_length: None,
|
||||
// What this neuron says each effort level buys (#223).
|
||||
reasoning_budget: node.reasoning_budget.clone(),
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -975,10 +956,6 @@ async fn list_models(State(fleet): State<Arc<CortexState>>) -> Json<Value> {
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
context_window: None,
|
||||
context_length: None,
|
||||
// Catalogue-seeded: no neuron has reported rungs yet.
|
||||
reasoning_budget: Vec::new(),
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
@@ -141,15 +141,6 @@ pub fn usage_sink(
|
||||
/// returns a guard the caller settles with actual usage; on refusal returns
|
||||
/// the #63 envelope (`rate_limit_exceeded` + `Retry-After` for a resetting
|
||||
/// window, `insufficient_quota` for a hard balance — never `402`).
|
||||
// The `Err` variant is the #63 envelope itself, which is a data-carrying
|
||||
// struct (status, type, code, message, param, retry hint, diagnostics) and
|
||||
// is passed by value everywhere it is built, matched and rendered. Boxing it
|
||||
// at this one boundary would push `Box` conversions through three handlers
|
||||
// and both HTTP adapters to save an allocation on a path taken once per
|
||||
// rejected request. clippy 1.98 lowered what it considers large enough to
|
||||
// flag; the shape is deliberate. Same call as the existing allows on the
|
||||
// figment-returning config loaders.
|
||||
#[allow(clippy::result_large_err)]
|
||||
pub async fn reserve_or_reject(
|
||||
provider: Arc<dyn EntitlementProvider>,
|
||||
principal: &Principal,
|
||||
@@ -288,7 +279,7 @@ mod tests {
|
||||
// Requested output dominates; prompt estimate is small for a tiny body.
|
||||
let body = br#"{"model":"m","max_tokens":1000}"#;
|
||||
let est = reservation_estimate(body, Some(8192));
|
||||
assert!((1000..1100).contains(&est), "est was {est}");
|
||||
assert!(est >= 1000 && est < 1100, "est was {est}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
//! in Prometheus text format.
|
||||
|
||||
use anyhow::Result;
|
||||
use metrics_exporter_prometheus::{Matcher, PrometheusBuilder};
|
||||
use metrics_exporter_prometheus::PrometheusBuilder;
|
||||
use std::net::SocketAddr;
|
||||
|
||||
/// Install the Prometheus metrics recorder and return a handle.
|
||||
@@ -12,7 +12,8 @@ use std::net::SocketAddr;
|
||||
pub fn install(listen: &str) -> Result<()> {
|
||||
let addr: SocketAddr = listen.parse()?;
|
||||
|
||||
with_buckets(PrometheusBuilder::new().with_http_listener(addr))?
|
||||
PrometheusBuilder::new()
|
||||
.with_http_listener(addr)
|
||||
.install()
|
||||
.map_err(|e| anyhow::anyhow!("failed to install Prometheus exporter: {e}"))?;
|
||||
|
||||
@@ -24,77 +25,13 @@ pub fn install(listen: &str) -> Result<()> {
|
||||
/// Install a recorder for testing (no HTTP listener). Returns a handle
|
||||
/// that can render the current metrics as Prometheus text.
|
||||
pub fn install_test_recorder() -> Result<metrics_exporter_prometheus::PrometheusHandle> {
|
||||
let handle = with_buckets(PrometheusBuilder::new())?
|
||||
let handle = PrometheusBuilder::new()
|
||||
.install_recorder()
|
||||
.map_err(|e| anyhow::anyhow!("failed to install test recorder: {e}"))?;
|
||||
describe_metrics();
|
||||
Ok(handle)
|
||||
}
|
||||
|
||||
/// Give every histogram explicit buckets, so it is exported as a
|
||||
/// Prometheus **histogram** rather than a summary.
|
||||
///
|
||||
/// Without this, `metrics-exporter-prometheus` renders every
|
||||
/// `histogram!` as a summary: `{quantile="0.95"}` series and no
|
||||
/// `_bucket` series at all. Three things break as a result, and the
|
||||
/// third is what made it visible.
|
||||
///
|
||||
/// 1. `histogram_quantile()` has nothing to read, so any dashboard
|
||||
/// panel written the idiomatic way returns *No data* forever. The
|
||||
/// fleet dashboard's TTFT panel did exactly that while cortex was
|
||||
/// serving thousands of requests.
|
||||
/// 2. Summary quantiles are computed per process over a rolling
|
||||
/// window, so they **cannot be aggregated**. Averaging p95 across
|
||||
/// two gateways is not p95 of anything.
|
||||
/// 3. They decay: with no samples in the window every quantile reads
|
||||
/// `0`, which is indistinguishable from "genuinely instant" on a
|
||||
/// graph.
|
||||
///
|
||||
/// Buckets are per-metric because the quantities differ by orders of
|
||||
/// magnitude — a request lasting minutes and a TTFT of milliseconds
|
||||
/// have no useful shared scale. Ranges are chosen from observed fleet
|
||||
/// behaviour rather than round numbers: decode runs for minutes on a
|
||||
/// long turn, prefill is seconds on a long prompt, and decode
|
||||
/// throughput sits in the tens of tokens/sec.
|
||||
fn with_buckets(builder: PrometheusBuilder) -> Result<PrometheusBuilder> {
|
||||
let seconds_short = &[
|
||||
0.05, 0.1, 0.25, 0.5, 1.0, 2.0, 5.0, 10.0, 20.0, 30.0, 60.0, 120.0,
|
||||
];
|
||||
let seconds_long = &[
|
||||
0.1, 0.5, 1.0, 2.5, 5.0, 10.0, 30.0, 60.0, 120.0, 300.0, 600.0, 1200.0,
|
||||
];
|
||||
let tokens_per_second = &[
|
||||
1.0, 2.5, 5.0, 10.0, 15.0, 20.0, 30.0, 40.0, 60.0, 80.0, 120.0, 200.0,
|
||||
];
|
||||
builder
|
||||
// Whole-request latency: a long agentic turn legitimately runs
|
||||
// for many minutes, so the tail has to reach there.
|
||||
.set_buckets_for_metric(
|
||||
Matcher::Full("cortex_request_duration_seconds".into()),
|
||||
seconds_long,
|
||||
)?
|
||||
// Prefill: sub-second for a short prompt, seconds for a long
|
||||
// one. Anything past a minute is pathological and belongs in
|
||||
// the overflow bucket.
|
||||
.set_buckets_for_metric(
|
||||
Matcher::Full("cortex_time_to_first_token_seconds".into()),
|
||||
seconds_short,
|
||||
)?
|
||||
// Image generation is inherently slower than a text turn and
|
||||
// scales with resolution and step count.
|
||||
.set_buckets_for_metric(
|
||||
Matcher::Full("cortex_images_generation_seconds".into()),
|
||||
seconds_long,
|
||||
)?
|
||||
// Not a duration — decode throughput, tens of tokens/sec on
|
||||
// this fleet.
|
||||
.set_buckets_for_metric(
|
||||
Matcher::Full("cortex_tokens_per_second".into()),
|
||||
tokens_per_second,
|
||||
)
|
||||
.map_err(|e| anyhow::anyhow!("failed to configure histogram buckets: {e}"))
|
||||
}
|
||||
|
||||
fn describe_metrics() {
|
||||
metrics::describe_histogram!(
|
||||
"cortex_request_duration_seconds",
|
||||
@@ -121,10 +58,6 @@ fn describe_metrics() {
|
||||
"cortex_request_errors_total",
|
||||
"Total number of failed proxy requests"
|
||||
);
|
||||
metrics::describe_counter!(
|
||||
"cortex_cached_prompt_tokens_total",
|
||||
"Prompt tokens served from neuron's prefix KV cache; over cortex_prompt_tokens_total this is the cache-hit rate (#269)"
|
||||
);
|
||||
metrics::describe_counter!("cortex_evictions_total", "Total number of model evictions");
|
||||
metrics::describe_counter!(
|
||||
"cortex_cold_starts_total",
|
||||
@@ -178,15 +111,7 @@ fn describe_metrics() {
|
||||
);
|
||||
metrics::describe_counter!(
|
||||
"cortex_model_rejections_total",
|
||||
"Admission rejections per neuron:model by reason: queue_full / wait_timeout / per_principal / anon_yield — the load-shedding signal (#137, #262)"
|
||||
);
|
||||
metrics::describe_gauge!(
|
||||
"cortex_model_anon_in_flight",
|
||||
"Anonymous (unattributable) requests holding a seat on a neuron:model (#262)"
|
||||
);
|
||||
metrics::describe_gauge!(
|
||||
"cortex_model_anon_max_in_flight",
|
||||
"Seats anonymous traffic may hold at once, so it cannot starve identified callers (#262)"
|
||||
"Admission rejections per neuron:model by reason: queue_full / wait_timeout / per_principal — the load-shedding signal (#137)"
|
||||
);
|
||||
metrics::describe_gauge!(
|
||||
"cortex_model_tok_s_decode",
|
||||
@@ -197,43 +122,3 @@ fn describe_metrics() {
|
||||
"Live prefill throughput per neuron:model, tokens/sec EMA (#137)"
|
||||
);
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod bucket_tests {
|
||||
/// Histograms must export as Prometheus **histograms**, with
|
||||
/// `_bucket` series — not as summaries.
|
||||
///
|
||||
/// This asserts the exported *shape*, not the recording call,
|
||||
/// because the recording was never the problem: cortex measured
|
||||
/// TTFT correctly for months while the fleet dashboard's panel sat
|
||||
/// on "No data", since `histogram_quantile()` reads `_bucket`
|
||||
/// series and a summary has none. A metric that is collected but
|
||||
/// cannot be queried is indistinguishable from one that was never
|
||||
/// collected — from the graph, and from the operator's chair.
|
||||
#[test]
|
||||
fn histograms_export_buckets_not_summary_quantiles() {
|
||||
let handle = match super::install_test_recorder() {
|
||||
Ok(h) => h,
|
||||
// Another test in this binary owns the global recorder;
|
||||
// it installs the same buckets, so skipping is honest.
|
||||
Err(_) => return,
|
||||
};
|
||||
metrics::histogram!("cortex_time_to_first_token_seconds", "node" => "n", "model" => "m")
|
||||
.record(0.42);
|
||||
let rendered = handle.render();
|
||||
|
||||
assert!(
|
||||
rendered.contains("cortex_time_to_first_token_seconds_bucket"),
|
||||
"no _bucket series — histogram_quantile() cannot read this:\n{rendered}"
|
||||
);
|
||||
assert!(
|
||||
rendered.contains("# TYPE cortex_time_to_first_token_seconds histogram"),
|
||||
"exported as the wrong metric type:\n{rendered}"
|
||||
);
|
||||
assert!(
|
||||
!rendered
|
||||
.contains(r#"cortex_time_to_first_token_seconds{node="n",model="m",quantile="#),
|
||||
"still exporting summary quantiles, which cannot be aggregated across gateways"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -130,17 +130,6 @@ async fn poll_neuron(fleet: &CortexState, name: &str, endpoint: &str) {
|
||||
Ok(resp) if resp.status().is_success() => {
|
||||
match resp.json::<Vec<ModelInfo>>().await {
|
||||
Ok(models) => {
|
||||
// The reasoning-effort ladder is host configuration:
|
||||
// every model on a neuron reports the same rungs, so
|
||||
// it is held once per node rather than copied onto
|
||||
// each model entry where the two could drift (#223).
|
||||
// Taken from the first model that offers one — a
|
||||
// non-reasoning model advertises none.
|
||||
node.reasoning_budget = models
|
||||
.iter()
|
||||
.map(|m| m.reasoning_budget.clone())
|
||||
.find(|rungs| !rungs.is_empty())
|
||||
.unwrap_or_default();
|
||||
let mut seen = std::collections::HashSet::new();
|
||||
for upstream in &models {
|
||||
seen.insert(upstream.id.clone());
|
||||
@@ -391,21 +380,6 @@ fn export_health_metrics(node: &str, h: &HealthResponse) {
|
||||
counter!("cortex_model_rejections_total",
|
||||
"node" => node.to_string(), "model" => m.id.clone(), "reason" => "per_principal")
|
||||
.absolute(m.rejected_per_principal);
|
||||
counter!("cortex_model_rejections_total",
|
||||
"node" => node.to_string(), "model" => m.id.clone(), "reason" => "anon_yield")
|
||||
.absolute(m.rejected_anon_yield);
|
||||
// How much of this model's load is unattributable (#262), and the
|
||||
// ceiling that keeps it from starving identified callers. 0 for a
|
||||
// pre-#262 neuron, which had no ceiling — skip rather than publish
|
||||
// a 0 that reads as "anonymous is refused" when it means the
|
||||
// opposite.
|
||||
gauge!("cortex_model_anon_in_flight", "node" => node.to_string(), "model" => m.id.clone())
|
||||
.set(m.anon_in_flight as f64);
|
||||
if m.anon_max_in_flight > 0 {
|
||||
gauge!("cortex_model_anon_max_in_flight",
|
||||
"node" => node.to_string(), "model" => m.id.clone())
|
||||
.set(m.anon_max_in_flight as f64);
|
||||
}
|
||||
}
|
||||
for d in &h.devices {
|
||||
let device = d.index.to_string();
|
||||
|
||||
@@ -171,9 +171,6 @@ impl IntoResponse for ProxyError {
|
||||
// over the decode window (first→last chunk); falls back to the
|
||||
// full request duration for single-chunk (non-streaming) bodies
|
||||
// cortex_prompt_tokens_total / cortex_completion_tokens_total (counters)
|
||||
// cortex_cached_prompt_tokens_total (counter) — prompt tokens served
|
||||
// from neuron's prefix cache; over prompt_tokens_total this is the
|
||||
// fleet's cache-hit rate (#269)
|
||||
|
||||
/// Cap on the retained body tail. The usage object rides on the final
|
||||
/// chunk, so a generous tail is plenty; the cap bounds memory on huge
|
||||
@@ -246,15 +243,6 @@ impl ChunkObserver for CortexMetrics {
|
||||
if let Some(prompt) = prompt {
|
||||
metrics::counter!("cortex_prompt_tokens_total", &self.labels).increment(prompt);
|
||||
}
|
||||
// Prefix-cache reuse (#269), read from the same usage object.
|
||||
// Against `cortex_prompt_tokens_total` this gives fleet-wide
|
||||
// cache-hit rate as a ratio, which was previously only
|
||||
// obtainable by grepping `reused=` out of a neuron journal —
|
||||
// per-host, unaggregated, and gone on log rotation.
|
||||
if let Some(cached) = last_count_for(self.tail.as_str(), "cached_tokens") {
|
||||
metrics::counter!("cortex_cached_prompt_tokens_total", &self.labels)
|
||||
.increment(cached);
|
||||
}
|
||||
if let Some(completion) = completion.filter(|c| *c > 0) {
|
||||
metrics::counter!("cortex_completion_tokens_total", &self.labels)
|
||||
.increment(completion);
|
||||
|
||||
@@ -535,11 +535,6 @@ async fn profile_to_spec(
|
||||
quant: profile.quant.clone(),
|
||||
tensor_parallel,
|
||||
devices: Some(devices),
|
||||
// The catalogue's operator override rides along with the load
|
||||
// (#283), so a cold-loaded model samples the same way as one
|
||||
// this host was configured to hold resident.
|
||||
sampling: profile.sampling.clone(),
|
||||
preserve_thinking: profile.preserve_thinking,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -647,8 +642,6 @@ mod tests {
|
||||
pinned_on: vec![],
|
||||
residency_priority: None,
|
||||
source: source.map(String::from),
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
limit: None,
|
||||
cost: None,
|
||||
capabilities: vec![],
|
||||
|
||||
@@ -66,9 +66,6 @@ impl CortexState {
|
||||
endpoint: nc.endpoint.clone(),
|
||||
healthy: false,
|
||||
models: HashMap::new(),
|
||||
// Filled from the neuron's /models reply at the
|
||||
// first poll (#223).
|
||||
reasoning_budget: Vec::new(),
|
||||
lifecycle_cycles: 0,
|
||||
last_poll: None,
|
||||
discovery: None,
|
||||
@@ -101,29 +98,8 @@ impl CortexState {
|
||||
neuron_configs: config.neurons.clone(),
|
||||
eviction: config.eviction.clone(),
|
||||
catalogue,
|
||||
// READ timeout, not a total one. reqwest's `.timeout()` is a
|
||||
// total deadline — "from when the request starts connecting
|
||||
// until the response body has finished" — which for a streamed
|
||||
// completion is a hard cap on how long a model may generate,
|
||||
// not a liveness check. At 300s and ~13 tok/s that capped every
|
||||
// stream at roughly 3.9k tokens: cortex severed the connection
|
||||
// mid-answer, the client reported the stream as terminated, and
|
||||
// neuron carried on generating into a socket nobody was reading.
|
||||
// A long agentic turn could therefore never complete through the
|
||||
// gateway however healthy the fleet was, and the failure looked
|
||||
// like a model fault because the model was blameless.
|
||||
//
|
||||
// `.read_timeout()` resets on every successful read, so it times
|
||||
// out a stalled upstream while letting a producing one run as
|
||||
// long as it needs. The same 300s is kept deliberately: it is
|
||||
// the headroom a cold model load needs before its first byte,
|
||||
// which is what the original total timeout was reaching for.
|
||||
//
|
||||
// This pairs with neuron's 1s SSE keep-alive: a healthy stream
|
||||
// puts bytes on the wire every second, so idle here means idle,
|
||||
// and the deadline finally measures what it was meant to.
|
||||
http_client: reqwest::Client::builder()
|
||||
.read_timeout(std::time::Duration::from_secs(300))
|
||||
.timeout(std::time::Duration::from_secs(300))
|
||||
.build()
|
||||
.expect("failed to build HTTP client"),
|
||||
entitlements,
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
//! Integration tests for budget enforcement (#52) — the A0 seatbelt.
|
||||
//!
|
||||
//! A reservation over the key's hard cap is refused *before* neuron is hit,
|
||||
//! with the #63 code matching the cap-window semantics: `rate_limit_exceeded`
|
||||
//! plus `Retry-After` for a resetting window, `insufficient_quota` for a hard
|
||||
//! balance. Spend never exceeds the cap. No 402, ever.
|
||||
//! with the #63 code matching the cap-window semantics (rate_limit_exceeded
|
||||
//! + Retry-After for a resetting window, insufficient_quota for a hard
|
||||
//! balance). Spend never exceeds the cap. No 402, ever.
|
||||
|
||||
use axum::Json;
|
||||
use axum::extract::Path;
|
||||
|
||||
@@ -55,9 +55,6 @@ async fn seed_loaded(fleet: &CortexState, node: &str, in_flight: usize, queue_de
|
||||
kv_available_mb: 0,
|
||||
rejected_timeout: 0,
|
||||
rejected_per_principal: 0,
|
||||
anon_in_flight: 0,
|
||||
anon_max_in_flight: 7,
|
||||
rejected_anon_yield: 0,
|
||||
tok_s_prefill: 0.0,
|
||||
tok_s_decode: 0.0,
|
||||
},
|
||||
|
||||
@@ -69,21 +69,6 @@ capabilities = ["text"]
|
||||
let mut nodes = fleet.nodes.write().await;
|
||||
let node = nodes.get_mut("mock-node").expect("node exists");
|
||||
node.healthy = true;
|
||||
// The rungs the neuron reported at poll time. Since #290 these
|
||||
// come from the model's own chat template rather than operator
|
||||
// configuration, so the fixture uses the shape a real reasoning
|
||||
// model ships: Qwen3.8-27B accepts exactly low/medium/xhigh and
|
||||
// defaults to xhigh.
|
||||
node.reasoning_budget = ["low", "medium", "xhigh"]
|
||||
.into_iter()
|
||||
.map(|effort| cortex_core::harness::ReasoningBudgetRung {
|
||||
default: effort == "xhigh",
|
||||
effort: effort.into(),
|
||||
// No cap: effort is expressed to the model through its
|
||||
// template, not enforced by truncating its thinking.
|
||||
tokens: None,
|
||||
})
|
||||
.collect();
|
||||
node.models.insert(
|
||||
"test-model".into(),
|
||||
ModelEntry {
|
||||
@@ -100,9 +85,6 @@ capabilities = ["text"]
|
||||
context: 49152,
|
||||
input: Some(40960),
|
||||
output: 8192,
|
||||
// The ceiling a request may name, distinct from the
|
||||
// 8192-token reserve above (#278).
|
||||
output_ceiling: 32768,
|
||||
}),
|
||||
servable: None,
|
||||
},
|
||||
@@ -165,53 +147,7 @@ capabilities = ["text"]
|
||||
// vLLM-convention probes (Hermes Agent) auto-detect the window.
|
||||
assert_eq!(entry["max_model_len"], 49152);
|
||||
assert_eq!(entry["max_input_tokens"], 40960);
|
||||
// The ceiling, not the reserve (#278). A client that reads this
|
||||
// field turns it into the cap it sends on each request; advertising
|
||||
// the 8192 reserve told a reasoning model's harness to stop below
|
||||
// the cost of a single think block. Observed with dsh — pi takes
|
||||
// `maxTokens` from static config and reads nothing here.
|
||||
assert_eq!(entry["max_output_tokens"], 32768);
|
||||
// The rungs the model itself accepts (#290). A caller can only send
|
||||
// a rung name, so a name we invent is one the template will reject.
|
||||
// Publishing the true set is correct regardless of who reads it —
|
||||
// pi-ai, for one, takes its levels from static config instead.
|
||||
let rungs = entry["reasoning_budget"]
|
||||
.as_array()
|
||||
.expect("reasoning_budget advertised for a reasoning model");
|
||||
let names: Vec<&str> = rungs
|
||||
.iter()
|
||||
.map(|r| r["effort"].as_str().expect("effort"))
|
||||
.collect();
|
||||
assert_eq!(names, ["low", "medium", "xhigh"]);
|
||||
// Which rung applies when the caller names none. Without this a
|
||||
// silent caller cannot tell what it is getting — on Qwen3.8 that is
|
||||
// xhigh, the most expensive rung on the ladder.
|
||||
let default_rung: Vec<&str> = rungs
|
||||
.iter()
|
||||
.filter(|r| r["default"].as_bool().unwrap_or(false))
|
||||
.map(|r| r["effort"].as_str().expect("effort"))
|
||||
.collect();
|
||||
assert_eq!(
|
||||
default_rung,
|
||||
["xhigh"],
|
||||
"the model's own default must be visible"
|
||||
);
|
||||
// A named rung carries no token count: effort reaches the model
|
||||
// through its template, and enforcing it by truncation is the defect
|
||||
// #290 fixed.
|
||||
assert!(
|
||||
rungs.iter().all(|r| r.get("tokens").is_none()),
|
||||
"a named rung must not masquerade as a token budget"
|
||||
);
|
||||
|
||||
// The window under the two names a generic client may read, for one
|
||||
// that probes these rather than `max_model_len`. Publish all three;
|
||||
// do not assume a particular client consumes any of them. pi, in
|
||||
// particular, reads none — `contextWindow` is a required static
|
||||
// field on its model type (checked against 0.82.1 and 0.84.3), so
|
||||
// its window is hand-maintained whatever we advertise.
|
||||
assert_eq!(entry["context_window"], 49152);
|
||||
assert_eq!(entry["context_length"], 49152);
|
||||
assert_eq!(entry["max_output_tokens"], 8192);
|
||||
|
||||
// No limit → flat fields omitted entirely, never 0 or a guess.
|
||||
let unknown = body["data"]
|
||||
@@ -221,13 +157,7 @@ capabilities = ["text"]
|
||||
.find(|m| m["id"] == "no-limit-model")
|
||||
.expect("no-limit-model present in /v1/models");
|
||||
assert!(unknown.get("limit").is_none());
|
||||
for key in [
|
||||
"max_model_len",
|
||||
"max_input_tokens",
|
||||
"max_output_tokens",
|
||||
"context_window",
|
||||
"context_length",
|
||||
] {
|
||||
for key in ["max_model_len", "max_input_tokens", "max_output_tokens"] {
|
||||
assert!(
|
||||
unknown.get(key).is_none(),
|
||||
"{key} must be omitted when the window is unknown"
|
||||
|
||||
@@ -96,7 +96,6 @@ async fn spawn_gateway(neuron: &str, context: usize) -> String {
|
||||
context,
|
||||
input: None,
|
||||
output: 16,
|
||||
output_ceiling: 0,
|
||||
}),
|
||||
servable: None,
|
||||
},
|
||||
|
||||
@@ -80,7 +80,7 @@ The fastest path: env-var single-endpoint config.
|
||||
|
||||
```sh
|
||||
export HELEXA_ACP_BASE_URL=http://hanzalova.internal:31313/v1
|
||||
export HELEXA_ACP_MODEL=Qwen/Qwen3.8-27B
|
||||
export HELEXA_ACP_MODEL=Qwen/Qwen3.6-27B
|
||||
helexa-acp # speaks ACP over stdin/stdout; not interactive
|
||||
```
|
||||
|
||||
@@ -117,7 +117,7 @@ default_endpoint = "helexa"
|
||||
name = "helexa"
|
||||
base_url = "http://hanzalova.internal:31313/v1"
|
||||
wire_api = "openai-chat"
|
||||
default_model = "Qwen/Qwen3.8-27B"
|
||||
default_model = "Qwen/Qwen3.6-27B"
|
||||
max_tokens = 8192
|
||||
context_window = 32768
|
||||
|
||||
@@ -138,7 +138,7 @@ default_model = "claude-opus-4"
|
||||
|
||||
Restart Zed. The model dropdown lists every model from every
|
||||
configured endpoint with the `endpoint:model` selector
|
||||
(`helexa:Qwen/Qwen3.8-27B`, `openrouter:anthropic/claude-opus-4`,
|
||||
(`helexa:Qwen/Qwen3.6-27B`, `openrouter:anthropic/claude-opus-4`,
|
||||
…). Switch mid-session; the next prompt routes to the new endpoint.
|
||||
|
||||
When only one endpoint is configured the prefix is dropped (model
|
||||
@@ -166,7 +166,7 @@ Copy-pasteable blocks. Mix and match.
|
||||
name = "helexa"
|
||||
base_url = "http://hanzalova.internal:31313/v1"
|
||||
wire_api = "openai-chat"
|
||||
default_model = "Qwen/Qwen3.8-27B"
|
||||
default_model = "Qwen/Qwen3.6-27B"
|
||||
max_tokens = 8192
|
||||
context_window = 32768
|
||||
```
|
||||
@@ -241,7 +241,7 @@ vLLM.
|
||||
name = "lan"
|
||||
base_url = "http://hanzalova.internal:31313/v1"
|
||||
wire_api = "openai-chat"
|
||||
default_model = "Qwen/Qwen3.8-27B"
|
||||
default_model = "Qwen/Qwen3.6-27B"
|
||||
|
||||
[[endpoints]]
|
||||
name = "cloud"
|
||||
|
||||
@@ -214,39 +214,11 @@ fn default_notify_to() -> String {
|
||||
}
|
||||
|
||||
impl AngelsConfig {
|
||||
/// A sibling `secrets.toml`, if present, merges after the main file
|
||||
/// and wins — see [`secrets_path`].
|
||||
pub fn load(path: impl AsRef<Path>) -> anyhow::Result<Self> {
|
||||
let path = path.as_ref();
|
||||
let cfg: Self = Figment::new()
|
||||
.merge(Toml::file(path))
|
||||
.merge(Toml::file(secrets_path(path)))
|
||||
.merge(Toml::file(path.as_ref()))
|
||||
.merge(Env::prefixed("ANGELS_").split("__"))
|
||||
.extract()?;
|
||||
Ok(cfg)
|
||||
}
|
||||
}
|
||||
|
||||
/// `secrets.toml` beside the main config.
|
||||
///
|
||||
/// The main file holds structure and is deployed by CI; this one holds
|
||||
/// credentials, is written only by the operator, and is never read,
|
||||
/// written or diffed by the pipeline. Merging it last means the
|
||||
/// operator's value wins, so a deploy cannot swap a live credential for
|
||||
/// a placeholder.
|
||||
///
|
||||
/// The split exists because config CI cannot write is config no check
|
||||
/// can defend — `helexa-router.toml` was kept out of git for sitting
|
||||
/// beside secret-bearing files, and its stale alias then took a node
|
||||
/// down (2026-08-27). The answer is to separate secrets from structure,
|
||||
/// not to hand the pipeline the credentials.
|
||||
///
|
||||
/// A missing file is not an error: figment treats an absent
|
||||
/// `Toml::file` as an empty source, so existing single-file deployments
|
||||
/// keep working untouched.
|
||||
fn secrets_path(config: &Path) -> std::path::PathBuf {
|
||||
config
|
||||
.parent()
|
||||
.unwrap_or_else(|| Path::new("."))
|
||||
.join("secrets.toml")
|
||||
}
|
||||
|
||||
@@ -34,7 +34,6 @@ pub fn api_routes(state: ApiState) -> Router {
|
||||
Router::new()
|
||||
.route("/api/health", get(health))
|
||||
.route("/api/dimensions", get(dimensions))
|
||||
.route("/api/regimes", get(regimes))
|
||||
.route("/api/summary", get(summary))
|
||||
.route("/api/scaling", get(scaling))
|
||||
.route("/api/concurrency", get(concurrency))
|
||||
@@ -66,14 +65,6 @@ async fn health(State(s): State<ApiState>) -> Result<Json<serde_json::Value>, Ap
|
||||
Ok(Json(json!({ "status": "ok", "run_count": count })))
|
||||
}
|
||||
|
||||
/// Declared measurement-regime boundaries (#288).
|
||||
///
|
||||
/// Static — no store access — but served from the API rather than
|
||||
/// hardcoded in the frontend so `report` and the UI cite one list.
|
||||
async fn regimes() -> Json<&'static [crate::regime::MeasurementRegime]> {
|
||||
Json(crate::regime::REGIMES)
|
||||
}
|
||||
|
||||
async fn dimensions(State(s): State<ApiState>) -> Result<Json<crate::store::Dimensions>, ApiError> {
|
||||
let store = s.lock().await;
|
||||
store.dimensions().map(Json).map_err(err500)
|
||||
|
||||
@@ -6,7 +6,6 @@ use crate::config::{TargetConfig, TargetKind};
|
||||
use anyhow::{Context, Result, anyhow};
|
||||
use cortex_core::build_info::BuildInfo;
|
||||
use cortex_core::discovery::{DiscoveryResponse, HealthResponse};
|
||||
use cortex_core::entitlements::{HEADER_ACCOUNT_ID, HEADER_KEY_ID};
|
||||
use cortex_core::harness::{ModelInfo, ModelSpec};
|
||||
use cortex_core::openai::ModelsResponse;
|
||||
use std::time::Duration;
|
||||
@@ -20,49 +19,10 @@ pub struct TargetClient {
|
||||
|
||||
impl TargetClient {
|
||||
pub fn new(request_timeout: Duration) -> Result<Self> {
|
||||
Self::with_principal(request_timeout, None)
|
||||
}
|
||||
|
||||
/// Build a client that stamps `principal`'s identity headers on every
|
||||
/// request (#288).
|
||||
///
|
||||
/// Set on the client rather than at each call site so no scenario can
|
||||
/// be added later that silently measures as anonymous — which is the
|
||||
/// failure this fixes, and it was invisible for a week.
|
||||
///
|
||||
/// `None` keeps the historical anonymous behaviour, which is correct
|
||||
/// for `openai` targets (the headers mean nothing to a foreign
|
||||
/// engine) and for a fresh install with no principal configured.
|
||||
pub fn with_principal(
|
||||
request_timeout: Duration,
|
||||
principal: Option<&crate::config::PrincipalSettings>,
|
||||
) -> Result<Self> {
|
||||
let mut builder = reqwest::Client::builder().timeout(request_timeout);
|
||||
if let Some(p) = principal {
|
||||
let mut headers = reqwest::header::HeaderMap::new();
|
||||
headers.insert(
|
||||
HEADER_ACCOUNT_ID,
|
||||
reqwest::header::HeaderValue::from_str(&p.account_id)
|
||||
.context("principal.account_id is not a valid header value")?,
|
||||
);
|
||||
headers.insert(
|
||||
HEADER_KEY_ID,
|
||||
reqwest::header::HeaderValue::from_str(&p.key_id)
|
||||
.context("principal.key_id is not a valid header value")?,
|
||||
);
|
||||
tracing::info!(
|
||||
account_id = %p.account_id,
|
||||
key_id = %p.key_id,
|
||||
"bench authenticates: measurements reflect identified-caller capacity (#288)"
|
||||
);
|
||||
builder = builder.default_headers(headers);
|
||||
} else {
|
||||
tracing::warn!(
|
||||
"bench has no [bench.principal]: requests are anonymous, so since #262 \
|
||||
they measure the anonymous-yield policy rather than serving capacity (#288)"
|
||||
);
|
||||
}
|
||||
let http = builder.build().context("building HTTP client")?;
|
||||
let http = reqwest::Client::builder()
|
||||
.timeout(request_timeout)
|
||||
.build()
|
||||
.context("building HTTP client")?;
|
||||
Ok(TargetClient { http })
|
||||
}
|
||||
|
||||
@@ -209,15 +169,6 @@ impl TargetClient {
|
||||
quant: None,
|
||||
tensor_parallel: (info.devices.len() > 1).then_some(info.devices.len() as u32),
|
||||
devices: Some(info.devices.clone()),
|
||||
// `GET /models` does not report the operator sampling
|
||||
// override (#283), so a spec reconstructed here cannot carry
|
||||
// it — same limitation as `quant` directly above. Benign
|
||||
// while this is only used to re-load a model the host
|
||||
// already has a `[[default_models]]` entry for, since that
|
||||
// entry supplies the override; it would matter if this were
|
||||
// ever used to load a model the host has no config for.
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -282,11 +233,9 @@ impl TargetClient {
|
||||
cost: None,
|
||||
tool_call: false,
|
||||
reasoning: false,
|
||||
preserve_thinking: None,
|
||||
// A generic OpenAI endpoint says nothing about
|
||||
// serviceability, and absent means "no opinion".
|
||||
servable: None,
|
||||
reasoning_budget: Vec::new(),
|
||||
})
|
||||
.collect())
|
||||
}
|
||||
|
||||
@@ -67,44 +67,6 @@ pub struct BenchSettings {
|
||||
/// SQLite system-of-record path.
|
||||
#[serde(default = "default_db_path")]
|
||||
pub db_path: String,
|
||||
/// Identity bench presents to a neuron (#288).
|
||||
///
|
||||
/// Without this bench is *anonymous*, and since #262 anonymous
|
||||
/// callers are served only from capacity left over once identified
|
||||
/// traffic is satisfied — they are capped below `max_in_flight` and
|
||||
/// park at the class gate ahead of every other gate. Measured on
|
||||
/// beast, that moved `concurrency:8` from 168.9 tok/s / 0.53 s
|
||||
/// ttft_p95 to 104.6 / 11.77 s the day #262 landed, and held there.
|
||||
///
|
||||
/// So an unauthenticated bench does not measure serving capacity; it
|
||||
/// measures the yield policy. Real traffic arrives through cortex
|
||||
/// with a principal and is subject to none of it.
|
||||
///
|
||||
/// Deliberately not an admission *exemption*: bench should be
|
||||
/// subject to the same rules as any caller, or it measures something
|
||||
/// no user experiences — the same class of error in the other
|
||||
/// direction. Give it a principal and let it queue like everyone
|
||||
/// else.
|
||||
#[serde(default)]
|
||||
pub principal: Option<PrincipalSettings>,
|
||||
}
|
||||
|
||||
/// The account/key pair bench stamps on inference requests (#288).
|
||||
///
|
||||
/// These are the headers cortex asserts after a bearer resolves (#49).
|
||||
/// Bench talks to neurons **directly** over the WireGuard mesh, so it
|
||||
/// stamps them itself — the same trust model the link already relies on,
|
||||
/// since a neuron accepts them from cortex on exactly that basis.
|
||||
///
|
||||
/// Give bench its *own* pair rather than borrowing a real caller's: it
|
||||
/// then holds its own fair-share allocation (#54) and cannot starve
|
||||
/// interactive traffic, which is the failure #262 was fixing.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct PrincipalSettings {
|
||||
/// Stamped as `x-helexa-account-id`.
|
||||
pub account_id: String,
|
||||
/// Stamped as `x-helexa-key-id`.
|
||||
pub key_id: String,
|
||||
}
|
||||
|
||||
impl Default for BenchSettings {
|
||||
@@ -115,7 +77,6 @@ impl Default for BenchSettings {
|
||||
iteration_pause_secs: default_iter_pause(),
|
||||
request_timeout_secs: default_timeout(),
|
||||
db_path: default_db_path(),
|
||||
principal: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -149,18 +110,6 @@ pub struct ScenarioConfig {
|
||||
/// deliberately, e.g. `concurrency_levels = [2, 4, 8]`.
|
||||
#[serde(default)]
|
||||
pub concurrency_levels: Vec<u32>,
|
||||
/// Concurrency levels to run **non-streaming** (#285). Separate from
|
||||
/// `concurrency_levels` because the two shapes are not
|
||||
/// interchangeable: streaming multiplexes through the batch engine,
|
||||
/// non-streaming did not until #285 and serialized completely — a
|
||||
/// measured 1.00x aggregate throughput at every level against 3.98x
|
||||
/// streamed.
|
||||
///
|
||||
/// Defaults to the top level only. The signal is starkest there and
|
||||
/// each extra level costs a full burst per sample per build; an
|
||||
/// operator who wants the whole curve can list it.
|
||||
#[serde(default = "default_concurrency_nonstreaming_levels")]
|
||||
pub concurrency_nonstreaming_levels: Vec<u32>,
|
||||
/// Square image sizes (px per side) — one `image:<px>` scenario per
|
||||
/// entry (#203), run only against models advertising the `image`
|
||||
/// capability. Defaults to `[1024]`.
|
||||
@@ -199,7 +148,6 @@ impl Default for ScenarioConfig {
|
||||
prompt_sizes: default_prompt_sizes(),
|
||||
max_tokens: default_max_tokens(),
|
||||
concurrency_levels: Vec::new(),
|
||||
concurrency_nonstreaming_levels: Vec::new(),
|
||||
concurrency_prompt_tokens: default_concurrency_prompt_tokens(),
|
||||
image_sizes: default_image_sizes(),
|
||||
capability_probes: Vec::new(),
|
||||
@@ -267,10 +215,6 @@ fn default_timeout() -> u64 {
|
||||
fn default_db_path() -> String {
|
||||
"/var/lib/helexa-bench/bench.sqlite".to_string()
|
||||
}
|
||||
fn default_concurrency_nonstreaming_levels() -> Vec<u32> {
|
||||
vec![8]
|
||||
}
|
||||
|
||||
fn default_api_enabled() -> bool {
|
||||
true
|
||||
}
|
||||
@@ -299,44 +243,6 @@ fn default_capability_max_tokens() -> u64 {
|
||||
// figment's, not ours, so suppress the lint here.
|
||||
#[allow(clippy::result_large_err)]
|
||||
mod tests {
|
||||
|
||||
/// #288: a config with no `[bench.principal]` must still parse — the
|
||||
/// anonymous behaviour is the historical one and correct for
|
||||
/// `openai` targets — but a configured one must round-trip, because
|
||||
/// a silently-dropped principal reverts the measurement to the
|
||||
/// anonymous-yield path without changing a visible number.
|
||||
#[test]
|
||||
fn principal_is_optional_and_round_trips() {
|
||||
let parse = |t: &str| -> BenchConfig {
|
||||
figment::Figment::new()
|
||||
.merge(figment::providers::Toml::string(t))
|
||||
.extract()
|
||||
.expect("parse")
|
||||
};
|
||||
let none = parse("[bench]\nsamples_per_version = 3\n");
|
||||
assert!(none.bench.principal.is_none());
|
||||
|
||||
let some = parse(
|
||||
"[bench]\nsamples_per_version = 3\n\n\
|
||||
[bench.principal]\naccount_id = \"acct\"\nkey_id = \"k1\"\n",
|
||||
);
|
||||
let p = some.bench.principal.expect("principal");
|
||||
assert_eq!((p.account_id.as_str(), p.key_id.as_str()), ("acct", "k1"));
|
||||
}
|
||||
|
||||
/// The non-streaming burst defaults on (#285). If it defaulted off,
|
||||
/// the path that serialized completely would stay unmeasured on every
|
||||
/// fleet that had not opted in — which is how it went unnoticed.
|
||||
#[test]
|
||||
fn nonstreaming_concurrency_defaults_to_the_top_level() {
|
||||
let cfg: BenchConfig = figment::Figment::new()
|
||||
.merge(figment::providers::Toml::string(
|
||||
"[scenarios]\nprompt_sizes = [128]\n",
|
||||
))
|
||||
.extract()
|
||||
.expect("parse");
|
||||
assert_eq!(cfg.scenarios.concurrency_nonstreaming_levels, vec![8]);
|
||||
}
|
||||
use super::*;
|
||||
use figment::Jail;
|
||||
|
||||
|
||||
@@ -7,7 +7,6 @@
|
||||
pub mod api;
|
||||
pub mod client;
|
||||
pub mod config;
|
||||
pub mod regime;
|
||||
pub mod report;
|
||||
pub mod scenario;
|
||||
pub mod store;
|
||||
|
||||
@@ -1,148 +0,0 @@
|
||||
//! Measurement-regime boundaries — builds where a number changed
|
||||
//! meaning rather than value.
|
||||
//!
|
||||
//! A trend line silently spans them, and every reader re-derives the
|
||||
//! same thing: that a cliff was the instrument, not the engine. Three
|
||||
//! have already cost real investigation time:
|
||||
//!
|
||||
//! - beast's `concurrency:8` fell 168.9 → 104.6 tok/s with `ttft_p95`
|
||||
//! rising 0.53 → 11.77 s, and it read as a 38% throughput regression
|
||||
//! until the one commit in the window turned out to be an admission
|
||||
//! *policy* change that bench, being anonymous, was subject to (#288).
|
||||
//! - quadbrat's `capability:debug-reason` TTFT fell 88.8 → 0.1 s, which
|
||||
//! read as a latency win and was a redefinition of when the clock
|
||||
//! stops.
|
||||
//! - the same redefinition put decode rates at ~250 tok/s on a 3060
|
||||
//! beforehand, by dividing reasoning-inclusive token counts by a
|
||||
//! visible-content-only window.
|
||||
//!
|
||||
//! So the boundaries are declared, not remembered. Declared here rather
|
||||
//! than in the frontend because `report` renders the same series into
|
||||
//! `benchmarks.md` and needs the same caveats.
|
||||
//!
|
||||
//! ## What belongs here
|
||||
//!
|
||||
//! Only changes to **what a metric means**. A change that made the
|
||||
//! server genuinely faster, slower, or differently behaved does *not*
|
||||
//! belong — that is the signal these lines exist to keep readable. #280
|
||||
//! (fetch the model's own chat template) moved quadbrat's
|
||||
//! `completion_tokens` from 4096 to 1053 by ending a truncation loop;
|
||||
//! that is a real behavioural change and stays unmarked.
|
||||
//!
|
||||
//! The identified/anonymous split is deliberately absent too: it is
|
||||
//! recorded per-row in `runs.principal`, so the UI derives it from the
|
||||
//! data instead of trusting a constant to stay true.
|
||||
|
||||
use serde::Serialize;
|
||||
|
||||
/// A build at which one or more metrics changed meaning.
|
||||
#[derive(Debug, Clone, Serialize)]
|
||||
pub struct MeasurementRegime {
|
||||
/// Short SHA of the first build measured under the new semantics.
|
||||
/// Matched against `SeriesPoint::git_sha`, so a boundary whose build
|
||||
/// never appears in a selection simply does not draw.
