Chat: finalize gracefully at tool-call cap + stop redundant loops #14
Merged
Conversation
….10.25) The @binlog chat participant hit a hardcoded round cap (depth > 10) and dead-ended with "Too many tool calls — stopping here." producing no answer, even after dozens of successful tool calls. The model also looped, re-issuing near-identical perf-tool calls (expensive_targets/tasks/projects with only cosmetic arg changes) until it exhausted the budget. - Graceful finalization: at the cap, make one final tool-free request so the model synthesizes a response from the data already gathered (reuses the existing no-tools fallback pattern). - Repeat-call short-circuit: byte-identical tool calls (name + args) reuse the earlier result instead of re-querying the MCP server, so commands like /summary converge within budget. Errored calls are not memoized, so transient failures remain retryable. - System-prompt tool-use efficiency rule: instruct the model to call each tool at most once per distinct args and stop once it can answer. Bumps version to 0.10.25 and updates CHANGELOG. Co-authored-by: Copilot <[email protected]>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The @binlog chat participant hit a hardcoded round cap (depth > 10) and dead-ended with "Too many tool calls — stopping here." producing no answer, even after dozens of successful tool calls. The model also looped, re-issuing near-identical perf-tool calls (expensive_targets/tasks/projects with only cosmetic arg changes) until it exhausted the budget.
Bumps version to 0.10.25 and updates CHANGELOG.