• Joined on 2026-02-17
grenade commented on issue helexa/helexa#223 2026-08-24 12:26:11 +00:00
/no_think is honoured on chat/completions but ignored on /v1/responses

Status after #277: one of three items done, and the repro no longer

reproduces — which is not the same as fixed

Re-ran the issue's exact repro against beast on the deployed build (74df8fd): …

grenade closed issue helexa/helexa#254 2026-08-24 12:25:57 +00:00
neuron ignores max_completion_tokens, so the output cap is unenforced for current OpenAI clients
grenade closed issue helexa/helexa#278 2026-08-24 12:25:56 +00:00
limit.output is a KV planning reserve advertised as an output ceiling — nothing reconciles the two
grenade closed issue helexa/helexa#277 2026-08-24 12:25:55 +00:00
The Responses translator silently discards conversation state — a truncated agentic turn can never be continued
grenade commented on issue helexa/helexa#278 2026-08-24 12:25:51 +00:00
limit.output is a KV planning reserve advertised as an output ceiling — nothing reconciles the two

Landed and verified — closing, with one item handed to #223

Merged 74df8fd0, deployed, checked against beast and through cortex.

The advertisement is now the ceiling:

neuron …
grenade commented on issue helexa/helexa#254 2026-08-24 12:25:34 +00:00
neuron ignores max_completion_tokens, so the output cap is unenforced for current OpenAI clients

Fixed and verified — closing

Landed as part of #278 (74df8fd0) rather than the branch described above: the four generation loops now take the cap from effective_max_tokens() (current…

grenade commented on issue helexa/helexa#277 2026-08-24 12:25:28 +00:00
The Responses translator silently discards conversation state — a truncated agentic turn can never be continued

Verified live — closing

Merged 6945cf98, deployed to the fleet, probed against beast's Qwen3.8-27B on 74df8fd.

The test plants a fact that exists only inside a replayed reasoning item…

grenade pushed to main at helexa/helexa 2026-08-24 12:24:46 +00:00
acef01bc4c Merge branch 'fix/fetch-the-models-own-prompt-format'
441cddea37 fix(load): fetch the model's own prompt format, not just its weights
Compare 2 commits »
grenade opened issue helexa/helexa#280 2026-08-24 11:56:55 +00:00
Every model neuron downloads itself is served with our prompt format, not its own
grenade created branch fix/fetch-the-models-own-prompt-format in helexa/helexa 2026-08-24 11:56:17 +00:00
grenade pushed to fix/fetch-the-models-own-prompt-format at helexa/helexa 2026-08-24 11:56:17 +00:00
441cddea37 fix(load): fetch the model's own prompt format, not just its weights
grenade pushed to main at helexa/helexa 2026-08-24 11:26:54 +00:00
74df8fd07f Merge branch 'fix/278-advertise-the-real-limits'
7f9e240a78 fix(limits): advertise the ceiling, price the budget the caller declared
Compare 2 commits »
grenade pushed to main at helexa/helexa 2026-08-24 11:12:15 +00:00
6945cf9871 Merge branch 'fix/277-responses-reasoning-roundtrip'
e9b43b572e fix(responses): stop discarding the caller's reasoning and extensions
Compare 2 commits »
grenade pushed to fix/278-advertise-the-real-limits at helexa/helexa 2026-08-24 11:02:14 +00:00
7f9e240a78 fix(limits): advertise the ceiling, price the budget the caller declared
grenade created branch fix/278-advertise-the-real-limits in helexa/helexa 2026-08-24 11:02:13 +00:00
grenade pushed to fix/277-responses-reasoning-roundtrip at helexa/helexa 2026-08-24 10:49:42 +00:00
e9b43b572e fix(responses): stop discarding the caller's reasoning and extensions
grenade created branch fix/277-responses-reasoning-roundtrip in helexa/helexa 2026-08-24 10:49:41 +00:00
grenade commented on issue helexa/helexa#278 2026-08-24 10:34:09 +00:00
limit.output is a KV planning reserve advertised as an output ceiling — nothing reconciles the two

A real client already reads this field, and our value would break it

Checked against the DSH/pi-ai source. pi-ai's provider discovery parses an OpenAI-compatible GET /models listing and…

grenade commented on issue helexa/helexa#137 2026-08-24 10:19:47 +00:00
Export live per-neuron:model load + capacity signals (in_flight / queue_depth / saturation / tok-s)

A case for what "saturation" has to mean here

An investigation on 2026-08-24 needed exactly the signals this issue proposes to export, could not get them from a dashboard, and had to reconstruc…

grenade commented on issue helexa/helexa#275 2026-08-24 10:19:37 +00:00
[epic] helexa.ai/games — nightly generative benchmark scored by people playing the results

A real run of this benchmark, by hand, with numbers

The operator ran the tower-defence prompt across three models through DSH on 2026-08-24 (~/git/tower-defense: opus5/, `deepseek-v4-flash/…