|
||||
pub first_sha: &'static str,
|
||||
/// Terse label for the chart rule.
|
||||
pub label: &'static str,
|
||||
/// What changed, and why the step is not a performance result.
|
||||
pub detail: &'static str,
|
||||
/// Series keys the change affects, as the API/UI name them. A
|
||||
/// boundary only draws on panels carrying one of these — marking
|
||||
/// every panel would train people to ignore the rules.
|
||||
pub affects: &'static [&'static str],
|
||||
}
|
||||
|
||||
/// The declared boundaries, oldest first.
|
||||
pub const REGIMES: &[MeasurementRegime] = &[
|
||||
MeasurementRegime {
|
||||
first_sha: "92dddc0",
|
||||
label: "#262 anonymous callers yield",
|
||||
detail: "Anonymous traffic became servable only from capacity left over \
|
||||
once identified traffic is satisfied — capped below max_in_flight \
|
||||
and parked at the class gate. An anonymous bench therefore \
|
||||
characterises the yield policy rather than serving capacity. \
|
||||
Steps here are admission policy, not the engine (#288).",
|
||||
affects: &["decode", "ttft", "ttftP95", "queueWait", "rejected"],
|
||||
},
|
||||
MeasurementRegime {
|
||||
first_sha: "0fe7aa3",
|
||||
label: "#117 reasoning counts as liveness",
|
||||
detail: "TTFT previously waited for the first *visible content* chunk, so \
|
||||
on a thinking model it measured the whole reasoning span (88.8 s \
|
||||
on quadbrat). It now stops at the first delta of any kind. The \
|
||||
same change fixed decode rates computed by dividing \
|
||||
reasoning-inclusive token counts by a content-only window, which \
|
||||
had produced ~250 tok/s on a 3060.",
|
||||
affects: &["decode", "ttft"],
|
||||
},
|
||||
];
|
||||
|
||||
/// Boundaries affecting `metric`, in declaration order.
|
||||
pub fn regimes_for(metric: &str) -> Vec<&'static MeasurementRegime> {
|
||||
REGIMES
|
||||
.iter()
|
||||
.filter(|r| r.affects.contains(&metric))
|
||||
.collect()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// A boundary that names no metric would draw nowhere and mislead by
|
||||
/// omission; one naming an unknown key would draw nowhere and look
|
||||
/// fine. Both are typos this catches.
|
||||
#[test]
|
||||
fn every_regime_affects_a_known_series_key() {
|
||||
// The keys `Trends.tsx` maps `SeriesPoint` onto.
|
||||
const KNOWN: &[&str] = &[
|
||||
"decode",
|
||||
"ttft",
|
||||
"ttftP95",
|
||||
"queueWait",
|
||||
"rejected",
|
||||
"prefillTps",
|
||||
"reasoning",
|
||||
"cached",
|
||||
"completion",
|
||||
"tpot",
|
||||
];
|
||||
for r in REGIMES {
|
||||
assert!(
|
||||
!r.affects.is_empty(),
|
||||
"{} affects nothing, so it would never draw",
|
||||
r.first_sha
|
||||
);
|
||||
for key in r.affects {
|
||||
assert!(
|
||||
KNOWN.contains(key),
|
||||
"{} names unknown series key {key:?}",
|
||||
r.first_sha
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn regimes_for_selects_by_metric() {
|
||||
assert!(regimes_for("ttft").iter().any(|r| r.first_sha == "0fe7aa3"));
|
||||
assert!(
|
||||
regimes_for("completion").is_empty(),
|
||||
"#280 changed behaviour, not meaning — it must not be marked"
|
||||
);
|
||||
}
|
||||
|
||||
/// Short SHAs are matched against `SeriesPoint::git_sha`, which the
|
||||
/// store records at the width `/version` reports.
|
||||
#[test]
|
||||
fn declared_shas_are_short_form() {
|
||||
for r in REGIMES {
|
||||
assert_eq!(
|
||||
r.first_sha.len(),
|
||||
7,
|
||||
"{} is not a 7-char short sha; it would never match a series point",
|
||||
r.first_sha
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -9,7 +9,6 @@
|
||||
use crate::config::ScenarioConfig;
|
||||
use anyhow::{Context, Result, anyhow};
|
||||
use async_trait::async_trait;
|
||||
use cortex_core::entitlements::HEADER_KEY_ID;
|
||||
use cortex_core::harness::ModelInfo;
|
||||
use cortex_core::openai::ChatCompletionChunk;
|
||||
use eventsource_stream::Eventsource;
|
||||
@@ -47,17 +46,6 @@ pub struct RunCtx<'a> {
|
||||
pub model_id: String,
|
||||
pub max_tokens: u64,
|
||||
pub timeout: Duration,
|
||||
/// Base `x-helexa-key-id` bench presents (#288), when configured.
|
||||
///
|
||||
/// The client already sends this as a default header, so every
|
||||
/// scenario is identified without having to remember. A concurrency
|
||||
/// burst overrides it per stream — see
|
||||
/// [`ConcurrencyScenario`] — because fair-share (#54) bounds one
|
||||
/// principal to `max_per_principal` in-flight-or-queued requests,
|
||||
/// which defaults to 2. Eight streams under one identity would be
|
||||
/// capped at two and the rest rejected, measuring the fair-share cap
|
||||
/// instead of the server.
|
||||
pub principal_key_id: Option<String>,
|
||||
}
|
||||
|
||||
/// Operator-felt metrics for a single measured request.
|
||||
@@ -84,34 +72,6 @@ pub struct ScenarioMetrics {
|
||||
pub decode_ms: Option<u64>,
|
||||
/// Tokens submitted to prefill — the denominator for prefill tok/s.
|
||||
pub prefill_tokens: Option<u64>,
|
||||
/// Tokens spent inside the reasoning span, from
|
||||
/// `usage.completion_tokens_details.reasoning_tokens` (#223). A
|
||||
/// sub-count of `completion_tokens`.
|
||||
///
|
||||
/// Worth a trend of its own: on a reasoning model this is the
|
||||
/// dominant cost driver and it moves independently of speed. A
|
||||
/// template change, a sampling change (#283) or a reasoning-budget
|
||||
/// change can double what the model thinks before answering while
|
||||
/// every tok/s number stays flat — the bill doubles and no chart
|
||||
/// moves.
|
||||
pub reasoning_tokens: Option<u64>,
|
||||
/// p95 inter-token arrival gap in milliseconds — the tail of the
|
||||
/// stream's smoothness, client-observed.
|
||||
///
|
||||
/// `decode_tps` is a mean over the whole decode window, so a stream
|
||||
/// that stalls for a second and then catches up is indistinguishable
|
||||
/// from one that never stalled. This is the number a user actually
|
||||
/// feels, and the one a batching stall or a mid-stream rebatch shows
|
||||
/// up in. `None` for non-streaming, which has no inter-token gaps by
|
||||
/// construction, and for streams too short to have a tail.
|
||||
pub tpot_p95_ms: Option<f64>,
|
||||
/// Prompt tokens served from neuron's prefix KV cache (#269), from
|
||||
/// `usage.prompt_tokens_details.cached_tokens`.
|
||||
///
|
||||
/// The reason prefill timing varies between otherwise identical
|
||||
/// samples. #269 exists because the saving was invisible and every
|
||||
/// client reported a 0% hit rate; bench then threw the number away.
|
||||
pub cached_tokens: Option<u64>,
|
||||
// ── Concurrency / agentic-load fields (#89) ──────────────────────────
|
||||
// Set only by the concurrency scenario, which fans out N simultaneous
|
||||
// streams to characterize the real a0/hermes/opencode workload that
|
||||
@@ -243,9 +203,6 @@ impl Scenario for ImageLatencyScenario {
|
||||
.as_u64()
|
||||
.map(|d| d + timing["decode_ms"].as_u64().unwrap_or(0)),
|
||||
prefill_tokens: None,
|
||||
reasoning_tokens: None,
|
||||
cached_tokens: None,
|
||||
tpot_p95_ms: None,
|
||||
concurrency: None,
|
||||
ttft_p95_s: None,
|
||||
queue_wait_ms_median: None,
|
||||
@@ -276,18 +233,6 @@ pub fn build_scenarios(cfg: &ScenarioConfig) -> Vec<Box<dyn Scenario>> {
|
||||
id: format!("concurrency:{n}"),
|
||||
concurrency: n,
|
||||
approx_prompt_tokens: cfg.concurrency_prompt_tokens,
|
||||
streaming: true,
|
||||
}) as Box<dyn Scenario>);
|
||||
}
|
||||
// Non-streaming bursts (#285). A separate cell id so the two shapes
|
||||
// never average together — they measured 1.00x against 3.98x before
|
||||
// #285, and a combined number would have hidden both.
|
||||
for &n in &cfg.concurrency_nonstreaming_levels {
|
||||
scenarios.push(Box::new(ConcurrencyScenario {
|
||||
id: format!("concurrency:{n}:nostream"),
|
||||
concurrency: n,
|
||||
approx_prompt_tokens: cfg.concurrency_prompt_tokens,
|
||||
streaming: false,
|
||||
}) as Box<dyn Scenario>);
|
||||
}
|
||||
for &side in &cfg.image_sizes {
|
||||
@@ -312,7 +257,7 @@ pub fn build_scenarios(cfg: &ScenarioConfig) -> Vec<Box<dyn Scenario>> {
|
||||
pub async fn cold_probe(ctx: &RunCtx<'_>) -> Result<ScenarioMetrics> {
|
||||
let prompt = build_prompt(128);
|
||||
let payload = chat_payload(ctx, &prompt);
|
||||
tokio::time::timeout(ctx.timeout, stream_and_measure(ctx, &payload, None))
|
||||
tokio::time::timeout(ctx.timeout, stream_and_measure(ctx, &payload))
|
||||
.await
|
||||
.map_err(|_| anyhow!("cold probe timed out after {:?}", ctx.timeout))?
|
||||
}
|
||||
@@ -350,7 +295,7 @@ impl Scenario for ChatLatencyScenario {
|
||||
async fn run(&self, ctx: &RunCtx) -> Result<ScenarioMetrics> {
|
||||
let prompt = build_prompt(self.approx_prompt_tokens);
|
||||
let payload = chat_payload(ctx, &prompt);
|
||||
let fut = stream_and_measure(ctx, &payload, None);
|
||||
let fut = stream_and_measure(ctx, &payload);
|
||||
tokio::time::timeout(ctx.timeout, fut)
|
||||
.await
|
||||
.map_err(|_| anyhow!("request timed out after {:?}", ctx.timeout))?
|
||||
@@ -368,16 +313,6 @@ pub struct ConcurrencyScenario {
|
||||
id: String,
|
||||
concurrency: u32,
|
||||
approx_prompt_tokens: u32,
|
||||
/// Whether the burst streams (#285).
|
||||
///
|
||||
/// Both shapes matter and they are not interchangeable. Streaming
|
||||
/// multiplexes through the batch engine; non-streaming did not until
|
||||
/// #285, and serialized completely — 1.00x aggregate throughput at
|
||||
/// every concurrency level against 3.98x streamed. A bench that only
|
||||
/// streams cannot see that, which is why it went unmeasured: the
|
||||
/// neuron reports `in_flight: 8`, admission accepts, `/health` looks
|
||||
/// healthy, and throughput is single-stream.
|
||||
streaming: bool,
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
@@ -392,26 +327,13 @@ impl Scenario for ConcurrencyScenario {
|
||||
|
||||
async fn run(&self, ctx: &RunCtx) -> Result<ScenarioMetrics> {
|
||||
let prompt = build_prompt(self.approx_prompt_tokens);
|
||||
let payload = if self.streaming {
|
||||
chat_payload(ctx, &prompt)
|
||||
} else {
|
||||
nonstreaming_payload(ctx, &prompt)
|
||||
};
|
||||
let payload = chat_payload(ctx, &prompt);
|
||||
|
||||
// Fire all requests at once; each is independently timed and capped
|
||||
// by the per-request timeout so one hung request can't stall the
|
||||
// burst.
|
||||
// Fire all streams at once; each is independently timed and capped by
|
||||
// the per-request timeout so one hung stream can't stall the burst.
|
||||
let burst_start = Instant::now();
|
||||
let streaming = self.streaming;
|
||||
let payload = &payload;
|
||||
let futs = (0..self.concurrency).map(move |i| async move {
|
||||
// Each stream presents its own identity — see
|
||||
// `with_stream_identity`.
|
||||
if streaming {
|
||||
tokio::time::timeout(ctx.timeout, stream_and_measure(ctx, payload, Some(i))).await
|
||||
} else {
|
||||
tokio::time::timeout(ctx.timeout, request_and_measure(ctx, payload, Some(i))).await
|
||||
}
|
||||
let futs = (0..self.concurrency).map(|_| async {
|
||||
tokio::time::timeout(ctx.timeout, stream_and_measure(ctx, &payload)).await
|
||||
});
|
||||
let results = futures::future::join_all(futs).await;
|
||||
let burst_window = burst_start.elapsed().as_secs_f64();
|
||||
@@ -429,7 +351,7 @@ impl Scenario for ConcurrencyScenario {
|
||||
}
|
||||
if streams.is_empty() {
|
||||
return Err(anyhow!(
|
||||
"all {} concurrent requests failed ({rejected} shed by admission)",
|
||||
"all {} concurrent streams failed ({rejected} shed by admission)",
|
||||
self.concurrency
|
||||
));
|
||||
}
|
||||
@@ -458,50 +380,9 @@ impl Scenario for ConcurrencyScenario {
|
||||
total_s: burst_window,
|
||||
prompt_tokens: streams.iter().find_map(|m| m.prompt_tokens),
|
||||
completion_tokens: total_tokens,
|
||||
// Median server-side phase timing across the burst. These
|
||||
// were `None`, which left the prefill-tok/s panel blank for
|
||||
// exactly the cells where queue behaviour matters most, and
|
||||
// made `queue_wait_ms` (TTFT minus server prefill, #85)
|
||||
// uncomputable for a burst — the one number that separates
|
||||
// "the server is slow" from "you were queued".
|
||||
//
|
||||
// Median rather than sum: every stream prefills its own copy
|
||||
// of the same prompt, so the representative per-stream cost
|
||||
// is the meaningful figure and it composes with `ttft_s`,
|
||||
// which is also a median.
|
||||
prefill_ms: median(
|
||||
&streams
|
||||
.iter()
|
||||
.filter_map(|m| m.prefill_ms.map(|v| v as f64))
|
||||
.collect::<Vec<_>>(),
|
||||
)
|
||||
.map(|v| v as u64),
|
||||
decode_ms: median(
|
||||
&streams
|
||||
.iter()
|
||||
.filter_map(|m| m.decode_ms.map(|v| v as f64))
|
||||
.collect::<Vec<_>>(),
|
||||
)
|
||||
.map(|v| v as u64),
|
||||
prefill_tokens: median(
|
||||
&streams
|
||||
.iter()
|
||||
.filter_map(|m| m.prefill_tokens.map(|v| v as f64))
|
||||
.collect::<Vec<_>>(),
|
||||
)
|
||||
.map(|v| v as u64),
|
||||
// Summed across the burst, like `completion_tokens`: the cell
|
||||
// describes the whole burst, so a per-stream figure here
|
||||
// would not compose with it.
|
||||
reasoning_tokens: sum_opt(&streams, |m| m.reasoning_tokens),
|
||||
cached_tokens: sum_opt(&streams, |m| m.cached_tokens),
|
||||
// The worst stream in the burst, not a median of medians:
|
||||
// under load the question is how bad it got for somebody,
|
||||
// and averaging tails is how a stall stays invisible.
|
||||
tpot_p95_ms: streams
|
||||
.iter()
|
||||
.filter_map(|m| m.tpot_p95_ms)
|
||||
.max_by(|a, b| a.total_cmp(b)),
|
||||
prefill_ms: None,
|
||||
decode_ms: None,
|
||||
prefill_tokens: None,
|
||||
concurrency: Some(self.concurrency),
|
||||
ttft_p95_s: percentile(&ttfts, 95.0),
|
||||
queue_wait_ms_median: median(&queue_waits),
|
||||
@@ -512,146 +393,6 @@ impl Scenario for ConcurrencyScenario {
|
||||
}
|
||||
}
|
||||
|
||||
/// Sum an optional per-stream count across a burst, `None` when no
|
||||
/// stream reported it — so "nobody measured it" stays distinguishable
|
||||
/// from "measured as zero", the same distinction #269 exists to
|
||||
/// preserve.
|
||||
fn sum_opt(
|
||||
streams: &[ScenarioMetrics],
|
||||
f: impl Fn(&ScenarioMetrics) -> Option<u64>,
|
||||
) -> Option<u64> {
|
||||
let vals: Vec<u64> = streams.iter().filter_map(f).collect();
|
||||
(!vals.is_empty()).then(|| vals.iter().sum())
|
||||
}
|
||||
|
||||
/// Per-stream identity for a concurrency burst (#288/#54).
|
||||
///
|
||||
/// Fair-share bounds *one principal* to `max_per_principal`
|
||||
/// in-flight-or-queued requests, defaulting to 2. A burst of 8 under a
|
||||
/// single identity would therefore have 6 rejected with `PrincipalCap`,
|
||||
/// and the scenario would measure the fair-share cap rather than the
|
||||
/// server.
|
||||
///
|
||||
/// Giving each stream its own key is also the more faithful model: a
|
||||
/// concurrency-8 burst is meant to stand in for eight simultaneous
|
||||
/// *callers*, not one caller issuing eight requests. Fair-share is still
|
||||
/// exercised — each identity is subject to it — just not self-inflicted.
|
||||
fn with_stream_identity(
|
||||
rb: reqwest::RequestBuilder,
|
||||
ctx: &RunCtx<'_>,
|
||||
stream: Option<u32>,
|
||||
) -> reqwest::RequestBuilder {
|
||||
match (ctx.principal_key_id.as_deref(), stream) {
|
||||
(Some(base), Some(i)) => rb.header(HEADER_KEY_ID, format!("{base}-{i}")),
|
||||
// No principal configured, or a single-request scenario: the
|
||||
// client's default headers already carry the base identity.
|
||||
_ => rb,
|
||||
}
|
||||
}
|
||||
|
||||
/// The non-streaming counterpart to [`chat_payload`] (#285).
|
||||
///
|
||||
/// `stream_options` is deliberately absent: usage is part of the body on
|
||||
/// this shape, and sending the streaming-only option to a strict server
|
||||
/// is a needless compatibility risk.
|
||||
fn nonstreaming_payload(ctx: &RunCtx, prompt: &str) -> serde_json::Value {
|
||||
json!({
|
||||
"model": ctx.model_id,
|
||||
"messages": [{"role": "user", "content": prompt}],
|
||||
"max_tokens": ctx.max_tokens,
|
||||
"temperature": 0,
|
||||
"stream": false,
|
||||
})
|
||||
}
|
||||
|
||||
/// Time one non-streaming chat completion (#285).
|
||||
///
|
||||
/// There is no first-chunk moment on this shape — the whole body arrives
|
||||
/// at once — so `ttft_s` is the full request wall-clock rather than a
|
||||
/// separate measurement. That is the honest reading: for a non-streaming
|
||||
/// caller, time-to-first-token *is* time-to-everything, and it is exactly
|
||||
/// what makes the serialization this scenario exists to detect so
|
||||
/// expensive.
|
||||
///
|
||||
/// `decode_tps` is per-request; the burst aggregate is computed by the
|
||||
/// caller over the whole window, the same way the streaming path does it.
|
||||
async fn request_and_measure(
|
||||
ctx: &RunCtx<'_>,
|
||||
payload: &serde_json::Value,
|
||||
stream: Option<u32>,
|
||||
) -> Result<ScenarioMetrics> {
|
||||
let start = Instant::now();
|
||||
let resp = with_stream_identity(ctx.client.post(&ctx.chat_url), ctx, stream)
|
||||
.json(payload)
|
||||
.send()
|
||||
.await
|
||||
.context("sending non-streaming chat request")?;
|
||||
if !resp.status().is_success() {
|
||||
let status = resp.status();
|
||||
let body = resp.text().await.unwrap_or_default();
|
||||
return Err(anyhow!("upstream returned {status}: {}", body.trim()));
|
||||
}
|
||||
let v: serde_json::Value = resp
|
||||
.json()
|
||||
.await
|
||||
.context("non-streaming chat response was not JSON")?;
|
||||
let total_s = start.elapsed().as_secs_f64();
|
||||
|
||||
let usage = v.get("usage");
|
||||
let completion_tokens = usage
|
||||
.and_then(|u| u.get("completion_tokens"))
|
||||
.and_then(|t| t.as_u64())
|
||||
.unwrap_or(0);
|
||||
let prompt_tokens = usage
|
||||
.and_then(|u| u.get("prompt_tokens"))
|
||||
.and_then(|t| t.as_u64());
|
||||
let reasoning_tokens = usage
|
||||
.and_then(|u| u.get("completion_tokens_details"))
|
||||
.and_then(|d| d.get("reasoning_tokens"))
|
||||
.and_then(|t| t.as_u64());
|
||||
let cached_tokens = usage
|
||||
.and_then(|u| u.get("prompt_tokens_details"))
|
||||
.and_then(|d| d.get("cached_tokens"))
|
||||
.and_then(|t| t.as_u64());
|
||||
let timing = usage.and_then(|u| u.get("helexa_timing"));
|
||||
let field = |name: &str| timing.and_then(|t| t.get(name)).and_then(|x| x.as_u64());
|
||||
let (prefill_ms, decode_ms, prefill_tokens) = (
|
||||
field("prefill_ms"),
|
||||
field("decode_ms"),
|
||||
field("prefill_tokens"),
|
||||
);
|
||||
|
||||
// Prefer the server's own decode window when it reports one (#85);
|
||||
// it excludes prefill, so it is comparable with the streaming path's
|
||||
// decode-window rate rather than being diluted by it.
|
||||
let decode_tps = match decode_ms {
|
||||
Some(ms) if ms > 200 => Some(completion_tokens as f64 / (ms as f64 / 1000.0)),
|
||||
_ if total_s > 0.2 => Some(completion_tokens as f64 / total_s),
|
||||
_ => None,
|
||||
};
|
||||
|
||||
Ok(ScenarioMetrics {
|
||||
ttft_s: total_s,
|
||||
decode_tps,
|
||||
total_s,
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
prefill_ms,
|
||||
decode_ms,
|
||||
prefill_tokens,
|
||||
reasoning_tokens,
|
||||
cached_tokens,
|
||||
// Non-streaming has no inter-token gaps: the body arrives whole.
|
||||
tpot_p95_ms: None,
|
||||
concurrency: None,
|
||||
ttft_p95_s: None,
|
||||
queue_wait_ms_median: None,
|
||||
rejected: None,
|
||||
artifact: None,
|
||||
image_units: None,
|
||||
})
|
||||
}
|
||||
|
||||
/// Quality probe (#91): runs a fixed prompt and stores the full generated
|
||||
/// text as an artifact for later scoring (manual now, LLM-judge later). The
|
||||
/// point is to compare reasoning/planning quality across models — the axis
|
||||
@@ -684,7 +425,7 @@ impl Scenario for CapabilityScenario {
|
||||
"stream": true,
|
||||
"stream_options": {"include_usage": true},
|
||||
});
|
||||
let fut = stream_and_measure_inner(ctx, &payload, true, None);
|
||||
let fut = stream_and_measure_inner(ctx, &payload, true);
|
||||
tokio::time::timeout(ctx.timeout, fut)
|
||||
.await
|
||||
.map_err(|_| anyhow!("capability probe timed out after {:?}", ctx.timeout))?
|
||||
@@ -727,9 +468,8 @@ fn percentile(values: &[f64], p: f64) -> Option<f64> {
|
||||
async fn stream_and_measure(
|
||||
ctx: &RunCtx<'_>,
|
||||
payload: &serde_json::Value,
|
||||
stream: Option<u32>,
|
||||
) -> Result<ScenarioMetrics> {
|
||||
stream_and_measure_inner(ctx, payload, false, stream).await
|
||||
stream_and_measure_inner(ctx, payload, false).await
|
||||
}
|
||||
|
||||
/// As [`stream_and_measure`] but accumulates the full visible text when
|
||||
@@ -739,10 +479,11 @@ async fn stream_and_measure_inner(
|
||||
ctx: &RunCtx<'_>,
|
||||
payload: &serde_json::Value,
|
||||
capture_text: bool,
|
||||
stream_ix: Option<u32>,
|
||||
) -> Result<ScenarioMetrics> {
|
||||
let start = Instant::now();
|
||||
let resp = with_stream_identity(ctx.client.post(&ctx.chat_url), ctx, stream_ix)
|
||||
let resp = ctx
|
||||
.client
|
||||
.post(&ctx.chat_url)
|
||||
.json(payload)
|
||||
.send()
|
||||
.await
|
||||
@@ -762,10 +503,6 @@ async fn stream_and_measure_inner(
|
||||
let mut prefill_ms: Option<u64> = None;
|
||||
let mut decode_ms: Option<u64> = None;
|
||||
let mut prefill_tokens: Option<u64> = None;
|
||||
let mut reasoning_tokens: Option<u64> = None;
|
||||
let mut cached_tokens: Option<u64> = None;
|
||||
// Inter-token arrival gaps, for the p95 tail.
|
||||
let mut gaps_ms: Vec<f64> = Vec::new();
|
||||
let mut captured = String::new();
|
||||
|
||||
while let Some(event) = stream.next().await {
|
||||
@@ -803,11 +540,6 @@ async fn stream_and_measure_inner(
|
||||
if content.is_some() || reasoning.is_some() {
|
||||
if first.is_none() {
|
||||
first = Some(now);
|
||||
} else if let Some(prev) = last {
|
||||
// Gaps only *between* generated deltas: the wait for
|
||||
// the first one is TTFT and belongs to prefill, not
|
||||
// to stream smoothness.
|
||||
gaps_ms.push(now.duration_since(prev).as_secs_f64() * 1000.0);
|
||||
}
|
||||
last = Some(now);
|
||||
chunk_count += 1;
|
||||
@@ -819,14 +551,6 @@ async fn stream_and_measure_inner(
|
||||
if let Some(usage) = chunk.usage {
|
||||
prompt_tokens = Some(usage.prompt_tokens);
|
||||
completion_tokens = Some(usage.completion_tokens);
|
||||
reasoning_tokens = usage
|
||||
.completion_tokens_details
|
||||
.as_ref()
|
||||
.map(|d| d.reasoning_tokens);
|
||||
cached_tokens = usage
|
||||
.prompt_tokens_details
|
||||
.as_ref()
|
||||
.map(|d| d.cached_tokens);
|
||||
if let Some(t) = usage.helexa_timing {
|
||||
prefill_ms = Some(t.prefill_ms);
|
||||
decode_ms = Some(t.decode_ms);
|
||||
@@ -865,9 +589,6 @@ async fn stream_and_measure_inner(
|
||||
prefill_ms,
|
||||
decode_ms,
|
||||
prefill_tokens,
|
||||
reasoning_tokens,
|
||||
cached_tokens,
|
||||
tpot_p95_ms: percentile(&gaps_ms, 95.0),
|
||||
// Concurrency fields unset on the single-request path; the
|
||||
// concurrency scenario builds its own aggregate (#89).
|
||||
concurrency: None,
|
||||
@@ -883,113 +604,6 @@ async fn stream_and_measure_inner(
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// A burst must report server-side phase timing, or `queue_wait_ms`
|
||||
/// (TTFT minus server prefill, #85) cannot be computed for the very
|
||||
/// cells it was designed for, and the prefill-tok/s panel stays
|
||||
/// blank under concurrency.
|
||||
#[test]
|
||||
fn a_burst_reports_median_phase_timing_not_none() {
|
||||
let s = |prefill_ms, decode_ms, prefill_tokens| ScenarioMetrics {
|
||||
ttft_s: 0.1,
|
||||
decode_tps: Some(10.0),
|
||||
total_s: 1.0,
|
||||
prompt_tokens: Some(100),
|
||||
completion_tokens: 10,
|
||||
prefill_ms,
|
||||
decode_ms,
|
||||
prefill_tokens,
|
||||
reasoning_tokens: None,
|
||||
cached_tokens: None,
|
||||
tpot_p95_ms: Some(5.0),
|
||||
concurrency: None,
|
||||
ttft_p95_s: None,
|
||||
queue_wait_ms_median: None,
|
||||
rejected: None,
|
||||
artifact: None,
|
||||
image_units: None,
|
||||
};
|
||||
let streams = [
|
||||
s(Some(10), Some(100), Some(512)),
|
||||
s(Some(20), Some(200), Some(512)),
|
||||
s(Some(30), Some(300), Some(512)),
|
||||
];
|
||||
let med = |f: fn(&ScenarioMetrics) -> Option<u64>| {
|
||||
median(
|
||||
&streams
|
||||
.iter()
|
||||
.filter_map(|m| f(m).map(|v| v as f64))
|
||||
.collect::<Vec<_>>(),
|
||||
)
|
||||
.map(|v| v as u64)
|
||||
};
|
||||
assert_eq!(med(|m| m.prefill_ms), Some(20));
|
||||
assert_eq!(med(|m| m.decode_ms), Some(200));
|
||||
// Every stream prefills the same prompt, so the median is the
|
||||
// prompt size rather than a sum across the burst.
|
||||
assert_eq!(med(|m| m.prefill_tokens), Some(512));
|
||||
}
|
||||
|
||||
/// #288/#54: a burst must present one identity *per stream*.
|
||||
///
|
||||
/// Fair-share bounds a single principal to `max_per_principal`
|
||||
/// in-flight-or-queued requests, which defaults to 2. Eight streams
|
||||
/// under one key would have six rejected with `PrincipalCap`, and
|
||||
/// `concurrency:8` would silently measure the fair-share cap instead
|
||||
/// of the server — a worse failure than the anonymity it replaced,
|
||||
/// because it looks like backpressure.
|
||||
#[test]
|
||||
fn a_burst_presents_one_identity_per_stream() {
|
||||
let client = reqwest::Client::new();
|
||||
let ctx = RunCtx {
|
||||
client: &client,
|
||||
chat_url: "http://x/v1/chat/completions".into(),
|
||||
model_id: "m".into(),
|
||||
max_tokens: 16,
|
||||
timeout: Duration::from_secs(1),
|
||||
principal_key_id: Some("fleet-benchmark".into()),
|
||||
};
|
||||
let key_of = |stream: Option<u32>| -> Option<String> {
|
||||
with_stream_identity(client.post(&ctx.chat_url), &ctx, stream)
|
||||
.build()
|
||||
.expect("build")
|
||||
.headers()
|
||||
.get(HEADER_KEY_ID)
|
||||
.map(|v| v.to_str().expect("utf8").to_string())
|
||||
};
|
||||
let keys: Vec<Option<String>> = (0..3).map(|i| key_of(Some(i))).collect();
|
||||
assert_eq!(
|
||||
keys,
|
||||
vec![
|
||||
Some("fleet-benchmark-0".to_string()),
|
||||
Some("fleet-benchmark-1".to_string()),
|
||||
Some("fleet-benchmark-2".to_string()),
|
||||
]
|
||||
);
|
||||
// Distinct, or the cap bites anyway.
|
||||
let uniq: std::collections::HashSet<_> = keys.iter().collect();
|
||||
assert_eq!(uniq.len(), 3);
|
||||
}
|
||||
|
||||
/// A single-request scenario adds no override: the client's default
|
||||
/// headers already carry the base identity, and a per-request copy
|
||||
/// would be a second place for it to drift.
|
||||
#[test]
|
||||
fn a_single_request_scenario_keeps_the_client_identity() {
|
||||
let client = reqwest::Client::new();
|
||||
let ctx = RunCtx {
|
||||
client: &client,
|
||||
chat_url: "http://x/v1/chat/completions".into(),
|
||||
model_id: "m".into(),
|
||||
max_tokens: 16,
|
||||
timeout: Duration::from_secs(1),
|
||||
principal_key_id: Some("fleet-benchmark".into()),
|
||||
};
|
||||
let req = with_stream_identity(client.post(&ctx.chat_url), &ctx, None)
|
||||
.build()
|
||||
.expect("build");
|
||||
assert!(req.headers().get(HEADER_KEY_ID).is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prompt_grows_with_token_target() {
|
||||
let small = build_prompt(128);
|
||||
@@ -1032,7 +646,6 @@ mod tests {
|
||||
prompt_sizes: vec![128],
|
||||
max_tokens: 64,
|
||||
concurrency_levels: vec![2, 8],
|
||||
concurrency_nonstreaming_levels: vec![8],
|
||||
concurrency_prompt_tokens: 512,
|
||||
capability_probes: vec![CapabilityProbe {
|
||||
name: "plan".into(),
|
||||
|
||||
@@ -14,22 +14,6 @@ use std::path::Path;
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct RunRecord {
|
||||
pub ts: String, // RFC3339
|
||||
/// Identity this sample was taken under (#288), `account/key`, or
|
||||
/// `None` for an anonymous run. Anonymous samples measure the
|
||||
/// admission yield policy rather than serving capacity once #262 is
|
||||
/// in the build, so this is the column that says whether two rows
|
||||
/// are comparable at all.
|
||||
pub principal: Option<String>,
|
||||
/// Tokens spent reasoning (#223) — the dominant cost driver on a
|
||||
/// reasoning model, and one that moves independently of every tok/s
|
||||
/// number on the dashboard.
|
||||
pub reasoning_tokens: Option<u64>,
|
||||
/// Prompt tokens served from the prefix cache (#269) — the reason
|
||||
/// prefill timing varies between otherwise identical samples.
|
||||
pub cached_tokens: Option<u64>,
|
||||
/// p95 inter-token arrival gap (ms) — stream smoothness, which a
|
||||
/// mean tok/s cannot express.
|
||||
pub tpot_p95_ms: Option<f64>,
|
||||
// target
|
||||
pub target_name: String,
|
||||
pub target_kind: String,
|
||||
@@ -220,18 +204,6 @@ impl Store {
|
||||
("artifact", "TEXT"),
|
||||
("quality_score", "REAL"),
|
||||
("scorer", "TEXT"),
|
||||
// #288: which identity the sample was taken under. Rows
|
||||
// predating this are NULL, which is honest — they were
|
||||
// anonymous, and since #262 that measures a different
|
||||
// thing. Without the column the 2026-08-18 discontinuity
|
||||
// is folklore rather than data.
|
||||
("principal", "TEXT"),
|
||||
// #223 / #269: both are on the wire and were being discarded.
|
||||
("reasoning_tokens", "INTEGER"),
|
||||
("cached_tokens", "INTEGER"),
|
||||
// #285: inter-token tail. `decode_tps` is a mean and hides
|
||||
// a stall that later catches up.
|
||||
("tpot_p95_ms", "REAL"),
|
||||
],
|
||||
)?;
|
||||
Ok(())
|
||||
@@ -292,7 +264,6 @@ impl Store {
|
||||
swap_unload_ms, swap_load_ms,
|
||||
artifact, quality_score, scorer,
|
||||
image_units,
|
||||
principal, reasoning_tokens, cached_tokens, tpot_p95_ms,
|
||||
ok, error
|
||||
) VALUES (
|
||||
?1, ?2, ?3, ?4,
|
||||
@@ -309,8 +280,7 @@ impl Store {
|
||||
?42, ?43,
|
||||
?44, ?45, ?46,
|
||||
?47,
|
||||
?48, ?49, ?50, ?51,
|
||||
?52, ?53
|
||||
?48, ?49
|
||||
)",
|
||||
params![
|
||||
r.ts,
|
||||
@@ -360,10 +330,6 @@ impl Store {
|
||||
r.quality_score,
|
||||
r.scorer,
|
||||
r.image_units,
|
||||
r.principal,
|
||||
r.reasoning_tokens,
|
||||
r.cached_tokens,
|
||||
r.tpot_p95_ms,
|
||||
r.ok as i64,
|
||||
r.error,
|
||||
],
|
||||
@@ -737,15 +703,7 @@ impl Store {
|
||||
}
|
||||
};
|
||||
let mut stmt = self.conn.prepare(
|
||||
"SELECT git_sha, build_timestamp, package_version, ttft_s, decode_tps, total_s,
|
||||
ttft_p95_s, queue_wait_ms, rejected,
|
||||
-- Prefill rate derived here rather than stored: the
|
||||
-- inputs are already recorded and a stored rate
|
||||
-- would be a third thing to keep consistent.
|
||||
CASE WHEN prefill_ms > 0 AND prefill_tokens IS NOT NULL
|
||||
THEN (prefill_tokens * 1000.0) / prefill_ms END AS prefill_tps,
|
||||
reasoning_tokens, cached_tokens, completion_tokens,
|
||||
tpot_p95_ms, principal, ts
|
||||
"SELECT git_sha, build_timestamp, package_version, ttft_s, decode_tps, total_s, ts
|
||||
FROM runs
|
||||
WHERE ok=1 AND target_name=?1 AND model_id=?2 AND scenario_id=?3
|
||||
ORDER BY id",
|
||||
@@ -759,16 +717,7 @@ impl Store {
|
||||
ttft_s: r.get(3)?,
|
||||
decode_tps: r.get(4)?,
|
||||
total_s: r.get(5)?,
|
||||
ttft_p95_s: r.get(6)?,
|
||||
queue_wait_ms: r.get(7)?,
|
||||
rejected: r.get(8)?,
|
||||
prefill_tps: r.get(9)?,
|
||||
reasoning_tokens: r.get(10)?,
|
||||
cached_tokens: r.get(11)?,
|
||||
completion_tokens: r.get(12)?,
|
||||
tpot_p95_ms: r.get(13)?,
|
||||
principal: r.get(14)?,
|
||||
ts: r.get(15)?,
|
||||
ts: r.get(6)?,
|
||||
})
|
||||
})?
|
||||
.collect::<rusqlite::Result<_>>()?;
|
||||
@@ -889,33 +838,6 @@ pub struct SeriesPoint {
|
||||
pub ttft_s_median: Option<f64>,
|
||||
pub decode_tps_median: Option<f64>,
|
||||
pub total_s_median: Option<f64>,
|
||||
// ── Added because the two above cannot show what changed ──────
|
||||
/// Tail TTFT. The median above stayed flat at ~0.3 s across the
|
||||
/// build where p95 went 0.53 s → 11.77 s (#288); charting only the
|
||||
/// median is why that went unnoticed for a week.
|
||||
pub ttft_p95_s_median: Option<f64>,
|
||||
/// Admission queue wait — separates "the server is slow" from
|
||||
/// "you were queued behind someone".
|
||||
pub queue_wait_ms_median: Option<f64>,
|
||||
/// Requests shed by admission during the burst.
|
||||
pub rejected_median: Option<f64>,
|
||||
/// Prefill throughput, derived from `prefill_tokens / prefill_ms`.
|
||||
/// The other half of serving speed; only decode was ever charted.
|
||||
pub prefill_tps_median: Option<f64>,
|
||||
/// Tokens spent reasoning (#223) — the dominant cost driver on a
|
||||
/// reasoning model, and independent of every speed metric here.
|
||||
pub reasoning_tokens_median: Option<f64>,
|
||||
/// Prompt tokens served from the prefix cache (#269).
|
||||
pub cached_tokens_median: Option<f64>,
|
||||
/// Total generated tokens — catches a model that starts truncating
|
||||
/// or rambling, which no rate metric shows.
|
||||
pub completion_tokens_median: Option<f64>,
|
||||
/// p95 inter-token gap (ms) — stream smoothness.
|
||||
pub tpot_p95_ms_median: Option<f64>,
|
||||
/// Identity the samples were taken under (#288), or `None` if
|
||||
/// anonymous. Anonymous and identified points are **not
|
||||
/// comparable** once #262 is in the build.
|
||||
pub principal: Option<String>,
|
||||
pub samples: usize,
|
||||
}
|
||||
|
||||
@@ -926,15 +848,6 @@ struct SeriesRaw {
|
||||
ttft_s: Option<f64>,
|
||||
decode_tps: Option<f64>,
|
||||
total_s: Option<f64>,
|
||||
ttft_p95_s: Option<f64>,
|
||||
queue_wait_ms: Option<f64>,
|
||||
rejected: Option<f64>,
|
||||
prefill_tps: Option<f64>,
|
||||
reasoning_tokens: Option<f64>,
|
||||
cached_tokens: Option<f64>,
|
||||
completion_tokens: Option<f64>,
|
||||
tpot_p95_ms: Option<f64>,
|
||||
principal: Option<String>,
|
||||
ts: String,
|
||||
}
|
||||
|
||||
@@ -967,19 +880,6 @@ fn aggregate_series(raws: Vec<SeriesRaw>) -> Vec<SeriesPoint> {
|
||||
ttft_s_median: median(rows.iter().filter_map(|r| r.ttft_s)),
|
||||
decode_tps_median: median(rows.iter().filter_map(|r| r.decode_tps)),
|
||||
total_s_median: median(rows.iter().filter_map(|r| r.total_s)),
|
||||
ttft_p95_s_median: median(rows.iter().filter_map(|r| r.ttft_p95_s)),
|
||||
queue_wait_ms_median: median(rows.iter().filter_map(|r| r.queue_wait_ms)),
|
||||
rejected_median: median(rows.iter().filter_map(|r| r.rejected)),
|
||||
prefill_tps_median: median(rows.iter().filter_map(|r| r.prefill_tps)),
|
||||
reasoning_tokens_median: median(rows.iter().filter_map(|r| r.reasoning_tokens)),
|
||||
cached_tokens_median: median(rows.iter().filter_map(|r| r.cached_tokens)),
|
||||
completion_tokens_median: median(rows.iter().filter_map(|r| r.completion_tokens)),
|
||||
tpot_p95_ms_median: median(rows.iter().filter_map(|r| r.tpot_p95_ms)),
|
||||
// Any row's principal: a build's samples are all taken
|
||||
// under one identity, and a mixture would mean the
|
||||
// config changed mid-build, which the chart should show
|
||||
// as a discontinuity rather than average away.
|
||||
principal: rows.iter().find_map(|r| r.principal.clone()),
|
||||
samples: rows.len(),
|
||||
};
|
||||
(sort_key, point)
|
||||
@@ -1381,10 +1281,6 @@ mod tests {
|
||||
fn rec(target: &str, sha: &str, model: &str, scenario: &str, ok: bool) -> RunRecord {
|
||||
RunRecord {
|
||||
ts: "2026-06-13T00:00:00Z".into(),
|
||||
principal: None,
|
||||
reasoning_tokens: None,
|
||||
cached_tokens: None,
|
||||
tpot_p95_ms: None,
|
||||
target_name: target.into(),
|
||||
target_kind: "neuron".into(),
|
||||
endpoint: "http://x:13131".into(),
|
||||
|
||||
@@ -78,10 +78,7 @@ pub struct Sweeper {
|
||||
|
||||
impl Sweeper {
|
||||
pub fn new(cfg: BenchConfig) -> Result<Self> {
|
||||
let client = TargetClient::with_principal(
|
||||
cfg.bench.request_timeout(),
|
||||
cfg.bench.principal.as_ref(),
|
||||
)?;
|
||||
let client = TargetClient::new(cfg.bench.request_timeout())?;
|
||||
let store = Store::open(&cfg.bench.db_path)?;
|
||||
Ok(Sweeper { cfg, client, store })
|
||||
}
|
||||
@@ -172,7 +169,6 @@ impl Sweeper {
|
||||
model_id: model.id.clone(),
|
||||
max_tokens: self.cfg.scenarios.max_tokens,
|
||||
timeout: self.cfg.bench.request_timeout(),
|
||||
principal_key_id: self.cfg.bench.principal.as_ref().map(|p| p.key_id.clone()),
|
||||
};
|
||||
let cold = crate::scenario::cold_probe(&ctx).await;
|
||||
let swap = SwapTiming { unload_ms, load_ms };
|
||||
@@ -256,7 +252,6 @@ impl Sweeper {
|
||||
model_id: model.id.clone(),
|
||||
max_tokens: self.cfg.scenarios.max_tokens,
|
||||
timeout: self.cfg.bench.request_timeout(),
|
||||
principal_key_id: self.cfg.bench.principal.as_ref().map(|p| p.key_id.clone()),
|
||||
};
|
||||
|
||||
// One unmeasured warmup when the cell is empty (matches
|
||||
@@ -351,15 +346,6 @@ impl Sweeper {
|
||||
|
||||
RunRecord {
|
||||
ts: chrono::Utc::now().to_rfc3339(),
|
||||
// #288: stamp the identity this sample was taken under, so a
|
||||
// later reader can tell an anonymous row from an identified
|
||||
// one instead of inferring it from the date.
|
||||
principal: self
|
||||
.cfg
|
||||
.bench
|
||||
.principal
|
||||
.as_ref()
|
||||
.map(|p| format!("{}/{}", p.account_id, p.key_id)),
|
||||
target_name: target.name.clone(),
|
||||
target_kind: kind_str(target.kind).to_string(),
|
||||
endpoint: target.endpoint.clone(),
|
||||
@@ -397,9 +383,6 @@ impl Sweeper {
|
||||
prefill_ms: m.and_then(|m| m.prefill_ms),
|
||||
decode_ms: m.and_then(|m| m.decode_ms),
|
||||
prefill_tokens: m.and_then(|m| m.prefill_tokens),
|
||||
reasoning_tokens: m.and_then(|x| x.reasoning_tokens),
|
||||
cached_tokens: m.and_then(|x| x.cached_tokens),
|
||||
tpot_p95_ms: m.and_then(|x| x.tpot_p95_ms),
|
||||
vram_used_mb: health.map(|h| h.vram_used_mb),
|
||||
gpu_util_pct: health.map(|h| h.gpu_util_pct),
|
||||
gpu_temp_c: health.map(|h| h.gpu_temp_c),
|
||||
|
||||
@@ -15,10 +15,6 @@ fn rec(
|
||||
ok: bool,
|
||||
) -> RunRecord {
|
||||
RunRecord {
|
||||
principal: None,
|
||||
reasoning_tokens: None,
|
||||
cached_tokens: None,
|
||||
tpot_p95_ms: None,
|
||||
ts: "2026-06-13T00:00:00Z".into(),
|
||||
target_name: host.into(),
|
||||
target_kind: "neuron".into(),
|
||||
|
||||
@@ -80,7 +80,6 @@ async fn spawn_mock(sha: &str) -> (String, Arc<Mutex<String>>) {
|
||||
fn config_for(endpoint: String, db_path: String) -> BenchConfig {
|
||||
BenchConfig {
|
||||
bench: BenchSettings {
|
||||
principal: None,
|
||||
sweep_interval_secs: 1,
|
||||
samples_per_version: 2,
|
||||
iteration_pause_secs: 0,
|
||||
@@ -92,7 +91,6 @@ fn config_for(endpoint: String, db_path: String) -> BenchConfig {
|
||||
prompt_sizes: vec![128], // single scenario keeps assertions simple
|
||||
max_tokens: 16,
|
||||
concurrency_levels: Vec::new(),
|
||||
concurrency_nonstreaming_levels: vec![],
|
||||
concurrency_prompt_tokens: 512,
|
||||
capability_probes: Vec::new(),
|
||||
},
|
||||
|
||||
@@ -80,19 +80,10 @@ fn router_entry(cortex: &str, e: &CortexModelEntry) -> CortexModelEntry {
|
||||
cost: e.cost.clone(),
|
||||
tool_call: e.tool_call,
|
||||
reasoning: e.reasoning,
|
||||
// Every flat ecosystem field is derived from `limit` by the
|
||||
// final sync pass in aggregate_models, so they are cleared here
|
||||
// rather than copied. Spread from `e` keeps a field added to the
|
||||
// entry later from being silently dropped at this hop.
|
||||
..CortexModelEntry {
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
context_window: None,
|
||||
context_length: None,
|
||||
reasoning_budget: Vec::new(),
|
||||
..e.clone()
|
||||
}
|
||||
// Derived from `limit` by the final sync pass in aggregate_models.
