fix(google): use includeThoughts/part.thought for thinking handling#7593
fix(google): use includeThoughts/part.thought for thinking handling#7593jamadeo merged 1 commit intoblock:mainfrom
includeThoughts/part.thought for thinking handling#7593Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e108e2aa15
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: bf33a85cb8
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 9bf89d27b8
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Use includeThoughts/part.thought to handle thinking content and preserve thought signatures across active tool loops, including synthetic signature fallback for the first model tool call. Align thinking config by model family: - includeThoughts for 2.5/3 - thinkingLevel for 3.x - thinkingBudget for 2.5 - no thinking config for 2.0 This simplifies Gemini thinking handling across model families. Change-Id: I7ab897c5e423939ae38ab322dbf4f91898d3df8b Signed-off-by: rabi <ramishra@redhat.com>
| ) -> Option<MessageContent> { | ||
| let signature = part.get(THOUGHT_SIGNATURE_KEY).and_then(|v| v.as_str()); | ||
| let is_thought = part | ||
| .get("thought") |
There was a problem hiding this comment.
do you think these would benefit from defining structs that are serde::Deserialize? I see we're working a lot with Values here
* main: (270 commits) test(acp): align provider and server test parity (#7822) fix(acp): register MCP extensions when resuming a session (#7806) fix(goose): load .gitignore in prompt_manager for hint file filtering (#7795) fix: remap max_completion_tokens to max_tokens for OpenAI-compatible providers (#7765) fix(openai): preserve Responses API tool call/output linkage (#7759) chore(deps): bump @hono/node-server from 1.19.9 to 1.19.11 in /evals/open-model-gym/mcp-harness (#7687) fix: return ContextLengthExceeded when prompt exceeds effective KV cache size (#7815) feat: MCP Roots support (#7790) fix(google): use `includeThoughts/part.thought` for thinking handling (#7593) refactor: simplify tokenizer initialization — remove unnecessary Result wrapper (#7744) Fix model selector showing wrong model in tabs (#7784) Stop collecting goosed stderr after startup (#7814) fix: avoid word splitting by space for windows shell commands (#7781) (#7810) Simplify and make it not break on linux (#7813) Add preferred microphone selection (#7805) Remove dependency on posthog-rs (#7811) feat: load hints in nested subdirs (#7772) feat(acp): add read tool and delegate filesystem I/O to ACP clients (#7668) Support secret interpolation in streamable HTTP extension URLs (#7782) More logging for command injection classifier model training (#7779) ...
2 participants
Summary
Use
includeThoughts/part.thoughtto simplify thinking content handling and preserve thought signatures across active tool loops, including synthetic signature fallback for the first tool call.Align thinking config by model family:
includeThoughtsfor 2.5/3.XthinkingLevelfor 3.xthinkingBudgetfor 2.5This simplifies Gemini thinking handling across model families.
Type of Change
AI Assistance
Testing
Tested locally with all gemini models.