0121a1930f4c78b7fe467a358ba0ca820b265b06
3 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
0121a1930f
|
feat(helexa-acp): inject and parse Qwen3 Hermes tool format
Some checks failed
CI / Format (push) Successful in 38s
build-prerelease / Resolve version stamps (push) Successful in 42s
CI / Clippy (push) Successful in 2m33s
CI / Test (push) Successful in 5m45s
CI / Build cortex SRPM (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
build-prerelease / Build cortex binary (push) Successful in 5m13s
build-prerelease / Build neuron-blackwell (push) Successful in 6m0s
build-prerelease / Package cortex RPM (push) Successful in 1m27s
build-prerelease / Build neuron-ampere (push) Successful in 7m55s
build-prerelease / Package helexa-neuron-ada RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-ampere RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-blackwell RPM (push) Has been cancelled
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Has been cancelled
build-prerelease / Build neuron-ada (push) Has been cancelled
The OpenAI `tools` API field isn't load-bearing in this stack —
neuron's chat template renders only message.content, so tool
definitions sent that way never reach the model. Move both sides
of the tool conversation into the Qwen3 Hermes wire format the
model is actually trained on:
- Append a `# Tools` block to the system prompt describing every
available function (qwen3::render_tool_block).
- Parse `<tool_call>{json}</tool_call>` markers out of the streamed
content via a chunk-boundary-safe state machine (qwen3::ToolCallParser),
surfacing them as the existing CompletionEvent::ToolCall* events
so the agent loop doesn't change.
- Re-serialise assistant turns that called tools with inline
`<tool_call>` blocks and tool results as user turns wrapped in
`<tool_response>` (qwen3::render_assistant_with_tool_calls,
render_tool_response).
Verified against cortex+Qwen3.6-27B: the model produces a
well-formed `<tool_call>{"name":"list_dir","arguments":{"path":"/tmp"}}</tool_call>`
in response to a Hermes-formatted prompt.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
|||
|
4a51a54554
|
fix(helexa-acp): describe Stage 3 tools in the default system prompt
Some checks failed
build-prerelease / Build cortex binary (push) Blocked by required conditions
CI / Test (push) Waiting to run
build-prerelease / Resolve version stamps (push) Successful in 35s
CI / Format (push) Successful in 42s
CI / Clippy (push) Successful in 2m39s
build-prerelease / Build neuron-ada (push) Has been cancelled
build-prerelease / Package cortex RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-ada RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-ampere RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-blackwell RPM (push) Has been cancelled
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Has been cancelled
CI / Build cortex SRPM (push) Has been cancelled
CI / Build neuron SRPM (push) Has been cancelled
CI / Publish cortex to COPR (push) Has been cancelled
CI / Publish neuron to COPR (push) Has been cancelled
CI / Bump version in source (push) Has been cancelled
build-prerelease / Build neuron-ampere (push) Has been cancelled
build-prerelease / Build neuron-blackwell (push) Has been cancelled
The Stage 2 prompt told the model it had no tools, which models
trained for caution then dutifully repeat back ("Stage 2 build: no
tools available — I can't read files…"). Stage 3 ships tools in the
CompletionRequest.tools array, but the system message was still
overriding that. Update the default prompt to list the five tools
and instruct the model to use them rather than asking the user to
paste contents.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
|||
|
96fc379893
|
feat(helexa-acp): wire ACP agent loop for text-only conversations
Some checks failed
build-prerelease / Package helexa-neuron-ada RPM (push) Blocked by required conditions
build-prerelease / Package helexa-neuron-ampere RPM (push) Blocked by required conditions
build-prerelease / Package helexa-neuron-blackwell RPM (push) Blocked by required conditions
build-prerelease / Resolve version stamps (push) Successful in 41s
CI / Format (push) Successful in 38s
CI / Clippy (push) Successful in 2m35s
build-prerelease / Build cortex binary (push) Successful in 5m26s
CI / Test (push) Successful in 5m43s
build-prerelease / Build neuron-blackwell (push) Successful in 5m47s
CI / Build cortex SRPM (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
build-prerelease / Package cortex RPM (push) Successful in 1m23s
build-prerelease / Build neuron-ampere (push) Successful in 8m13s
build-prerelease / Build neuron-ada (push) Successful in 5m28s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Has been cancelled
Stage 2 lands the agent loop on top of the Stage 1 scaffold: session state with per-session cancellation, a system-prompt builder honouring HELEXA_ACP_SYSTEM_PROMPT_PATH / system_prompt_path TOML, and handlers for initialize / session/new / session/prompt / session/cancel that stream provider output back as session/update notifications. Verified end-to-end against cortex from Zed. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