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -173,9 +164,6 @@ mod tests {
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
context_window: None,
|
||||
context_length: None,
|
||||
reasoning_budget: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -236,7 +224,6 @@ mod tests {
|
||||
context: 32_768,
|
||||
input: None,
|
||||
output: 4096,
|
||||
output_ceiling: 0,
|
||||
});
|
||||
a.cost = Some(ModelCost {
|
||||
input: 0.50,
|
||||
@@ -249,7 +236,6 @@ mod tests {
|
||||
context: 16_384, // tighter
|
||||
input: None,
|
||||
output: 4096,
|
||||
output_ceiling: 0,
|
||||
});
|
||||
b.cost = Some(ModelCost {
|
||||
input: 0.20, // cheaper
|
||||
|
||||
@@ -42,9 +42,6 @@ fn model_entry(loaded: bool, feasible: bool) -> CortexModelEntry {
|
||||
max_model_len: None,
|
||||
max_input_tokens: None,
|
||||
max_output_tokens: None,
|
||||
context_window: None,
|
||||
context_length: None,
|
||||
reasoning_budget: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -58,11 +58,6 @@ mod tests {
|
||||
assert!(cfg.max_redirects > 0);
|
||||
}
|
||||
|
||||
// The closure's error type is `figment::Error`, which is 208 bytes and
|
||||
// not ours to shrink; `Jail::expect_with` dictates the signature. The
|
||||
// usual remedy (box the Err) is not available through a third-party
|
||||
// callback contract, and this is a test closure run once.
|
||||
#[allow(clippy::result_large_err)]
|
||||
#[test]
|
||||
fn loads_toml_with_env_override() {
|
||||
figment::Jail::expect_with(|jail| {
|
||||
|
||||
@@ -287,44 +287,15 @@ fn default_from_addr() -> String {
|
||||
impl UpstreamConfig {
|
||||
/// Load from a TOML file with `UPSTREAM_`-prefixed env overrides
|
||||
/// (`__` nesting separator).
|
||||
///
|
||||
/// A sibling `secrets.toml`, if present, merges after the main file
|
||||
/// and wins — see [`secrets_path`].
|
||||
pub fn load(path: impl AsRef<Path>) -> Result<Self, Box<figment::Error>> {
|
||||
let path = path.as_ref();
|
||||
Figment::new()
|
||||
.merge(Toml::file(path))
|
||||
.merge(Toml::file(secrets_path(path)))
|
||||
.merge(Env::prefixed("UPSTREAM_").split("__"))
|
||||
.extract()
|
||||
.map_err(Box::new)
|
||||
}
|
||||
}
|
||||
|
||||
/// `secrets.toml` beside the main config.
|
||||
///
|
||||
/// The main file holds structure and is deployed by CI; this one holds
|
||||
/// credentials, is written only by the operator, and is never read,
|
||||
/// written or diffed by the pipeline. Merging it last means the
|
||||
/// operator's value wins, so a deploy cannot swap a live credential for
|
||||
/// a placeholder.
|
||||
///
|
||||
/// The split exists because config CI cannot write is config no check
|
||||
/// can defend — `helexa-router.toml` was kept out of git for sitting
|
||||
/// beside secret-bearing files, and its stale alias then took a node
|
||||
/// down (2026-08-27). The answer is to separate secrets from structure,
|
||||
/// not to hand the pipeline the credentials.
|
||||
///
|
||||
/// A missing file is not an error: figment treats an absent
|
||||
/// `Toml::file` as an empty source, so existing single-file deployments
|
||||
/// keep working untouched.
|
||||
fn secrets_path(config: &Path) -> std::path::PathBuf {
|
||||
config
|
||||
.parent()
|
||||
.unwrap_or_else(|| Path::new("."))
|
||||
.join("secrets.toml")
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
@@ -53,6 +53,18 @@ fn unique_email() -> String {
|
||||
format!("u-{}@test.local", uuid::Uuid::new_v4())
|
||||
}
|
||||
|
||||
/// A fixture value that is unique per run.
|
||||
///
|
||||
/// Rows keyed on a hash of these (`email_tokens.token_hash`,
|
||||
/// `api_keys.key_hash`) are uniquely indexed, so a hard-coded literal
|
||||
/// passes against a virgin database and then fails with `23505` on every
|
||||
/// run afterwards — the tests only looked deterministic because CI always
|
||||
/// gets a fresh one. Anything inserted under a unique constraint gets a
|
||||
/// fresh value here.
|
||||
fn unique_secret(prefix: &str) -> String {
|
||||
format!("{prefix}-{}", uuid::Uuid::new_v4())
|
||||
}
|
||||
|
||||
async fn post(url: String, body: Value, bearer: Option<&str>) -> reqwest::Response {
|
||||
let c = reqwest::Client::new();
|
||||
let mut req = c.post(url).json(&body);
|
||||
@@ -85,13 +97,13 @@ async fn verify_endpoint_consumes_token_once() {
|
||||
.await
|
||||
.unwrap()
|
||||
.get("id");
|
||||
let raw = "verify-raw-token-xyz";
|
||||
let raw = unique_secret("verify-raw-token");
|
||||
pool.execute(
|
||||
sqlx::query(
|
||||
"INSERT INTO email_tokens (token_hash, user_id, kind, expires_at) \
|
||||
VALUES ($1, $2, 'verify', now() + interval '1 hour')",
|
||||
)
|
||||
.bind(sha256(raw))
|
||||
.bind(sha256(&raw))
|
||||
.bind(user_id),
|
||||
)
|
||||
.await
|
||||
@@ -273,13 +285,13 @@ async fn fingerprint_abuse_silently_deactivates_all_no_clue() {
|
||||
.await
|
||||
.unwrap()
|
||||
.get("id");
|
||||
let raw = "sk-helexa-deactivated-probe";
|
||||
let raw = unique_secret("sk-helexa-deactivated-probe");
|
||||
pool.execute(
|
||||
sqlx::query(
|
||||
"INSERT INTO api_keys (account_id, key_hash, key_prefix) VALUES ($1, $2, 'sk-helexa-')",
|
||||
)
|
||||
.bind(acct)
|
||||
.bind(sha256(raw)),
|
||||
.bind(sha256(&raw)),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
+12
-119
@@ -2,7 +2,6 @@
|
||||
|
||||
use crate::activation::ActivationTracker;
|
||||
use crate::harness::HarnessRegistry;
|
||||
use crate::harness::candle::WireSurface;
|
||||
use crate::harness::candle::{CandleHarness, InferenceError};
|
||||
use crate::harness::preflight::PreflightError;
|
||||
use crate::health::HealthCache;
|
||||
@@ -22,7 +21,7 @@ use futures::stream::{self, StreamExt};
|
||||
use serde_json::{Value, json};
|
||||
use std::convert::Infallible;
|
||||
use std::sync::Arc;
|
||||
use std::time::{Duration, SystemTime, UNIX_EPOCH};
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
use tokio::sync::RwLock;
|
||||
use tokio_stream::wrappers::ReceiverStream;
|
||||
|
||||
@@ -273,35 +272,6 @@ fn default_enable_thinking(req: &mut ChatCompletionRequest, include_thinking: bo
|
||||
/// client-supplied copy and asserts the authoritative value, so over the
|
||||
/// trusted WireGuard link these are safe to key fair-share on. `None` for an
|
||||
/// unauthenticated/direct request — exempt from the per-principal cap.
|
||||
/// SSE keep-alive for the inference streams.
|
||||
///
|
||||
/// A streamed completion emits its `role` delta immediately and then says
|
||||
/// **nothing at all until prefill finishes** — there is no token to send
|
||||
/// yet. On a long prompt that silence is seconds long: a 7.4k-token prompt
|
||||
/// on a TP-2 27B prefills in about six.
|
||||
///
|
||||
/// `KeepAlive::default()` is axum's 15s, which is longer than almost every
|
||||
/// prefill we serve, so in practice it never fired and the gap went out on
|
||||
/// the wire as dead air. Clients read dead air as a dropped stream: the
|
||||
/// DeepSeek Harness gives up after roughly a second and reports
|
||||
/// `terminated`, then retries — and because the abandoned request keeps its
|
||||
/// admission permit and the TP pool lock until it finishes, each retry
|
||||
/// queues behind the last one and waits *longer*, so the session never
|
||||
/// recovers on its own. Every attempt failed while the model was healthy
|
||||
/// and, by then, three sequences deep in work nobody was listening to.
|
||||
///
|
||||
/// One second is chosen to sit under the shortest client idle timeout we
|
||||
/// have met rather than to be tuned to any particular one. The cost is a
|
||||
/// 3-byte comment frame per idle second, which SSE parsers discard by
|
||||
/// spec; the benefit is that a prefill of any length looks alive.
|
||||
///
|
||||
/// This does not make a slow prefill fast — see the `chunked prefill`
|
||||
/// path for that — it stops a slow prefill being indistinguishable from a
|
||||
/// dead connection.
|
||||
fn prefill_keep_alive() -> KeepAlive {
|
||||
KeepAlive::new().interval(Duration::from_secs(1))
|
||||
}
|
||||
|
||||
fn principal_key(headers: &axum::http::HeaderMap) -> Option<String> {
|
||||
let account = headers.get(HEADER_ACCOUNT_ID)?.to_str().ok()?;
|
||||
let key = headers.get(HEADER_KEY_ID)?.to_str().ok()?;
|
||||
@@ -363,7 +333,7 @@ async fn chat_completions(
|
||||
|
||||
if req.stream.unwrap_or(false) {
|
||||
match candle
|
||||
.chat_completion_stream_with(req, chat_config, principal, WireSurface::Chat)
|
||||
.chat_completion_stream_with(req, chat_config, principal)
|
||||
.await
|
||||
{
|
||||
Ok(rx) => {
|
||||
@@ -376,16 +346,13 @@ async fn chat_completions(
|
||||
let done_stream =
|
||||
stream::once(async { Ok::<_, Infallible>(Event::default().data("[DONE]")) });
|
||||
Sse::new(body_stream.chain(done_stream))
|
||||
.keep_alive(prefill_keep_alive())
|
||||
.keep_alive(KeepAlive::default())
|
||||
.into_response()
|
||||
}
|
||||
Err(e) => inference_error_response(e),
|
||||
}
|
||||
} else {
|
||||
match candle
|
||||
.chat_completion(req, principal, WireSurface::Chat)
|
||||
.await
|
||||
{
|
||||
match candle.chat_completion(req, principal).await {
|
||||
Ok(resp) => Json(resp).into_response(),
|
||||
Err(e) => inference_error_response(e),
|
||||
}
|
||||
@@ -438,13 +405,7 @@ async fn responses(
|
||||
|
||||
if stream_requested {
|
||||
match candle
|
||||
.responses_stream(
|
||||
chat_req,
|
||||
response_id,
|
||||
message_item_id,
|
||||
principal,
|
||||
WireSurface::Responses,
|
||||
)
|
||||
.responses_stream(chat_req, response_id, message_item_id, principal)
|
||||
.await
|
||||
{
|
||||
Ok(rx) => {
|
||||
@@ -458,7 +419,7 @@ async fn responses(
|
||||
Ok::<_, Infallible>(Event::default().event(frame.event_name).data(body))
|
||||
});
|
||||
Sse::new(body_stream)
|
||||
.keep_alive(prefill_keep_alive())
|
||||
.keep_alive(KeepAlive::default())
|
||||
.into_response()
|
||||
}
|
||||
Err(e) => inference_error_response(e),
|
||||
@@ -468,10 +429,7 @@ async fn responses(
|
||||
// and translate the result. We don't currently re-tokenise
|
||||
// to compute usage; the harness returns it via the chat
|
||||
// response and we pass it through.
|
||||
match candle
|
||||
.chat_completion(chat_req, principal, WireSurface::Responses)
|
||||
.await
|
||||
{
|
||||
match candle.chat_completion(chat_req, principal).await {
|
||||
Ok(chat_resp) => {
|
||||
// Extract the assistant text (chat completions
|
||||
// always emits one choice on the candle path).
|
||||
@@ -499,9 +457,9 @@ async fn responses(
|
||||
input_tokens: u.prompt_tokens,
|
||||
output_tokens: u.completion_tokens,
|
||||
total_tokens: u.prompt_tokens + u.completion_tokens,
|
||||
// Carry the reasoning sub-count through from the
|
||||
// chat usage: the collector counts the `<think>`
|
||||
// span and returns its text separately.
|
||||
// Carry the reasoning sub-count through from the chat
|
||||
// usage — the non-streaming path now splits off the
|
||||
// `<think>` span and counts it (see `split_off_reasoning`).
|
||||
output_tokens_details: u.completion_tokens_details.as_ref().map(|d| {
|
||||
OutputTokensDetails {
|
||||
reasoning_tokens: d.reasoning_tokens,
|
||||
@@ -515,18 +473,8 @@ async fn responses(
|
||||
model_id,
|
||||
message_item_id: mint_message_item_id(),
|
||||
};
|
||||
// The model's think block, which the chat collector now
|
||||
// returns on `message.reasoning_content` (#300). Without
|
||||
// this the caller is billed for `reasoning_tokens` it
|
||||
// never sees, and cannot replay the model's own
|
||||
// reasoning on the next turn.
|
||||
let reasoning = chat_resp
|
||||
.choices
|
||||
.first()
|
||||
.and_then(|c| c.message.extra.get("reasoning_content"))
|
||||
.and_then(|v| v.as_str())
|
||||
.map(str::to_string);
|
||||
let resp = openai_responses::build_response(&meta, text, finish, usage, reasoning);
|
||||
let _ = chat_resp; // make the borrow-checker happy if `text` consumed it
|
||||
let resp = openai_responses::build_response(&meta, text, finish, usage);
|
||||
Json(resp).into_response()
|
||||
}
|
||||
Err(e) => inference_error_response(e),
|
||||
@@ -781,18 +729,6 @@ fn inference_error_response(err: InferenceError) -> axum::response::Response {
|
||||
"too many concurrent requests for this key; retry shortly",
|
||||
)
|
||||
.with_retry_after(retry_after_secs),
|
||||
// Draining (#256). 503 + Retry-After, like any transient capacity
|
||||
// condition: the node is coming back, and a well-behaved client
|
||||
// should retry rather than surface a failure. Deliberately not
|
||||
// `rate_limit_exceeded` — nothing about this is the caller's
|
||||
// fault or their rate.
|
||||
InferenceError::ShuttingDown => OpenAiError::new(
|
||||
503,
|
||||
"api_error",
|
||||
"shutting_down",
|
||||
"neuron is shutting down; retry shortly",
|
||||
)
|
||||
.with_retry_after(15),
|
||||
InferenceError::Other(e) => OpenAiError::without_code(500, "api_error", format!("{e:#}")),
|
||||
};
|
||||
// Every failed request says why, once, here (#63). Before this the
|
||||
@@ -1109,46 +1045,3 @@ where
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod keep_alive_tests {
|
||||
use super::*;
|
||||
use futures::StreamExt;
|
||||
|
||||
/// A stream that emits its opening frame and then goes quiet — the
|
||||
/// shape of every streamed completion while it prefills — must keep
|
||||
/// putting bytes on the wire.
|
||||
///
|
||||
/// The deadline here is the point: with axum's 15s default this test
|
||||
/// times out, which is exactly the production failure. A 7.4k-token
|
||||
/// prompt prefills in ~6s, so the default never fired once, the
|
||||
/// connection sat silent for the whole prefill, and clients dropped it
|
||||
/// as dead — the DeepSeek Harness after ~1s, reporting `terminated`.
|
||||
///
|
||||
/// Asserted against observable output rather than the configured
|
||||
/// interval because `KeepAlive` exposes no getter, and because what
|
||||
/// broke was the behaviour, not the number.
|
||||
#[tokio::test]
|
||||
async fn a_silent_stream_still_sends_bytes_while_prefilling() {
|
||||
let silent = stream::pending::<Result<Event, Infallible>>();
|
||||
let response = Sse::new(silent)
|
||||
.keep_alive(prefill_keep_alive())
|
||||
.into_response();
|
||||
|
||||
let mut body = response.into_body().into_data_stream();
|
||||
let frame = tokio::time::timeout(Duration::from_secs(3), body.next())
|
||||
.await
|
||||
.expect("a silent stream must emit a keep-alive well inside any client idle timeout")
|
||||
.expect("stream ended instead of keeping alive")
|
||||
.expect("keep-alive frame");
|
||||
|
||||
// SSE comment frames start with ':' and are discarded by parsers
|
||||
// per spec, so this costs the client nothing but proves liveness.
|
||||
assert_eq!(
|
||||
frame.first(),
|
||||
Some(&b':'),
|
||||
"expected an SSE comment frame, got {:?}",
|
||||
String::from_utf8_lossy(&frame)
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -86,16 +86,6 @@ pub struct CandleHarnessConfig {
|
||||
#[serde(default)]
|
||||
pub context_limit: ContextLimitConfig,
|
||||
|
||||
/// What each OpenAI effort level costs, in reasoning tokens (#223).
|
||||
///
|
||||
/// OpenAI-shaped clients cannot send a token count — their whole
|
||||
/// vocabulary is the `minimal|low|medium|high` ladder — so the
|
||||
/// numbers live here and are advertised on `/models`. Operator
|
||||
/// configurable because the right values depend on the model and the
|
||||
/// hardware.
|
||||
#[serde(default)]
|
||||
pub reasoning_budget: crate::harness::reasoning_budget::ReasoningBudgetLadder,
|
||||
|
||||
/// Admission control (#53): bounds the per-model wait queue so a busy
|
||||
/// model returns a fast, retryable `429`/`503` instead of stalling new
|
||||
/// requests until their client times out.
|
||||
@@ -190,36 +180,9 @@ pub struct AdmissionConfig {
|
||||
/// for any single principal (resolved from the `x-helexa-*` headers
|
||||
/// cortex stamps), so one client can't monopolize the queue while others
|
||||
/// wait. Over-cap → `429 rate_limit_exceeded` + `Retry-After`. `0`
|
||||
/// disables the cap.
|
||||
///
|
||||
/// Anonymous requests carry no principal and so cannot be capped by it.
|
||||
/// They are bounded instead by `anon_max_in_flight` / `anon_max_pending`
|
||||
/// below (#262).
|
||||
/// disables the cap; anonymous requests are always exempt.
|
||||
#[serde(default = "default_admission_max_per_principal")]
|
||||
pub max_per_principal: usize,
|
||||
/// Ceiling on **anonymous** requests holding an in-flight seat (#262).
|
||||
///
|
||||
/// Anonymous traffic is served from capacity left over once identified
|
||||
/// traffic is satisfied: it never takes a seat while an identified
|
||||
/// request is waiting, and it may never hold every seat at once — which
|
||||
/// is what this bounds, because a request already running cannot be
|
||||
/// preempted. Reserving one seat is what caps how long a newly arrived
|
||||
/// identified request waits: one request's duration, not all of them.
|
||||
///
|
||||
/// Unset (the default) derives `max_in_flight - 1`, floored at 1 so a
|
||||
/// single-seat model still serves anonymous callers. `0` refuses
|
||||
/// anonymous traffic outright.
|
||||
#[serde(default)]
|
||||
pub anon_max_in_flight: Option<usize>,
|
||||
/// Ceiling on anonymous requests in flight **plus** queued (#262).
|
||||
///
|
||||
/// The queue needs the same reservation as the seats: without it an
|
||||
/// anonymous flood fills the queue and identified callers are refused at
|
||||
/// the door, before priority can help them.
|
||||
///
|
||||
/// Unset derives `max_in_flight + max_queue_depth - 1`, floored at 1.
|
||||
#[serde(default)]
|
||||
pub anon_max_pending: Option<usize>,
|
||||
/// Maximum seconds a request waits for enough **KV budget** to free
|
||||
/// before it is refused (#257). Deliberately far longer than
|
||||
/// `max_wait_secs`: that one waits for a slot to turn over, this one
|
||||
@@ -237,8 +200,6 @@ impl Default for AdmissionConfig {
|
||||
max_queue_depth: default_admission_max_queue_depth(),
|
||||
max_wait_secs: default_admission_max_wait_secs(),
|
||||
max_per_principal: default_admission_max_per_principal(),
|
||||
anon_max_in_flight: None,
|
||||
anon_max_pending: None,
|
||||
kv_max_wait_secs: default_admission_kv_max_wait_secs(),
|
||||
}
|
||||
}
|
||||
@@ -343,24 +304,8 @@ pub struct ContextLimitConfig {
|
||||
/// Generation reserve (tokens) left below the context wall:
|
||||
/// `input = context − output_reserve_tokens`. Defaults to neuron's
|
||||
/// default `max_tokens`.
|
||||
///
|
||||
/// This is the budget a request gets when it names none, and the
|
||||
/// figure the input/output split is derived from. It is **not** the
|
||||
/// most a request may ask for — see `max_output_tokens` (#278).
|
||||
#[serde(default = "default_output_reserve_tokens")]
|
||||
pub output_reserve_tokens: usize,
|
||||
|
||||
/// The largest output a request may name, advertised as
|
||||
/// `max_output_tokens` on `/v1/models` (#278).
|
||||
///
|
||||
/// `None` derives it as `min(max_position_embeddings,
|
||||
/// DEFAULT_OUTPUT_CEILING)`. Separate from the reserve because the
|
||||
/// two answer different questions and were previously the same
|
||||
/// number: publishing the reserve told every client that read the
|
||||
/// advertisement to cap itself at the default, which on a reasoning
|
||||
/// model can be less than one think block.
|
||||
#[serde(default)]
|
||||
pub max_output_tokens: Option<usize>,
|
||||
}
|
||||
|
||||
impl Default for ContextLimitConfig {
|
||||
@@ -372,7 +317,6 @@ impl Default for ContextLimitConfig {
|
||||
activation_headroom_mb: default_activation_headroom_mb(),
|
||||
min_free_floor_mb: default_context_min_free_floor_mb(),
|
||||
output_reserve_tokens: default_output_reserve_tokens(),
|
||||
max_output_tokens: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -380,23 +380,7 @@ impl GatedDeltaNet {
|
||||
self.head_v_dim,
|
||||
)?;
|
||||
// Stash the updated recurrent state for the next call.
|
||||
//
|
||||
// The delta rule ran in f32 and `state_init` upcasts back to f32
|
||||
// on entry, so storing at the model dtype is a round trip that
|
||||
// buys only memory (#284). Decode takes it once per token.
|
||||
//
|
||||
// Storing f32 keeps `new_state` as-is, which on the CUDA decode
|
||||
// path is the same buffer the kernel updated in place — so the
|
||||
// stored state aliases it, where the `to_dtype` branch always
|
||||
// allocated afresh. That is sound: the pre-update value is dead
|
||||
// by this point, and prefix snapshots deep-copy
|
||||
// (`snapshot_state`) precisely so they never share storage with
|
||||
// a buffer a later forward will overwrite.
|
||||
self.state.recurrent_state = Some(if gdn_state_f32() {
|
||||
new_state
|
||||
} else {
|
||||
new_state.to_dtype(dtype)?
|
||||
});
|
||||
self.state.recurrent_state = Some(new_state.to_dtype(dtype)?);
|
||||
|
||||
// core_attn_out: (B, H, L, D_v) → (B, L, H, D_v) → (B*L*H, D_v).
|
||||
let core_attn_out = core_attn_out.transpose(1, 2)?.contiguous()?; // (B, L, H, D_v)
|
||||
@@ -480,33 +464,6 @@ fn chunked_prefill_enabled() -> bool {
|
||||
})
|
||||
}
|
||||
|
||||
/// `NEURON_GDN_STATE_F32=1` keeps the recurrent state in f32 between
|
||||
/// forwards instead of storing it at the model's activation dtype (#284).
|
||||
///
|
||||
/// The delta rule computes in f32 throughout, so storing the result at
|
||||
/// BF16 and upcasting it again next call is a pure round-trip loss.
|
||||
/// Measured on the chunked path: bit-exact carrying f32 at every chunk
|
||||
/// size, against 1.3e-3 relative error after 16 prefill chunks and
|
||||
/// **1.0e-2 after 4096 decode steps** — decode round-trips once per
|
||||
/// token, across 48 of this arch's 64 layers.
|
||||
///
|
||||
/// Off by default on purpose. Every #283 measurement was taken against
|
||||
/// the bf16 baseline, and flipping this silently would move the ground
|
||||
/// underneath the sampling A/B and the decode-rate work (#282, #285)
|
||||
/// at the same time. Turn it on deliberately, measure, then decide the
|
||||
/// default.
|
||||
///
|
||||
/// Costs ~2× the recurrent slab: +37.7 MB per GPU per sequence on the
|
||||
/// deployed 27B under TP=2, so +302 MB/GPU at `max_in_flight = 8`.
|
||||
fn gdn_state_f32() -> bool {
|
||||
static ENABLED: std::sync::OnceLock<bool> = std::sync::OnceLock::new();
|
||||
*ENABLED.get_or_init(|| {
|
||||
std::env::var("NEURON_GDN_STATE_F32")
|
||||
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
|
||||
.unwrap_or(false)
|
||||
})
|
||||
}
|
||||
|
||||
/// Chunk-parallel gated delta rule — a faithful port of the HF
|
||||
/// reference `torch_chunk_gated_delta_rule` (chunk_size = 64) in
|
||||
/// `transformers/models/qwen3_5/modeling_qwen3_5.py`, minus the steps
|
||||
@@ -1140,94 +1097,6 @@ mod tests {
|
||||
assert!(d_state < 2e-4, "final state diverged: {d_state}");
|
||||
}
|
||||
|
||||
/// #284: the state carried *between* forwards must not lose
|
||||
/// precision. Every other parity test here is single-call and
|
||||
/// all-f32, so none of them crosses the boundary where
|
||||
/// `GatedDeltaNet::forward` stores the state at the model's
|
||||
/// activation dtype — which is why the defect lived.
|
||||
///
|
||||
/// Two properties, one test:
|
||||
///
|
||||
/// 1. carrying f32, an N-chunk run equals a single call **exactly**,
|
||||
/// so the chunk-boundary math itself is sound (this kills the
|
||||
/// "chunked prefill corrupts state" hypothesis, #283 H1);
|
||||
/// 2. carrying the model dtype loses a measurable, chunk-count-
|
||||
/// dependent amount — the defect the `NEURON_GDN_STATE_F32` flag
|
||||
/// exists to switch off.
|
||||
///
|
||||
/// Asserting (2) is deliberate: if a future change makes the bf16
|
||||
/// carry lossless this test fails loudly and the flag can go, rather
|
||||
/// than the flag quietly outliving its reason.
|
||||
#[test]
|
||||
fn state_carried_across_chunks_is_exact_in_f32_and_lossy_in_bf16() {
|
||||
let (b, h, dk, dv) = (1, 2, 32, 32);
|
||||
let dev = Device::Cpu;
|
||||
let l = 1024;
|
||||
// Long-memory decay: g near zero keeps the state alive across
|
||||
// every boundary, which is both the realistic regime for
|
||||
// long-context retrieval and the one that accumulates most.
|
||||
let scale = 1.0 / (dk as f64).sqrt();
|
||||
let q = Tensor::randn(0f32, 1.0, (b, h, l, dk), &dev).unwrap();
|
||||
let q = (l2norm(&q, 1e-6).unwrap() * scale).unwrap();
|
||||
let k = Tensor::randn(0f32, 1.0, (b, h, l, dk), &dev).unwrap();
|
||||
let k = l2norm(&k, 1e-6).unwrap();
|
||||
let v = (Tensor::randn(0f32, 1.0, (b, h, l, dv), &dev).unwrap() * 0.5).unwrap();
|
||||
let g = (Tensor::rand(0f32, 1f32, (b, h, l), &dev).unwrap() * -0.02).unwrap();
|
||||
let beta = Tensor::rand(0.05f32, 0.95f32, (b, h, l), &dev).unwrap();
|
||||
let zeros = || Tensor::zeros((b, h, dk, dv), DType::F32, &dev).unwrap();
|
||||
|
||||
// Ground truth: the whole sequence in one call, f32 throughout.
|
||||
let (out_ref, _) = run_chunk_gated_delta_rule(&q, &k, &v, &g, &beta, zeros()).unwrap();
|
||||
|
||||
// Replay it in `chunk`-sized pieces, carrying the state the way
|
||||
// `forward` does.
|
||||
let replay = |chunk: usize, carry: Option<DType>| {
|
||||
let mut state = zeros();
|
||||
let mut outs = Vec::new();
|
||||
let mut pos = 0;
|
||||
while pos < l {
|
||||
let n = chunk.min(l - pos);
|
||||
let take = |t: &Tensor| t.narrow(2, pos, n).unwrap().contiguous().unwrap();
|
||||
let (o, s) = run_chunk_gated_delta_rule(
|
||||
&take(&q),
|
||||
&take(&k),
|
||||
&take(&v),
|
||||
&take(&g),
|
||||
&take(&beta),
|
||||
state,
|
||||
)
|
||||
.unwrap();
|
||||
state = match carry {
|
||||
Some(dt) => s.to_dtype(dt).unwrap().to_dtype(DType::F32).unwrap(),
|
||||
None => s,
|
||||
};
|
||||
outs.push(o);
|
||||
pos += n;
|
||||
}
|
||||
Tensor::cat(&outs, 2).unwrap()
|
||||
};
|
||||
|
||||
for chunk in [128usize, 256, 512] {
|
||||
let exact = max_abs_diff(&out_ref, &replay(chunk, None));
|
||||
assert_eq!(
|
||||
exact, 0.0,
|
||||
"chunk={chunk}: an f32 state carry must reproduce the \
|
||||
single-call result bit for bit, got {exact:e}"
|
||||
);
|
||||
}
|
||||
|
||||
// And the dtype round trip is what costs us. Compared on the
|
||||
// final chunk, where the accumulated state has done the most work.
|
||||
let tail = |t: &Tensor| t.narrow(2, l - 128, 128).unwrap().contiguous().unwrap();
|
||||
let lossy = max_abs_diff(&tail(&out_ref), &tail(&replay(128, Some(DType::BF16))));
|
||||
assert!(
|
||||
lossy > 1e-5,
|
||||
"storing the state at BF16 between chunks is expected to lose \
|
||||
precision (#284); if this now passes losslessly the flag can \
|
||||
be retired, got {lossy:e}"
|
||||
);
|
||||
}
|
||||
|
||||
/// Adversarially correlated inputs: near-identical keys with
|
||||
/// beta ≈ 1 and negligible decay make the UT-transform matrix T
|
||||
/// maximally coherent — raw powers of T grow combinatorially
|
||||
|
||||
@@ -562,9 +562,9 @@ mod tests {
|
||||
.forward_batch_decode(&input, &positions, mask.as_ref())
|
||||
.expect("batched step");
|
||||
assert_eq!(h.dims()[0], 3);
|
||||
for (row, exp) in expected.iter().enumerate() {
|
||||
for row in 0..3 {
|
||||
let got: Vec<f32> = h.i((row, 0, ..)).unwrap().to_vec1().unwrap();
|
||||
let diff = max_abs_diff(&exp[t], &got);
|
||||
let diff = max_abs_diff(&expected[row][t], &got);
|
||||
assert!(diff < 1e-4, "row {row} step {t} diverged: {diff}");
|
||||
}
|
||||
}
|
||||
@@ -610,9 +610,9 @@ mod tests {
|
||||
let h = model
|
||||
.forward_batch_decode(&input, &[3, 3], None)
|
||||
.expect("step");
|
||||
for (row, exp) in expected.iter().enumerate() {
|
||||
for row in 0..2 {
|
||||
let got: Vec<f32> = h.i((row, 0, ..)).unwrap().to_vec1().unwrap();
|
||||
let diff = max_abs_diff(exp, &got);
|
||||
let diff = max_abs_diff(&expected[row], &got);
|
||||
assert!(diff < 1e-4, "row {row} diverged: {diff}");
|
||||
}
|
||||
}
|
||||
@@ -674,9 +674,9 @@ mod tests {
|
||||
let h = model
|
||||
.forward_batch_decode(&input, &positions, mask.as_ref())
|
||||
.expect("batched step");
|
||||
for (row, exp) in expected.iter().enumerate() {
|
||||
for row in 0..2 {
|
||||
let got: Vec<f32> = h.i((row, 0, ..)).unwrap().to_vec1().unwrap();
|
||||
let diff = max_abs_diff(&exp[t], &got);
|
||||
let diff = max_abs_diff(&expected[row][t], &got);
|
||||
assert!(diff < 1e-4, "batched row {row} step {t}: {diff}");
|
||||
}
|
||||
}
|
||||
|
||||
+1364
-1633
File diff suppressed because it is too large
Load Diff
@@ -233,24 +233,7 @@ pub fn render_chat_template(
|
||||
MessageContent::Null => Value::Null,
|
||||
};
|
||||
let mut obj = serde_json::Map::new();
|
||||
// `developer` is OpenAI's successor to `system` and is what
|
||||
// a client sends once a model is declared reasoning-capable
|
||||
// (pi-ai: `model.reasoning && supportsDeveloperRole`). Most
|
||||
// chat templates — every one on this fleet — only know the
|
||||
// older spelling and `raise_exception` on anything else, so
|
||||
// an unmodified client got a 422 for a system prompt it sent
|
||||
// correctly.
|
||||
//
|
||||
// Rewritten only when the template does not handle the role
|
||||
// itself: a template that knows `developer` may treat it as
|
||||
// distinct from `system`, and substituting there would be us
|
||||
// deciding something the model's authors already decided.
|
||||
let role = if m.role == "developer" && !template.contains("developer") {
|
||||
"system"
|
||||
} else {
|
||||
m.role.as_str()
|
||||
};
|
||||
obj.insert("role".into(), Value::String(role.to_string()));
|
||||
obj.insert("role".into(), Value::String(m.role.clone()));
|
||||
obj.insert("content".into(), content_value);
|
||||
// Forward extras (e.g. tool_calls on assistant turns,
|
||||
// tool_call_id on tool result turns). HF templates that
|
||||
@@ -438,139 +421,6 @@ mod tests {
|
||||
assert!(out.contains("<|vision_start|>") && out.contains("<|vision_end|>"));
|
||||
}
|
||||
|
||||
/// A file read back through a tool result must reach the model
|
||||
/// byte-for-byte.
|
||||
///
|
||||
/// The reported symptom: the model writes a file correctly, reads it
|
||||
/// back, and sees errors that are not in the file — consistently,
|
||||
/// after every write. Anything that mangles `<`, `&`, `"` or
|
||||
/// newlines on this path would produce exactly that, and would make
|
||||
/// the model burn its budget reconciling a file against a corrupted
|
||||
/// view of itself.
|
||||
#[test]
|
||||
fn a_file_read_back_through_a_tool_result_is_byte_exact() {
|
||||
let template = include_str!("../../tests/data/qwen3.8-27b.chat_template.jinja");
|
||||
// The characters most likely to be mangled, in the shapes a real
|
||||
// web project contains them.
|
||||
let file = "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"utf-8\">\n</head>\n<body>\n <script>\n if (a && b || c < d) { g.fillStyle = '#b8905a'; }\n const s = `rgba(${r},${g},0.5)`;\n\n // a comment & an ampersand\n </script>\n</body>\n</html>\n";
|
||||
|
||||
let mut tool_extras = serde_json::Map::new();
|
||||
tool_extras.insert("tool_call_id".into(), json!("call_0"));
|
||||
let mut assistant_extras = serde_json::Map::new();
|
||||
assistant_extras.insert(
|
||||
"tool_calls".into(),
|
||||
json!([{"id":"call_0","type":"function",
|
||||
"function":{"name":"read","arguments":"{\"path\":\"/tmp/index.html\"}"}}]),
|
||||
);
|
||||
|
||||
let messages = vec![
|
||||
user_msg("read the file back"),
|
||||
ChatMessage {
|
||||
role: "assistant".into(),
|
||||
content: MessageContent::Null,
|
||||
extra: Value::Object(assistant_extras),
|
||||
},
|
||||
ChatMessage {
|
||||
role: "tool".into(),
|
||||
content: MessageContent::Text(file.to_string()),
|
||||
extra: Value::Object(tool_extras),
|
||||
},
|
||||
user_msg("is it correct?"),
|
||||
];
|
||||
let out =
|
||||
render_chat_template(template, &messages, &Value::Null, &Value::Null).expect("render");
|
||||
|
||||
for probe in [
|
||||
"<!DOCTYPE html>",
|
||||
"<html lang=\"en\">",
|
||||
"if (a && b || c < d)",
|
||||
"g.fillStyle = '#b8905a';",
|
||||
"`rgba(${r},${g},0.5)`",
|
||||
"// a comment & an ampersand",
|
||||
] {
|
||||
assert!(
|
||||
out.contains(probe),
|
||||
"the model would not see {probe:?} verbatim — rendered prompt mangles it"
|
||||
);
|
||||
}
|
||||
// And nothing HTML-escaped anywhere.
|
||||
for bad in ["<", ">", "&", """, "'", "'"] {
|
||||
assert!(
|
||||
!out.contains(bad),
|
||||
"found {bad:?} in the rendered prompt: content is being HTML-escaped"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// Blank lines inside a replayed tool-call argument must survive
|
||||
/// rendering intact.
|
||||
///
|
||||
/// A model that writes a source file and then re-reads it from its
|
||||
/// own replayed tool call is comparing what it remembers writing
|
||||
/// against what the prompt now shows. Any whitespace the pipeline
|
||||
/// eats makes those disagree, and the model has no way to tell a
|
||||
/// rendering artifact from a mistake of its own — which is a
|
||||
/// plausible route into the announce-then-stop stall (#296).
|
||||
///
|
||||
/// The JSON string→object normalisation above is the step that
|
||||
/// could plausibly lose them, since it round-trips the arguments
|
||||
/// through a parser.
|
||||
#[test]
|
||||
fn a_replayed_tool_call_keeps_the_blank_lines_in_its_arguments() {
|
||||
let template = include_str!("../../tests/data/qwen3.8-27b.chat_template.jinja");
|
||||
// Blank lines between sections, exactly as a written source file
|
||||
// carries them.
|
||||
let file_body = "'use strict';\n\n// ---- constants ----\nconst A = 1;\n\n\nfunction f() {\n return A;\n}\n";
|
||||
let args = json!({ "path": "/tmp/game.js", "content": file_body });
|
||||
let mut assistant_extras = serde_json::Map::new();
|
||||
assistant_extras.insert(
|
||||
"tool_calls".into(),
|
||||
json!([{
|
||||
"id": "call_0", "type": "function",
|
||||
"function": {
|
||||
"name": "write",
|
||||
// The OpenAI wire form: arguments as a JSON *string*.
|
||||
"arguments": serde_json::to_string(&args).unwrap()
|
||||
}
|
||||
}]),
|
||||
);
|
||||
let mut tool_extras = serde_json::Map::new();
|
||||
tool_extras.insert("tool_call_id".into(), json!("call_0"));
|
||||
|
||||
let messages = vec![
|
||||
user_msg("write the file"),
|
||||
ChatMessage {
|
||||
role: "assistant".into(),
|
||||
content: MessageContent::Null,
|
||||
extra: Value::Object(assistant_extras),
|
||||
},
|
||||
ChatMessage {
|
||||
role: "tool".into(),
|
||||
content: MessageContent::Text("Successfully wrote 84 bytes".into()),
|
||||
extra: Value::Object(tool_extras),
|
||||
},
|
||||
user_msg("now check it parses"),
|
||||
];
|
||||
let out =
|
||||
render_chat_template(template, &messages, &Value::Null, &Value::Null).expect("render");
|
||||
|
||||
assert!(
|
||||
out.contains(file_body),
|
||||
"the file body must appear verbatim in the rendered prompt"
|
||||
);
|
||||
let blanks_in = file_body.lines().filter(|l| l.is_empty()).count();
|
||||
assert_eq!(blanks_in, 3, "fixture sanity");
|
||||
// And specifically the double newline the model would notice.
