Thinking agent #576
Open
Thinking agent #576
+257
−107
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ities - Add new THINKING_AGENT chat mode with dedicated system prompt and tools - Introduce ReasoningEffort enum for controlling model's thinking depth - Add reasoning_effort parameter to SamplingParameters for fine-tuning responses - Rename tool_deep_thinking to tool_think with improved interface and prompts - Update chat passthrough to support optional system prompt prepending - Adjust tools filtering per chat mode to accommodate new thinking capabilities - Fix subchat and related modules to handle new parameters
…zation_compiled_in.yaml
…2k for RAG, 16k for generation) - Implementing smart token budget calculation for context prioritization - Adding line number references to file context for better traceability - Enforcing proper context gathering before processing - Adding safeguards against premature think() calls
…an code improvements
- Restructure agent prompt into clear sections with better formatting and headings - Add conditional formatting for files context in think() tool to avoid empty section - Streamline strategy steps with clear objectives and hierarchical structure - Keep core functionality intact while making documentation more readable
…to improve clarity and maintainability of AI responses
JegernOUTT
force-pushed
the
thinking_agent
branch
from
764c267 to
660d6b4
Compare
- Update 'think' tool configuration to use o3-mini model with larger context window (128k) - Pass subchat temperature parameter through deep thinking tool instead of hardcoded value - Clarify comment about token budget handling in deep thinking
…ader Only add Bearer authorization header when the API token starts with 'hf_' prefix, which is the expected format for Hugging Face tokens. This prevents invalid authorization attempts with empty or malformed tokens.
Previously, temperature was hardcoded to 0.0 and always required. This change: - Removes the TEMPERATURE constant - Makes temperature parameter truly optional in API calls - Updates logging to handle None case for temperature - Removes unused subchat_temperature from config
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.