Commit Graph

11 Commits

Author SHA1 Message Date
Guoguo 407707a7cc Revert "feat(agent): add vision/image support to agent pipeline" 2026-03-03 11:38:32 +08:00
Orgmar 12d4570a36 Merge pull request #990 from shikihane/feat/agent-vision-pipeline
feat(agent): add vision/image support to agent pipeline
2026-03-03 11:32:07 +08:00
shikihane 8ebeefc59f fix(agent,openai_compat): address review feedback on vision pipeline
- serializeMessages: preserve ToolCallID/ToolCalls when Media is present
- resolveMediaRefs: add 20MB file size limit to prevent OOM
- mimeFromExtension: return empty string for unknown extensions
- Add 11 unit tests for serializeMessages, resolveMediaRefs, mimeFromExtension

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 11:13:22 +08:00
Alfonso 946af6b53d feat: add LiteLLM provider alias support (#930) 2026-03-03 08:23:55 +11:00
winterfx 9efdde25ad fix: preserve reasoning_content in multi-turn conversation history
The openaiMessage struct and stripSystemParts() were not carrying over
the ReasoningContent field when serializing conversation history for
API requests. This caused thinking models (e.g. kimi-k2.5) to receive
incomplete assistant messages on subsequent turns, resulting in 400
errors from the Moonshot API.

Add the ReasoningContent field to openaiMessage and copy it in
stripSystemParts(). Also add a test to verify reasoning_content is
preserved when sending conversation history.

Fixes #588
Related: #876

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 16:23:05 +08:00
Yiliu 438f764c7a fix(providers): support per-model request_timeout in model_list (#733)
* fix(providers): support per-model request_timeout in model_list

* fix(lint): format provider constructors for golines

* refactor(providers): adopt functional options and preserve timeout migration

* docs(readme): sync request_timeout guidance across translated docs

---------

Co-authored-by: Yiliu <yiliu@affiliate-guide.com>
2026-02-26 19:08:19 +11:00
winterfx d224397f40 fix: preserve reasoning_content for OpenAI-compatible reasoning models
Models like Moonshot kimi-k2.5 and DeepSeek-R1 return a
reasoning_content field in assistant messages. When thinking is enabled,
the API requires this field to be echoed back in subsequent requests.
PicoClaw was silently dropping it, causing 400 errors on tool-call
round-trips.

- Add ReasoningContent to Message and LLMResponse types
- Parse reasoning_content in openai_compat parseResponse()
- Carry reasoning_content through assistant tool-call messages
- Add unit test for reasoning_content parsing

Fixes #588
2026-02-21 23:29:40 +08:00
Artem Yadelskyi 9e120f90ea feat(fmt): Run formatters 2026-02-18 21:48:23 +02:00
Jared Mahotiere c4cbb5fb35 providers: finalize PR213 review fixes
Phase 1: centralize protocol message/tool/response types in protocoltypes and keep compatibility aliases in providers and protocol packages.

Phase 1: preserve HTTPProvider constructor compatibility and route Anthropic api_base through factory auth/provider constructors with base URL normalization.

Phase 2: expand provider routing/auth tests (deepseek/nvidia/shengsuanyun, codex/claude oauth/codex-cli) and add openai_compat + anthropic coverage for proxy transport, model normalization, numeric option coercion, token-source refresh, and base URL behavior.

Phase 3: apply gofmt and validate with Dockerized tests (go test ./pkg/providers/... ./pkg/migrate and go test ./...).
2026-02-17 11:13:10 -05:00
Jared Mahotiere e3c246a36f Merge origin/main into refactor/provider-protocol-122 2026-02-17 09:28:56 -05:00
Jared Mahotiere a6e885bb47 refactor(providers): extract protocol factory and openai-compat transport 2026-02-15 08:04:07 -05:00