|
||||
assert!(
|
||||
out.contains("'use strict';\n\n// ---- constants ----"),
|
||||
"blank line after the prologue was eaten"
|
||||
);
|
||||
assert!(
|
||||
out.contains("const A = 1;\n\n\nfunction f()"),
|
||||
"consecutive blank lines were collapsed"
|
||||
);
|
||||
}
|
||||
|
||||
/// The second turn of an OpenAI-native agentic loop: the client
|
||||
/// replays its own assistant turn, which carries `tool_calls` and
|
||||
/// `"content": null`. That must render as the tool-call block —
|
||||
@@ -648,78 +498,6 @@ mod tests {
|
||||
/// Minimal Qwen3-style template — enough surface to confirm
|
||||
/// our renderer threads role + content correctly without
|
||||
/// loading a real model's tokenizer_config.json.
|
||||
/// A reasoning-capable model makes OpenAI clients send the system
|
||||
/// prompt as `developer` — and every chat template on this fleet
|
||||
/// raises on an unknown role, so the caller got a 422 for a prompt
|
||||
/// it had sent correctly. Observed live: pi with `reasoning: true`,
|
||||
/// `template_render_failed: Unexpected message role`.
|
||||
#[test]
|
||||
fn the_developer_role_reaches_a_template_that_only_knows_system() {
|
||||
const SYSTEM_ONLY: &str = "{%- for message in messages -%}\
|
||||
{%- if message.role == 'system' -%}SYS:{{ message.content }}\
|
||||
{%- elif message.role == 'user' -%}USR:{{ message.content }}\
|
||||
{%- else -%}{{ raise_exception('Unexpected message role.') }}\
|
||||
{%- endif -%}\
|
||||
{%- endfor -%}";
|
||||
let messages = vec![
|
||||
ChatMessage {
|
||||
role: "developer".into(),
|
||||
content: MessageContent::Text("be terse".into()),
|
||||
extra: Value::Object(Default::default()),
|
||||
},
|
||||
user_msg("hi"),
|
||||
];
|
||||
let out = render_chat_template(SYSTEM_ONLY, &messages, &Value::Null, &Value::Null)
|
||||
.expect("a developer role must not blow up a system-only template");
|
||||
assert!(out.contains("SYS:be terse"), "got {out:?}");
|
||||
}
|
||||
|
||||
/// A template that models `developer` itself keeps it: the role may
|
||||
/// mean something distinct there, and substituting would override a
|
||||
/// decision the model's authors already made.
|
||||
#[test]
|
||||
fn a_template_that_knows_developer_keeps_it() {
|
||||
const KNOWS_DEVELOPER: &str = "{%- for message in messages -%}\
|
||||
{%- if message.role == 'developer' -%}DEV:{{ message.content }}\
|
||||
{%- else -%}{{ message.role }}:{{ message.content }}\
|
||||
{%- endif -%}\
|
||||
{%- endfor -%}";
|
||||
let messages = vec![ChatMessage {
|
||||
role: "developer".into(),
|
||||
content: MessageContent::Text("be terse".into()),
|
||||
extra: Value::Object(Default::default()),
|
||||
}];
|
||||
let out = render_chat_template(KNOWS_DEVELOPER, &messages, &Value::Null, &Value::Null)
|
||||
.expect("render");
|
||||
assert!(out.contains("DEV:be terse"), "got {out:?}");
|
||||
}
|
||||
|
||||
/// The fetcher and the reader must agree on the filenames, or the
|
||||
/// reader looks for something nobody downloaded and falls back to a
|
||||
/// built-in prompt format without anything failing (#280 — observed
|
||||
/// live: every model neuron downloaded itself was served with the
|
||||
/// fallback because no sidecar was ever fetched).
|
||||
#[test]
|
||||
fn every_template_source_this_reads_is_one_the_loader_fetches() {
|
||||
for name in crate::harness::candle::CandleHarness::SIDECAR_FILES {
|
||||
assert!(
|
||||
!name.is_empty(),
|
||||
"sidecar names are the contract between fetch and read"
|
||||
);
|
||||
}
|
||||
// The three the reader consults, in its own priority order.
|
||||
for source in [
|
||||
"chat_template.jinja",
|
||||
"chat_template.json",
|
||||
"tokenizer_config.json",
|
||||
] {
|
||||
assert!(
|
||||
crate::harness::candle::CandleHarness::SIDECAR_FILES.contains(&source),
|
||||
"{source} is read by load_chat_template_alongside but never fetched"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
const QWEN3_LIKE: &str = "{%- for message in messages -%}\
|
||||
<|im_start|>{{ message.role }}\n{{ message.content }}<|im_end|>\n\
|
||||
{%- endfor -%}\
|
||||
|
||||
@@ -36,28 +36,6 @@ use crate::config::ContextLimitConfig;
|
||||
/// few turns.
|
||||
const RATE_EMA_ALPHA: f64 = 0.3;
|
||||
|
||||
/// Smallest prompt whose prefill time says anything about throughput.
|
||||
///
|
||||
/// A prefill has a fixed per-request cost — tokenize, launch, sync —
|
||||
/// that dominates a short prompt completely. The deploy's own smoke
|
||||
/// probe prefills 19 tokens in ~130 ms and reads as **145 tok/s** on a
|
||||
/// host that measures ~1,400. Folding that in does not make the
|
||||
/// estimate slightly worse; it replaces it.
|
||||
///
|
||||
/// That mattered because the fallback it displaces is the whole
|
||||
/// cold-start guard: with no sample at all, `derive_limit` uses
|
||||
/// `bootstrap_prefill_tok_per_sec` (800, ≈96k context at the default
|
||||
/// 120 s target). One 19-token probe replaced it with 145 tok/s, and
|
||||
/// the host advertised **17,408** — a sixth of what it can serve —
|
||||
/// until real traffic happened to warm it (#295).
|
||||
///
|
||||
/// 512 excludes the smoke probe and the short auxiliary calls agent
|
||||
/// harnesses make (observed at 19, 143 and 469 tokens) while admitting
|
||||
/// ordinary prompts. At ~1,400 tok/s a 512-token prefill runs ~370 ms,
|
||||
/// so fixed overhead is roughly a tenth of it — informative rather than
|
||||
/// dominant.
|
||||
const MIN_PREFILL_SAMPLE_TOKENS: usize = 512;
|
||||
|
||||
/// Fold one throughput sample (`tokens` in `elapsed`) into the EMA held in
|
||||
/// `bits`. No-op for degenerate inputs so a probe request or a clock blip
|
||||
/// can't poison the average.
|
||||
@@ -121,15 +99,7 @@ impl ThroughputEma {
|
||||
|
||||
/// Fold one prefill measurement (`prompt_tokens` processed in
|
||||
/// `elapsed`) into the prefill EMA.
|
||||
///
|
||||
/// Samples below [`MIN_PREFILL_SAMPLE_TOKENS`] are ignored: they
|
||||
/// measure fixed per-request cost rather than throughput, and the
|
||||
/// value they displace — the bootstrap estimate — is better than
|
||||
/// they are.
|
||||
pub fn record(&self, prompt_tokens: usize, elapsed: Duration) {
|
||||
if prompt_tokens < MIN_PREFILL_SAMPLE_TOKENS {
|
||||
return;
|
||||
}
|
||||
fold_rate(&self.prefill_bits, prompt_tokens, elapsed);
|
||||
}
|
||||
|
||||
@@ -264,23 +234,10 @@ fn round_down(tokens: usize, granularity: usize) -> usize {
|
||||
|
||||
const CONTEXT_GRANULARITY: usize = 1024;
|
||||
|
||||
/// Default ceiling on what a request may name as its output budget.
|
||||
///
|
||||
/// Not derived from anything — a deliberate figure, and configurable
|
||||
/// per host (`[context_limit] max_output_tokens`). The evidence behind
|
||||
/// it: a reasoning model asked to build a small application front-loads
|
||||
/// one long think block before it acts, measured at 27,504 tokens for a
|
||||
/// frontier model on a task Qwen3.8-27B was cut off attempting at
|
||||
/// 24,433 (#271, #278). A ceiling below that turns a capable model into
|
||||
/// one that never reaches its first tool call, so the default sits
|
||||
/// above the observed cost of that class of turn.
|
||||
const DEFAULT_OUTPUT_CEILING: usize = 32_768;
|
||||
|
||||
/// Derive `limit{context,input,output}` for a loaded model.
|
||||
///
|
||||
/// ```text
|
||||
/// output = output_reserve_tokens (default + KV planning)
|
||||
/// output_ceiling = min(max_output_tokens, max_position_embeddings)
|
||||
/// output = output_reserve_tokens
|
||||
/// vram_ceiling = (free_tightest − activation_headroom − min_free_floor) / kv_bytes_per_token_per_card
|
||||
/// throughput_ceiling = target_prefill_latency_secs × prefill_tok_per_sec
|
||||
/// context = min(max_position_embeddings, vram_ceiling, throughput_ceiling) [clamped by `hard_ceiling` if set]
|
||||
@@ -361,163 +318,17 @@ pub fn derive_limit(
|
||||
);
|
||||
|
||||
let input = context.saturating_sub(output);
|
||||
// The ceiling a request may name, distinct from the reserve above
|
||||
// (#278). Bounded by the model's own position limit rather than by
|
||||
// the live context, because the advertisement is read once and
|
||||
// cached by clients: a ceiling that shrank with fleet VRAM would be
|
||||
// stale in whichever direction hurt — either rejecting what we said
|
||||
// we would serve, or leaving budget unclaimed. A request that will
|
||||
// not actually fit is refused at request time, with the numbers,
|
||||
// instead of being under-promised here.
|
||||
let output_ceiling = round_down(
|
||||
cfg.max_output_tokens
|
||||
.unwrap_or(DEFAULT_OUTPUT_CEILING)
|
||||
.min(profile.max_position_embeddings),
|
||||
CONTEXT_GRANULARITY,
|
||||
)
|
||||
.max(output);
|
||||
ModelLimit {
|
||||
context,
|
||||
input: Some(input),
|
||||
output,
|
||||
output_ceiling,
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
|
||||
/// The deploy's smoke probe must not set the advertised context.
|
||||
///
|
||||
/// 19 tokens in 130 ms reads as ~145 tok/s on a host that measures
|
||||
/// ~1,400. Before this guard that one sample displaced the
|
||||
/// bootstrap estimate and the host advertised 17,408 instead of
|
||||
/// ~96,000 — until real traffic happened along (#295).
|
||||
#[test]
|
||||
fn a_smoke_probe_does_not_poison_the_prefill_rate() {
|
||||
let ema = ThroughputEma::new();
|
||||
ema.record(19, Duration::from_millis(130));
|
||||
assert_eq!(
|
||||
ema.get(),
|
||||
None,
|
||||
"a 19-token prefill must leave the EMA unset so the bootstrap value stands"
|
||||
);
|
||||
}
|
||||
|
||||
/// The short auxiliary calls agent harnesses make are the same
|
||||
/// shape as the probe and equally uninformative — observed at 143
|
||||
/// and 469 tokens against prompts three orders of magnitude larger.
|
||||
#[test]
|
||||
fn short_auxiliary_prompts_are_ignored_too() {
|
||||
let ema = ThroughputEma::new();
|
||||
for tokens in [143usize, 469] {
|
||||
ema.record(tokens, Duration::from_millis(200));
|
||||
}
|
||||
assert_eq!(ema.get(), None);
|
||||
}
|
||||
|
||||
/// A real prompt still records, and still tracks a shift.
|
||||
#[test]
|
||||
fn representative_prefills_still_measure() {
|
||||
let ema = ThroughputEma::new();
|
||||
ema.record(1400, Duration::from_secs(1));
|
||||
let first = ema.get().expect("a 1400-token sample must record");
|
||||
assert!((first - 1400.0).abs() < 1.0, "got {first}");
|
||||
|
||||
// A slower host is tracked, not ignored.
|
||||
for _ in 0..20 {
|
||||
ema.record(700, Duration::from_secs(1));
|
||||
}
|
||||
let after = ema.get().unwrap();
|
||||
assert!(after < first && after > 600.0, "got {after}");
|
||||
}
|
||||
|
||||
/// Exactly at the threshold counts — the boundary is inclusive so
|
||||
/// the constant means what it says.
|
||||
#[test]
|
||||
fn the_threshold_itself_is_a_valid_sample() {
|
||||
let ema = ThroughputEma::new();
|
||||
ema.record(MIN_PREFILL_SAMPLE_TOKENS, Duration::from_secs(1));
|
||||
assert!(ema.get().is_some());
|
||||
}
|
||||
use super::*;
|
||||
|
||||
/// The ceiling a client is told to plan against must not be the
|
||||
/// reserve. Advertising the reserve is what told a reasoning model's
|
||||
/// harness to cap itself below the cost of one think block (#278).
|
||||
#[test]
|
||||
fn the_advertised_ceiling_is_not_the_reserve() {
|
||||
let cfg = ContextLimitConfig::default();
|
||||
let profile = ContextProfile {
|
||||
max_position_embeddings: 131_072,
|
||||
kv_bytes_per_token_per_card: 65_536,
|
||||
world_size: 2,
|
||||
};
|
||||
let limit = derive_limit(&profile, 0, 0.0, None, &cfg);
|
||||
assert_eq!(limit.output, cfg.output_reserve_tokens, "reserve unchanged");
|
||||
assert_eq!(limit.output_ceiling, DEFAULT_OUTPUT_CEILING);
|
||||
assert!(limit.output_ceiling > limit.output);
|
||||
}
|
||||
|
||||
/// A model whose own position limit is below the default ceiling
|
||||
/// cannot generate past it, so the advertisement must not claim it.
|
||||
#[test]
|
||||
fn the_ceiling_never_exceeds_the_models_own_position_limit() {
|
||||
let cfg = ContextLimitConfig::default();
|
||||
let profile = ContextProfile {
|
||||
max_position_embeddings: 16_384,
|
||||
kv_bytes_per_token_per_card: 65_536,
|
||||
world_size: 1,
|
||||
};
|
||||
let limit = derive_limit(&profile, 0, 0.0, None, &cfg);
|
||||
assert_eq!(limit.output_ceiling, 16_384);
|
||||
}
|
||||
|
||||
/// The operator's number wins, which is what makes the default a
|
||||
/// starting point rather than a guess baked into the binary.
|
||||
#[test]
|
||||
fn a_configured_ceiling_overrides_the_default() {
|
||||
let cfg = ContextLimitConfig {
|
||||
max_output_tokens: Some(65_536),
|
||||
..ContextLimitConfig::default()
|
||||
};
|
||||
let profile = ContextProfile {
|
||||
max_position_embeddings: 131_072,
|
||||
kv_bytes_per_token_per_card: 65_536,
|
||||
world_size: 2,
|
||||
};
|
||||
assert_eq!(
|
||||
derive_limit(&profile, 0, 0.0, None, &cfg).output_ceiling,
|
||||
65_536
|
||||
);
|
||||
}
|
||||
|
||||
/// The ceiling is deliberately *not* a function of live VRAM: it is
|
||||
/// read once and cached by clients, so it has to mean the same thing
|
||||
/// tomorrow. The live context still moves — that is what a request
|
||||
/// is judged against — but the contract does not.
|
||||
#[test]
|
||||
fn the_ceiling_holds_still_while_the_context_moves() {
|
||||
let cfg = ContextLimitConfig::default();
|
||||
let profile = ContextProfile {
|
||||
max_position_embeddings: 131_072,
|
||||
kv_bytes_per_token_per_card: 65_536,
|
||||
world_size: 2,
|
||||
};
|
||||
let roomy = derive_limit(&profile, 60_000, 5_000.0, None, &cfg);
|
||||
// Tight enough that the VRAM term binds — the same shape as the
|
||||
// fleet advertising 109568 one hour and 131072 the next.
|
||||
let tight = derive_limit(&profile, 6_000, 5_000.0, None, &cfg);
|
||||
assert!(
|
||||
tight.context < roomy.context,
|
||||
"the live window should shrink under VRAM pressure"
|
||||
);
|
||||
assert_eq!(
|
||||
tight.output_ceiling, roomy.output_ceiling,
|
||||
"the advertised ceiling must not move with fleet load"
|
||||
);
|
||||
}
|
||||
|
||||
/// beast Qwen3.6-27B: 16 full-attn layers, 4 kv heads, head_dim 256,
|
||||
/// f16 (2 B), TP=2 → 64 KiB/token total, 32 KiB/token/card.
|
||||
fn beast_profile() -> ContextProfile {
|
||||
|
||||
@@ -297,23 +297,14 @@ async fn op_drop_snap(cfg: &EngineConfig, session: &mut ActiveSession, id: u64)
|
||||
|
||||
/// Prefill one joining request at B=1 through the backend's existing
|
||||
/// chunked-prefill + prefix-cache paths. Returns the prefill logits.
|
||||
/// Prefill, returning the logits **and** how many leading tokens the
|
||||
/// prefix cache let us skip (#269).
|
||||
///
|
||||
/// The reuse count is computed here and was previously only logged, so
|
||||
/// no caller could report it — every client saw a 0% cache hit rate on
|
||||
/// a cache that was working. Returning it is what lets `usage` carry
|
||||
/// `cached_tokens`.
|
||||
async fn op_prefill(
|
||||
cfg: &EngineConfig,
|
||||
session: &mut ActiveSession,
|
||||
prompt_tokens: &[u32],
|
||||
) -> Result<(Vec<f32>, usize)> {
|
||||
) -> Result<Vec<f32>> {
|
||||
let prompt_len = prompt_tokens.len();
|
||||
let prefill_start = std::time::Instant::now();
|
||||
// Each arm yields its logits plus how many leading tokens the
|
||||
// prefix cache served, so neither can be forgotten.
|
||||
let (logits, cached_tokens) = match (&cfg.backend, session) {
|
||||
let logits = match (&cfg.backend, session) {
|
||||
(
|
||||
BackendConfig::Single {
|
||||
worker,
|
||||
@@ -349,7 +340,7 @@ async fn op_prefill(
|
||||
None => chunked_prefill_via_worker(worker, *handle, prompt_tokens, reused).await?,
|
||||
};
|
||||
prefill_rate.record(prompt_len, prefill_start.elapsed());
|
||||
(logits, reused)
|
||||
logits
|
||||
}
|
||||
#[cfg(feature = "cuda")]
|
||||
(BackendConfig::Tp { .. }, ActiveSession::Tp { tp, pool }) => {
|
||||
@@ -393,12 +384,12 @@ async fn op_prefill(
|
||||
}
|
||||
};
|
||||
tp.prefill_rate.record(prompt_len, prefill_start.elapsed());
|
||||
(logits, reused)
|
||||
logits
|
||||
}
|
||||
#[cfg(feature = "cuda")]
|
||||
_ => anyhow::bail!("engine backend/session mismatch"),
|
||||
};
|
||||
Ok((logits, cached_tokens))
|
||||
Ok(logits)
|
||||
}
|
||||
|
||||
/// One queued request. Admission has already been passed — the permit
|
||||
@@ -406,14 +397,9 @@ async fn op_prefill(
|
||||
pub struct EngineRequest {
|
||||
pub prompt_tokens: Vec<u32>,
|
||||
pub max_new: usize,
|
||||
/// Sampling resolved once from request → model `generation_config`
|
||||
/// → fallback (#272), rather than loose scalars each caller could
|
||||
/// default differently.
|
||||
pub sampling: crate::harness::sampling::SamplingParams,
|
||||
/// Reasoning-token budget for this request (#223). `None` is
|
||||
/// unbounded — the default, and the behaviour before it existed.
|
||||
/// Per-request because slots in one batch can differ.
|
||||
pub reasoning_budget: Option<usize>,
|
||||
pub temperature: f64,
|
||||
pub top_p: Option<f64>,
|
||||
pub seed: u64,
|
||||
pub eos_id: Option<u32>,
|
||||
pub tool_schemas: ToolSchemas,
|
||||
pub tx: mpsc::Sender<InferenceEvent>,
|
||||
@@ -453,8 +439,6 @@ enum RouterMsg {
|
||||
reason: FinishReason,
|
||||
prompt_tokens: u32,
|
||||
completion_tokens: u32,
|
||||
/// Leading prompt tokens the prefix cache let us skip (#269).
|
||||
cached_tokens: u32,
|
||||
timing: FinishTiming,
|
||||
},
|
||||
}
|
||||
@@ -471,12 +455,6 @@ struct Slot {
|
||||
max_new: usize,
|
||||
eos_id: Option<u32>,
|
||||
lp: LogitsProcessor,
|
||||
/// The slot's resolved sampling (#272). Held per-slot because the
|
||||
/// repetition penalty and its window are per-request knobs, and
|
||||
/// slots in one batch can carry different ones.
|
||||
sampling: crate::harness::sampling::SamplingParams,
|
||||
/// Bounds this slot's think block (#223); `None` = unbounded.
|
||||
governor: Option<crate::harness::reasoning_budget::ReasoningGovernor>,
|
||||
router: mpsc::Sender<RouterMsg>,
|
||||
/// Set by the router when the consumer hangs up; the engine stops
|
||||
/// feeding the slot and compacts it out.
|
||||
@@ -484,9 +462,6 @@ struct Slot {
|
||||
finished: Option<FinishReason>,
|
||||
prefill_ms: u32,
|
||||
prefill_tokens: u32,
|
||||
/// Prompt tokens served from the prefix cache (#269), reported to
|
||||
/// the caller as `cached_tokens` so a working cache is visible.
|
||||
cached_tokens: u32,
|
||||
decode_start: std::time::Instant,
|
||||
_admit: AdmissionPermit,
|
||||
}
|
||||
@@ -584,13 +559,7 @@ async fn run_engine(cfg: EngineConfig, mut rx: mpsc::Receiver<EngineRequest>) {
|
||||
break;
|
||||
}
|
||||
};
|
||||
let nt = match sample_with_penalty(
|
||||
&logits,
|
||||
&slot.generated,
|
||||
&mut slot.lp,
|
||||
&slot.sampling,
|
||||
slot.governor.as_mut(),
|
||||
) {
|
||||
let nt = match sample_with_penalty(&logits, &slot.generated, &mut slot.lp) {
|
||||
Ok(t) => t,
|
||||
Err(e) => {
|
||||
let health = logits_health_slice(&logits_vec);
|
||||
@@ -658,7 +627,6 @@ async fn finish_slot(slot: &mut Slot, reason: FinishReason, rate: &PrefillRateEm
|
||||
reason,
|
||||
prompt_tokens: slot.prompt_len as u32,
|
||||
completion_tokens: slot.generated.len() as u32,
|
||||
cached_tokens: slot.cached_tokens,
|
||||
timing: FinishTiming {
|
||||
prefill_ms: slot.prefill_ms,
|
||||
decode_ms: slot.decode_start.elapsed().as_millis() as u32,
|
||||
@@ -791,11 +759,14 @@ async fn prefill_join(
|
||||
session: &mut ActiveSession,
|
||||
req: EngineRequest,
|
||||
) -> Result<Option<(Slot, u64)>> {
|
||||
use candle_transformers::generation::Sampling;
|
||||
|
||||
let EngineRequest {
|
||||
prompt_tokens,
|
||||
max_new,
|
||||
sampling,
|
||||
reasoning_budget,
|
||||
temperature,
|
||||
top_p,
|
||||
seed,
|
||||
eos_id,
|
||||
tool_schemas,
|
||||
tx,
|
||||
@@ -803,37 +774,37 @@ async fn prefill_join(
|
||||
span,
|
||||
} = req;
|
||||
|
||||
let mut lp = LogitsProcessor::from_sampling(sampling.seed, sampling.to_sampling());
|
||||
// Built before prefill's first sample so a prompt that opens the
|
||||
// think block is governed from its very first token (#223).
|
||||
let mut governor = crate::harness::reasoning_budget::ReasoningGovernor::new(
|
||||
reasoning_budget,
|
||||
cfg.reasoning_tokens
|
||||
.as_ref()
|
||||
.map(|p| (p.open_id, p.close_id)),
|
||||
prompt_opens_reasoning(&prompt_tokens, cfg.reasoning_tokens.as_ref()),
|
||||
);
|
||||
let mut lp = {
|
||||
let sampling = if temperature <= 0.0 {
|
||||
Sampling::ArgMax
|
||||
} else {
|
||||
match top_p {
|
||||
Some(p) => Sampling::TopP { p, temperature },
|
||||
None => Sampling::All { temperature },
|
||||
}
|
||||
};
|
||||
LogitsProcessor::from_sampling(seed, sampling)
|
||||
};
|
||||
|
||||
let prompt_len = prompt_tokens.len();
|
||||
let prefill_start = std::time::Instant::now();
|
||||
let (logits_vec, cached_tokens) = op_prefill(cfg, session, &prompt_tokens).await?;
|
||||
let logits_vec = op_prefill(cfg, session, &prompt_tokens).await?;
|
||||
let prefill_elapsed = prefill_start.elapsed();
|
||||
|
||||
// First token from the prefill logits.
|
||||
let generated: Vec<u32> = Vec::new();
|
||||
let logits = Tensor::new(logits_vec.as_slice(), &Device::Cpu)?;
|
||||
let first =
|
||||
match sample_with_penalty(&logits, &generated, &mut lp, &sampling, governor.as_mut()) {
|
||||
Ok(t) => t,
|
||||
Err(e) => {
|
||||
let health = logits_health_slice(&logits_vec);
|
||||
tracing::warn!(
|
||||
?health,
|
||||
"batch engine: prefill sample failed; logits unhealthy"
|
||||
);
|
||||
return Err(e);
|
||||
}
|
||||
};
|
||||
let first = match sample_with_penalty(&logits, &generated, &mut lp) {
|
||||
Ok(t) => t,
|
||||
Err(e) => {
|
||||
let health = logits_health_slice(&logits_vec);
|
||||
tracing::warn!(
|
||||
?health,
|
||||
"batch engine: prefill sample failed; logits unhealthy"
|
||||
);
|
||||
return Err(e);
|
||||
}
|
||||
};
|
||||
|
||||
// Router task for this slot.
|
||||
let hangup = Arc::new(AtomicBool::new(false));
|
||||
@@ -856,14 +827,11 @@ async fn prefill_join(
|
||||
let mut slot = Slot {
|
||||
prefix_len: prompt_len,
|
||||
prompt_len,
|
||||
cached_tokens: cached_tokens as u32,
|
||||
generated,
|
||||
next_token: first,
|
||||
max_new,
|
||||
eos_id,
|
||||
lp,
|
||||
sampling,
|
||||
governor,
|
||||
router: router_tx,
|
||||
hangup,
|
||||
finished: None,
|
||||
@@ -922,9 +890,6 @@ async fn run_router(
|
||||
let mut tool_call_idx: usize = 0;
|
||||
let mut emitted_tool_call = false;
|
||||
let mut consumer_alive = true;
|
||||
// Whether a Finish was seen, so the fall-through below can tell a
|
||||
// clean end from a dropped slot.
|
||||
let mut finished = false;
|
||||
|
||||
while let Some(msg) = rx.recv().await {
|
||||
match msg {
|
||||
@@ -1013,43 +978,17 @@ async fn run_router(
|
||||
mut reason,
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
cached_tokens,
|
||||
timing,
|
||||
} => {
|
||||
if emitted_tool_call && reason == FinishReason::Stop {
|
||||
reason = FinishReason::ToolCalls;
|
||||
}
|
||||
// Close the journal trail for this turn (#268). The
|
||||
// non-streaming path has always logged this; streamed
|
||||
// turns logged nothing at all, so whether one finished,
|
||||
// hit its output cap, or was abandoned mid-flight was
|
||||
// unanswerable afterwards — and an absence of lines was
|
||||
// repeatedly misread as an absence of work.
|
||||
//
|
||||
// `run_router` is instrumented with the request's span,
|
||||
// so req_id and model come along without being passed.
|
||||
tracing::info!(
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens = reasoning_token_count,
|
||||
cached_tokens,
|
||||
finish_reason = ?reason,
|
||||
prefill_ms = timing.prefill_ms,
|
||||
decode_ms = timing.decode_ms,
|
||||
// The turn ran to completion with nobody reading it:
|
||||
// it held its admission permit and the pool lock the
|
||||
// whole time. Invisible until now.
|
||||
client_gone = !consumer_alive,
|
||||
"chat_completion (stream): done"
|
||||
);
|
||||
finished = true;
|
||||
let _ = tx
|
||||
.send(InferenceEvent::Finish {
|
||||
reason,
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens: reasoning_token_count,
|
||||
cached_tokens,
|
||||
timing: Some(timing),
|
||||
})
|
||||
.await;
|
||||
@@ -1057,17 +996,6 @@ async fn run_router(
|
||||
}
|
||||
}
|
||||
}
|
||||
// Fell out of the loop without a Finish: the engine dropped this
|
||||
// slot's channel (fatal worker error, shutdown). The client's stream
|
||||
// ends either way, but silently — so say so rather than leaving the
|
||||
// turn's last trace to be a prefill line (#268).
|
||||
if !finished {
|
||||
tracing::warn!(
|
||||
reasoning_tokens = reasoning_token_count,
|
||||
client_gone = !consumer_alive,
|
||||
"chat_completion (stream): ended without a finish event — engine dropped the slot"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// `tracing::Instrument` without importing the trait at every use
|
||||
@@ -1085,92 +1013,6 @@ mod tests {
|
||||
use crate::config::AdmissionConfig;
|
||||
use crate::harness::admission::AdmissionController;
|
||||
|
||||
/// A streamed turn must close its own journal trail (#268).
|
||||
///
|
||||
/// Streaming used to end silently: no token counts, no
|
||||
/// `finish_reason`, no duration. That made a finished turn, a turn
|
||||
/// that hit its output cap, and a turn abandoned by a disconnected
|
||||
/// client indistinguishable after the fact — and during the #267
|
||||
/// investigation an absence of log lines was twice mistaken for an
|
||||
/// absence of work on a daemon that was healthy and decoding.
|
||||
///
|
||||
/// Asserts the emitted line rather than the struct, because a
|
||||
/// `Finish` event that reaches the client but leaves no server-side
|
||||
/// record is exactly the state this fixes.
|
||||
#[tokio::test]
|
||||
async fn a_streamed_turn_logs_how_it_ended() {
|
||||
use std::sync::{Arc, Mutex};
|
||||
use tracing_subscriber::prelude::*;
|
||||
|
||||
#[derive(Clone, Default)]
|
||||
struct Capture(Arc<Mutex<Vec<u8>>>);
|
||||
impl std::io::Write for Capture {
|
||||
fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
|
||||
self.0
|
||||
.lock()
|
||||
.expect("capture poisoned")
|
||||
.extend_from_slice(buf);
|
||||
Ok(buf.len())
|
||||
}
|
||||
fn flush(&mut self) -> std::io::Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
impl<'a> tracing_subscriber::fmt::MakeWriter<'a> for Capture {
|
||||
type Writer = Self;
|
||||
fn make_writer(&'a self) -> Self::Writer {
|
||||
self.clone()
|
||||
}
|
||||
}
|
||||
|
||||
let capture = Capture::default();
|
||||
let subscriber = tracing_subscriber::registry()
|
||||
.with(tracing_subscriber::fmt::layer().with_writer(capture.clone()));
|
||||
let _guard = tracing::subscriber::set_default(subscriber);
|
||||
|
||||
let (router_tx, router_rx) = mpsc::channel::<RouterMsg>(8);
|
||||
let (tx, mut rx) = mpsc::channel::<InferenceEvent>(8);
|
||||
let handle = tokio::spawn(run_router(
|
||||
tiny_tokenizer(8),
|
||||
None,
|
||||
None,
|
||||
ToolSchemas::default(),
|
||||
false,
|
||||
tx,
|
||||
Arc::new(AtomicBool::new(false)),
|
||||
router_rx,
|
||||
));
|
||||
|
||||
router_tx
|
||||
.send(RouterMsg::Finish {
|
||||
reason: FinishReason::Length,
|
||||
prompt_tokens: 7413,
|
||||
completion_tokens: 24576,
|
||||
cached_tokens: 2068,
|
||||
timing: FinishTiming {
|
||||
prefill_ms: 6000,
|
||||
decode_ms: 900_000,
|
||||
prefill_tokens: 7413,
|
||||
},
|
||||
})
|
||||
.await
|
||||
.expect("router accepts finish");
|
||||
drop(router_tx);
|
||||
handle.await.expect("router task joins");
|
||||
while rx.recv().await.is_some() {}
|
||||
|
||||
let logged = String::from_utf8(capture.0.lock().expect("capture poisoned").clone())
|
||||
.expect("utf8 log output");
|
||||
assert!(
|
||||
logged.contains("chat_completion (stream): done"),
|
||||
"streamed turn left no completion line:\n{logged}"
|
||||
);
|
||||
// The counts are the point — "it ended" without them cannot
|
||||
// distinguish a complete answer from an exhausted budget.
|
||||
assert!(logged.contains("24576"), "no completion_tokens:\n{logged}");
|
||||
assert!(logged.contains("Length"), "no finish_reason:\n{logged}");
|
||||
}
|
||||
|
||||
/// A WordLevel tokenizer whose vocab covers the whole fixture
|
||||
/// vocab (`w0`..`w511`), so every decoded token maps to a unique
|
||||
/// word and the emitted text uniquely encodes the token sequence.
|
||||
@@ -1204,20 +1046,9 @@ mod tests {
|
||||
.submit(EngineRequest {
|
||||
prompt_tokens: prompt,
|
||||
max_new,
|
||||
// Greedy, deterministic: the fixture asserts exact
|
||||
// token sequences.
|
||||
sampling: crate::harness::sampling::SamplingParams::resolve(
|
||||
&crate::harness::sampling::RequestedSampling {
|
||||
temperature: Some(0.0),
|
||||
seed: Some(0),
|
||||
..Default::default()
|
||||
},
|
||||
&crate::harness::sampling::ModelGenerationDefaults::default(),
|
||||
0,
|
||||
),
|
||||
// Unbounded: this fixture asserts exact token sequences,
|
||||
// so nothing may substitute a close marker (#223).
|
||||
reasoning_budget: None,
|
||||
temperature: 0.0, // greedy — deterministic
|
||||
top_p: None,
|
||||
seed: 0,
|
||||
eos_id: None,
|
||||
tool_schemas: ToolSchemas::new(),
|
||||
tx,
|
||||
|
||||
@@ -12,9 +12,6 @@ pub mod image;
|
||||
pub mod prefix_cache;
|
||||
pub mod preflight;
|
||||
pub mod preprocess;
|
||||
pub mod reasoning_budget;
|
||||
pub mod reasoning_effort;
|
||||
pub mod sampling;
|
||||
pub mod speculative;
|
||||
pub mod tp;
|
||||
|
||||
|
||||
@@ -401,8 +401,6 @@ mod tests {
|
||||
quant: quant.map(String::from),
|
||||
tensor_parallel: tp,
|
||||
devices: None,
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,305 +0,0 @@
|
||||
//! Bounding how long a model may think before it must answer (#223).
|
||||
//!
|
||||
//! A reasoning model with no stopping criterion will fill whatever
|
||||
//! output budget it is given. Measured on Qwen3.8-27B: given 16,384
|
||||
//! tokens it used 16,384; given 32,768 it used 32,768; both times it was
|
||||
//! still opening new topics when the cap bit, and both times the caller
|
||||
//! received no answer at all.
|
||||
//!
|
||||
//! The fix is not to stop the model thinking — the run that did produce
|
||||
//! files designed for 27,157 tokens first, and that design was good. It
|
||||
//! is to bound the thinking so the rest of the output budget survives
|
||||
//! for the answer.
|
||||
//!
|
||||
//! Two halves live here:
|
||||
//!
|
||||
//! - [`ReasoningBudget`] — how many reasoning tokens this request may
|
||||
//! spend, resolved from whichever control the caller's wire format
|
||||
//! gave them.
|
||||
//! - [`ReasoningGovernor`] — the per-request state that enforces it, by
|
||||
//! substituting the model's own `</think>` token when the budget runs
|
||||
//! out so generation transitions to answering instead of being cut off.
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
/// Per-model mapping from an OpenAI effort level to a token budget.
|
||||
///
|
||||
/// OpenAI-shaped clients cannot send a token count — pi-ai's vocabulary
|
||||
/// is the ladder `off | minimal | low | medium | high | xhigh | max` and
|
||||
/// nothing else — so the numbers have to live on the server. Operator
|
||||
/// configurable, because the right values depend on the model and the
|
||||
/// hardware; a derived default would be a guess baked into the binary.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ReasoningBudgetLadder {
|
||||
pub minimal: usize,
|
||||
pub low: usize,
|
||||
pub medium: usize,
|
||||
pub high: usize,
|
||||
/// `xhigh` and `max` are only offered by a client when the model
|
||||
/// declares them; absent here means "not offered", and a request
|
||||
/// naming one falls back to `high` rather than being rejected.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub xhigh: Option<usize>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub max: Option<usize>,
|
||||
/// Tokens of the caller's **own** output budget held back for the
|
||||
/// answer, when the caller names no explicit `reasoning.max_tokens`.
|
||||
///
|
||||
/// This is what an OpenAI-shaped client gets instead of the rungs
|
||||
/// above, and it is deliberately not derived from effort. Effort is
|
||||
/// a prompt instruction the model is trained to follow (#290);
|
||||
/// making it *also* set a guillotine is what told Qwen3.8-27B to
|
||||
/// reason at `xhigh` and then cut it off at `medium`'s 12,288.
|
||||
///
|
||||
/// A reserve has no such double meaning. The model thinks as long
|
||||
/// as it likes within the budget the caller declared, minus enough
|
||||
/// to answer — so the caller always gets an answer, and the size of
|
||||
/// the think block stays the model's decision rather than ours.
|
||||
///
|
||||
/// Set to `0` to disable, restoring fully unbounded reasoning.
|
||||
#[serde(default = "default_answer_reserve")]
|
||||
pub answer_reserve_tokens: usize,
|
||||
}
|
||||
|
||||
/// Enough for a substantive answer with tool calls, not so much that it
|
||||
/// meaningfully shortens a think block: at the 32,768 budget pi sends,
|
||||
/// this leaves ~28.7 k for reasoning — above the ~27.2 k a full agentic
|
||||
/// design turn was measured to use.
|
||||
fn default_answer_reserve() -> usize {
|
||||
4_096
|
||||
}
|
||||
|
||||
impl Default for ReasoningBudgetLadder {
|
||||
/// Rungs sized against observed behaviour rather than round numbers:
|
||||
/// a long agentic design turn on this class of model runs to ~27k
|
||||
/// tokens, so `high` sits above that (bounded but rarely binding),
|
||||
/// `medium` at roughly half (enough to plan a whole implementation),
|
||||
/// and `low` at the scale of a focused single-file change.
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
minimal: 1_024,
|
||||
low: 4_096,
|
||||
medium: 12_288,
|
||||
high: 32_768,
|
||||
xhigh: None,
|
||||
max: None,
|
||||
answer_reserve_tokens: default_answer_reserve(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl ReasoningBudgetLadder {
|
||||
/// Resolve an effort level to a token budget.
|
||||
///
|
||||
/// `none`/`off` are handled before this — they disable thinking
|
||||
/// outright via the chat template — so they have no budget here.
|
||||
/// An unrecognised level resolves to `None` (unbounded) rather than
|
||||
/// to a guess: silently substituting a budget nobody asked for is
|
||||
/// the failure mode this whole area has been full of.
|
||||
pub fn for_effort(&self, effort: &str) -> Option<usize> {
|
||||
match effort.trim().to_ascii_lowercase().as_str() {
|
||||
"minimal" => Some(self.minimal),
|
||||
"low" => Some(self.low),
|
||||
"medium" => Some(self.medium),
|
||||
"high" => Some(self.high),
|
||||
"xhigh" => Some(self.xhigh.unwrap_or(self.high)),
|
||||
"max" => Some(self.max.or(self.xhigh).unwrap_or(self.high)),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
/// The mapping as a client should see it on `/v1/models` — the rungs
|
||||
/// this deployment actually offers, so a caller picking `low` knows
|
||||
/// what it bought instead of guessing (#274).
|
||||
pub fn advertised(&self) -> Vec<(String, usize)> {
|
||||
let mut out = vec![
|
||||
("minimal".to_string(), self.minimal),
|
||||
("low".to_string(), self.low),
|
||||
("medium".to_string(), self.medium),
|
||||
("high".to_string(), self.high),
|
||||
];
|
||||
if let Some(v) = self.xhigh {
|
||||
out.push(("xhigh".to_string(), v));
|
||||
}
|
||||
if let Some(v) = self.max {
|
||||
out.push(("max".to_string(), v));
|
||||
}
|
||||
out
|
||||
}
|
||||
}
|
||||
|
||||
/// Enforces a resolved budget over one request's token stream.
|
||||
///
|
||||
/// Fed every sampled token; returns the token that should actually be
|
||||
/// emitted. While the model is inside a think block and over budget, it
|
||||
/// returns the close marker instead, exactly once — after which the
|
||||
/// model is answering and the governor is inert.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ReasoningGovernor {
|
||||
limit: usize,
|
||||
open_id: u32,
|
||||
close_id: u32,
|
||||
inside: bool,
|
||||
used: usize,
|
||||
forced: bool,
|
||||
}
|
||||
|
||||
impl ReasoningGovernor {
|
||||
/// `None` when the request named no budget, or the model has no
|
||||
/// reasoning markers to enforce one with — in both cases generation
|
||||
/// proceeds exactly as it did before this existed.
|
||||
pub fn new(
|
||||
limit: Option<usize>,
|
||||
markers: Option<(u32, u32)>,
|
||||
prompt_opened_reasoning: bool,
|
||||
) -> Option<Self> {
|
||||
let limit = limit?;
|
||||
let (open_id, close_id) = markers?;
|
||||
Some(Self {
|
||||
limit,
|
||||
open_id,
|
||||
close_id,
|
||||
inside: prompt_opened_reasoning,
|
||||
used: 0,
|
||||
forced: false,
|
||||
})
|
||||
}
|
||||
|
||||
/// Whether the forced close has already been spent.
|
||||
pub fn forced(&self) -> bool {
|
||||
self.forced
|
||||
}
|
||||
|
||||
/// Reasoning tokens counted so far.
|
||||
pub fn used(&self) -> usize {
|
||||
self.used
|
||||
}
|
||||
|
||||
/// Govern one sampled token, returning the token to emit.
|
||||
pub fn govern(&mut self, sampled: u32) -> u32 {
|
||||
if sampled == self.open_id {
|
||||
self.inside = true;
|
||||
return sampled;
|
||||
}
|
||||
if sampled == self.close_id {
|
||||
self.inside = false;
|
||||
return sampled;
|
||||
}
|
||||
if !self.inside {
|
||||
return sampled;
|
||||
}
|
||||
if self.used >= self.limit {
|
||||
// Budget spent: hand the model its own close marker so it
|
||||
// transitions to answering. Cutting the stream here instead
|
||||
// would reproduce the very failure this exists to prevent.
|
||||
self.inside = false;
|
||||
self.forced = true;
|
||||
return self.close_id;
|
||||
}
|
||||
self.used += 1;
|
||||
sampled
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
const OPEN: u32 = 100;
|
||||
const CLOSE: u32 = 101;
|
||||
|
||||
fn governor(limit: usize, opened: bool) -> ReasoningGovernor {
|
||||
ReasoningGovernor::new(Some(limit), Some((OPEN, CLOSE)), opened).expect("governor")
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_request_with_no_budget_is_ungoverned() {
|
||||
assert!(ReasoningGovernor::new(None, Some((OPEN, CLOSE)), true).is_none());
|
||||
}
|
||||
|
||||
/// A model with no detected markers cannot be governed — better
|
||||
/// unbounded than truncated at an arbitrary token.
|
||||
#[test]
|
||||
fn a_model_without_markers_is_ungoverned() {
|
||||
assert!(ReasoningGovernor::new(Some(10), None, true).is_none());
|
||||
}
|
||||
|
||||
/// The case that motivated this: the chat template left the think
|
||||
/// block open, so the model is reasoning from the first token.
|
||||
#[test]
|
||||
fn a_prompt_opened_block_is_bounded_and_force_closed() {
|
||||
let mut g = governor(3, true);
|
||||
assert_eq!(g.govern(7), 7);
|
||||
assert_eq!(g.govern(8), 8);
|
||||
assert_eq!(g.govern(9), 9);
|
||||
assert_eq!(g.govern(10), CLOSE, "the fourth token must close the block");
|
||||
assert!(g.forced());
|
||||
assert_eq!(g.used(), 3);
|
||||
// Answering now — the governor is inert.
|
||||
assert_eq!(g.govern(11), 11);
|
||||
assert_eq!(g.govern(12), 12);
|
||||
}
|
||||
|
||||
/// Content before the block opens is never counted against the
|
||||
/// reasoning budget.
|
||||
#[test]
|
||||
fn only_tokens_inside_the_block_are_counted() {
|
||||
let mut g = governor(2, false);
|
||||
assert_eq!(g.govern(5), 5);
|
||||
assert_eq!(g.govern(6), 6);
|
||||
assert_eq!(g.used(), 0);
|
||||
assert_eq!(g.govern(OPEN), OPEN);
|
||||
assert_eq!(g.govern(7), 7);
|
||||
assert_eq!(g.govern(8), 8);
|
||||
assert_eq!(g.govern(9), CLOSE);
|
||||
assert_eq!(g.used(), 2);
|
||||
}
|
||||
|
||||
/// A model that finishes thinking on its own is untouched — the
|
||||
/// budget is a ceiling, not a target.
|
||||
#[test]
|
||||
fn a_model_that_stops_on_its_own_is_not_forced() {
|
||||
let mut g = governor(100, true);
|
||||
for t in 20..30 {
|
||||
assert_eq!(g.govern(t), t);
|
||||
}
|
||||
assert_eq!(g.govern(CLOSE), CLOSE);
|
||||
assert!(!g.forced());
|
||||
for t in 40..50 {
|
||||
assert_eq!(g.govern(t), t);
|
||||
}
|
||||
assert!(!g.forced(), "content after the block must not be governed");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_ladder_resolves_the_levels_clients_can_send() {
|
||||
let l = ReasoningBudgetLadder::default();
|
||||
assert_eq!(l.for_effort("minimal"), Some(1_024));
|
||||
assert_eq!(l.for_effort("LOW"), Some(4_096));
|
||||
assert_eq!(l.for_effort(" medium "), Some(12_288));
|
||||
assert_eq!(l.for_effort("high"), Some(32_768));
|
||||
// Not offered by default → falls back to high rather than
|
||||
// rejecting a level the client was told it could send.
|
||||
assert_eq!(l.for_effort("xhigh"), Some(32_768));
|
||||
assert_eq!(l.for_effort("max"), Some(32_768));
|
||||
// Unknown → unbounded, never a substituted guess.
|
||||
assert_eq!(l.for_effort("enthusiastic"), None);
|
||||
assert_eq!(l.for_effort("none"), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_advertised_ladder_lists_only_what_is_offered() {
|
||||
let l = ReasoningBudgetLadder::default();
|
||||
let names: Vec<_> = l.advertised().into_iter().map(|(k, _)| k).collect();
|
||||
assert_eq!(names, ["minimal", "low", "medium", "high"]);
|
||||
let l2 = ReasoningBudgetLadder {
|
||||
xhigh: Some(49_152),
|
||||
..ReasoningBudgetLadder::default()
|
||||
};
|
||||
assert!(
|
||||
l2.advertised()
|
||||
.iter()
|
||||
.any(|(k, v)| k == "xhigh" && *v == 49_152)
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -1,302 +0,0 @@
|
||||
//! Which reasoning-effort rungs a model actually supports, discovered
|
||||
//! from the model itself (#290).
|
||||
//!
|
||||
//! ## Why this is discovered rather than configured
|
||||
//!
|
||||
//! `Qwen/Qwen3.8-27B` accepts exactly three efforts and hard-fails on
|
||||
//! anything else:
|
||||
//!
|
||||
//! ```jinja
|
||||
//! {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
|
||||
//! {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
|
||||
//! {{- raise_exception('Unexpected reasoning effort ...') }}
|
||||
//! ```
|
||||
//!
|
||||
//! We previously advertised an invented ladder — `minimal`, `low`,
|
||||
//! `medium`, `high` — of which two values the template rejects outright
|
||||
//! and which omits `xhigh`, the model's own default and strongest rung.
|
||||
//!
|
||||
//! A caution about *why* that mattered, because the obvious story is
|
||||
//! wrong. It is tempting to say clients read our advertisement and were
|
||||
//! misled by it. pi-ai does not: its `getSupportedThinkingLevels` reads
|
||||
//! `model.thinkingLevelMap`, a static field in the operator's
|
||||
//! `models.json`, and treats `xhigh`/`max` as unavailable unless that
|
||||
//! map names them explicitly. So a pi user saw exactly
|
||||
//! `minimal, low, medium, high` — the invented ladder, to the value —
|
||||
//! for a reason that had nothing to do with what we published.
|
||||
//!
|
||||
//! The coincidence is the trap: our wrong advertisement and pi's
|
||||
//! default produced the same symptom, which made the advertisement look
|
||||
//! causal. Publishing rungs the model actually accepts is still correct
|
||||
//! — it is the truth, other clients may read it, and it is what makes
|
||||
//! `apply_effort_kwarg` right — but do not assume a given client
|
||||
//! consumes it. For pi the operator must also set `thinkingLevelMap`,
|
||||
//! by hand, and nothing validates that they match.
|
||||
//!
|
||||
//! A hardcoded per-model table would drift the moment a model ships a
|
||||
//! new template, which is exactly the class of defect #280 fixed by
|
||||
//! fetching the template instead of assuming it. So the rungs come from
|
||||
//! the artifact.
|
||||
//!
|
||||
//! ## How the probe works
|
||||
//!
|
||||
//! `raise_exception` is already wired to a render error, so the template
|
||||
//! answers the question directly: render it once per candidate effort
|
||||
//! and see which ones survive.
|
||||
//!
|
||||
//! Two ambiguities the probe has to resolve, or it would report
|
||||
//! confident nonsense:
|
||||
//!
|
||||
//! 1. **A template that ignores `reasoning_effort` entirely** renders
|
||||
//! successfully for every candidate. Supporting "all six" would be a
|
||||
//! lie. So a candidate only counts when the rendered prompt actually
|
||||
//! *differs* across efforts — if every render is identical the model
|
||||
//! has no effort control and we advertise none.
|
||||
//! 2. **The default** is whichever supported candidate renders
|
||||
//! identically to a render with no effort supplied. Qwen3.8 defaults
|
||||
//! to `xhigh`; without detecting that, a caller who says nothing gets
|
||||
//! the strongest rung while we believe it got nothing.
|
||||
|
||||
use anyhow::Result;
|
||||
use cortex_core::openai::{ChatMessage, MessageContent};
|
||||
use serde_json::{Value, json};
|
||||
|
||||
/// Effort names in ascending order of thinking, as clients spell them.
|
||||
///
|
||||
/// Deliberately a superset of what any one model supports: this is the
|
||||
/// *candidate* set the probe tries, and the conventional vocabulary
|
||||
/// OpenAI-compatible clients use (pi-ai's `EXTENDED_THINKING_LEVELS`
|
||||
/// minus `off`, which is not an effort but a separate switch handled by
|
||||
/// `enable_thinking`).
|
||||
pub const CANDIDATE_EFFORTS: &[&str] = &["minimal", "low", "medium", "high", "xhigh", "max"];
|
||||
|
||||
/// What one model's template accepts.
|
||||
#[derive(Debug, Clone, Default, PartialEq, Eq)]
|
||||
pub struct SupportedEfforts {
|
||||
/// Accepted efforts, ascending, as the template spells them.
|
||||
pub levels: Vec<String>,
|
||||
/// The effort applied when the caller names none — the template's
|
||||
/// own `|default(...)`. `None` when it cannot be determined.
|
||||
pub default: Option<String>,
|
||||
}
|
||||
|
||||
impl SupportedEfforts {
|
||||
pub fn is_empty(&self) -> bool {
|
||||
self.levels.is_empty()
|
||||
}
|
||||
|
||||
pub fn supports(&self, effort: &str) -> bool {
|
||||
self.levels.iter().any(|l| l == effort)
|
||||
}
|
||||
|
||||
/// Map a caller's effort onto the nearest rung this model has.
|
||||
///
|
||||
/// Exact match wins. Otherwise walk **down** from the requested
|
||||
/// level first, then up — a caller asking for more thinking than the
|
||||
/// model offers should get the most it has, and a caller asking for
|
||||
/// less should not be silently upgraded into a slower, costlier
|
||||
/// response than they asked for.
|
||||
///
|
||||
/// Descending-first is the opposite of pi-ai's `clampThinkingLevel`,
|
||||
/// which searches upward first. That is deliberate: pi is choosing
|
||||
/// among levels it believes exist, whereas we are the ones who know
|
||||
/// what exists, and over-delivering thinking is the failure that
|
||||
/// costs the caller money and latency.
|
||||
///
|
||||
/// `None` when the model has no rungs at all.
|
||||
pub fn nearest(&self, requested: &str) -> Option<&str> {
|
||||
if self.levels.is_empty() {
|
||||
return None;
|
||||
}
|
||||
if let Some(exact) = self.levels.iter().find(|l| *l == requested) {
|
||||
return Some(exact.as_str());
|
||||
}
|
||||
let idx = CANDIDATE_EFFORTS.iter().position(|c| *c == requested)?;
|
||||
for c in CANDIDATE_EFFORTS[..idx].iter().rev() {
|
||||
if let Some(hit) = self.levels.iter().find(|l| l.as_str() == *c) {
|
||||
return Some(hit.as_str());
|
||||
}
|
||||
}
|
||||
for c in &CANDIDATE_EFFORTS[idx + 1..] {
|
||||
if let Some(hit) = self.levels.iter().find(|l| l.as_str() == *c) {
|
||||
return Some(hit.as_str());
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
/// Render a probe prompt at `effort`, or `None` if the template rejects
|
||||
/// it.
|
||||
fn probe_render(template: &str, effort: Option<&str>) -> Option<String> {
|
||||
let messages = [ChatMessage {
|
||||
role: "user".into(),
|
||||
content: MessageContent::Text("probe".into()),
|
||||
extra: Value::Null,
|
||||
}];
|
||||
let kwargs = match effort {
|
||||
Some(e) => json!({ "reasoning_effort": e }),
|
||||
None => Value::Null,
|
||||
};
|
||||
super::chat_template::render_chat_template(template, &messages, &Value::Null, &kwargs).ok()
|
||||
}
|
||||
|
||||
/// Discover which efforts `template` accepts (#290).
|
||||
///
|
||||
/// Errors are not propagated: a template that cannot render even the
|
||||
/// baseline probe yields no rungs, and the caller behaves as it did
|
||||
/// before this existed.
|
||||
pub fn probe(template: &str, model_id: &str) -> Result<SupportedEfforts> {
|
||||
let Some(baseline) = probe_render(template, None) else {
|
||||
tracing::debug!(
|
||||
model = %model_id,
|
||||
"reasoning effort: template does not render a baseline probe; advertising no rungs"
|
||||
);
|
||||
return Ok(SupportedEfforts::default());
|
||||
};
|
||||
|
||||
let mut rendered: Vec<(&str, String)> = Vec::new();
|
||||
for candidate in CANDIDATE_EFFORTS {
|
||||
if let Some(out) = probe_render(template, Some(candidate)) {
|
||||
rendered.push((candidate, out));
|
||||
}
|
||||
}
|
||||
|
||||
// A template that never reads `reasoning_effort` renders the same
|
||||
// bytes whatever we pass. Advertising every candidate in that case
|
||||
// would be the invented-ladder mistake again, in a new place.
|
||||
let effort_aware = rendered.windows(2).any(|w| w[0].1 != w[1].1)
|
||||
|| rendered.iter().any(|(_, out)| *out != baseline);
|
||||
if !effort_aware {
|
||||
tracing::debug!(
|
||||
model = %model_id,
|
||||
"reasoning effort: template ignores reasoning_effort; advertising no rungs"
|
||||
);
|
||||
return Ok(SupportedEfforts::default());
|
||||
}
|
||||
|
||||
let default = rendered
|
||||
.iter()
|
||||
.find(|(_, out)| *out == baseline)
|
||||
.map(|(name, _)| (*name).to_string());
|
||||
let levels: Vec<String> = rendered
|
||||
.iter()
|
||||
.map(|(name, _)| (*name).to_string())
|
||||
.collect();
|
||||
|
||||
tracing::info!(
|
||||
model = %model_id,
|
||||
levels = %levels.join(","),
|
||||
default = ?default,
|
||||
"reasoning effort: rungs discovered from the model's chat template (#290)"
|
||||
);
|
||||
Ok(SupportedEfforts { levels, default })
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// The probe against the **real** deployed Qwen3.8-27B template,
|
||||
/// not a hand-written approximation of it. A synthetic template
|
||||
/// proves the probe logic; only the shipped artifact proves the
|
||||
/// answer, and the artifact is what #290 is about.
|
||||
#[test]
|
||||
fn the_real_qwen38_template_yields_low_medium_xhigh_defaulting_to_xhigh() {
|
||||
let path = concat!(
|
||||
env!("CARGO_MANIFEST_DIR"),
|
||||
"/tests/data/qwen3.8-27b.chat_template.jinja"
|
||||
);
|
||||
let Ok(template) = std::fs::read_to_string(path) else {
|
||||
// The fixture is checked in; if it is ever removed this test
|
||||
// should fail loudly rather than silently pass.
|
||||
panic!("missing fixture {path}");
|
||||
};
|
||||
let s = probe(&template, "Qwen/Qwen3.8-27B").expect("probe");
|
||||
assert_eq!(
|
||||
s.levels,
|
||||
vec!["low", "medium", "xhigh"],
|
||||
"the shipped template accepts exactly these"
|
||||
);
|
||||
assert_eq!(s.default.as_deref(), Some("xhigh"));
|
||||
// The two rungs we used to advertise are rejected outright.
|
||||
assert!(!s.supports("minimal"));
|
||||
assert!(!s.supports("high"));
|
||||
}
|
||||
|
||||
/// The shape Qwen3.8-27B actually ships: three rungs, `xhigh`
|
||||
/// default, `raise_exception` on anything else.
|
||||
const QWEN38: &str = r#"
|
||||
{%- set resolved = reasoning_effort|default('xhigh') %}
|
||||
{%- if resolved not in ('xhigh', 'medium', 'low') %}
|
||||
{{- raise_exception('Unexpected reasoning effort ' ~ resolved) }}
|
||||
{%- endif %}
|
||||
{%- if resolved == 'xhigh' %}EFFORT-XHIGH{% elif resolved == 'low' %}EFFORT-LOW{% else %}EFFORT-MEDIUM{% endif %}
|
||||
{%- for m in messages %}<|im_start|>{{ m.role }}
|
||||
{{ m.content }}<|im_end|>
|
||||
{%- endfor %}
|
||||
"#;
|
||||
|
||||
/// A template with no effort control at all.
|
||||
const PLAIN: &str = r#"
|
||||
{%- for m in messages %}<|im_start|>{{ m.role }}
|
||||
{{ m.content }}<|im_end|>
|
||||
{%- endfor %}
|
||||
"#;
|
||||
|
||||
#[test]
|
||||
fn discovers_exactly_the_rungs_the_template_accepts() {
|
||||
let s = probe(QWEN38, "test").expect("probe");
|
||||
assert_eq!(s.levels, vec!["low", "medium", "xhigh"]);
|
||||
assert!(!s.supports("minimal"), "template raises on minimal");
|
||||
assert!(!s.supports("high"), "template raises on high");
|
||||
}
|
||||
|
||||
/// Without this, a caller who names no effort silently receives the
|
||||
/// strongest rung while we believe it received nothing — which is
|
||||
/// how the xhigh instruction ended up on every request in #290.
|
||||
#[test]
|
||||
fn detects_the_templates_own_default() {
|
||||
let s = probe(QWEN38, "test").expect("probe");
|
||||
assert_eq!(s.default.as_deref(), Some("xhigh"));
|
||||
}
|
||||
|
||||
/// A template that ignores the kwarg must advertise nothing rather
|
||||
/// than appearing to support all six.
|
||||
#[test]
|
||||
fn a_template_without_effort_control_advertises_no_rungs() {
|
||||
let s = probe(PLAIN, "test").expect("probe");
|
||||
assert!(s.is_empty(), "got {:?}", s.levels);
|
||||
assert_eq!(s.nearest("medium"), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_exact_match_is_returned_unchanged() {
|
||||
let s = probe(QWEN38, "test").expect("probe");
|
||||
assert_eq!(s.nearest("medium"), Some("medium"));
|
||||
assert_eq!(s.nearest("xhigh"), Some("xhigh"));
|
||||
}
|
||||
|
||||
/// `high` does not exist on this model. Descending first means it
|
||||
/// resolves to `medium`, not `xhigh`: a caller is never given more
|
||||
/// thinking (slower, dearer) than it asked for.
|
||||
#[test]
|
||||
fn an_unsupported_level_resolves_downward_not_upward() {
|
||||
let s = probe(QWEN38, "test").expect("probe");
|
||||
assert_eq!(s.nearest("high"), Some("medium"));
|
||||
}
|
||||
|
||||
/// `minimal` is below every rung the model has, so there is nothing
|
||||
/// to descend to and the nearest is the weakest available.
|
||||
#[test]
|
||||
fn a_level_below_every_rung_resolves_up_to_the_weakest() {
|
||||
let s = probe(QWEN38, "test").expect("probe");
|
||||
assert_eq!(s.nearest("minimal"), Some("low"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_unknown_level_name_resolves_to_nothing_rather_than_a_guess() {
|
||||
let s = probe(QWEN38, "test").expect("probe");
|
||||
assert_eq!(s.nearest("turbo"), None);
|
||||
}
|
||||
}
|
||||
@@ -1,687 +0,0 @@
|
||||
//! Sampling parameter resolution (#272, #283).
|
||||
//!
|
||||
//! Four sources, in priority order:
|
||||
//!
|
||||
//! 1. what the **request** asked for,
|
||||
//! 2. what the **operator** set for this model (#283),
|
||||
//! 3. what the **model** published in `generation_config.json`,
|
||||
//! 4. a built-in fallback.
|
||||
//!
|
||||
//! Tier (2) exists because honouring the model's own file is right by
|
||||
//! default and still wrong sometimes: `Qwen/Qwen3.8-27B` publishes
|
||||
//! `temperature = 1.0`, which measured a 20% structural-defect rate on
|
||||
//! ~2k-token code generation against 0/60 at `<= 0.6` (#283,
|
||||
//! p = 0.0031). The operator's correction is explicit and lives in a
|
||||
//! config file — never a heuristic that inspects the model and guesses,
|
||||
//! which would be a footgun.
|
||||
//!
|
||||
//! The operator sits *below* the request on purpose. An explicit API
|
||||
//! parameter that is silently ignored is a contract break; the observed
|
||||
//! failure came from callers that named nothing, so a default-tier
|
||||
//! override is sufficient to fix it.
|
||||
//!
|
||||
//! Mechanically, tier (2) is folded into tier (3) once at load time by
|
||||
//! [`ModelGenerationDefaults::with_operator_override`], so the
|
||||
//! per-request resolve path stays a two-tier lookup and every call site
|
||||
//! gets the override for free — there is no site that can forget it.
|
||||
//!
|
||||
//! Before this, (2) did not exist and (3) was a hardcoded
|
||||
//! `temperature = 0.7` with `top_p = None` — and `None` selects
|
||||
//! `Sampling::All`, meaning no truncation at all. So a caller that
|
||||
//! omitted sampling fields (the common case: the DeepSeek Harness sends
|
||||
//! only `temperature`) got untruncated sampling across the full ~250k
|
||||
//! vocabulary on a model whose authors published `top_k = 20,
|
||||
//! top_p = 0.95, temperature = 1.0`.
|
||||
//!
|
||||
//! Picking "no truncation" for an absent field is not a neutral default,
|
||||
//! it is the widest possible one. The neutral default is what the model
|
||||
//! shipped with.
|
||||
//!
|
||||
//! Resolved **once** per request and threaded whole. The eight
|
||||
//! `LogitsProcessor` construction sites this replaces could each have
|
||||
//! disagreed about a default — the same shape of bug as #252, where two
|
||||
//! config files described one model and drifted.
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::path::Path;
|
||||
|
||||
/// Fallback temperature when neither the request nor the model says.
|
||||
/// Retained from the previous hardcoded value so a model without a
|
||||
/// `generation_config.json` behaves exactly as it did before.
|
||||
const FALLBACK_TEMPERATURE: f64 = 0.7;
|
||||
|
||||
/// Repetition penalty applied to recently-generated tokens before
|
||||
/// sampling. 1.0 disables it; >1.0 makes recently-emitted tokens less
|
||||
/// likely. mistral.rs and llama.cpp default to 1.1, which is enough to
|
||||
/// stop small quantized models from degenerating into "Wait, no, no..."
|
||||
/// loops without distorting normal output.
|
||||
pub const DEFAULT_REPEAT_PENALTY: f32 = 1.1;
|
||||
|
||||
/// Number of recently-generated tokens fed into the repetition penalty.
|
||||
/// Matches the candle quantized-qwen3 example default.
|
||||
///
|
||||
/// Defensible for chat and poorly suited to a 24k-token reasoning block,
|
||||
/// where a derivation repeated 500 tokens later is well outside the
|
||||
/// window — which is why it is now a per-request knob rather than a
|
||||
/// constant.
|
||||
pub const DEFAULT_REPEAT_LAST_N: usize = 64;
|
||||
|
||||
/// What a model published in its `generation_config.json`.
|
||||
///
|
||||
/// Every field optional: the file is a HuggingFace convention, not a
|
||||
/// schema, and models populate different subsets of it.
|
||||
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
|
||||
pub struct ModelGenerationDefaults {
|
||||
pub temperature: Option<f64>,
|
||||
pub top_p: Option<f64>,
|
||||
pub top_k: Option<usize>,
|
||||
/// Not published in `generation_config.json` — this struct is the
|
||||
/// resolved per-model default layer, and the operator override
|
||||
/// (#283) lands here so the repetition knobs sit in the same
|
||||
/// precedence chain as the rest.
|
||||
pub repeat_penalty: Option<f32>,
|
||||
pub repeat_last_n: Option<usize>,
|
||||
pub presence_penalty: Option<f32>,
|
||||
pub frequency_penalty: Option<f32>,
|
||||
pub seed: Option<u64>,
|
||||
}
|
||||
|
||||
impl ModelGenerationDefaults {
|
||||
/// Read `generation_config.json` from a model snapshot directory.
|
||||
///
|
||||
/// Absent or unparseable is not an error — we fall back exactly as
|
||||
/// before — but it is logged, because silently guessing the model's
|
||||
/// sampling is how the untruncated default went unnoticed.
|
||||
pub fn load_from_dir(dir: &Path) -> Self {
|
||||
let path = dir.join("generation_config.json");
|
||||
let text = match std::fs::read_to_string(&path) {
|
||||
Ok(t) => t,
|
||||
Err(e) => {
|
||||
tracing::debug!(
|
||||
path = %path.display(),
|
||||
error = %e,
|
||||
"sampling: no generation_config.json; using built-in fallbacks"
|
||||
);
|
||||
return Self::default();
|
||||
}
|
||||
};
|
||||
match serde_json::from_str::<Self>(&text) {
|
||||
Ok(d) => {
|
||||
tracing::info!(
|
||||
path = %path.display(),
|
||||
temperature = ?d.temperature,
|
||||
top_p = ?d.top_p,
|
||||
top_k = ?d.top_k,
|
||||
"sampling: model generation defaults loaded"
|
||||
);
|
||||
d
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!(
|
||||
path = %path.display(),
|
||||
error = %e,
|
||||
"sampling: generation_config.json did not parse; using built-in fallbacks"
|
||||
);
|
||||
Self::default()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Overlay the operator's per-model override (#283) onto what the
|
||||
/// model published, field by field.
|
||||
///
|
||||
/// Applied **once at load**, not per request, so the override cannot
|
||||
/// be forgotten at one of the resolve sites — the same reasoning
|
||||
/// that made #272 resolve sampling once rather than at eight
|
||||
/// `LogitsProcessor` construction sites.
|
||||
///
|
||||
/// Each field overlays independently: setting only `temperature`
|
||||
/// leaves the model's `top_p`/`top_k` in force, because an operator
|
||||
/// correcting one number should not silently blank the other two
|
||||
/// back to "no truncation".
|
||||
///
|
||||
/// Logged at `info` whenever it changes something — an operator
|
||||
/// override that is in force but invisible is how a fleet ends up
|
||||
/// with two configs that disagree and nobody noticing (#252).
|
||||
pub fn with_operator_override(
|
||||
mut self,
|
||||
model_id: &str,
|
||||
operator: Option<&cortex_core::harness::SamplingOverride>,
|
||||
) -> Self {
|
||||
let Some(op) = operator else {
|
||||
return self;
|
||||
};
|
||||
if op.is_empty() {
|
||||
return self;
|
||||
}
|
||||
let before = self.clone();
|
||||
if let Some(t) = op.temperature {
|
||||
self.temperature = Some(t);
|
||||
}
|
||||
if let Some(p) = op.top_p {
|
||||
self.top_p = Some(p);
|
||||
}
|
||||
if let Some(k) = op.top_k {
|
||||
self.top_k = Some(k);
|
||||
}
|
||||
if let Some(r) = op.repeat_penalty {
|
||||
self.repeat_penalty = Some(r);
|
||||
}
|
||||
if let Some(n) = op.repeat_last_n {
|
||||
self.repeat_last_n = Some(n);
|
||||
}
|
||||
if let Some(v) = op.presence_penalty {
|
||||
self.presence_penalty = Some(v);
|
||||
}
|
||||
if let Some(v) = op.frequency_penalty {
|
||||
self.frequency_penalty = Some(v);
|
||||
}
|
||||
if let Some(v) = op.seed {
|
||||
self.seed = Some(v);
|
||||
}
|
||||
tracing::info!(
|
||||
model = %model_id,
|
||||
model_temperature = ?before.temperature,
|
||||
model_top_p = ?before.top_p,
|
||||
model_top_k = ?before.top_k,
|
||||
temperature = ?self.temperature,
|
||||
top_p = ?self.top_p,
|
||||
top_k = ?self.top_k,
|
||||
repeat_penalty = ?self.repeat_penalty,
|
||||
repeat_last_n = ?self.repeat_last_n,
|
||||
presence_penalty = ?self.presence_penalty,
|
||||
frequency_penalty = ?self.frequency_penalty,
|
||||
seed = ?self.seed,
|
||||
"sampling: operator override applied over the model's published defaults (#283)"
|
||||
);
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
/// What the caller asked for. All optional — absent means "no opinion",
|
||||
/// which defers to the model's published value.
|
||||
#[derive(Debug, Clone, Default)]
|
||||
pub struct RequestedSampling {
|
||||
pub temperature: Option<f64>,
|
||||
pub top_p: Option<f64>,
|
||||
pub top_k: Option<usize>,
|
||||
pub seed: Option<u64>,
|
||||
pub repeat_penalty: Option<f32>,
|
||||
pub repeat_last_n: Option<usize>,
|
||||
pub presence_penalty: Option<f32>,
|
||||
pub frequency_penalty: Option<f32>,
|
||||
}
|
||||
|
||||
/// Fully-resolved sampling for one request.
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
pub struct SamplingParams {
|
||||
pub temperature: f64,
|
||||
pub top_p: Option<f64>,
|
||||
pub top_k: Option<usize>,
|
||||
pub seed: u64,
|
||||
pub repeat_penalty: f32,
|
||||
pub repeat_last_n: usize,
|
||||
/// Sequence-wide penalties, OpenAI semantics. `0.0` disables.
|
||||
pub presence_penalty: f32,
|
||||
pub frequency_penalty: f32,
|
||||
}
|
||||
|
||||
impl SamplingParams {
|
||||
/// Resolve request over model defaults over fallback.
|
||||
///
|
||||
/// `random_seed` is the per-request seed used when the caller did
|
||||
/// not pin one; it is passed in rather than generated here so this
|
||||
/// stays a pure function and the "same seed reproduces" property is
|
||||
/// testable without a clock.
|
||||
pub fn resolve(
|
||||
requested: &RequestedSampling,
|
||||
model: &ModelGenerationDefaults,
|
||||
random_seed: u64,
|
||||
) -> Self {
|
||||
Self {
|
||||
temperature: requested
|
||||
.temperature
|
||||
.or(model.temperature)
|
||||
.unwrap_or(FALLBACK_TEMPERATURE),
|
||||
// No `unwrap_or` here on purpose: `None` still means "do not
|
||||
// truncate", but it is now only reachable when neither the
|
||||
// caller nor the model expressed a preference, rather than
|
||||
// whenever the caller stayed quiet.
|
||||
top_p: requested.top_p.or(model.top_p),
|
||||
top_k: requested.top_k.or(model.top_k),
|
||||
seed: requested.seed.or(model.seed).unwrap_or(random_seed),
|
||||
repeat_penalty: requested
|
||||
.repeat_penalty
|
||||
.or(model.repeat_penalty)
|
||||
.unwrap_or(DEFAULT_REPEAT_PENALTY),
|
||||
repeat_last_n: requested
|
||||
.repeat_last_n
|
||||
.or(model.repeat_last_n)
|
||||
.unwrap_or(DEFAULT_REPEAT_LAST_N),
|
||||
presence_penalty: requested
|
||||
.presence_penalty
|
||||
.or(model.presence_penalty)
|
||||
.unwrap_or(0.0),
|
||||
frequency_penalty: requested
|
||||
.frequency_penalty
|
||||
.or(model.frequency_penalty)
|
||||
.unwrap_or(0.0),
|
||||
}
|
||||
}
|
||||
|
||||
/// The candle sampling strategy these parameters select.
|
||||
///
|
||||
/// `temperature <= 0` is greedy regardless of the rest — a caller
|
||||
/// asking for determinism that way should not have it silently
|
||||
/// softened by a `top_k` the model happened to publish.
|
||||
pub fn to_sampling(&self) -> candle_transformers::generation::Sampling {
|
||||
use candle_transformers::generation::Sampling;
|
||||
if self.temperature <= 0.0 {
|
||||
return Sampling::ArgMax;
|
||||
}
|
||||
let temperature = self.temperature;
|
||||
match (self.top_k, self.top_p) {
|
||||
(Some(k), Some(p)) => Sampling::TopKThenTopP { k, p, temperature },
|
||||
(Some(k), None) => Sampling::TopK { k, temperature },
|
||||
(None, Some(p)) => Sampling::TopP { p, temperature },
|
||||
(None, None) => Sampling::All { temperature },
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use candle_transformers::generation::Sampling;
|
||||
use cortex_core::harness::SamplingOverride;
|
||||
|
||||
fn qwen3_defaults() -> ModelGenerationDefaults {
|
||||
ModelGenerationDefaults {
|
||||
temperature: Some(1.0),
|
||||
top_p: Some(0.95),
|
||||
top_k: Some(20),
|
||||
..Default::default()
|
||||
}
|
||||
}
|
||||
|
||||
/// The case that motivated #271: a caller that names no sampling
|
||||
/// parameters must get the model's published ones, not untruncated
|
||||
/// sampling at a hardcoded 0.7.
|
||||
#[test]
|
||||
fn a_silent_request_inherits_the_models_published_sampling() {
|
||||
let p = SamplingParams::resolve(&RequestedSampling::default(), &qwen3_defaults(), 42);
|
||||
assert_eq!(p.temperature, 1.0);
|
||||
assert_eq!(p.top_p, Some(0.95));
|
||||
assert_eq!(p.top_k, Some(20));
|
||||
assert_eq!(
|
||||
p.to_sampling(),
|
||||
Sampling::TopKThenTopP {
|
||||
k: 20,
|
||||
p: 0.95,
|
||||
temperature: 1.0
|
||||
},
|
||||
"the combination Qwen3 asks for must be expressible"
|
||||
);
|
||||
}
|
||||
|
||||
/// The caller still wins. A harness that deliberately sets a low
|
||||
/// temperature must not have it overridden by the model's file.
|
||||
#[test]
|
||||
fn the_request_overrides_the_model() {
|
||||
let requested = RequestedSampling {
|
||||
temperature: Some(0.2),
|
||||
top_k: Some(5),
|
||||
..Default::default()
|
||||
};
|
||||
let p = SamplingParams::resolve(&requested, &qwen3_defaults(), 42);
|
||||
assert_eq!(p.temperature, 0.2);
|
||||
assert_eq!(p.top_k, Some(5));
|
||||
// Untouched fields still fall through to the model.
|
||||
assert_eq!(p.top_p, Some(0.95));
|
||||
}
|
||||
|
||||
// ── Operator override (#283) ──────────────────────────────
|
||||
|
||||
fn op(temperature: Option<f64>, top_p: Option<f64>, top_k: Option<usize>) -> SamplingOverride {
|
||||
SamplingOverride {
|
||||
temperature,
|
||||
top_p,
|
||||
top_k,
|
||||
..Default::default()
|
||||
}
|
||||
}
|
||||
|
||||
fn with_op(o: SamplingOverride) -> ModelGenerationDefaults {
|
||||
qwen3_defaults().with_operator_override("Qwen/Qwen3.8-27B", Some(&o))
|
||||
}
|
||||
|
||||
/// The #283 case: the model publishes `temperature = 1.0`, which
|
||||
/// measured a 20% structural-defect rate on code generation. The
|
||||
/// operator sets 0.6 and a silent caller must get 0.6.
|
||||
#[test]
|
||||
fn the_operator_override_replaces_what_the_model_published() {
|
||||
let p = SamplingParams::resolve(
|
||||
&RequestedSampling::default(),
|
||||
&with_op(op(Some(0.6), None, None)),
|
||||
42,
|
||||
);
|
||||
assert_eq!(p.temperature, 0.6);
|
||||
}
|
||||
|
||||
/// Precedence is request > operator > model. An explicit API
|
||||
/// parameter that is silently ignored is a contract break, so a
|
||||
/// caller naming a temperature still wins over the operator.
|
||||
#[test]
|
||||
fn an_explicit_request_still_beats_the_operator() {
|
||||
let requested = RequestedSampling {
|
||||
temperature: Some(0.9),
|
||||
..Default::default()
|
||||
};
|
||||
let p = SamplingParams::resolve(&requested, &with_op(op(Some(0.6), None, None)), 42);
|
||||
assert_eq!(p.temperature, 0.9);
|
||||
}
|
||||
|
||||
/// Overriding one field must not blank the others back to "no
|
||||
/// truncation" — that was the #271 failure mode, reintroduced by a
|
||||
/// wholesale replace instead of a field-by-field overlay.
|
||||
#[test]
|
||||
fn overriding_temperature_alone_leaves_top_p_and_top_k_intact() {
|
||||
let d = with_op(op(Some(0.6), None, None));
|
||||
assert_eq!(d.temperature, Some(0.6));
|
||||
assert_eq!(d.top_p, Some(0.95), "the model's top_p must survive");
|
||||
assert_eq!(d.top_k, Some(20), "the model's top_k must survive");
|
||||
}
|
||||
|
||||
/// Each field overlays independently.
|
||||
#[test]
|
||||
fn every_field_can_be_overridden_independently() {
|
||||
let d = with_op(op(None, Some(0.8), Some(40)));
|
||||
assert_eq!(d.temperature, Some(1.0), "untouched, so the model's");
|
||||
assert_eq!(d.top_p, Some(0.8));
|
||||
assert_eq!(d.top_k, Some(40));
|
||||
}
|
||||
|
||||
/// No override, and an override that sets nothing, must both be
|
||||
/// indistinguishable from the pre-#283 behaviour.
|
||||
#[test]
|
||||
fn absent_or_empty_override_changes_nothing() {
|
||||
let base = qwen3_defaults();
|
||||
let none = qwen3_defaults().with_operator_override("m", None);
|
||||
let empty =
|
||||
qwen3_defaults().with_operator_override("m", Some(&SamplingOverride::default()));
|
||||
for d in [none, empty] {
|
||||
assert_eq!(d.temperature, base.temperature);
|
||||
assert_eq!(d.top_p, base.top_p);
|
||||
assert_eq!(d.top_k, base.top_k);
|
||||
}
|
||||
}
|
||||
|
||||
/// An operator override on a model that ships no
|
||||
/// `generation_config.json` must still take effect, rather than
|
||||
/// falling through to the built-in 0.7.
|
||||
#[test]
|
||||
fn the_override_applies_even_without_a_generation_config() {
|
||||
let d = ModelGenerationDefaults::default()
|
||||
.with_operator_override("m", Some(&op(Some(0.6), None, None)));
|
||||
let p = SamplingParams::resolve(&RequestedSampling::default(), &d, 42);
|
||||
assert_eq!(p.temperature, 0.6);
|
||||
assert_ne!(p.temperature, FALLBACK_TEMPERATURE);
|
||||
}
|
||||
|
||||
/// `temperature = 0` from an operator must select greedy decoding,
|
||||
/// not be treated as "unset" by an `unwrap_or`-shaped bug.
|
||||
#[test]
|
||||
fn an_operator_temperature_of_zero_is_greedy_not_unset() {
|
||||
let p = SamplingParams::resolve(
|
||||
&RequestedSampling::default(),
|
||||
&with_op(op(Some(0.0), None, None)),
|
||||
42,
|
||||
);
|
||||
assert_eq!(p.temperature, 0.0);
|
||||
assert_eq!(p.to_sampling(), Sampling::ArgMax);
|
||||
}
|
||||
|
||||
/// A model with no `generation_config.json` must behave exactly as
|
||||
/// it did before this landed, so nothing regresses on the models
|
||||
/// that do not ship one.
|
||||
/// An operator can pin the seed, because the client that needs it
|
||||
/// pinned cannot send one: pi's request builder emits no `seed`, so
|
||||
/// without this a parameter search runs unseeded and sampling
|
||||
/// variance is indistinguishable from the effect being measured.
|
||||
#[test]
|
||||
fn an_operator_can_pin_the_seed() {
|
||||
let op = cortex_core::harness::SamplingOverride {
|
||||
seed: Some(424_242),
|
||||
..Default::default()
|
||||
};
|
||||
let defaults = ModelGenerationDefaults::default().with_operator_override("m", Some(&op));
|
||||
// The random seed argument must be ignored once an operator pinned one.
|
||||
let p = SamplingParams::resolve(&RequestedSampling::default(), &defaults, 999);
|
||||
assert_eq!(p.seed, 424_242);
|
||||
}
|
||||
|
||||
/// Precedence holds: a caller that names its own seed keeps it.
|
||||
#[test]
|
||||
fn a_requested_seed_outranks_the_operator() {
|
||||
let op = cortex_core::harness::SamplingOverride {
|
||||
seed: Some(424_242),
|
||||
..Default::default()
|
||||
};
|
||||
let defaults = ModelGenerationDefaults::default().with_operator_override("m", Some(&op));
|
||||
let req = RequestedSampling {
|
||||
seed: Some(7),
|
||||
..Default::default()
|
||||
};
|
||||
assert_eq!(SamplingParams::resolve(&req, &defaults, 999).seed, 7);
|
||||
}
|
||||
|
||||
/// With neither, the per-request random seed still applies — an
|
||||
/// unset override must not accidentally freeze the fleet's RNG.
|
||||
#[test]
|
||||
fn no_pinned_seed_leaves_generation_random() {
|
||||
let d = ModelGenerationDefaults::default().with_operator_override("m", None);
|
||||
assert_eq!(
|
||||
SamplingParams::resolve(&RequestedSampling::default(), &d, 999).seed,
|
||||
999
|
||||
);
|
||||
}
|
||||
|
||||
/// The gap this closes: `repeat_last_n` defaults to 64 — candle's
|
||||
/// chat example value — while a reasoning model's think block runs
|
||||
/// to tens of thousands of tokens. Anything restated more than 64
|
||||
/// tokens later is invisible to the penalty, and before this there
|
||||
/// was no operator route to the knob at all: `SamplingOverride`
|
||||
/// carried only temperature/top_p/top_k, and OpenAI-shaped clients
|
||||
/// do not send repetition parameters. The 64 was effectively
|
||||
/// hardcoded in production.
|
||||
#[test]
|
||||
fn an_operator_can_widen_the_repetition_window() {
|
||||
let op = cortex_core::harness::SamplingOverride {
|
||||
repeat_penalty: Some(1.05),
|
||||
repeat_last_n: Some(2048),
|
||||
presence_penalty: None,
|
||||
frequency_penalty: None,
|
||||
..Default::default()
|
||||
};
|
||||
let defaults = ModelGenerationDefaults::default().with_operator_override("m", Some(&op));
|
||||
let p = SamplingParams::resolve(&RequestedSampling::default(), &defaults, 7);
|
||||
assert_eq!(p.repeat_last_n, 2048);
|
||||
assert!((p.repeat_penalty - 1.05).abs() < f32::EPSILON);
|
||||
}
|
||||
|
||||
/// Precedence is request > operator > built-in, same as every other
|
||||
/// sampling field — a caller that named a window keeps it.
|
||||
#[test]
|
||||
fn a_requested_repetition_window_outranks_the_operator() {
|
||||
let op = cortex_core::harness::SamplingOverride {
|
||||
repeat_last_n: Some(2048),
|
||||
presence_penalty: None,
|
||||
frequency_penalty: None,
|
||||
..Default::default()
|
||||
};
|
||||
let defaults = ModelGenerationDefaults::default().with_operator_override("m", Some(&op));
|
||||
let req = RequestedSampling {
|
||||
repeat_last_n: Some(128),
|
||||
presence_penalty: None,
|
||||
frequency_penalty: None,
|
||||
..Default::default()
|
||||
};
|
||||
assert_eq!(
|
||||
SamplingParams::resolve(&req, &defaults, 7).repeat_last_n,
|
||||
128
|
||||
);
|
||||
}
|
||||
|
||||
/// An operator who sets nothing must not change the constants.
|
||||
#[test]
|
||||
fn no_operator_setting_leaves_the_repetition_defaults_alone() {
|
||||
let d = ModelGenerationDefaults::default().with_operator_override("m", None);
|
||||
let p = SamplingParams::resolve(&RequestedSampling::default(), &d, 7);
|
||||
assert_eq!(p.repeat_last_n, DEFAULT_REPEAT_LAST_N);
|
||||
assert!((p.repeat_penalty - DEFAULT_REPEAT_PENALTY).abs() < f32::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn without_model_defaults_the_old_behaviour_is_preserved() {
|
||||
let p = SamplingParams::resolve(
|
||||
&RequestedSampling::default(),
|
||||
&ModelGenerationDefaults::default(),
|
||||
42,
|
||||
);
|
||||
assert_eq!(p.temperature, FALLBACK_TEMPERATURE);
|
||||
assert_eq!(p.top_p, None);
|
||||
assert_eq!(p.top_k, None);
|
||||
assert_eq!(p.to_sampling(), Sampling::All { temperature: 0.7 });
|
||||
}
|
||||
|
||||
/// A pinned seed is honoured; an absent one takes the per-request
|
||||
/// random value. Reproducibility is the whole point — the text paths
|
||||
/// previously called `unix_subsec_nanos()` unconditionally, so
|
||||
/// `seed` was accepted and discarded.
|
||||
#[test]
|
||||
fn seed_is_pinned_when_given_and_random_otherwise() {
|
||||
let pinned = SamplingParams::resolve(
|
||||
&RequestedSampling {
|
||||
seed: Some(7),
|
||||
..Default::default()
|
||||
},
|
||||
&ModelGenerationDefaults::default(),
|
||||
42,
|
||||
);
|
||||
assert_eq!(pinned.seed, 7);
|
||||
|
||||
let unpinned = SamplingParams::resolve(
|
||||
&RequestedSampling::default(),
|
||||
&ModelGenerationDefaults::default(),
|
||||
42,
|
||||
);
|
||||
assert_eq!(unpinned.seed, 42);
|
||||
}
|
||||
|
||||
/// Greedy beats every truncation setting: a caller asking for
|
||||
/// `temperature = 0` wants determinism, not a softened version of it.
|
||||
#[test]
|
||||
fn zero_temperature_is_greedy_even_with_model_top_k() {
|
||||
let requested = RequestedSampling {
|
||||
temperature: Some(0.0),
|
||||
..Default::default()
|
||||
};
|
||||
let p = SamplingParams::resolve(&requested, &qwen3_defaults(), 42);
|
||||
assert_eq!(p.to_sampling(), Sampling::ArgMax);
|
||||
}
|
||||
|
||||
/// Each truncation knob alone selects the matching strategy.
|
||||
#[test]
|
||||
fn single_knobs_select_their_own_strategy() {
|
||||
let only_k = SamplingParams::resolve(
|
||||
&RequestedSampling {
|
||||
top_k: Some(20),
|
||||
..Default::default()
|
||||
},
|
||||
&ModelGenerationDefaults::default(),
|
||||
1,
|
||||
);
|
||||
assert_eq!(
|
||||
only_k.to_sampling(),
|
||||
Sampling::TopK {
|
||||
k: 20,
|
||||
temperature: 0.7
|
||||
}
|
||||
);
|
||||
|
||||
let only_p = SamplingParams::resolve(
|
||||
&RequestedSampling {
|
||||
top_p: Some(0.9),
|
||||
..Default::default()
|
||||
},
|
||||
&ModelGenerationDefaults::default(),
|
||||
1,
|
||||
);
|
||||
assert_eq!(
|
||||
only_p.to_sampling(),
|
||||
Sampling::TopP {
|
||||
p: 0.9,
|
||||
temperature: 0.7
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
/// Repetition penalty and its window are now per-request, defaulting
|
||||
/// to the values that were previously constants.
|
||||
#[test]
|
||||
fn repetition_knobs_default_to_the_former_constants() {
|
||||
let d = SamplingParams::resolve(
|
||||
&RequestedSampling::default(),
|
||||
&ModelGenerationDefaults::default(),
|
||||
1,
|
||||
);
|
||||
assert_eq!(d.repeat_penalty, DEFAULT_REPEAT_PENALTY);
|
||||
assert_eq!(d.repeat_last_n, DEFAULT_REPEAT_LAST_N);
|
||||
|
||||
let tuned = SamplingParams::resolve(
|
||||
&RequestedSampling {
|
||||
repeat_penalty: Some(1.05),
|
||||
repeat_last_n: Some(512),
|
||||
presence_penalty: None,
|
||||
frequency_penalty: None,
|
||||
..Default::default()
|
||||
},
|
||||
&ModelGenerationDefaults::default(),
|
||||
1,
|
||||
);
|
||||
assert_eq!(tuned.repeat_penalty, 1.05);
|
||||
assert_eq!(tuned.repeat_last_n, 512);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn absent_generation_config_is_not_an_error() {
|
||||
let dir = tempfile::tempdir().expect("tempdir");
|
||||
let d = ModelGenerationDefaults::load_from_dir(dir.path());
|
||||
assert!(d.temperature.is_none() && d.top_p.is_none() && d.top_k.is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_real_generation_config_parses() {
|
||||
let dir = tempfile::tempdir().expect("tempdir");
|
||||
// Verbatim from Qwen/Qwen3.8-27B, extra fields included — the
|
||||
// reader must tolerate the ones it does not model.
|
||||
std::fs::write(
|
||||
dir.path().join("generation_config.json"),
|
||||
r#"{"bos_token_id":248044,"do_sample":true,"eos_token_id":[248046,248044],
|
||||
"pad_token_id":248044,"temperature":1.0,"top_k":20,"top_p":0.95}"#,
|
||||
)
|
||||
.expect("write");
|
||||
let d = ModelGenerationDefaults::load_from_dir(dir.path());
|
||||
assert_eq!(d.temperature, Some(1.0));
|
||||
assert_eq!(d.top_p, Some(0.95));
|
||||
assert_eq!(d.top_k, Some(20));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn malformed_generation_config_falls_back_rather_than_failing() {
|
||||
let dir = tempfile::tempdir().expect("tempdir");
|
||||
std::fs::write(dir.path().join("generation_config.json"), "{not json").expect("write");
|
||||
let d = ModelGenerationDefaults::load_from_dir(dir.path());
|
||||
assert!(d.temperature.is_none());
|
||||
}
|
||||
}
|
||||
@@ -30,10 +30,6 @@ pub mod worker;
|
||||
use anyhow::{Context, Result};
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::process::Stdio;
|
||||
#[cfg(any(feature = "cuda", test))]
|
||||
use std::sync::Arc;
|
||||
#[cfg(any(feature = "cuda", test))]
|
||||
use std::sync::atomic::{AtomicBool, Ordering};
|
||||
use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader, Lines};
|
||||
use tokio::process::{Child, ChildStdin, ChildStdout, Command};
|
||||
|
||||
@@ -323,87 +319,6 @@ pub struct WorkerPool {
|
||||
leader_comm: Option<nccl_state::SendComm>,
|
||||
}
|
||||
|
||||
/// How long the watchdog waits for `ncclCommAbort` to return before
|
||||
/// concluding the process is unrecoverable (#265). Generous relative to a
|
||||
/// healthy abort (milliseconds) and short relative to a human noticing.
|
||||
#[cfg(any(feature = "cuda", test))]
|
||||
fn tp_abort_deadline() -> std::time::Duration {
|
||||
let secs = std::env::var("NEURON_TP_ABORT_DEADLINE_S")
|
||||
.ok()
|
||||
.and_then(|v| v.parse::<u64>().ok())
|
||||
.filter(|s| *s > 0)
|
||||
.unwrap_or(60);
|
||||
std::time::Duration::from_secs(secs)
|
||||
}
|
||||
|
||||
/// Wait for the abort thread to signal completion. `true` if it returned
|
||||
/// in time (recovery proceeds normally), `false` if the deadline elapsed
|
||||
/// (the process is unrecoverable).
|
||||
///
|
||||
/// Split out from the deadman thread so the decision is testable without
|
||||
/// a GPU: the branch that ends the process is the one most worth
|
||||
/// exercising, and the one hardest to reach by accident.
|
||||
#[cfg(any(feature = "cuda", test))]
|
||||
fn wait_for_abort(done: &AtomicBool, deadline: std::time::Duration) -> bool {
|
||||
let start = std::time::Instant::now();
|
||||
while start.elapsed() < deadline {
|
||||
if done.load(Ordering::Acquire) {
|
||||
return true;
|
||||
}
|
||||
std::thread::sleep(std::time::Duration::from_millis(25));
|
||||
}
|
||||
// One last look: the abort may have landed inside the final sleep.
|
||||
done.load(Ordering::Acquire)
|
||||
}
|
||||
|
||||
/// Exit non-zero so systemd's `Restart=on-failure` restarts us (#265).
|
||||
///
|
||||
/// Called only when the process cannot recover on its own: the NCCL
|
||||
/// collective is wedged and the abort that would unblock it has itself
|
||||
/// hung. The daemon then serves nothing — on beast 2026-08-17 it sat in
|
||||
/// that state for 70 minutes with GPUs idle, weights resident, 27
|
||||
/// connections queued on the listener, and `systemctl` reporting it
|
||||
/// active. A process that knows it is unrecoverable should not wait for a
|
||||
/// human.
|
||||
///
|
||||
/// **Everything diagnostic is logged first.** A restart destroys the
|
||||
/// state that explains the hang, so trading a diagnosable outage for an
|
||||
/// undiagnosable self-healing one would be a poor bargain.
|
||||
///
|
||||
/// `process::exit` deliberately skips destructors and the graceful-drain
|
||||
/// path. That is normally the wrong instinct, but draining a wedged
|
||||
/// process cannot work — and `TimeoutStopSec=120s` plus
|
||||
/// `TimeoutStopFailureMode=abort` would add two more minutes of outage on
|
||||
/// top of the wedge (#256).
|
||||
#[cfg(feature = "cuda")]
|
||||
fn exit_unrecoverable(model_id: &str, reason: &str) -> ! {
|
||||
// Read straight from the driver rather than any cached value: the
|
||||
// cache is refreshed by the very machinery that is wedged.
|
||||
let vram = std::process::Command::new("nvidia-smi")
|
||||
.args([
|
||||
"--query-gpu=index,memory.used,memory.free,utilization.gpu",
|
||||
"--format=csv,noheader",
|
||||
])
|
||||
.output()
|
||||
.ok()
|
||||
.map(|o| String::from_utf8_lossy(&o.stdout).replace('\n', " | "))
|
||||
.unwrap_or_else(|| "unavailable".into());
|
||||
tracing::error!(
|
||||
model = %model_id,
|
||||
reason = %reason,
|
||||
vram = %vram,
|
||||
pid = std::process::id(),
|
||||
"tp watchdog: UNRECOVERABLE — exiting non-zero so systemd restarts this daemon (#265). \
|
||||
The GPU state above is from immediately before the exit; the wedged collective and its \
|
||||
request id are in the preceding watchdog lines."
|
||||
);
|
||||
// Give the logging layer a moment to flush before the process dies —
|
||||
// an exit that eats its own explanation is the failure mode this
|
||||
// whole change exists to avoid.
|
||||
std::thread::sleep(std::time::Duration::from_millis(500));
|
||||
std::process::exit(70) // EX_SOFTWARE
|
||||
}
|
||||
|
||||
/// Per-step deadline for a TP forward (#17 Stage 2). A healthy decode
|
||||
/// step or chunked prefill completes in well under a second; a wedged
|
||||
/// NCCL collective never returns. Generous default so no legitimate step
|
||||
@@ -434,66 +349,23 @@ impl WorkerPool {
|
||||
"tp watchdog: leader forward exceeded deadline — NCCL collective wedged; \
|
||||
aborting comm to unblock the leader thread for auto-recovery"
|
||||
);
|
||||
let Some(comm) = self.leader_comm.as_ref().map(|c| c.0.clone()) else {
|
||||
tracing::error!(
|
||||
match &self.leader_comm {
|
||||
Some(c) => match c.0.abort() {
|
||||
Ok(()) => tracing::error!(
|
||||
model = %model_id,
|
||||
"tp watchdog: ncclCommAbort succeeded — wedged collective unblocked; \
|
||||
failing the step so the model auto-recovers (unload+reload)"
|
||||
),
|
||||
Err(e) => tracing::error!(
|
||||
model = %model_id, error = ?e,
|
||||
"tp watchdog: ncclCommAbort failed — recovery may stall until a process restart"
|
||||
),
|
||||
},
|
||||
None => tracing::error!(
|
||||
model = %model_id,
|
||||
"tp watchdog: no cached leader comm handle — cannot abort; exiting so \
|
||||
systemd restarts us (#265)"
|
||||
);
|
||||
exit_unrecoverable(model_id, "no leader comm handle to abort");
|
||||
};
|
||||
|
||||
// `ncclCommAbort` can itself block forever — observed on beast
|
||||
// 2026-08-17, where neither the success nor the failure branch below
|
||||
// was ever reached and the daemon sat wedged for 70 minutes with 27
|
||||
// connections queued on its listener (#265). So the abort runs on its
|
||||
// own thread and the deadline below does NOT depend on it returning:
|
||||
// an abort that hangs must not take the supervisor with it.
|
||||
let done = Arc::new(AtomicBool::new(false));
|
||||
let signal = Arc::clone(&done);
|
||||
let owned_model = model_id.to_string();
|
||||
std::thread::Builder::new()
|
||||
.name("tp-watchdog-abort".into())
|
||||
.spawn(move || {
|
||||
match comm.abort() {
|
||||
Ok(()) => tracing::error!(
|
||||
model = %owned_model,
|
||||
"tp watchdog: ncclCommAbort succeeded — wedged collective unblocked; \
|
||||
failing the step so the model auto-recovers (unload+reload)"
|
||||
),
|
||||
Err(e) => tracing::error!(
|
||||
model = %owned_model, error = ?e,
|
||||
"tp watchdog: ncclCommAbort failed — the collective is still wedged"
|
||||
),
|
||||
}
|
||||
// Returning at all is the signal, success or failure: a
|
||||
// returned abort leaves the process responsive, so
|
||||
// auto-recovery can run and we must not exit under it.
|
||||
signal.store(true, Ordering::Release);
|
||||
})
|
||||
.map(|_| ())
|
||||
.unwrap_or_else(|e| {
|
||||
// Cannot even spawn a thread — nothing here can recover.
|
||||
tracing::error!(model = %model_id, error = %e, "tp watchdog: abort thread spawn failed");
|
||||
exit_unrecoverable(model_id, "could not spawn the abort thread");
|
||||
});
|
||||
|
||||
// Deadman. Disarmed only by the abort returning.
|
||||
let deadline = tp_abort_deadline();
|
||||
let owned_model = model_id.to_string();
|
||||
if let Err(e) = std::thread::Builder::new()
|
||||
.name("tp-watchdog-deadman".into())
|
||||
.spawn(move || {
|
||||
if wait_for_abort(&done, deadline) {
|
||||
return; // abort came back; the normal path owns recovery
|
||||
}
|
||||
exit_unrecoverable(
|
||||
&owned_model,
|
||||
"ncclCommAbort did not return within the deadline",
|
||||
);
|
||||
})
|
||||
{
|
||||
tracing::error!(model = %model_id, error = %e, "tp watchdog: deadman spawn failed");
|
||||
"tp watchdog: no cached leader comm handle — cannot abort; recovery will rely \
|
||||
on a process restart"
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1570,73 +1442,3 @@ impl WorkerPool {
|
||||
&self.exe
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod watchdog_tests {
|
||||
use super::*;
|
||||
use std::time::Duration;
|
||||
|
||||
/// An abort that returns disarms the deadman — the normal path then
|
||||
/// owns recovery and the process must NOT exit.
|
||||
#[test]
|
||||
fn abort_returning_disarms_the_deadman() {
|
||||
let done = Arc::new(AtomicBool::new(false));
|
||||
let signal = Arc::clone(&done);
|
||||
std::thread::spawn(move || {
|
||||
std::thread::sleep(Duration::from_millis(50));
|
||||
signal.store(true, Ordering::Release);
|
||||
});
|
||||
assert!(
|
||||
wait_for_abort(&done, Duration::from_secs(5)),
|
||||
"a returning abort must disarm the deadman"
|
||||
);
|
||||
}
|
||||
|
||||
/// The #265 case: `ncclCommAbort` never returns. The deadline must
|
||||
/// elapse and report unrecoverable, which is what triggers the exit.
|
||||
#[test]
|
||||
fn abort_that_never_returns_trips_the_deadline() {
|
||||
let done = Arc::new(AtomicBool::new(false)); // never set
|
||||
let start = std::time::Instant::now();
|
||||
assert!(
|
||||
!wait_for_abort(&done, Duration::from_millis(200)),
|
||||
"an abort that never returns must trip the deadline"
|
||||
);
|
||||
assert!(
|
||||
start.elapsed() >= Duration::from_millis(200),
|
||||
"must actually wait the deadline rather than failing fast"
|
||||
);
|
||||
}
|
||||
|
||||
/// An abort landing in the last instant still counts as returned —
|
||||
/// exiting on a race would restart a process that had just recovered.
|
||||
#[test]
|
||||
fn abort_landing_at_the_deadline_still_counts() {
|
||||
let done = Arc::new(AtomicBool::new(false));
|
||||
let signal = Arc::clone(&done);
|
||||
std::thread::spawn(move || {
|
||||
std::thread::sleep(Duration::from_millis(180));
|
||||
signal.store(true, Ordering::Release);
|
||||
});
|
||||
assert!(
|
||||
wait_for_abort(&done, Duration::from_millis(200)),
|
||||
"an abort landing at the deadline must not be treated as a hang"
|
||||
);
|
||||
}
|
||||
|
||||
/// The deadline is operator-tunable but never zero — a zero deadline
|
||||
/// would exit the moment any watchdog fired.
|
||||
#[test]
|
||||
fn deadline_defaults_sanely_and_rejects_zero() {
|
||||
assert_eq!(tp_abort_deadline(), Duration::from_secs(60));
|
||||
unsafe { std::env::set_var("NEURON_TP_ABORT_DEADLINE_S", "0") };
|
||||
assert_eq!(
|
||||
tp_abort_deadline(),
|
||||
Duration::from_secs(60),
|
||||
"zero must fall back, not exit instantly on every watchdog"
|
||||
);
|
||||
unsafe { std::env::set_var("NEURON_TP_ABORT_DEADLINE_S", "15") };
|
||||
assert_eq!(tp_abort_deadline(), Duration::from_secs(15));
|
||||
unsafe { std::env::remove_var("NEURON_TP_ABORT_DEADLINE_S") };
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2445,7 +2445,7 @@ mod tests {
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "cuda"))]
|
||||
fn vb_over(path: &std::path::Path) -> ShardedVarBuilder<'_> {
|
||||
fn vb_over(path: &std::path::Path) -> ShardedVarBuilder {
|
||||
// SAFETY: mmap of a file the test just wrote; nothing mutates it.
|
||||
unsafe {
|
||||
candle_nn::var_builder::ShardedSafeTensors::var_builder(
|
||||
|
||||
@@ -186,9 +186,6 @@ async fn daemon(args: Args) -> Result<()> {
|
||||
let registry = HarnessRegistry::from_configs(&cfg.harnesses, &bind_url, &cfg.harness);
|
||||
discovery_result.harnesses = registry.names();
|
||||
let candle = registry.candle();
|
||||
// A second handle for the shutdown future: it must close admission
|
||||
// before the drain begins, and `candle` is moved into NeuronState.
|
||||
let shutdown_candle = candle.clone();
|
||||
|
||||
let health_cache = Arc::new(health::HealthCache::new());
|
||||
health_cache
|
||||
@@ -249,7 +246,7 @@ async fn daemon(args: Args) -> Result<()> {
|
||||
}
|
||||
|
||||
axum::serve(listener, app)
|
||||
.with_graceful_shutdown(startup::shutdown_signal(shutdown_candle))
|
||||
.with_graceful_shutdown(startup::shutdown_signal())
|
||||
.await?;
|
||||
|
||||
// Deactivation: serve has returned (graceful shutdown signal
|
||||
|
||||
@@ -9,7 +9,6 @@ use crate::activation::ActivationTracker;
|
||||
use crate::harness::HarnessRegistry;
|
||||
use crate::harness::preflight::PreflightError;
|
||||
use cortex_core::harness::ModelSpec;
|
||||
use std::sync::Arc;
|
||||
use std::time::{Duration, Instant};
|
||||
use tokio::signal;
|
||||
|
||||
@@ -166,18 +165,7 @@ fn preflight_kind(err: &PreflightError) -> &'static str {
|
||||
/// Wired into `axum::serve(...).with_graceful_shutdown(shutdown_signal())`
|
||||
/// so the HTTP listener stops accepting new connections, lets in-flight
|
||||
/// requests drain, and then yields control back to main for cleanup.
|
||||
///
|
||||
/// **Before returning, it closes admission and wakes every waiter (#256).**
|
||||
/// Order matters: axum's graceful shutdown waits for *all* in-flight
|
||||
/// requests, and a request queued behind the TP pool lock is in-flight as
|
||||
/// far as axum is concerned. Those waits are unbounded — held by whichever
|
||||
/// request is mid-forward — so without this the drain cannot finish and
|
||||
/// systemd SIGKILLs at `TimeoutStopSec`. Observed 2026-08-15: SIGTERM at
|
||||
/// 13:03:14, one queued request logging "still waiting on pool lock" every
|
||||
/// two seconds, `Failed with result 'timeout'` at 13:05:24. The same node
|
||||
/// drained in about a second when idle, which is what identified the
|
||||
/// queued waiter as the cause.
|
||||
pub async fn shutdown_signal(candle: Option<Arc<crate::harness::candle::CandleHarness>>) {
|
||||
pub async fn shutdown_signal() {
|
||||
let ctrl_c = async {
|
||||
signal::ctrl_c().await.ok();
|
||||
};
|
||||
@@ -191,13 +179,6 @@ pub async fn shutdown_signal(candle: Option<Arc<crate::harness::candle::CandleHa
|
||||
_ = ctrl_c => tracing::info!("received SIGINT, shutting down"),
|
||||
_ = terminate => tracing::info!("received SIGTERM, shutting down"),
|
||||
}
|
||||
// Refuse new admissions and abandon the unbounded waits, so the drain
|
||||
// that starts the moment this future resolves has a bounded amount of
|
||||
// work left to wait for.
|
||||
crate::harness::candle::begin_shutdown();
|
||||
if let Some(candle) = candle {
|
||||
candle.close_all_admission().await;
|
||||
}
|
||||
}
|
||||
|
||||
/// Unload every model currently registered. Called from `main.rs` after
|
||||
|
||||
@@ -84,13 +84,6 @@ pub enum InferenceEvent {
|
||||
/// `output_tokens_details.reasoning_tokens` (responses).
|
||||
/// Zero for non-reasoning models.
|
||||
reasoning_tokens: u32,
|
||||
/// Leading prompt tokens served from the prefix cache (#269) — a
|
||||
/// sub-count of `prompt_tokens`, never added to `total_tokens`.
|
||||
/// Surfaced as `prompt_tokens_details.cached_tokens` (chat) /
|
||||
/// `input_tokens_details.cached_tokens` (responses). The cache
|
||||
/// has worked since #11; without this the saving was invisible
|
||||
/// and every client reported a 0% hit rate.
|
||||
cached_tokens: u32,
|
||||
/// Server-measured prefill/decode timing for the request, or
|
||||
/// `None` on paths that don't measure it (CPU fallback that
|
||||
/// doesn't instrument, tests). Streaming projectors surface
|
||||
|
||||
@@ -27,8 +27,7 @@
|
||||
//! propagate without us writing any logic.
|
||||
|
||||
use cortex_core::openai::{
|
||||
ChatCompletionChoice, ChatCompletionChunk, ChatCompletionResponse, ChatMessage, ChunkChoice,
|
||||
CompletionTokensDetails, HelexaTiming, MessageContent, PromptTokensDetails, Usage,
|
||||
ChatCompletionChunk, ChunkChoice, CompletionTokensDetails, HelexaTiming, Usage,
|
||||
};
|
||||
use serde_json::json;
|
||||
use tokio::sync::mpsc;
|
||||
@@ -140,35 +139,11 @@ pub fn project_chat_stream_with(
|
||||
}
|
||||
InferenceEvent::ReasoningDelta(text) => {
|
||||
if !config.include_thinking {
|
||||
// Default path. This used to `continue` —
|
||||
// dropping the token and emitting nothing at
|
||||
// all — to keep model-internal scratchpad out
|
||||
// of naïve clients' UIs. That goal was right;
|
||||
// the method silenced the stream.
|
||||
//
|
||||
// A reasoning model can think for minutes on a
|
||||
// hard prompt, and for that whole span not one
|
||||
// SSE event went out. Clients time that out: the
|
||||
// DeepSeek Harness reports `pi-ai stream idle
|
||||
// timeout after 300000ms` and retries, so a task
|
||||
// that reasons for over five minutes could never
|
||||
// complete no matter how healthy the model was.
|
||||
// SSE comment keep-alives do not help — idle
|
||||
// timers reset on events, not comments.
|
||||
//
|
||||
// Emitting `reasoning_content` instead keeps the
|
||||
// original guarantee (it is not `content`, so
|
||||
// unaware clients still show clean output) while
|
||||
// the stream stays visibly alive, and hands
|
||||
// reasoning-aware clients the field they are
|
||||
// already looking for.
|
||||
if text.is_empty() {
|
||||
continue;
|
||||
}
|
||||
let chunk = reasoning_chunk(&id, created, &model_id, &text);
|
||||
if tx.send(chunk).await.is_err() {
|
||||
return;
|
||||
}
|
||||
// Default path — reasoning has no slot in
|
||||
// chat completions, so it's dropped. Naïve
|
||||
// clients (Zed commit-message generator,
|
||||
// any vanilla OpenAI client) get clean
|
||||
// output.
|
||||
continue;
|
||||
}
|
||||
let Some(markers) = config.reasoning_markers.as_ref() else {
|
||||
@@ -220,7 +195,6 @@ pub fn project_chat_stream_with(
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens,
|
||||
cached_tokens,
|
||||
timing,
|
||||
} => {
|
||||
// The finish_reason chunk, then an OpenAI-style
|
||||
@@ -235,12 +209,9 @@ pub fn project_chat_stream_with(
|
||||
&id,
|
||||
created,
|
||||
&model_id,
|
||||
UsageCounts {
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens,
|
||||
cached_tokens,
|
||||
},
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens,
|
||||
timing,
|
||||
),
|
||||
]
|
||||
@@ -275,35 +246,6 @@ fn role_chunk(id: &str, created: u64, model_id: &str) -> ChatCompletionChunk {
|
||||
}
|
||||
}
|
||||
|
||||
/// A reasoning delta, in the field reasoning-aware clients read.
|
||||
///
|
||||
/// `reasoning_content` is not in the OpenAI spec, but it is the
|
||||
/// de-facto slot: DeepSeek's API emits it, and so do vLLM and SGLang
|
||||
/// for reasoning models. Our own consumers already expect it —
|
||||
/// `helexa-acp`'s OpenAI provider reads `choice.delta.reasoning_content`,
|
||||
/// and `helexa-bench` times a stream's first reasoning token from it.
|
||||
///
|
||||
/// Crucially it is NOT `content`, so a client that has never heard of
|
||||
/// reasoning ignores the unknown field and sees clean output — the
|
||||
/// property the old drop-it-entirely default was protecting, kept
|
||||
/// without the silence that came with it.
|
||||
fn reasoning_chunk(id: &str, created: u64, model_id: &str, text: &str) -> ChatCompletionChunk {
|
||||
ChatCompletionChunk {
|
||||
id: id.into(),
|
||||
object: "chat.completion.chunk".into(),
|
||||
created,
|
||||
model: model_id.into(),
|
||||
choices: vec![ChunkChoice {
|
||||
index: 0,
|
||||
delta: json!({ "reasoning_content": text }),
|
||||
finish_reason: None,
|
||||
extra: serde_json::Value::Object(Default::default()),
|
||||
}],
|
||||
usage: None,
|
||||
extra: serde_json::Value::Object(Default::default()),
|
||||
}
|
||||
}
|
||||
|
||||
fn content_chunk(id: &str, created: u64, model_id: &str, text: &str) -> ChatCompletionChunk {
|
||||
ChatCompletionChunk {
|
||||
id: id.into(),
|
||||
@@ -390,32 +332,15 @@ fn final_chunk(
|
||||
/// ignore the empty-choices chunk; clients that do (opencode, and
|
||||
/// cortex's Anthropic translator) get the token counts they need to
|
||||
/// track context.
|
||||
/// The token counts a finished turn reports. Grouped rather than passed
|
||||
/// loose: adding `cached_tokens` (#269) put the list past the point
|
||||
/// where four adjacent bare `u32`s are safe to read at a call site.
|
||||
struct UsageCounts {
|
||||
prompt_tokens: u32,
|
||||
completion_tokens: u32,
|
||||
/// Sub-count of `completion_tokens` — tokens spent reasoning.
|
||||
reasoning_tokens: u32,
|
||||
/// Sub-count of `prompt_tokens` — tokens served from the prefix
|
||||
/// cache. Neither sub-count is added into `total_tokens`.
|
||||
cached_tokens: u32,
|
||||
}
|
||||
|
||||
fn usage_chunk(
|
||||
id: &str,
|
||||
created: u64,
|
||||
model_id: &str,
|
||||
counts: UsageCounts,
|
||||
prompt_tokens: u32,
|
||||
completion_tokens: u32,
|
||||
reasoning_tokens: u32,
|
||||
timing: Option<FinishTiming>,
|
||||
) -> ChatCompletionChunk {
|
||||
let UsageCounts {
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens,
|
||||
cached_tokens,
|
||||
} = counts;
|
||||
ChatCompletionChunk {
|
||||
id: id.into(),
|
||||
object: "chat.completion.chunk".into(),
|
||||
@@ -431,12 +356,7 @@ fn usage_chunk(
|
||||
completion_tokens_details: (reasoning_tokens > 0).then_some(CompletionTokensDetails {
|
||||
reasoning_tokens: reasoning_tokens as u64,
|
||||
}),
|
||||
// Prefix-cache reuse (#269). Omitted at zero so a client
|
||||
// sees unchanged JSON when nothing was cached, and so
|
||||
// "absent" stays distinguishable from "measured as none".
|
||||
prompt_tokens_details: (cached_tokens > 0).then_some(PromptTokensDetails {
|
||||
cached_tokens: cached_tokens as u64,
|
||||
}),
|
||||
prompt_tokens_details: None,
|
||||
// helexa extension (#85): server-measured prefill/decode
|
||||
// timing for the bench harness. Omitted on paths that don't
|
||||
// measure it so standard clients see unchanged JSON.
|
||||
@@ -450,379 +370,10 @@ fn usage_chunk(
|
||||
}
|
||||
}
|
||||
|
||||
/// Drain an [`InferenceEvent`] stream into a single non-streaming
|
||||
/// [`ChatCompletionResponse`] (#285).
|
||||
///
|
||||
/// Non-streaming used to be a *separate inference path* that took the
|
||||
/// per-model `inference_lock` for the whole request. That made it
|
||||
/// invisible to the batch engine (#98), so concurrent non-streaming
|
||||
/// callers serialized completely — measured on beast at 1.00x aggregate
|
||||
/// throughput across 1/2/4/8 concurrency, against 3.98x for the same
|
||||
/// work streamed. `max_in_flight` bought those requests admission and
|
||||
/// nothing else.
|
||||
///
|
||||
/// Expressing non-streaming as "run the stream, buffer the result"
|
||||
/// collapses the two paths onto one producer, so batching, prefix-cache
|
||||
/// reuse, tool-call extraction, the reasoning governor and server-side
|
||||
/// timing all apply identically to both. It also removes a second place
|
||||
/// where the same wire object could be assembled differently — the
|
||||
/// shape of defect #252 and #272 both were.
|
||||
///
|
||||
/// Reasoning is kept out of `content` — it is not the assistant's
|
||||
/// reply — but it is **returned** on `message.reasoning_content`, the
|
||||
/// same field the streaming path emits as
|
||||
/// `choice.delta.reasoning_content`.
|
||||
///
|
||||
/// It used to be discarded here (#300). That was inherited from the
|
||||
/// path this replaced and was wrong on both counts: the tokens are
|
||||
/// metered in `usage.completion_tokens_details.reasoning_tokens`, so a
|
||||
/// caller paid for text it could never see; and a client cannot replay
|
||||
/// what it never received, so on the next turn the model saw its own
|
||||
/// prior turn as a bare assertion with the reasoning that produced it
|
||||
/// deleted.
|
||||
///
|
||||
/// `finish_reason` becomes `"tool_calls"` whenever any tool call was
|
||||
/// parsed.
|
||||
///
|
||||
/// Two fields that the old path hardcoded to `None` now populate,
|
||||
/// because the events carry them and the struct already had the slots:
|
||||
/// `prompt_tokens_details.cached_tokens` and `helexa_timing`.
|
||||
///
|
||||
/// A stream that ends without a `Finish` is an error, not an empty
|
||||
/// reply: that is how a dropped engine slot or a fatal worker fault
|
||||
/// presents, and returning a 200 with partial text would hide it.
|
||||
pub async fn collect_chat_completion(
|
||||
mut rx: mpsc::Receiver<InferenceEvent>,
|
||||
id: String,
|
||||
created: u64,
|
||||
model_id: String,
|
||||
) -> Result<ChatCompletionResponse, String> {
|
||||
let mut content = String::new();
|
||||
let mut reasoning = String::new();
|
||||
let mut tool_calls: Vec<serde_json::Value> = Vec::new();
|
||||
let mut finish: Option<(FinishReason, u32, u32, u32, u32, Option<FinishTiming>)> = None;
|
||||
|
||||
while let Some(event) = rx.recv().await {
|
||||
match event {
|
||||
InferenceEvent::Start => {}
|
||||
InferenceEvent::TextDelta(t) => content.push_str(&t),
|
||||
// Kept out of `content`, returned on `reasoning_content`.
|
||||
InferenceEvent::ReasoningDelta(t) => reasoning.push_str(&t),
|
||||
InferenceEvent::ToolCall {
|
||||
index,
|
||||
id: call_id,
|
||||
name,
|
||||
arguments,
|
||||
} => tool_calls.push(json!({
|
||||
"index": index,
|
||||
"id": call_id,
|
||||
"type": "function",
|
||||
"function": { "name": name, "arguments": arguments },
|
||||
})),
|
||||
InferenceEvent::Finish {
|
||||
reason,
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens,
|
||||
cached_tokens,
|
||||
timing,
|
||||
} => {
|
||||
finish = Some((
|
||||
reason,
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
reasoning_tokens,
|
||||
cached_tokens,
|
||||
timing,
|
||||
));
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let Some((reason, prompt_tokens, completion_tokens, reasoning_tokens, cached_tokens, timing)) =
|
||||
finish
|
||||
else {
|
||||
return Err(
|
||||
"inference stream ended without a finish event (engine slot dropped?)".to_string(),
|
||||
);
|
||||
};
|
||||
|
||||
// A parsed tool call outranks whatever the sampler stopped on, so a
|
||||
// model that emits a call and then hits EOS still reports
|
||||
// `tool_calls` and the client dispatches instead of rendering.
|
||||
let finish_reason = if tool_calls.is_empty() {
|
||||
reason.as_openai_str().to_string()
|
||||
} else {
|
||||
"tool_calls".to_string()
|
||||
};
|
||||
let mut message_extra = serde_json::Map::new();
|
||||
if !tool_calls.is_empty() {
|
||||
message_extra.insert("tool_calls".into(), json!(tool_calls));
|
||||
}
|
||||
// Absent rather than empty when the model did not think: a
|
||||
// non-reasoning model must keep the unchanged message shape.
|
||||
if !reasoning.is_empty() {
|
||||
message_extra.insert("reasoning_content".into(), json!(reasoning));
|
||||
}
|
||||
let message_extra = serde_json::Value::Object(message_extra);
|
||||
|
||||
Ok(ChatCompletionResponse {
|
||||
id,
|
||||
object: "chat.completion".into(),
|
||||
created,
|
||||
model: model_id,
|
||||
choices: vec![ChatCompletionChoice {
|
||||
index: 0,
|
||||
message: ChatMessage {
|
||||
role: "assistant".into(),
|
||||
content: MessageContent::Text(content),
|
||||
extra: message_extra,
|
||||
},
|
||||
finish_reason: Some(finish_reason),
|
||||
extra: serde_json::Value::Object(Default::default()),
|
||||
}],
|
||||
usage: Some(Usage {
|
||||
prompt_tokens: prompt_tokens as u64,
|
||||
completion_tokens: completion_tokens as u64,
|
||||
total_tokens: (prompt_tokens + completion_tokens) as u64,
|
||||
completion_tokens_details: (reasoning_tokens > 0).then_some(CompletionTokensDetails {
|
||||
reasoning_tokens: reasoning_tokens as u64,
|
||||
}),
|
||||
prompt_tokens_details: (cached_tokens > 0).then_some(PromptTokensDetails {
|
||||
cached_tokens: cached_tokens as u64,
|
||||
}),
|
||||
helexa_timing: timing.map(|t| HelexaTiming {
|
||||
prefill_ms: t.prefill_ms as u64,
|
||||
decode_ms: t.decode_ms as u64,
|
||||
prefill_tokens: t.prefill_tokens as u64,
|
||||
}),
|
||||
}),
|
||||
extra: serde_json::Value::Object(Default::default()),
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
|
||||
/// The model's think block must come back on the non-streaming
|
||||
/// path too (#300).
|
||||
///
|
||||
/// It used to be dropped here while the streaming path emitted it
|
||||
/// as `choice.delta.reasoning_content`. The tokens were metered
|
||||
/// either way, so a non-streaming caller paid for text it could
|
||||
/// never see — and, worse, could not replay the model's reasoning
|
||||
/// on the next turn, leaving the model to face its own prior turn
|
||||
/// as a bare assertion.
|
||||
#[tokio::test]
|
||||
async fn non_streaming_returns_the_models_reasoning() {
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(8);
|
||||
tx.send(InferenceEvent::Start).await.unwrap();
|
||||
tx.send(InferenceEvent::ReasoningDelta(
|
||||
"weighing the options".into(),
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
tx.send(InferenceEvent::TextDelta("the answer".into()))
|
||||
.await
|
||||
.unwrap();
|
||||
tx.send(InferenceEvent::Finish {
|
||||
reason: FinishReason::Stop,
|
||||
prompt_tokens: 5,
|
||||
completion_tokens: 7,
|
||||
reasoning_tokens: 3,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
drop(tx);
|
||||
|
||||
let r = collect_chat_completion(rx, "id".into(), 0, "m".into())
|
||||
.await
|
||||
.expect("collect");
|
||||
let msg = &r.choices[0].message;
|
||||
assert_eq!(
|
||||
msg.extra["reasoning_content"], "weighing the options",
|
||||
"reasoning must be returned, not discarded"
|
||||
);
|
||||
// And it must NOT be folded into the visible reply.
|
||||
assert!(
|
||||
matches!(&msg.content, MessageContent::Text(t) if t == "the answer"),
|
||||
"reasoning leaked into content"
|
||||
);
|
||||
}
|
||||
|
||||
/// A non-reasoning model must keep the unchanged message shape —
|
||||
/// absent, not an empty string.
|
||||
#[tokio::test]
|
||||
async fn no_reasoning_means_no_reasoning_field() {
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(8);
|
||||
tx.send(InferenceEvent::Start).await.unwrap();
|
||||
tx.send(InferenceEvent::TextDelta("plain".into()))
|
||||
.await
|
||||
.unwrap();
|
||||
tx.send(InferenceEvent::Finish {
|
||||
reason: FinishReason::Stop,
|
||||
prompt_tokens: 1,
|
||||
completion_tokens: 1,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
drop(tx);
|
||||
let r = collect_chat_completion(rx, "id".into(), 0, "m".into())
|
||||
.await
|
||||
.expect("collect");
|
||||
assert!(
|
||||
r.choices[0]
|
||||
.message
|
||||
.extra
|
||||
.get("reasoning_content")
|
||||
.is_none()
|
||||
);
|
||||
}
|
||||
use super::*;
|
||||
|
||||
// ── Non-streaming collector (#285) ────────────────────────────
|
||||
|
||||
async fn collect_from(events: Vec<InferenceEvent>) -> Result<ChatCompletionResponse, String> {
|
||||
let (tx, rx) = mpsc::channel(64);
|
||||
for e in events {
|
||||
tx.send(e).await.expect("send");
|
||||
}
|
||||
drop(tx);
|
||||
collect_chat_completion(rx, "chatcmpl-test".into(), 1_700_000_000, "m".into()).await
|
||||
}
|
||||
|
||||
fn finish(reason: FinishReason) -> InferenceEvent {
|
||||
InferenceEvent::Finish {
|
||||
reason,
|
||||
prompt_tokens: 10,
|
||||
completion_tokens: 4,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn collector_concatenates_text_deltas() {
|
||||
let r = collect_from(vec![
|
||||
InferenceEvent::Start,
|
||||
InferenceEvent::TextDelta("hel".into()),
|
||||
InferenceEvent::TextDelta("lo".into()),
|
||||
finish(FinishReason::Stop),
|
||||
])
|
||||
.await
|
||||
.expect("collected");
|
||||
let c = &r.choices[0];
|
||||
assert!(matches!(&c.message.content, MessageContent::Text(t) if t == "hello"));
|
||||
assert_eq!(c.finish_reason.as_deref(), Some("stop"));
|
||||
assert_eq!(r.object, "chat.completion");
|
||||
}
|
||||
|
||||
/// Reasoning is counted but never rendered — the behaviour of the
|
||||
/// path this replaced. A regression here would leak scratchpad into
|
||||
/// `content` for every non-streaming caller.
|
||||
#[tokio::test]
|
||||
async fn collector_drops_reasoning_text_but_keeps_the_count() {
|
||||
let (tx, rx) = mpsc::channel(64);
|
||||
tx.send(InferenceEvent::ReasoningDelta("secret".into()))
|
||||
.await
|
||||
.expect("send");
|
||||
tx.send(InferenceEvent::TextDelta("answer".into()))
|
||||
.await
|
||||
.expect("send");
|
||||
tx.send(InferenceEvent::Finish {
|
||||
reason: FinishReason::Stop,
|
||||
prompt_tokens: 10,
|
||||
completion_tokens: 9,
|
||||
reasoning_tokens: 5,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
.expect("send");
|
||||
drop(tx);
|
||||
let r = collect_chat_completion(rx, "id".into(), 1, "m".into())
|
||||
.await
|
||||
.expect("collected");
|
||||
let c = &r.choices[0];
|
||||
assert!(matches!(&c.message.content, MessageContent::Text(t) if t == "answer"));
|
||||
let u = r.usage.expect("usage");
|
||||
assert_eq!(
|
||||
u.completion_tokens_details
|
||||
.expect("details")
|
||||
.reasoning_tokens,
|
||||
5
|
||||
);
|
||||
}
|
||||
|
||||
/// A parsed tool call outranks the sampler's stop reason, matching
|
||||
/// the streaming projector.
|
||||
#[tokio::test]
|
||||
async fn collector_promotes_finish_reason_to_tool_calls() {
|
||||
let r = collect_from(vec![
|
||||
InferenceEvent::ToolCall {
|
||||
index: 0,
|
||||
id: "call_1".into(),
|
||||
name: "read_file".into(),
|
||||
arguments: r#"{"path":"a.txt"}"#.into(),
|
||||
},
|
||||
finish(FinishReason::Stop),
|
||||
])
|
||||
.await
|
||||
.expect("collected");
|
||||
let c = &r.choices[0];
|
||||
assert_eq!(c.finish_reason.as_deref(), Some("tool_calls"));
|
||||
let calls = c.message.extra.get("tool_calls").expect("tool_calls");
|
||||
assert_eq!(calls[0]["function"]["name"], "read_file");
|
||||
assert_eq!(calls[0]["type"], "function");
|
||||
assert_eq!(calls[0]["id"], "call_1");
|
||||
}
|
||||
|
||||
/// cached_tokens and helexa_timing were hardcoded to `None` on the
|
||||
/// old non-streaming path; the events carried them all along.
|
||||
#[tokio::test]
|
||||
async fn collector_surfaces_cached_tokens_and_timing() {
|
||||
let (tx, rx) = mpsc::channel(8);
|
||||
tx.send(InferenceEvent::Finish {
|
||||
reason: FinishReason::Stop,
|
||||
prompt_tokens: 100,
|
||||
completion_tokens: 5,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 64,
|
||||
timing: Some(FinishTiming {
|
||||
prefill_ms: 12,
|
||||
decode_ms: 34,
|
||||
prefill_tokens: 100,
|
||||
}),
|
||||
})
|
||||
.await
|
||||
.expect("send");
|
||||
drop(tx);
|
||||
let r = collect_chat_completion(rx, "id".into(), 1, "m".into())
|
||||
.await
|
||||
.expect("collected");
|
||||
let u = r.usage.expect("usage");
|
||||
assert_eq!(u.prompt_tokens_details.expect("details").cached_tokens, 64);
|
||||
let t = u.helexa_timing.expect("timing");
|
||||
assert_eq!((t.prefill_ms, t.decode_ms, t.prefill_tokens), (12, 34, 100));
|
||||
}
|
||||
|
||||
/// A dropped engine slot ends the channel with no Finish. Returning
|
||||
/// a 200 with partial text would hide a fatal worker fault.
|
||||
#[tokio::test]
|
||||
async fn collector_errors_when_the_stream_ends_without_finish() {
|
||||
let err = collect_from(vec![InferenceEvent::TextDelta("partial".into())])
|
||||
.await
|
||||
.expect_err("must not succeed");
|
||||
assert!(err.contains("without a finish"), "unexpected: {err}");
|
||||
}
|
||||
|
||||
/// Drain the projection's output into a Vec for assertion.
|
||||
async fn collect(mut rx: mpsc::Receiver<ChatCompletionChunk>) -> Vec<ChatCompletionChunk> {
|
||||
let mut out = Vec::new();
|
||||
@@ -854,7 +405,6 @@ mod tests {
|
||||
prompt_tokens: 0,
|
||||
completion_tokens: 0,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
@@ -893,7 +443,6 @@ mod tests {
|
||||
prompt_tokens: 128,
|
||||
completion_tokens: 64,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: Some(FinishTiming {
|
||||
prefill_ms: 200,
|
||||
decode_ms: 1500,
|
||||
@@ -918,73 +467,6 @@ mod tests {
|
||||
assert_eq!(timing.prefill_tokens, 128);
|
||||
}
|
||||
|
||||
/// A cache hit must reach the caller (#269).
|
||||
///
|
||||
/// Prefix caching has worked since #11 — neuron logs `reused=2068`
|
||||
/// on prefills — but nothing carried the number onto the wire, so
|
||||
/// every client reported a 0% hit rate on a cache that was saving
|
||||
/// real prefill. dsh showed `Cache hit 0%` against a 42.1K-token
|
||||
/// context, and an agentic harness that believes nothing is cached
|
||||
/// may restructure the very prefix that was being reused.
|
||||
#[tokio::test]
|
||||
async fn cached_tokens_reach_the_usage_chunk() {
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
|
||||
let out_rx = project_chat_stream(rx, "id".into(), 1, "m".into());
|
||||
tx.send(InferenceEvent::Finish {
|
||||
reason: FinishReason::Stop,
|
||||
prompt_tokens: 7413,
|
||||
completion_tokens: 12,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 2068,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
drop(tx);
|
||||
|
||||
let out = collect(out_rx).await;
|
||||
let usage = out
|
||||
.iter()
|
||||
.find_map(|c| c.usage.as_ref())
|
||||
.expect("usage chunk present");
|
||||
let details = usage
|
||||
.prompt_tokens_details
|
||||
.as_ref()
|
||||
.expect("prompt_tokens_details populated when the cache was hit");
|
||||
assert_eq!(details.cached_tokens, 2068);
|
||||
// A sub-count of prompt_tokens, never added into the total —
|
||||
// otherwise a cache hit would inflate what a caller is billed.
|
||||
assert_eq!(usage.prompt_tokens, 7413);
|
||||
assert_eq!(usage.total_tokens, 7425);
|
||||
}
|
||||
|
||||
/// No reuse means no `prompt_tokens_details` at all, so a client
|
||||
/// sees byte-identical JSON to before this landed — and "absent"
|
||||
/// stays distinguishable from "measured as zero".
|
||||
#[tokio::test]
|
||||
async fn no_cache_hit_omits_the_details_object() {
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
|
||||
let out_rx = project_chat_stream(rx, "id".into(), 1, "m".into());
|
||||
tx.send(InferenceEvent::Finish {
|
||||
reason: FinishReason::Stop,
|
||||
prompt_tokens: 10,
|
||||
completion_tokens: 1,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
drop(tx);
|
||||
|
||||
let usage = collect(out_rx)
|
||||
.await
|
||||
.iter()
|
||||
.find_map(|c| c.usage.clone())
|
||||
.expect("usage chunk present");
|
||||
assert!(usage.prompt_tokens_details.is_none());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn empty_text_delta_is_dropped() {
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
|
||||
@@ -1006,7 +488,6 @@ mod tests {
|
||||
prompt_tokens: 0,
|
||||
completion_tokens: 0,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
@@ -1019,24 +500,10 @@ mod tests {
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
/// Reasoning is streamed as `reasoning_content`, never as `content`.
|
||||
///
|
||||
/// Both halves matter. Keeping it out of `content` is what stops
|
||||
/// scratchpad material appearing in the UI of a client that has
|
||||
/// never heard of reasoning — the guarantee the previous
|
||||
/// drop-everything default provided.
|
||||
///
|
||||
/// But emitting *something* is what keeps the connection alive. A
|
||||
/// model can think for minutes; while it did, this projection sent
|
||||
/// no events at all, and clients closed the stream as dead. The
|
||||
/// DeepSeek Harness reports `pi-ai stream idle timeout after
|
||||
/// 300000ms`, so any task whose reasoning outlasts the client's
|
||||
/// idle timeout could never complete. SSE comment keep-alives do
|
||||
/// not help, because idle timers reset on events, not comments.
|
||||
async fn reasoning_delta_is_streamed_as_reasoning_content() {
|
||||
async fn reasoning_delta_is_dropped_in_chat_projection() {
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
|
||||
let out_rx = project_chat_stream(rx, "id".into(), 1, "m".into());
|
||||
tx.send(InferenceEvent::ReasoningDelta("pondering".into()))
|
||||
tx.send(InferenceEvent::ReasoningDelta("<think>".into()))
|
||||
.await
|
||||
.unwrap();
|
||||
tx.send(InferenceEvent::TextDelta("real".into()))
|
||||
@@ -1044,27 +511,8 @@ mod tests {
|
||||
.unwrap();
|
||||
drop(tx);
|
||||
let out = collect(out_rx).await;
|
||||
assert_eq!(out.len(), 2, "reasoning must produce a chunk, not silence");
|
||||
assert_eq!(out[0].choices[0].delta["reasoning_content"], "pondering");
|
||||
assert!(
|
||||
out[0].choices[0].delta.get("content").is_none(),
|
||||
"reasoning must never arrive as content"
|
||||
);
|
||||
assert_eq!(out[1].choices[0].delta["content"], "real");
|
||||
}
|
||||
|
||||
/// An empty reasoning delta is still nothing to say — it must not
|
||||
/// manufacture a chunk, matching the text path.
|
||||
#[tokio::test]
|
||||
async fn empty_reasoning_delta_is_dropped() {
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
|
||||
let out_rx = project_chat_stream(rx, "id".into(), 1, "m".into());
|
||||
tx.send(InferenceEvent::ReasoningDelta(String::new()))
|
||||
.await
|
||||
.unwrap();
|
||||
drop(tx);
|
||||
let out = collect(out_rx).await;
|
||||
assert!(out.is_empty(), "empty reasoning deltas produce no chunks");
|
||||
assert_eq!(out.len(), 1);
|
||||
assert_eq!(out[0].choices[0].delta["content"], "real");
|
||||
}
|
||||
|
||||
fn pair() -> ReasoningTokenPair {
|
||||
@@ -1103,7 +551,6 @@ mod tests {
|
||||
prompt_tokens: 0,
|
||||
completion_tokens: 0,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
@@ -1156,7 +603,6 @@ mod tests {
|
||||
prompt_tokens: 0,
|
||||
completion_tokens: 0,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
@@ -1203,7 +649,6 @@ mod tests {
|
||||
prompt_tokens: 0,
|
||||
completion_tokens: 0,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
@@ -1222,12 +667,10 @@ mod tests {
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
/// With the flag off, reasoning stays out of `content` whether or
|
||||
/// not markers are configured — the flag is the gate, not the
|
||||
/// marker presence. It now travels as `reasoning_content` instead
|
||||
/// of being discarded, so this asserts the containment guarantee
|
||||
/// only: nothing model-internal reaches a naive client's `content`.
|
||||
async fn include_thinking_off_keeps_reasoning_out_of_content() {
|
||||
async fn include_thinking_off_drops_reasoning_even_with_markers() {
|
||||
// Default behaviour even when markers happen to be
|
||||
// configured. The flag is the gate, not the marker
|
||||
// presence.
|
||||
let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
|
||||
let out_rx = project_chat_stream_with(
|
||||
rx,
|
||||
@@ -1250,7 +693,6 @@ mod tests {
|
||||
prompt_tokens: 0,
|
||||
completion_tokens: 0,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
@@ -1279,7 +721,6 @@ mod tests {
|
||||
prompt_tokens: 42,
|
||||
completion_tokens: 5,
|
||||
reasoning_tokens: 2,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
@@ -1314,7 +755,6 @@ mod tests {
|
||||
prompt_tokens: 10,
|
||||
completion_tokens: 7,
|
||||
reasoning_tokens: 0,
|
||||
cached_tokens: 0,
|
||||
timing: None,
|
||||
})
|
||||
.await
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -29,8 +29,6 @@ async fn test_load_default_models_skips_unknown_harness() {
|
||||
quant: None,
|
||||
tensor_parallel: None,
|
||||
devices: None,
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
},
|
||||
ModelSpec {
|
||||
model_id: "model-b".into(),
|
||||
@@ -38,8 +36,6 @@ async fn test_load_default_models_skips_unknown_harness() {
|
||||
quant: None,
|
||||
tensor_parallel: None,
|
||||
devices: None,
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
},
|
||||
];
|
||||
|
||||
@@ -99,8 +95,6 @@ async fn test_load_default_models_skipped_on_driver_mismatch() {
|
||||
quant: Some("q6k".into()),
|
||||
tensor_parallel: Some(2),
|
||||
devices: None,
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
}];
|
||||
let activation = ActivationTracker::new(&specs);
|
||||
let reason = "host NVIDIA driver/library mismatch (userspace NVML 580.159 vs loaded \
|
||||
@@ -202,8 +196,6 @@ fn qwen_spec() -> ModelSpec {
|
||||
quant: None,
|
||||
tensor_parallel: None,
|
||||
devices: None,
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -53,8 +53,6 @@ async fn test_candle_qwen3_load_unload_lifecycle() {
|
||||
quant: Some(quant),
|
||||
tensor_parallel: None,
|
||||
devices: Some(vec![0]),
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
};
|
||||
|
||||
registry
|
||||
|
||||
@@ -1,170 +0,0 @@
|
||||
{%- set image_count = namespace(value=0) %}
|
||||
{%- set video_count = namespace(value=0) %}
|
||||
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
||||
{%- if content is string %}
|
||||
{{- content }}
|
||||
{%- elif content is iterable and content is not mapping %}
|
||||
{%- for item in content %}
|
||||
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
||||
{%- if is_system_content %}
|
||||
{{- raise_exception('System message cannot contain images.') }}
|
||||
{%- endif %}
|
||||
{%- if do_vision_count %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- endif %}
|
||||
{%- if add_vision_id %}
|
||||
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
||||
{%- endif %}
|
||||
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
||||
{%- elif 'video' in item or item.type == 'video' %}
|
||||
{%- if is_system_content %}
|
||||
{{- raise_exception('System message cannot contain videos.') }}
|
||||
{%- endif %}
|
||||
{%- if do_vision_count %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- endif %}
|
||||
{%- if add_vision_id %}
|
||||
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
||||
{%- endif %}
|
||||
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
||||
{%- elif 'text' in item %}
|
||||
{{- item.text }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unexpected item type in content.') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- elif content is none or content is undefined %}
|
||||
{{- '' }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unexpected content type.') }}
|
||||
{%- endif %}
|
||||
{%- endmacro %}
|
||||
{%- if not messages %}
|
||||
{{- raise_exception('No messages provided.') }}
|
||||
{%- endif %}
|
||||
{%- set reasoning_instructions = '' %}
|
||||
{%- if enable_thinking is undefined or enable_thinking is true %}
|
||||
{%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
|
||||
{%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
|
||||
{{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
|
||||
{%- endif %}
|
||||
{%- if resolved_reasoning_effort == 'xhigh' %}
|
||||
{%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
|
||||
{%- elif resolved_reasoning_effort == 'low' %}
|
||||
{%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if tools and tools is iterable and tools is not mapping %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if reasoning_instructions %}
|
||||
{{- reasoning_instructions + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>" }}
|
||||
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
||||
{%- if content %}
|
||||
{{- '\n\n' + content }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
||||
{%- if content %}
|
||||
{{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
|
||||
{%- elif reasoning_instructions %}
|
||||
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- elif reasoning_instructions %}
|
||||
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" %}
|
||||
{%- set content = render_content(message.content, false)|trim %}
|
||||
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if ns.multi_step_tool %}
|
||||
{{- raise_exception('No user query found in messages.') }}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- set content = render_content(message.content, true)|trim %}
|
||||
{%- if message.role == "system" %}
|
||||
{%- if not loop.first %}
|
||||
{{- raise_exception('System message must be at the beginning.') }}
|
||||
{%- endif %}
|
||||
{%- elif message.role == "user" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- endif %}
|
||||
{%- set reasoning_content = reasoning_content|trim %}
|
||||
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{%- if loop.first %}
|
||||
{%- if content|trim %}
|
||||
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
||||
{%- else %}
|
||||
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.arguments is defined and tool_call.arguments != '' %}
|
||||
{%- for args_name, args_value in tool_call.arguments|items %}
|
||||
{{- '<parameter=' + args_name + '>\n' }}
|
||||
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
||||
{{- args_value }}
|
||||
{{- '\n</parameter>\n' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif loop.last %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unexpected message role.') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- else %}
|
||||
{{- '<think>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
@@ -60,9 +60,7 @@ fn read_f32(path: &Path) -> Vec<f32> {
|
||||
let bytes = std::fs::read(path).unwrap_or_else(|e| panic!("read {path:?}: {e}"));
|
||||
assert!(bytes.len().is_multiple_of(4), "truncated f32 file {path:?}");
|
||||
bytes
|
||||
.as_chunks::<4>()
|
||||
.0
|
||||
.iter()
|
||||
.chunks_exact(4)
|
||||
.map(|b| f32::from_le_bytes([b[0], b[1], b[2], b[3]]))
|
||||
.collect()
|
||||
}
|
||||
|
||||
@@ -106,8 +106,6 @@ fn spec(model_id: &str, tp: Option<u32>, quant: Option<&str>) -> ModelSpec {
|
||||
quant: quant.map(String::from),
|
||||
tensor_parallel: tp,
|
||||
devices: None,
|
||||
sampling: None,
|
||||
preserve_thinking: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -37,9 +37,7 @@ fn fixture_dir() -> PathBuf {
|
||||
fn read_f32(path: &Path) -> Vec<f32> {
|
||||
let bytes = std::fs::read(path).unwrap_or_else(|e| panic!("read {path:?}: {e}"));
|
||||
bytes
|
||||
.as_chunks::<4>()
|
||||
.0
|
||||
.iter()
|
||||
.chunks_exact(4)
|
||||
.map(|c| f32::from_le_bytes([c[0], c[1], c[2], c[3]]))
|
||||
.collect()
|
||||
}
|
||||
|
||||
@@ -2,22 +2,6 @@
|
||||
Description=Neuron — per-node GPU discovery and harness daemon for cortex
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
# Start-limit bound for the self-restart path (#265). When a TP forward
|
||||
# wedges and the NCCL abort that would unblock it also hangs, neuron
|
||||
# exits 70 so Restart=on-failure recovers it in seconds instead of the
|
||||
# 70-minute outage that needed a human on 2026-08-17.
|
||||
#
|
||||
# That only helps if the wedge is transient. A deterministic one — a bad
|
||||
# build, a sick card, a model that wedges on load — would otherwise
|
||||
# restart forever, and a flapping node is WORSE than a down one: cortex
|
||||
# marks it healthy between restarts and keeps routing to it, so every
|
||||
# client sees intermittent failures instead of one node cleanly out.
|
||||
#
|
||||
# Four failures in ten minutes stops the unit and leaves it `failed`,
|
||||
# where `systemctl status` and an alert can see it. Visibly broken beats
|
||||
# invisibly cycling.
|
||||
StartLimitIntervalSec=600
|
||||
StartLimitBurst=4
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
@@ -40,11 +24,6 @@ TimeoutStartSec=1800s
|
||||
# On stop, neuron drains in-flight requests then unloads every model
|
||||
# to release CUDA contexts cleanly. Allow generous time for big-model
|
||||
# unloads; systemd will SIGKILL after this bound.
|
||||
#
|
||||
# Note this bound does NOT apply to the self-restart path (#265): a
|
||||
# wedged process exits directly rather than draining, precisely because
|
||||
# draining cannot work when the collective is stuck — and waiting this
|
||||
# out would add two minutes to an outage that is already total.
|
||||
TimeoutStopSec=120s
|
||||
KillSignal=SIGTERM
|
||||
|
||||
|
||||
@@ -35,7 +35,7 @@ default_endpoint = "helexa"
|
||||
name = "helexa"
|
||||
base_url = "http://hanzalova.internal:31313/v1"
|
||||
wire_api = "openai-chat"
|
||||
default_model = "Qwen/Qwen3.8-27B"
|
||||
default_model = "Qwen/Qwen3.6-27B"
|
||||
max_tokens = 8192
|
||||
# Compaction kicks in when the rolling history grows past this token
|
||||
# budget. Set to your model's context window. Disable by removing
|
||||
|
||||
@@ -23,7 +23,7 @@ listen = "0.0.0.0:8088"
|
||||
#
|
||||
# [aliases]
|
||||
# "helexa/small" = "Qwen/Qwen3-8B"
|
||||
# "helexa/balanced" = "Qwen/Qwen3.8-27B"
|
||||
# "helexa/balanced" = "Qwen/Qwen3.6-27B"
|
||||
|
||||
# -- Downstream cortexes -------------------------------------------------
|
||||
# Each [[cortexes]] entry is an operator-run cortex the router may dispatch
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# MANAGED BY CI — .gitea/workflows/deploy.yml is the only writer.
|
||||
#
|
||||
# Edits made directly to the deployed copy on gallumbits are reverted by
|
||||
# the next deploy, and until then the fleet runs something no commit
|
||||
# describes. Change it here, commit, let the pipeline ship it.
|
||||
# ─────────────────────────────────────────────────────────────────────
|
||||
# helexa-router — federation data plane on gallumbits.
|
||||
#
|
||||
# Tracked despite living beside the secret-bearing service configs,
|
||||
# because it holds no secrets: a listen address, the product-tier
|
||||
# aliases, and a mesh endpoint. Being untracked cost an outage on
|
||||
# 2026-08-27 — `helexa/balanced` still resolved to Qwen/Qwen3.6-27B
|
||||
# after that model had been retired from the catalogue, so every
|
||||
# authenticated web-chat turn evicted beast's resident flagship and
|
||||
# cold-loaded a model nobody had asked for. Nothing could diff the two
|
||||
# files, so nothing did.
|
||||
#
|
||||
# `script/check-alias-targets.py` now fails CI if any alias below names
|
||||
# a model that models.toml does not define.
|
||||
|
||||
[router]
|
||||
listen = "0.0.0.0:8088"
|
||||
poll_interval_secs = 10
|
||||
region = "eu-central"
|
||||
|
||||
# Product tiers → real model ids (#166). The SPA sends the tier names.
|
||||
[aliases]
|
||||
"helexa/small" = "Qwen/Qwen3-8B"
|
||||
"helexa/balanced" = "Qwen/Qwen3.8-27B"
|
||||
|
||||
# hanzalova operator cortex, plaintext over the WireGuard mesh (the mesh
|
||||
# is the trust boundary; no TLS pin needed for http://).
|
||||
[[cortexes]]
|
||||
name = "hanzalova"
|
||||
endpoint = "http://hanzalova.internal:31313"
|
||||
region = "eu-central"
|
||||
@@ -19,7 +19,7 @@ gateway.
|
||||
|
||||
```
|
||||
┌──────────────┐
|
||||
clients ────▶│ cortex │ :31313 API, :31314 metrics
|
||||
clients ─────▶│ cortex │ :31313 API, :31314 metrics
|
||||
└──┬────┬────┬─┘
|
||||
│ │ │
|
||||
┌────▼┐ ┌─▼──┐ ┌▼────┐
|
||||
|
||||
@@ -44,70 +44,6 @@ change.
|
||||
VRAM fragmentation has had time to accumulate. It is a signal to restart
|
||||
that neuron, not an automatic action.
|
||||
|
||||
## secrets.toml
|
||||
|
||||
Credentials do not belong in the file CI deploys. Put them in a
|
||||
`secrets.toml` beside the main config and the service will merge it
|
||||
last, so its values win:
|
||||
|
||||
```
|
||||
/etc/cortex/cortex.toml structure — deployed by CI, safe to diff
|
||||
/etc/cortex/secrets.toml credentials — yours, root-only, never in git
|
||||
```
|
||||
|
||||
```toml
|
||||
# /etc/cortex/secrets.toml (root:cortex 0640)
|
||||
[[entitlements.keys]]
|
||||
key = "sk-…"
|
||||
account_id = "acct-a"
|
||||
key_id = "a"
|
||||
|
||||
[upstream]
|
||||
bearer = "…"
|
||||
```
|
||||
|
||||
`helexa-upstream` and `helexa-angels` read a `secrets.toml` beside their
|
||||
own configs the same way — the DB URL, JWT secret and SMTP URL belong
|
||||
there.
|
||||
|
||||
**An absent `secrets.toml` is not an error.** A single-file deployment
|
||||
keeps working exactly as before, so this is opt-in per host and can be
|
||||
adopted one service at a time.
|
||||
|
||||
### Why bother
|
||||
|
||||
Because a config CI cannot write is a config no check can defend, and
|
||||
the cost of that is not hypothetical. `helexa-router.toml` was kept out
|
||||
of git for sitting beside secret-bearing files. Nothing could diff it
|
||||
against the catalogue, so its `helexa/balanced` alias went on pointing
|
||||
at a model that had been retired — and since both models were
|
||||
deliberately given equal residency priority so they could displace each
|
||||
other, every authenticated chat turn evicted the resident flagship to
|
||||
cold-load the retired one. Four of those overlapped and the node ended
|
||||
up holding 32 GB of GPU memory with no model loaded and nothing
|
||||
serving.
|
||||
|
||||
Splitting secrets from structure is what lets the structure be
|
||||
version-controlled, reviewed and checked. The ordering matters too: the
|
||||
operator's file merges last, so a deploy can never replace a live
|
||||
credential with a placeholder.
|
||||
|
||||
### Moving existing secrets
|
||||
|
||||
One-time, per host, and reversible — the service reads both files, so
|
||||
you can move a value and restart before moving the next:
|
||||
|
||||
1. Create `secrets.toml` beside the config, owned `root:<service>` mode
|
||||
`0640` (`0600` where the service runs as root).
|
||||
2. Move the credential blocks across. Leave everything else in place.
|
||||
3. Restart the service and confirm it still authenticates — for cortex,
|
||||
a request with a real key should be billed rather than treated as
|
||||
anonymous.
|
||||
4. Delete the moved lines from the main file only once step 3 passes.
|
||||
|
||||
Until step 4 the value exists in both files, which is safe: the
|
||||
operator's copy wins.
|
||||
|
||||
## models.toml
|
||||
|
||||
The catalogue says what each model needs and where it may run:
|
||||
@@ -142,7 +78,7 @@ Clients should not hardcode model ids. Aliases let them ask for a role:
|
||||
[aliases]
|
||||
"helexa/small" = "Qwen/Qwen3-1.7B"
|
||||
"helexa/balanced" = "Qwen/Qwen3-8B"
|
||||
"helexa/large" = "Qwen/Qwen3.8-27B"
|
||||
"helexa/large" = "Qwen/Qwen3.6-27B"
|
||||
"helexa/image" = "Tongyi-MAI/Z-Image-Turbo"
|
||||
```
|
||||
|
||||
|
||||
@@ -58,32 +58,6 @@ Two things that bite:
|
||||
- **Cold loads are disk-bound.** A 50 GB model off spinning rust is a
|
||||
very different experience from the same model on NVMe.
|
||||
|
||||
### Where weights come from
|
||||
|
||||
By default a bare `org/name` id is fetched from HuggingFace. Operators
|
||||
running a mirror, or serving models from more than one place, can
|
||||
declare sources explicitly:
|
||||
|
||||
```toml
|
||||
[harness.candle]
|
||||
default_source = "huggingface"
|
||||
|
||||
[harness.candle.sources.huggingface]
|
||||
endpoint = "https://huggingface.co"
|
||||
auth_env = "HF_TOKEN" # env var name, never the token itself
|
||||
cache_dir = "/archive/llm" # optional; per-source cache
|
||||
```
|
||||
|
||||
`auth_env` names an environment variable rather than holding a token, so
|
||||
credentials stay out of the config file — worth keeping to even when the
|
||||
file is not obviously shared, because config is exactly what gets copied
|
||||
between hosts.
|
||||
|
||||
Give a source its own `cache_dir` when two sources can serve the same
|
||||
`org/name`. The cache tree is keyed on the model id alone, so sharing a
|
||||
directory between sources that disagree about what `org/name` means will
|
||||
collide on disk.
|
||||
|
||||
## Default models
|
||||
|
||||
Models listed as defaults load when the daemon activates, so the host
|
||||
@@ -92,7 +66,7 @@ load cost:
|
||||
|
||||
```toml
|
||||
[[default_models]]
|
||||
model_id = "Qwen/Qwen3.8-27B"
|
||||
model_id = "Qwen/Qwen3.6-27B"
|
||||
harness = "candle"
|
||||
quant = "q6k"
|
||||
tensor_parallel = 2
|
||||
@@ -117,17 +91,10 @@ Each loaded model has bounded admission control:
|
||||
[harness.candle.admission]
|
||||
max_in_flight = 8 # concurrent requests actually running
|
||||
max_queue_depth = 8 # waiting before rejection
|
||||
max_wait_secs = 30 # how long a queued request waits for a slot
|
||||
kv_max_wait_secs = 300 # how long it waits for enough KV budget
|
||||
max_wait_secs = 30 # how long a queued request waits
|
||||
max_per_principal = 2 # fair share, so one caller cannot monopolise
|
||||
```
|
||||
|
||||
`kv_max_wait_secs` is deliberately much longer than `max_wait_secs`.
|
||||
The first waits for a slot to turn over; the second waits for a whole
|
||||
long-context sequence to finish, which on a 27B can be minutes. A
|
||||
request that needs KV budget nobody has yet is not a request to reject
|
||||
in thirty seconds.
|
||||
|
||||
Over-capacity requests are rejected promptly with `429`/`503` and a
|
||||
`Retry-After` rather than being allowed to queue invisibly. A fast
|
||||
rejection a client can retry is far better than a request that hangs
|
||||
@@ -135,82 +102,18 @@ until something times out.
|
||||
|
||||
`max_in_flight` above 1 enables batched decode on architectures that
|
||||
support it, so concurrent requests share a decode step instead of
|
||||
serialising.
|
||||
|
||||
**`max_in_flight` does not partition the KV budget.** KV is a shared
|
||||
pool, and each request reserves what its own prompt actually needs when
|
||||
it is admitted — which is why `kv_max_wait_secs` above exists at all. A
|
||||
request larger than what is currently free waits for bytes to come back
|
||||
rather than being handed a fixed 1/N slice, and a single long session
|
||||
can legitimately hold most of the pool.
|
||||
|
||||
So the slot count and the context window are separate questions. What
|
||||
bounds a busy moment is the pool: divide `kv_budget_mb` by the model's
|
||||
KV cost per token (`GET /health` reports both) to see how many tokens
|
||||
are available to share. Many ordinary chat turns fit at once; a few very
|
||||
long agentic sessions will queue on bytes.
|
||||
|
||||
Size `max_in_flight` against the concurrency you actually want to serve
|
||||
concurrently, not against context. Anything above it queues on admission
|
||||
with a `Retry-After` rather than being refused, so setting it too low
|
||||
converts capacity you have into latency your callers feel. Setting it
|
||||
very high mainly costs batch-step efficiency, since the engine pads to
|
||||
the widest active sequence.
|
||||
|
||||
Measure before assuming you need a high number — but measure the traffic
|
||||
you will have, not the traffic you had. On one production host, seven
|
||||
days of spans showed 89.6% of busy time at a single request in flight;
|
||||
that host's chat tier was at the time being routed to a *different*
|
||||
model, and the figure stopped describing it the moment that was
|
||||
corrected.
|
||||
serialising. Raise it on big cards, leave it at 1 on small ones — the
|
||||
KV cache for several concurrent long contexts is itself substantial.
|
||||
|
||||
`max_per_principal` is what stops one busy client consuming the whole
|
||||
model.
|
||||
|
||||
### Anonymous callers
|
||||
|
||||
Fair share is keyed on the account and key cortex resolves from the
|
||||
bearer token. A caller that sends no credential — or one that does not
|
||||
resolve, which `require_auth = false` deliberately tolerates — has no
|
||||
key to be shared out, so `max_per_principal` cannot bind it.
|
||||
|
||||
Anonymous traffic is therefore served from the capacity left over once
|
||||
identified traffic is satisfied. It never takes a seat while an
|
||||
authenticated request is waiting for one, whoever arrived first, and it
|
||||
cannot hold every seat at once:
|
||||
|
||||
```toml
|
||||
anon_max_in_flight = 7 # unset: max_in_flight - 1, floored at 1
|
||||
anon_max_pending = 15 # unset: max_in_flight + max_queue_depth - 1
|
||||
```
|
||||
|
||||
The defaults hold back one seat and one queue place, which is what
|
||||
bounds how long an authenticated request can be made to wait: a request
|
||||
already running cannot be preempted, so without a reserved seat an
|
||||
anonymous burst arriving during an idle moment locks the model for as
|
||||
long as all of it takes to finish. On a single-seat model the floor
|
||||
keeps anonymous callers served — priority alone decides who wins there.
|
||||
|
||||
Set `anon_max_in_flight = 0` to refuse anonymous traffic outright, or
|
||||
`require_auth = true` on the gateway to make attribution universal.
|
||||
Anonymous callers still contend with each other, and under sustained
|
||||
authenticated load they are refused rather than served slowly — the
|
||||
refusal is a retryable `503`, so a client that backs off gets served
|
||||
when the load passes.
|
||||
|
||||
Watch it with `cortex_model_anon_in_flight` against
|
||||
`cortex_model_in_flight` (how much of a model's load is unattributable)
|
||||
and `cortex_model_rejections_total{reason="anon_yield"}`. That last
|
||||
counter rising while `reason="wait_timeout"` stays flat means the
|
||||
reservation is doing its job, not that the model is overloaded.
|
||||
|
||||
## VRAM guards
|
||||
|
||||
neuron refuses work it cannot finish rather than crashing partway:
|
||||
|
||||
- a **static floor** of free VRAM below which prefill is refused
|
||||
(`NEURON_MIN_FREE_VRAM_MB`, or `min_free_floor_mb` under
|
||||
`[harness.candle.context_limit]`; default 1500)
|
||||
(`NEURON_MIN_FREE_VRAM_MB`, default 1500)
|
||||
- a **length-aware check** that estimates the KV cache the request will
|
||||
actually need and refuses if it will not fit
|
||||
|
||||
@@ -219,207 +122,15 @@ can pass the static floor and still be impossible, because KV grows with
|
||||
prompt *and* generation length. See [context
|
||||
limits](/docs/operating/context-limits) for how the numbers relate.
|
||||
|
||||
`activation_headroom_mb` reserves VRAM per card for prefill activations
|
||||
on top of the weights and the KV cache, before the context ceiling is
|
||||
computed. Raise it if prefill OOMs on a host whose steady-state
|
||||
occupancy looks fine — activations are transient and do not show up in
|
||||
the resident figure.
|
||||
|
||||
A host that cannot currently serve a model reports that on `/health`,
|
||||
and cortex stops routing to it — an unservable replica is not a routing
|
||||
target.
|
||||
|
||||
## Image models
|
||||
|
||||
```toml
|
||||
[harness.candle.image]
|
||||
te_device = "cpu" # where the text encoder runs
|
||||
te_resident = true # keep it loaded between generations
|
||||
max_dim = 2048 # resolution ceiling per side
|
||||
```
|
||||
|
||||
The text encoder is the placement decision. On CPU the ~8 GB encoder
|
||||
never touches the GPU — prompt encoding is one short forward and the
|
||||
features are tiny — which is what lets a 24 GB card serve a BF16 DiT at
|
||||
all. Move it to `cuda` only on a card with room to spare.
|
||||
|
||||
`te_resident` trades memory for latency: resident costs ~16 GB of system
|
||||
RAM on CPU (or ~8 GB of VRAM on CUDA) and saves a few seconds per
|
||||
request. CPU defaults to resident, CUDA to rebuilding per request, which
|
||||
are the right defaults for where each is scarce.
|
||||
|
||||
`max_dim` rejects oversized requests **before admission**, so an
|
||||
impossible resolution costs nothing. That matters more than it sounds:
|
||||
an OOM on the device poisons the worker context, so refusing early is
|
||||
the difference between one rejected request and a model that needs
|
||||
restarting.
|
||||
|
||||
## Prompt caps
|
||||
|
||||
`NEURON_MAX_PROMPT_TOKENS` sets a hard ceiling; larger prompts are
|
||||
rejected before any GPU work, so a runaway client costs nothing.
|
||||
|
||||
## Sampling
|
||||
|
||||
Every model publishes its own sampling defaults in
|
||||
`generation_config.json`, and a caller can override them per request.
|
||||
Between those two sits an operator override, for the cases where the
|
||||
model's published defaults are wrong for how you serve it:
|
||||
|
||||
```toml
|
||||
[[default_models]]
|
||||
model_id = "Qwen/Qwen3.8-27B"
|
||||
|
||||
[default_models.sampling]
|
||||
temperature = 0.6
|
||||
presence_penalty = 1.0
|
||||
```
|
||||
|
||||
Precedence is **request > operator > model > built-in**. Anything you
|
||||
leave unset changes nothing, so an empty table behaves exactly as no
|
||||
table at all.
|
||||
|
||||
Set the same values in the gateway's `models.toml` under
|
||||
`[models.sampling]`. A model that is cold-loaded on demand gets its
|
||||
sampling from the catalogue, not from this file, so the two must agree
|
||||
or the same model samples differently depending on how it arrived —
|
||||
`script/check-config-consistency.py` fails the deploy if they diverge.
|
||||
|
||||
### Which knob for which symptom
|
||||
|
||||
| symptom | knob |
|
||||
|---|---|
|
||||
| Structurally malformed output — truncated JSON, unbalanced braces | `temperature` |
|
||||
| The think block restates the same passage over and over | `presence_penalty` |
|
||||
| Common tokens over-represented across a long answer | `frequency_penalty` |
|
||||
| Short immediate loops — "no, no, no…" | `repeat_penalty` |
|
||||
| You need two runs to be comparable | `seed` |
|
||||
|
||||
**`temperature`** is the blunt one. Qwen3.8-27B publishes `1.0`, which
|
||||
measured a 20% structural-defect rate on long agentic turns against 0/60
|
||||
at `0.6`; the fleet therefore overrides it. Note that `0.6` is also what
|
||||
Qwen recommend for their thinking variants, so this is not fighting the
|
||||
model.
|
||||
|
||||
**`presence_penalty`** and **`frequency_penalty`** are scored over the
|
||||
*whole* generated sequence. They are the ones that matter for reasoning
|
||||
models, and Qwen name `presence_penalty` (0–2, 1.5 when severe) as the
|
||||
remedy for the endless repetition their models fall into during long
|
||||
thinking. Both default to `0.0`, which is off.
|
||||
|
||||
**`repeat_penalty`** (default `1.1`) and **`repeat_last_n`** (default
|
||||
`64`) are the older, *windowed* form: the penalty only sees the last
|
||||
`repeat_last_n` tokens. That is fine for chat and close to useless for a
|
||||
think block — a 20,000-token deliberation restating a passage 5,000
|
||||
tokens later is entirely outside a 64-token window. Measured across
|
||||
recorded sessions, **86% of think blocks over 60k characters contained
|
||||
verbatim repeated sentences**, one of them repeating 76% of its own
|
||||
content.
|
||||
|
||||
Widening the window is the obvious move and the wrong one: the penalty
|
||||
is token-level, and source code legitimately repeats tokens constantly
|
||||
(`const`, `function`, brace runs), so a wide window at a meaningful
|
||||
penalty degrades exactly the output you care about. Reach for
|
||||
`presence_penalty` first — what recurs is passages, not tokens.
|
||||
|
||||
**`seed`** pins the sampler's RNG for every request to this model. It
|
||||
exists because parameter search needs a control and the clients that
|
||||
would otherwise pin it often cannot. Leaving it set is a product
|
||||
decision, not just a testing one: every identical prompt then returns an
|
||||
identical answer to every caller, which is predictable and cacheable but
|
||||
removes the variation a user may expect from retrying.
|
||||
|
||||
## Reasoning
|
||||
|
||||
```toml
|
||||
[default_models.sampling]
|
||||
# nothing here — reasoning settings live in their own places, below
|
||||
```
|
||||
|
||||
**`preserve_thinking`** controls whether prior turns keep their think
|
||||
blocks when the conversation is re-rendered. It is the model's own chat
|
||||
template control, not ours:
|
||||
|
||||
```toml
|
||||
[[default_models]]
|
||||
preserve_thinking = false # keep reasoning only for the turn in progress
|
||||
```
|
||||
|
||||
Unset is the default and means the template decides. On Qwen3.8-27B that
|
||||
is `true` — every prior turn's reasoning is replayed. Full replay is
|
||||
what makes prompt growth track *total* completion rather than visible
|
||||
output: one measured session produced 28,672 reasoning tokens on turn 1
|
||||
and carried all of them into turn 2's 31,269-token prompt, at ~22 s of
|
||||
prefill on every turn thereafter.
|
||||
|
||||
Setting it to `false` is a legitimate experiment, not a recommendation.
|
||||
Whether narrowing replay *helps* the model is unmeasured. Set it in both
|
||||
`models.toml` and this file, like sampling, and the value is reported on
|
||||
`/v1/models` and logged at load so a session can be attributed to the
|
||||
arm it ran under.
|
||||
|
||||
**`reasoning_budget.answer_reserve_tokens`** (default `4096`) holds back
|
||||
part of the caller's output budget for the answer:
|
||||
|
||||
```toml
|
||||
[harness.candle.reasoning_budget]
|
||||
answer_reserve_tokens = 4096
|
||||
```
|
||||
|
||||
A reasoning model with no stopping criterion fills whatever budget it is
|
||||
given. Measured on Qwen3.8-27B: given 16,384 tokens it used 16,384;
|
||||
given 32,768 it used 32,768 — and both times returned no answer at all.
|
||||
The reserve bounds the think block at `max_tokens - answer_reserve` so
|
||||
the rest survives for the reply.
|
||||
|
||||
Deliberately *not* derived from reasoning effort. Effort is a prompt
|
||||
instruction the model is trained to follow; making it also set a
|
||||
guillotine is how a model came to be told to reason at `xhigh` and then
|
||||
cut off at `medium`'s budget. Set `0` to disable, restoring unbounded
|
||||
reasoning.
|
||||
|
||||
The trade to know: when the reserve fires, the model is interrupted
|
||||
mid-deliberation and its answer phase tends to state an *intention*
|
||||
rather than a conclusion. That is better than returning nothing, but it
|
||||
is not free.
|
||||
|
||||
## The prefix cache
|
||||
|
||||
Snapshots of previously-served prefixes, so a follow-up turn re-uses the
|
||||
KV cache instead of re-prefilling the whole conversation:
|
||||
|
||||
```toml
|
||||
[harness.candle.prefix_cache]
|
||||
enabled = true
|
||||
budget_mb = 2048 # snapshot bytes per loaded model
|
||||
max_entries = 8 # live snapshots per model, regardless of budget
|
||||
```
|
||||
|
||||
**Reach for `budget_mb` when `cached_tokens` stops growing mid-session.**
|
||||
That is the symptom: the prompt keeps growing, the cached prefix does
|
||||
not, and every turn re-prefills the difference. Observed on a 1 GiB
|
||||
default — `cached_tokens` pinned at 2,016 for ten consecutive turns
|
||||
while the prompt reached 52,869, so ~50k tokens were re-prefilled every turn
|
||||
at roughly 37 s each, against ~20 s of actual decode.
|
||||
|
||||
The number is not free, and the direction of the trade is the opposite
|
||||
of what it looks like. **The snapshot budget is reserved before the KV
|
||||
budget, not from what is left over.** On a 2×32 GB host serving a 27B,
|
||||
measured 1:1 — the token column is the pool all concurrent requests
|
||||
share, not a per-slot allowance:
|
||||
|
||||
| `budget_mb` | KV budget | tokens in the pool | holds a 53k snapshot |
|
||||
|---|---|---|---|
|
||||
| 1024 | 4713 MB | 150,800 | no |
|
||||
| 2048 | 3689 MB | 118,000 | yes |
|
||||
| 3072 | 2665 MB | 85,300 | yes, but a session cannot reach 53k |
|
||||
|
||||
So raising it too far starves the KV cache and shortens how long a
|
||||
single session can run — the model can no longer reach the context whose
|
||||
snapshot the larger cache was meant to hold. Size it against the deepest
|
||||
session you actually serve, and check `kv_budget_mb` in the journal
|
||||
after a reload.
|
||||
|
||||
## Checking on it
|
||||
|
||||
```sh
|
||||
|
||||
@@ -24,7 +24,7 @@ confined anywhere.
|
||||
|
||||
```toml
|
||||
[[models]]
|
||||
id = "Qwen/Qwen3.8-27B"
|
||||
id = "Qwen/Qwen3.6-27B"
|
||||
harness = "candle"
|
||||
min_devices = 2
|
||||
min_device_vram_mb = 24000
|
||||
|
||||
@@ -32,43 +32,6 @@ daemon now does automatically.
|
||||
| `limit.input` | same | compaction trigger — opencode compacts to keep the prompt at/under this |
|
||||
| `limit.output` | same | generation reserve opencode leaves below the wall |
|
||||
|
||||
### Tuning the derived limit
|
||||
|
||||
Since #67 the neuron computes `limit` itself (see below), and three
|
||||
`[harness.candle.context_limit]` settings shape that computation:
|
||||
|
||||
```toml
|
||||
[harness.candle.context_limit]
|
||||
target_prefill_latency_secs = 120 # longest acceptable prefill per turn
|
||||
bootstrap_prefill_tok_per_sec = 800 # cold-start estimate until measured
|
||||
output_reserve_tokens = 8192 # what a request gets when it names no cap
|
||||
max_output_tokens = 32768 # the largest output a request may name
|
||||
```
|
||||
|
||||
**`target_prefill_latency_secs`** is the one that usually binds. The
|
||||
throughput ceiling is `target_prefill_latency_secs × measured
|
||||
prefill tok/s`, so on a host measuring ~1,400 tok/s a 120-second target
|
||||
advertises about 168k — above most hard ceilings, in which case it stops
|
||||
mattering. On a slower host, or one whose recent traffic has been small
|
||||
prompts, it is what caps the window.
|
||||
|
||||
**`bootstrap_prefill_tok_per_sec`** applies until the model has measured
|
||||
its own rate, and stops the advertised window collapsing on a
|
||||
freshly-restarted host. Prefill samples below 512 tokens are ignored
|
||||
when computing that rate: a short prompt is dominated by fixed
|
||||
per-request cost and says nothing about throughput — the deploy's own
|
||||
19-token smoke probe reads as ~145 tok/s on a host that measures ~1,400.
|
||||
So a host that has served only small requests keeps the bootstrap
|
||||
estimate rather than adopting a misleading one, and no warm-up is
|
||||
needed after a restart.
|
||||
|
||||
**`output_reserve_tokens`** is what a request that names no cap
|
||||
receives. **`max_output_tokens`** is the ceiling advertised to clients
|
||||
as `max_output_tokens`, and it is the *ceiling*, not the reserve —
|
||||
publishing the reserve tells every client that reads the advertisement
|
||||
to cap itself there, which on a reasoning model can be less than a
|
||||
single think block.
|
||||
|
||||
## How they must relate
|
||||
|
||||
For a single model on a single neuron, all of these must hold:
|
||||
@@ -97,9 +60,9 @@ Notes:
|
||||
lands, treat the VRAM-safe ceiling in rule 5 as a hard limit you set
|
||||
`NEURON_MAX_PROMPT_TOKENS` below, not something the daemon enforces.
|
||||
|
||||
## VRAM cost of context (Qwen3.8-27B on beast)
|
||||
## VRAM cost of context (Qwen3.6-27B on beast)
|
||||
|
||||
Qwen3.8-27B is a hybrid linear-attention model: of its 64 layers only
|
||||
Qwen3.6-27B is a hybrid linear-attention model: of its 64 layers only
|
||||
every 4th is full-attention (`full_attention_interval = 4` → **16**
|
||||
full-attn layers); the rest are `linear_attention` with constant-size
|
||||
recurrent state. KV cache grows **only** on the 16 full-attn layers
|
||||
@@ -168,7 +131,7 @@ value wins over a hand override of the same variable. Use `local.conf`
|
||||
only for genuinely host-local, transient experiments — and remember a
|
||||
later deploy will re-assert `model.conf`.
|
||||
|
||||
**opencode** — `opencode.json`, `provider.models."Qwen/Qwen3.8-27B".limit`:
|
||||
**opencode** — `opencode.json`, `provider.models."Qwen/Qwen3.6-27B".limit`:
|
||||
|
||||
```json
|
||||
{ "context": 131072, "input": 122880, "output": 8192 }
|
||||
|
||||
Generated
+1
-451
@@ -36,8 +36,7 @@
|
||||
"globals": "^16.5.0",
|
||||
"typescript": "~5.9.3",
|
||||
"typescript-eslint": "^8.46.4",
|
||||
"vite": "^7.2.0",
|
||||
"vitest": "^3.2.7"
|
||||
"vite": "^7.2.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@babel/code-frame": {
|
||||
@@ -1815,17 +1814,6 @@
|
||||
"@swc/counter": "^0.1.3"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/chai": {
|
||||
"version": "5.2.3",
|
||||
"resolved": "https://registry.npmjs.org/@types/chai/-/chai-5.2.3.tgz",
|
||||
"integrity": "sha512-Mw558oeA9fFbv65/y4mHtXDs9bPnFMZAL/jxdPFUpOHHIXX91mcgEHbS5Lahr+pwZFR8A7GQleRWeI6cGFC2UA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/deep-eql": "*",
|
||||
"assertion-error": "^2.0.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/debug": {
|
||||
"version": "4.1.13",
|
||||
"resolved": "https://registry.npmjs.org/@types/debug/-/debug-4.1.13.tgz",
|
||||
@@ -1835,13 +1823,6 @@
|
||||
"@types/ms": "*"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/deep-eql": {
|
||||
"version": "4.0.2",
|
||||
"resolved": "https://registry.npmjs.org/@types/deep-eql/-/deep-eql-4.0.2.tgz",
|
||||
"integrity": "sha512-c9h9dVVMigMPc4bwTvC5dxqtqJZwQPePsWjPlpSOnojbor6pGqdk541lfA7AqFQr5pB1BRdq0juY9db81BwyFw==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/@types/estree": {
|
||||
"version": "1.0.9",
|
||||
"resolved": "https://registry.npmjs.org/@types/estree/-/estree-1.0.9.tgz",
|
||||
@@ -2262,121 +2243,6 @@
|
||||
"vite": "^4 || ^5 || ^6 || ^7 || ^8"
|
||||
}
|
||||
},
|
||||
"node_modules/@vitest/expect": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-3.2.7.tgz",
|
||||
"integrity": "sha512-E8eBXaKibuvH2pSZErOjdVb5vF4PbKYcrnluBTYxEk1l/VhhwZg1kZQsdtjq+CsF5CFydf2Rdkz7jDHKSisi3w==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/chai": "^5.2.2",
|
||||
"@vitest/spy": "3.2.7",
|
||||
"@vitest/utils": "3.2.7",
|
||||
"chai": "^5.2.0",
|
||||
"tinyrainbow": "^2.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
}
|
||||
},
|
||||
"node_modules/@vitest/mocker": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/@vitest/mocker/-/mocker-3.2.7.tgz",
|
||||
"integrity": "sha512-Trr0hYO9CM3Wj6ksWHRhK9IZpIY6wTMO5u/MqXurMxT57sWBaOPEtP3Oq60ihZuh5JsiagKfz95OcxdEP6dBrA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@vitest/spy": "3.2.7",
|
||||
"estree-walker": "^3.0.3",
|
||||
"magic-string": "^0.30.17"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"msw": "^2.4.9",
|
||||
"vite": "^5.0.0 || ^6.0.0 || ^7.0.0-0"
|
||||
},
|
||||
"peerDependenciesMeta": {
|
||||
"msw": {
|
||||
"optional": true
|
||||
},
|
||||
"vite": {
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/@vitest/pretty-format": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-3.2.7.tgz",
|
||||
"integrity": "sha512-KUHlwqVu0sRlhCdyPdQ/wBoTfRahjUky1MubOmYw9fWfIZy1gNoHpuaaQBPAaMaVYdQYHJLurzj8ECCj5OwTqA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"tinyrainbow": "^2.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
}
|
||||
},
|
||||
"node_modules/@vitest/runner": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/@vitest/runner/-/runner-3.2.7.tgz",
|
||||
"integrity": "sha512-sB9y4ovltoQP+WaUPwmSxO9WIg9Ig694Di5PalVPsYHklAdE027mehpWF2SQSVq+k6sFgaivbTjTJwZLSHbedA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@vitest/utils": "3.2.7",
|
||||
"pathe": "^2.0.3",
|
||||
"strip-literal": "^3.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
}
|
||||
},
|
||||
"node_modules/@vitest/snapshot": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/@vitest/snapshot/-/snapshot-3.2.7.tgz",
|
||||
"integrity": "sha512-7C+MwShwtBSI5Buwoyg3s/iY1eHL9PKAf+O1wVh/TdnjXUtkoL/9YQtre90i4MtNXM6edP1wJ2zOBpfCyhIS7g==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@vitest/pretty-format": "3.2.7",
|
||||
"magic-string": "^0.30.17",
|
||||
"pathe": "^2.0.3"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
}
|
||||
},
|
||||
"node_modules/@vitest/spy": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-3.2.7.tgz",
|
||||
"integrity": "sha512-Q2eQGI6d2L/hBtZ0qNuKcAGid68XK6cv1xsoaIma6PaJhHPoqcEJhYpXZ/5myCMqkNgtP6UKuBhbc0nHKnrkuQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"tinyspy": "^4.0.3"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
}
|
||||
},
|
||||
"node_modules/@vitest/utils": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-3.2.7.tgz",
|
||||
"integrity": "sha512-x6BDOd7dyo3PFLY3I9/HJ25X/6OurhGXk2/B9gOZNPF7XDVjeBK4k01lQE5uvDpbuheErh91qYuE1E2OEjK3Rw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@vitest/pretty-format": "3.2.7",
|
||||
"loupe": "^3.1.4",
|
||||
"tinyrainbow": "^2.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
}
|
||||
},
|
||||
"node_modules/acorn": {
|
||||
"version": "8.17.0",
|
||||
"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.17.0.tgz",
|
||||
@@ -2452,16 +2318,6 @@
|
||||
"node": ">=10"
|
||||
}
|
||||
},
|
||||
"node_modules/assertion-error": {
|
||||
"version": "2.0.1",
|
||||
"resolved": "https://registry.npmjs.org/assertion-error/-/assertion-error-2.0.1.tgz",
|
||||
"integrity": "sha512-Izi8RQcffqCeNVgFigKli1ssklIbpHnCYc6AknXGYoB6grJqyeby7jv12JUQgmTAnIDnbck1uxksT4dzN3PWBA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
}
|
||||
},
|
||||
"node_modules/bail": {
|
||||
"version": "2.0.2",
|
||||
"resolved": "https://registry.npmjs.org/bail/-/bail-2.0.2.tgz",
|
||||
@@ -2556,16 +2412,6 @@
|
||||
"node": "^6 || ^7 || ^8 || ^9 || ^10 || ^11 || ^12 || >=13.7"
|
||||
}
|
||||
},
|
||||
"node_modules/cac": {
|
||||
"version": "6.7.14",
|
||||
"resolved": "https://registry.npmjs.org/cac/-/cac-6.7.14.tgz",
|
||||
"integrity": "sha512-b6Ilus+c3RrdDk+JhLKUAQfzzgLEPy6wcXqS7f/xe1EETvsDP6GORG7SFuOs6cID5YkqchW/LXZbX5bc8j7ZcQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/callsites": {
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz",
|
||||
@@ -2607,23 +2453,6 @@
|
||||
"url": "https://github.com/sponsors/wooorm"
|
||||
}
|
||||
},
|
||||
"node_modules/chai": {
|
||||
"version": "5.3.3",
|
||||
"resolved": "https://registry.npmjs.org/chai/-/chai-5.3.3.tgz",
|
||||
"integrity": "sha512-4zNhdJD/iOjSH0A05ea+Ke6MU5mmpQcbQsSOkgdaUMJ9zTlDTD/GYlwohmIE2u0gaxHYiVHEn1Fw9mZ/ktJWgw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"assertion-error": "^2.0.1",
|
||||
"check-error": "^2.1.1",
|
||||
"deep-eql": "^5.0.1",
|
||||
"loupe": "^3.1.0",
|
||||
"pathval": "^2.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/chalk": {
|
||||
"version": "4.1.2",
|
||||
"resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
|
||||
@@ -2681,16 +2510,6 @@
|
||||
"url": "https://github.com/sponsors/wooorm"
|
||||
}
|
||||
},
|
||||
"node_modules/check-error": {
|
||||
"version": "2.1.3",
|
||||
"resolved": "https://registry.npmjs.org/check-error/-/check-error-2.1.3.tgz",
|
||||
"integrity": "sha512-PAJdDJusoxnwm1VwW07VWwUN1sl7smmC3OKggvndJFadxxDRyFJBX/ggnu/KE4kQAB7a3Dp8f/YXC1FlUprWmA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 16"
|
||||
}
|
||||
},
|
||||
"node_modules/classnames": {
|
||||
"version": "2.5.1",
|
||||
"resolved": "https://registry.npmjs.org/classnames/-/classnames-2.5.1.tgz",
|
||||
@@ -2814,16 +2633,6 @@
|
||||
"url": "https://github.com/sponsors/wooorm"
|
||||
}
|
||||
},
|
||||
"node_modules/deep-eql": {
|
||||
"version": "5.0.2",
|
||||
"resolved": "https://registry.npmjs.org/deep-eql/-/deep-eql-5.0.2.tgz",
|
||||
"integrity": "sha512-h5k/5U50IJJFpzfL6nO9jaaumfjO/f2NjK/oYB2Djzm4p9L+3T9qWpZqZ2hAbLPuuYq9wrU08WQyBTL5GbPk5Q==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=6"
|
||||
}
|
||||
},
|
||||
"node_modules/deep-is": {
|
||||
"version": "0.1.4",
|
||||
"resolved": "https://registry.npmjs.org/deep-is/-/deep-is-0.1.4.tgz",
|
||||
@@ -2886,13 +2695,6 @@
|
||||
"dev": true,
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/es-module-lexer": {
|
||||
"version": "1.7.0",
|
||||
"resolved": "https://registry.npmjs.org/es-module-lexer/-/es-module-lexer-1.7.0.tgz",
|
||||
"integrity": "sha512-jEQoCwk8hyb2AZziIOLhDqpm5+2ww5uIE6lkO/6jcOCusfk6LhMHpXXfBLXTZ7Ydyt0j4VoUQv6uGNYbdW+kBA==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/esbuild": {
|
||||
"version": "0.27.7",
|
||||
"resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.27.7.tgz",
|
||||
@@ -3142,16 +2944,6 @@
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/estree-walker": {
|
||||
"version": "3.0.3",
|
||||
"resolved": "https://registry.npmjs.org/estree-walker/-/estree-walker-3.0.3.tgz",
|
||||
"integrity": "sha512-7RUKfXgSMMkzt6ZuXmqapOurLGPPfgj6l9uRZ7lRGolvk0y2yocc35LdcxKC5PQZdn2DMqioAQ2NoWcrTKmm6g==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/estree": "^1.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/esutils": {
|
||||
"version": "2.0.3",
|
||||
"resolved": "https://registry.npmjs.org/esutils/-/esutils-2.0.3.tgz",
|
||||
@@ -3162,16 +2954,6 @@
|
||||
"node": ">=0.10.0"
|
||||
}
|
||||
},
|
||||
"node_modules/expect-type": {
|
||||
"version": "1.4.0",
|
||||
"resolved": "https://registry.npmjs.org/expect-type/-/expect-type-1.4.0.tgz",
|
||||
"integrity": "sha512-KfYbmpRm0VbLjEvVa9yGwCi9GI34xvi7A/HXYWQO65CSD2u3MczUJSuwXKFIxlGsgBQizV9q5J9NHj4VG0n+pA==",
|
||||
"dev": true,
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">=12.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/extend": {
|
||||
"version": "3.0.2",
|
||||
"resolved": "https://registry.npmjs.org/extend/-/extend-3.0.2.tgz",
|
||||
@@ -3757,13 +3539,6 @@
|
||||
"loose-envify": "cli.js"
|
||||
}
|
||||
},
|
||||
"node_modules/loupe": {
|
||||
"version": "3.2.1",
|
||||
"resolved": "https://registry.npmjs.org/loupe/-/loupe-3.2.1.tgz",
|
||||
"integrity": "sha512-CdzqowRJCeLU72bHvWqwRBBlLcMEtIvGrlvef74kMnV2AolS9Y8xUv1I0U/MNAWMhBlKIoyuEgoJ0t/bbwHbLQ==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/lowlight": {
|
||||
"version": "3.3.0",
|
||||
"resolved": "https://registry.npmjs.org/lowlight/-/lowlight-3.3.0.tgz",
|
||||
@@ -3789,16 +3564,6 @@
|
||||
"yallist": "^3.0.2"
|
||||
}
|
||||
},
|
||||
"node_modules/magic-string": {
|
||||
"version": "0.30.21",
|
||||
"resolved": "https://registry.npmjs.org/magic-string/-/magic-string-0.30.21.tgz",
|
||||
"integrity": "sha512-vd2F4YUyEXKGcLHoq+TEyCjxueSeHnFxyyjNp80yg0XV4vUhnDer/lvvlqM/arB5bXQN5K2/3oinyCRyx8T2CQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@jridgewell/sourcemap-codec": "^1.5.5"
|
||||
}
|
||||
},
|
||||
"node_modules/markdown-table": {
|
||||
"version": "3.0.4",
|
||||
"resolved": "https://registry.npmjs.org/markdown-table/-/markdown-table-3.0.4.tgz",
|
||||
@@ -4826,23 +4591,6 @@
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/pathe": {
|
||||
"version": "2.0.3",
|
||||
"resolved": "https://registry.npmjs.org/pathe/-/pathe-2.0.3.tgz",
|
||||
"integrity": "sha512-WUjGcAqP1gQacoQe+OBJsFA7Ld4DyXuUIjZ5cc75cLHvJ7dtNsTugphxIADwspS+AraAUePCKrSVtPLFj/F88w==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/pathval": {
|
||||
"version": "2.0.1",
|
||||
"resolved": "https://registry.npmjs.org/pathval/-/pathval-2.0.1.tgz",
|
||||
"integrity": "sha512-//nshmD55c46FuFw26xV/xFAaB5HF9Xdap7HJBBnrKdAd6/GxDBaNA1870O79+9ueg61cZLSVc+OaFlfmObYVQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 14.16"
|
||||
}
|
||||
},
|
||||
"node_modules/picocolors": {
|
||||
"version": "1.1.1",
|
||||
"resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
|
||||
@@ -5348,13 +5096,6 @@
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/siginfo": {
|
||||
"version": "2.0.0",
|
||||
"resolved": "https://registry.npmjs.org/siginfo/-/siginfo-2.0.0.tgz",
|
||||
"integrity": "sha512-ybx0WO1/8bSBLEWXZvEd7gMW3Sn3JFlW3TvX1nREbDLRNQNaeNN8WK0meBwPdAaOI7TtRRRJn/Es1zhrrCHu7g==",
|
||||
"dev": true,
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/source-map-js": {
|
||||
"version": "1.2.1",
|
||||
"resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz",
|
||||
@@ -5375,20 +5116,6 @@
|
||||
"url": "https://github.com/sponsors/wooorm"
|
||||
}
|
||||
},
|
||||
"node_modules/stackback": {
|
||||
"version": "0.0.2",
|
||||
"resolved": "https://registry.npmjs.org/stackback/-/stackback-0.0.2.tgz",
|
||||
"integrity": "sha512-1XMJE5fQo1jGH6Y/7ebnwPOBEkIEnT4QF32d5R1+VXdXveM0IBMJt8zfaxX1P3QhVwrYe+576+jkANtSS2mBbw==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/std-env": {
|
||||
"version": "3.10.0",
|
||||
"resolved": "https://registry.npmjs.org/std-env/-/std-env-3.10.0.tgz",
|
||||
"integrity": "sha512-5GS12FdOZNliM5mAOxFRg7Ir0pWz8MdpYm6AY6VPkGpbA7ZzmbzNcBJQ0GPvvyWgcY7QAhCgf9Uy89I03faLkg==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/stringify-entities": {
|
||||
"version": "4.0.4",
|
||||
"resolved": "https://registry.npmjs.org/stringify-entities/-/stringify-entities-4.0.4.tgz",
|
||||
@@ -5416,26 +5143,6 @@
|
||||
"url": "https://github.com/sponsors/sindresorhus"
|
||||
}
|
||||
},
|
||||
"node_modules/strip-literal": {
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmjs.org/strip-literal/-/strip-literal-3.1.0.tgz",
|
||||
"integrity": "sha512-8r3mkIM/2+PpjHoOtiAW8Rg3jJLHaV7xPwG+YRGrv6FP0wwk/toTpATxWYOW0BKdWwl82VT2tFYi5DlROa0Mxg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"js-tokens": "^9.0.1"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/antfu"
|
||||
}
|
||||
},
|
||||
"node_modules/strip-literal/node_modules/js-tokens": {
|
||||
"version": "9.0.1",
|
||||
"resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-9.0.1.tgz",
|
||||
"integrity": "sha512-mxa9E9ITFOt0ban3j6L5MpjwegGz6lBQmM1IJkWeBZGcMxto50+eWdjC/52xDbS2vy0k7vIMK0Fe2wfL9OQSpQ==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/style-to-js": {
|
||||
"version": "1.1.21",
|
||||
"resolved": "https://registry.npmjs.org/style-to-js/-/style-to-js-1.1.21.tgz",
|
||||
@@ -5467,20 +5174,6 @@
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/tinybench": {
|
||||
"version": "2.9.0",
|
||||
"resolved": "https://registry.npmjs.org/tinybench/-/tinybench-2.9.0.tgz",
|
||||
"integrity": "sha512-0+DUvqWMValLmha6lr4kD8iAMK1HzV0/aKnCtWb9v9641TnP/MFb7Pc2bxoxQjTXAErryXVgUOfv2YqNllqGeg==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/tinyexec": {
|
||||
"version": "0.3.2",
|
||||
"resolved": "https://registry.npmjs.org/tinyexec/-/tinyexec-0.3.2.tgz",
|
||||
"integrity": "sha512-KQQR9yN7R5+OSwaK0XQoj22pwHoTlgYqmUscPYoknOoWCWfj/5/ABTMRi69FrKU5ffPVh5QcFikpWJI/P1ocHA==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/tinyglobby": {
|
||||
"version": "0.2.17",
|
||||
"resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.17.tgz",
|
||||
@@ -5498,36 +5191,6 @@
|
||||
"url": "https://github.com/sponsors/SuperchupuDev"
|
||||
}
|
||||
},
|
||||
"node_modules/tinypool": {
|
||||
"version": "1.1.1",
|
||||
"resolved": "https://registry.npmjs.org/tinypool/-/tinypool-1.1.1.tgz",
|
||||
"integrity": "sha512-Zba82s87IFq9A9XmjiX5uZA/ARWDrB03OHlq+Vw1fSdt0I+4/Kutwy8BP4Y/y/aORMo61FQ0vIb5j44vSo5Pkg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": "^18.0.0 || >=20.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/tinyrainbow": {
|
||||
"version": "2.0.0",
|
||||
"resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-2.0.0.tgz",
|
||||
"integrity": "sha512-op4nsTR47R6p0vMUUoYl/a+ljLFVtlfaXkLQmqfLR1qHma1h/ysYk4hEXZ880bf2CYgTskvTa/e196Vd5dDQXw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=14.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/tinyspy": {
|
||||
"version": "4.0.4",
|
||||
"resolved": "https://registry.npmjs.org/tinyspy/-/tinyspy-4.0.4.tgz",
|
||||
"integrity": "sha512-azl+t0z7pw/z958Gy9svOTuzqIk6xq+NSheJzn5MMWtWTFywIacg2wUlzKFGtt3cthx0r2SxMK0yzJOR0IES7Q==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=14.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/trim-lines": {
|
||||
"version": "3.0.1",
|
||||
"resolved": "https://registry.npmjs.org/trim-lines/-/trim-lines-3.0.1.tgz",
|
||||
@@ -5894,102 +5557,6 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/vite-node": {
|
||||
"version": "3.2.4",
|
||||
"resolved": "https://registry.npmjs.org/vite-node/-/vite-node-3.2.4.tgz",
|
||||
"integrity": "sha512-EbKSKh+bh1E1IFxeO0pg1n4dvoOTt0UDiXMd/qn++r98+jPO1xtJilvXldeuQ8giIB5IkpjCgMleHMNEsGH6pg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"cac": "^6.7.14",
|
||||
"debug": "^4.4.1",
|
||||
"es-module-lexer": "^1.7.0",
|
||||
"pathe": "^2.0.3",
|
||||
"vite": "^5.0.0 || ^6.0.0 || ^7.0.0-0"
|
||||
},
|
||||
"bin": {
|
||||
"vite-node": "vite-node.mjs"
|
||||
},
|
||||
"engines": {
|
||||
"node": "^18.0.0 || ^20.0.0 || >=22.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
}
|
||||
},
|
||||
"node_modules/vitest": {
|
||||
"version": "3.2.7",
|
||||
"resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.7.tgz",
|
||||
"integrity": "sha512-KrxIJ62Fd89gfysR4WotlgZABiz2dqFPgqGzX7s+CwsqLFomRH7777ZcrOD6+WVAh7khPQP41A+BKbpcJFrdEg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/chai": "^5.2.2",
|
||||
"@vitest/expect": "3.2.7",
|
||||
"@vitest/mocker": "3.2.7",
|
||||
"@vitest/pretty-format": "^3.2.7",
|
||||
"@vitest/runner": "3.2.7",
|
||||
"@vitest/snapshot": "3.2.7",
|
||||
"@vitest/spy": "3.2.7",
|
||||
"@vitest/utils": "3.2.7",
|
||||
"chai": "^5.2.0",
|
||||
"debug": "^4.4.1",
|
||||
"expect-type": "^1.2.1",
|
||||
"magic-string": "^0.30.17",
|
||||
"pathe": "^2.0.3",
|
||||
"picomatch": "^4.0.2",
|
||||
"std-env": "^3.9.0",
|
||||
"tinybench": "^2.9.0",
|
||||
"tinyexec": "^0.3.2",
|
||||
"tinyglobby": "^0.2.14",
|
||||
"tinypool": "^1.1.1",
|
||||
"tinyrainbow": "^2.0.0",
|
||||
"vite": "^5.0.0 || ^6.0.0 || ^7.0.0-0",
|
||||
"vite-node": "3.2.4",
|
||||
"why-is-node-running": "^2.3.0"
|
||||
},
|
||||
"bin": {
|
||||
"vitest": "vitest.mjs"
|
||||
},
|
||||
"engines": {
|
||||
"node": "^18.0.0 || ^20.0.0 || >=22.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://opencollective.com/vitest"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@edge-runtime/vm": "*",
|
||||
"@types/debug": "^4.1.12",
|
||||
"@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0",
|
||||
"@vitest/browser": "3.2.7",
|
||||
"@vitest/ui": "3.2.7",
|
||||
"happy-dom": "*",
|
||||
"jsdom": "*"
|
||||
},
|
||||
"peerDependenciesMeta": {
|
||||
"@edge-runtime/vm": {
|
||||
"optional": true
|
||||
},
|
||||
"@types/debug": {
|
||||
"optional": true
|
||||
},
|
||||
"@types/node": {
|
||||
"optional": true
|
||||
},
|
||||
"@vitest/browser": {
|
||||
"optional": true
|
||||
},
|
||||
"@vitest/ui": {
|
||||
"optional": true
|
||||
},
|
||||
"happy-dom": {
|
||||
"optional": true
|
||||
},
|
||||
"jsdom": {
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/void-elements": {
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmjs.org/void-elements/-/void-elements-3.1.0.tgz",
|
||||
@@ -6024,23 +5591,6 @@
|
||||
"node": ">= 8"
|
||||
}
|
||||
},
|
||||
"node_modules/why-is-node-running": {
|
||||
"version": "2.3.0",
|
||||
"resolved": "https://registry.npmjs.org/why-is-node-running/-/why-is-node-running-2.3.0.tgz",
|
||||
"integrity": "sha512-hUrmaWBdVDcxvYqnyh09zunKzROWjbZTiNy8dBEjkS7ehEDQibXJ7XvlmtbwuTclUiIyN+CyXQD4Vmko8fNm8w==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"siginfo": "^2.0.0",
|
||||
"stackback": "0.0.2"
|
||||
},
|
||||
"bin": {
|
||||
"why-is-node-running": "cli.js"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/word-wrap": {
|
||||
"version": "1.2.5",
|
||||
"resolved": "https://registry.npmjs.org/word-wrap/-/word-wrap-1.2.5.tgz",
|
||||
|
||||
@@ -9,8 +9,6 @@
|
||||
"preview": "vite preview",
|
||||
"lint": "eslint .",
|
||||
"typecheck": "tsc -b",
|
||||
"test": "vitest run",
|
||||
"test:watch": "vitest",
|
||||
"i18n:check": "node ./scripts/check-i18n-keys.mjs",
|
||||
"i18n:meta": "node ./scripts/check-i18n-metadata.mjs",
|
||||
"i18n:lang-labels": "node ./scripts/check-i18n-lang-labels.mjs",
|
||||
@@ -45,7 +43,6 @@
|
||||
"globals": "^16.5.0",
|
||||
"typescript": "~5.9.3",
|
||||
"typescript-eslint": "^8.46.4",
|
||||
"vite": "^7.2.0",
|
||||
"vitest": "^3.2.7"
|
||||
"vite": "^7.2.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2063,108 +2063,3 @@ html[dir="rtl"] .hx-landing-composer textarea {
|
||||
display: none;
|
||||
}
|
||||
}
|
||||
|
||||
/* Assistant working — reasoning and tool calls (#TurnBlocks).
|
||||
*
|
||||
* Deliberately quieter than the answer: muted text, no bubble of its
|
||||
* own, hairline separators. The whole point is that it can be present
|
||||
* without competing, so it reads as an annotation on the reply rather
|
||||
* than as more reply. */
|
||||
.hx-blocks {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 0.25rem;
|
||||
margin-bottom: 0.5rem;
|
||||
}
|
||||
.hx-block {
|
||||
border-left: 2px solid var(--color-border-subtle);
|
||||
padding-left: 0.5rem;
|
||||
}
|
||||
.hx-block-open {
|
||||
border-left-color: var(--color-accent-soft);
|
||||
}
|
||||
.hx-block-head {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.35rem;
|
||||
width: 100%;
|
||||
padding: 0.15rem 0;
|
||||
background: none;
|
||||
border: 0;
|
||||
color: var(--color-text-muted);
|
||||
font-size: 0.78rem;
|
||||
text-align: start;
|
||||
cursor: pointer;
|
||||
}
|
||||
.hx-block-head:hover {
|
||||
color: var(--color-text);
|
||||
}
|
||||
.hx-block-caret {
|
||||
flex: none;
|
||||
transition: transform 0.12s ease;
|
||||
}
|
||||
.hx-block-caret-open {
|
||||
transform: rotate(90deg);
|
||||
}
|
||||
.hx-block-label {
|
||||
flex: none;
|
||||
font-weight: 600;
|
||||
}
|
||||
.hx-block-running {
|
||||
flex: none;
|
||||
opacity: 0.7;
|
||||
font-style: italic;
|
||||
}
|
||||
/* The peek is the first thing to give up space — it is a hint, and a
|
||||
* wrapped one would cost the header its single-line shape. */
|
||||
.hx-block-peek {
|
||||
flex: 1 1 auto;
|
||||
min-width: 0;
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
white-space: nowrap;
|
||||
opacity: 0.6;
|
||||
}
|
||||
.hx-block-body {
|
||||
/* Capped and scrollable: a long think block would otherwise push the
|
||||
* answer off-screen, which defeats the point of showing it. */
|
||||
max-height: 16rem;
|
||||
overflow-y: auto;
|
||||
margin: 0.15rem 0 0.35rem;
|
||||
padding-inline-end: 0.4rem;
|
||||
color: var(--color-text-muted);
|
||||
font-size: 0.82rem;
|
||||
line-height: 1.45;
|
||||
white-space: pre-wrap;
|
||||
overflow-wrap: anywhere;
|
||||
}
|
||||
|
||||
/* Reasoning toggle in the composer. Sits with the send button rather
|
||||
* than in a settings panel: it changes what the next message does, so it
|
||||
* belongs where the message is written. */
|
||||
.hx-thinking-toggle {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
gap: 0.35rem;
|
||||
margin: 0;
|
||||
padding: 0 0.5rem;
|
||||
color: var(--color-text-muted);
|
||||
font-size: 0.78rem;
|
||||
white-space: nowrap;
|
||||
cursor: pointer;
|
||||
user-select: none;
|
||||
}
|
||||
.hx-thinking-toggle:hover {
|
||||
color: var(--color-text);
|
||||
}
|
||||
.hx-thinking-toggle input {
|
||||
margin: 0;
|
||||
cursor: pointer;
|
||||
}
|
||||
/* Narrow screens: the composer is already tight, and the label is the
|
||||
* expendable half — the checkbox still reads as a control. */
|
||||
@media (max-width: 30rem) {
|
||||
.hx-thinking-toggle span {
|
||||
display: none;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,129 +0,0 @@
|
||||
import { useState } from "react";
|
||||
import { useTranslation } from "react-i18next";
|
||||
import { FaChevronRight, FaBrain, FaWrench } from "react-icons/fa6";
|
||||
import type { TurnBlock } from "../data/db";
|
||||
import { isOpen } from "../lib/turnBlockState";
|
||||
|
||||
/**
|
||||
* The assistant's working — reasoning and tool calls — shown above its
|
||||
* answer.
|
||||
*
|
||||
* Two things are in tension. All of this should be *available*, because a
|
||||
* model that reasons for two minutes and then answers has done work worth
|
||||
* inspecting, and a tool call the user cannot see is a claim they cannot
|
||||
* check. But none of it is what they asked for, so it must not bury the
|
||||
* answer.
|
||||
*
|
||||
* The resolution is that visibility follows activity:
|
||||
*
|
||||
* * While a block is the live one — still streaming, no answer text yet
|
||||
* — it is open. That span is otherwise dead air; a spinner would say
|
||||
* "working", this says what it is working *on*.
|
||||
* * The moment answer text starts, every block collapses to a one-line
|
||||
* header. The thing the user asked for takes the space.
|
||||
* * Completed turns load collapsed, so scrollback stays readable.
|
||||
*
|
||||
* A block the user opens or closes by hand stays that way. Explicit
|
||||
* intent outranks the automatic rule, including for the live block —
|
||||
* someone who closes a noisy reasoning stream should not have it reopen
|
||||
* itself on the next token.
|
||||
*/
|
||||
export function TurnBlocks({
|
||||
blocks,
|
||||
streaming,
|
||||
answerStarted,
|
||||
}: {
|
||||
blocks: TurnBlock[];
|
||||
/** This turn is still being generated. */
|
||||
streaming: boolean;
|
||||
/** Answer text has begun arriving, so the working is now history. */
|
||||
answerStarted: boolean;
|
||||
}) {
|
||||
const { t } = useTranslation();
|
||||
// Only blocks the user has touched appear here; everything else follows
|
||||
// the automatic rule. Keyed by index, which is stable because blocks
|
||||
// are only ever appended within a turn.
|
||||
const [overrides, setOverrides] = useState<Record<number, boolean>>({});
|
||||
|
||||
if (blocks.length === 0) return null;
|
||||
|
||||
return (
|
||||
<div className="hx-blocks">
|
||||
{blocks.map((b, i) => {
|
||||
const open = isOpen(i, blocks.length, streaming, answerStarted, overrides[i]);
|
||||
const body = b.kind === "reasoning" ? b.text : blockToolBody(b);
|
||||
return (
|
||||
<div key={i} className={`hx-block${open ? " hx-block-open" : ""}`}>
|
||||
<button
|
||||
type="button"
|
||||
className="hx-block-head"
|
||||
aria-expanded={open}
|
||||
onClick={() => setOverrides((o) => ({ ...o, [i]: !open }))}
|
||||
>
|
||||
<FaChevronRight
|
||||
className={`hx-block-caret${open ? " hx-block-caret-open" : ""}`}
|
||||
size={10}
|
||||
aria-hidden="true"
|
||||
/>
|
||||
{b.kind === "reasoning" ? (
|
||||
<FaBrain size={11} aria-hidden="true" />
|
||||
) : (
|
||||
<FaWrench size={11} aria-hidden="true" />
|
||||
)}
|
||||
<span className="hx-block-label">
|
||||
{b.kind === "reasoning"
|
||||
? t("chat:blockReasoning")
|
||||
: t("chat:blockTool", { name: b.name })}
|
||||
</span>
|
||||
{/* A pending tool call is the one case where the header
|
||||
* alone should say something is happening: its body is
|
||||
* empty until the result lands, so an open block would
|
||||
* otherwise look like a stall. */}
|
||||
{b.kind === "tool" && b.result === undefined && streaming && (
|
||||
<span className="hx-block-running">{t("chat:blockRunning")}</span>
|
||||
)}
|
||||
{!open && (
|
||||
<span className="hx-block-peek">{peek(body)}</span>
|
||||
)}
|
||||
</button>
|
||||
{open && <div className="hx-block-body">{body}</div>}
|
||||
</div>
|
||||
);
|
||||
})}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
/** Arguments, then the result once it arrives. */
|
||||
function blockToolBody(b: Extract<TurnBlock, { kind: "tool" }>): string {
|
||||
const args = prettyArgs(b.args);
|
||||
return b.result === undefined ? args : `${args}\n\n${b.result}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Tool arguments as sent, pretty-printed when they are JSON.
|
||||
*
|
||||
* Models emit malformed arguments often enough that this must never
|
||||
* throw — a UI that blanks because the model produced bad JSON hides the
|
||||
* very thing worth seeing.
|
||||
*/
|
||||
function prettyArgs(raw: string): string {
|
||||
try {
|
||||
return JSON.stringify(JSON.parse(raw), null, 2);
|
||||
} catch {
|
||||
return raw;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* The tail of a collapsed block, so a closed row still carries a hint of
|
||||
* its content.
|
||||
*
|
||||
* The tail rather than the head: while a block streams, the end is where
|
||||
* the model currently is. A head-anchored preview freezes on the first
|
||||
* few words and stops telling you anything.
|
||||
*/
|
||||
function peek(text: string): string {
|
||||
const flat = text.replace(/\s+/g, " ").trim();
|
||||
return flat.length <= 80 ? flat : `…${flat.slice(-79)}`;
|
||||
}
|
||||
@@ -39,23 +39,6 @@ export interface MessageSource {
|
||||
url: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Work the assistant did on the way to an answer: a stretch of reasoning,
|
||||
* or one tool call and its result.
|
||||
*
|
||||
* Kept as an ordered list rather than two separate fields because the
|
||||
* order is the story — a turn can reason, call a tool, reason about what
|
||||
* came back, and call another. Flattening that into "the reasoning" and
|
||||
* "the tool calls" would lose which thought preceded which call.
|
||||
*
|
||||
* `text` and `result` grow while streaming, so a block is also its own
|
||||
* progress indicator: a reasoning block with text and no following block
|
||||
* is what the model is doing *right now*.
|
||||
*/
|
||||
export type TurnBlock =
|
||||
| { kind: "reasoning"; text: string }
|
||||
| { kind: "tool"; name: string; args: string; result?: string };
|
||||
|
||||
export interface Message {
|
||||
id: string;
|
||||
conversationId: string;
|
||||
@@ -67,16 +50,6 @@ export interface Message {
|
||||
promptTokens?: number;
|
||||
completionTokens?: number;
|
||||
sources?: MessageSource[];
|
||||
/**
|
||||
* Reasoning and tool calls, in the order they happened. Absent on user
|
||||
* turns and on assistant turns that answered directly.
|
||||
*
|
||||
* Not indexed, so no schema version bump: Dexie stores the whole
|
||||
* object and only the declared indexes constrain it. Messages written
|
||||
* before this field existed simply have none, which renders as an
|
||||
* answer with no working shown — correct, since none was captured.
|
||||
*/
|
||||
blocks?: TurnBlock[];
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -10,7 +10,6 @@ import {
|
||||
type Message,
|
||||
type MessageRole,
|
||||
type Project,
|
||||
type TurnBlock,
|
||||
} from "./db";
|
||||
|
||||
function uuid(): string {
|
||||
@@ -139,22 +138,10 @@ export async function setMessageContent(id: string, content: string): Promise<vo
|
||||
await db.messages.update(id, { content });
|
||||
}
|
||||
|
||||
/**
|
||||
* Write the whole block list as an absolute snapshot.
|
||||
*
|
||||
* Same discipline as `setMessageContent`: the caller owns the array and
|
||||
* writes it entire, because a read-modify-write append races itself when
|
||||
* deltas arrive faster than the IndexedDB round-trip — which is how the
|
||||
* content path dropped tokens before it was written this way.
|
||||
*/
|
||||
export async function setMessageBlocks(id: string, blocks: TurnBlock[]): Promise<void> {
|
||||
await db.messages.update(id, { blocks });
|
||||
}
|
||||
|
||||
export async function finalizeMessage(
|
||||
id: string,
|
||||
patch: Partial<
|
||||
Pick<Message, "status" | "errorCode" | "promptTokens" | "completionTokens" | "sources" | "blocks">
|
||||
Pick<Message, "status" | "errorCode" | "promptTokens" | "completionTokens" | "sources">
|
||||
>,
|
||||
): Promise<void> {
|
||||
await db.messages.update(id, patch);
|
||||
|
||||
@@ -29,10 +29,5 @@
|
||||
"reading": "{{host}} እየተነበበ ነው…",
|
||||
"copyCode": "ኮድ ቅዳ",
|
||||
"copiedCode": "ተቀድቷል",
|
||||
"anonNearLimit": "ወደ የስም-አልባ ተጠቃሚ ገደብ እየተቃረቡ ነው። ነፃ ድልድል ለማግኘት ይመዝገቡ።",
|
||||
"blockReasoning": "በማሰብ ላይ",
|
||||
"blockTool": "{{name}}",
|
||||
"blockRunning": "በማስኬድ ላይ…",
|
||||
"showThinking": "ማመዛዘን",
|
||||
"showThinkingHint": "ሞዴሉ ከመመለሱ በፊት እንዲያስብ ጠይቅ፣ እና ማመዛዘኑን አሳይ"
|
||||
"anonNearLimit": "ወደ የስም-አልባ ተጠቃሚ ገደብ እየተቃረቡ ነው። ነፃ ድልድል ለማግኘት ይመዝገቡ።"
|
||||
}
|
||||
|
||||
@@ -29,10 +29,5 @@
|
||||
"reading": "تجري قراءة {{host}}…",
|
||||
"copyCode": "نسخ الكود",
|
||||
"copiedCode": "تم النسخ",
|
||||
"anonNearLimit": "أوشكت على بلوغ حد الاستخدام المجهول. أنشئ حسابًا للحصول على مخصّص مجاني.",
|
||||
"blockReasoning": "جارٍ التفكير",
|
||||
"blockTool": "{{name}}",
|
||||
"blockRunning": "قيد التشغيل…",
|
||||
"showThinking": "التفكير",
|
||||
"showThinkingHint": "اطلب من النموذج التفكير قبل الإجابة، واعرض تفكيره"
|
||||
"anonNearLimit": "أوشكت على بلوغ حد الاستخدام المجهول. أنشئ حسابًا للحصول على مخصّص مجاني."
|
||||
}
|
||||
|
||||
@@ -29,10 +29,5 @@
|
||||
"reading": "четене на {{host}}…",
|
||||
"copyCode": "Копиране на кода",
|
||||
"copiedCode": "Копирано",
|
||||
"anonNearLimit": "Наближавате анонимния лимит. Регистрирайте се за безплатна квота.",
|
||||
"blockReasoning": "Разсъждаване",
|
||||
"blockTool": "{{name}}",
|
||||
"blockRunning": "изпълнява се…",
|
||||
"showThinking": "Разсъждение",
|
||||
"showThinkingHint": "Моделът да мисли преди да отговори и да показва разсъжденията си"
|
||||
"anonNearLimit": "Наближавате анонимния лимит. Регистрирайте се за безплатна квота."
|
||||
}
|
||||
|
||||
@@ -29,10 +29,5 @@
|
||||
"reading": "s'està llegint {{host}}…",
|
||||
"copyCode": "Copia el codi",
|
||||
"copiedCode": "Copiat",
|
||||
"anonNearLimit": "Us acosteu al límit anònim. Registreu-vos per obtenir una assignació gratuïta.",
|
||||
"blockReasoning": "Pensant",
|
||||
"blockTool": "{{name}}",
|
||||
"blockRunning": "en execució…",
|
||||
"showThinking": "Raonament",
|
||||
"showThinkingHint": "Demana al model que pensi abans de respondre i mostra'n el raonament"
|
||||
"anonNearLimit": "Us acosteu al límit anònim. Registreu-vos per obtenir una assignació gratuïta."
|
||||
}
|
||||
|
||||
@@ -29,10 +29,5 @@
|
||||
"reading": "čtení {{host}}…",
|
||||
"copyCode": "Kopírovat kód",
|
||||
"copiedCode": "Zkopírováno",
|
||||
"anonNearLimit": "Blížíte se k anonymnímu limitu. Zaregistrujte se a získejte bezplatný příděl.",
|
||||
"blockReasoning": "Přemýšlení",
|
||||
"blockTool": "{{name}}",
|
||||
"blockRunning": "probíhá…",
|
||||
"showThinking": "Uvažování",
|
||||
"showThinkingHint": "Ať model před odpovědí přemýšlí a ukáže své uvažování"
|
||||
"anonNearLimit": "Blížíte se k anonymnímu limitu. Zaregistrujte se a získejte bezplatný příděl."
|
||||
}
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user