feat(context): ledger receipts name the invocation (call arg hint) - #34
Merged
Conversation
A compacted ContextSift receipt now includes a short hint of the call's key argument (shell command, file path, query, ...), so the ledger reads `run_shell(python3 build.py) -> ERROR: ...` instead of just `run_shell -> ERROR: ...`. With the conclusion (head+tail) change, a compacted tool exchange now conveys BOTH what ran and how it turned out. ContextManager pairs each tool result with its originating AgentToolCall (by id) to derive the hint. Regression coverage added. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to the receipt-conclusion fix (#32). A compacted receipt said that a
run_shellfailed but not which command. Now it includes a short hint of the call's key argument, so the ledger reads:run_shell(python3 build.py) → ERROR: … UnicodeEncodeError … [artifact-…]ContextManagerpairs each tool result with its originatingAgentToolCall(by id) and extracts a salient param (command/path/query/…, truncated). Together with the head+tail conclusion, a compacted tool exchange now tells the agent both what ran and how it turned out.Regression test: a compacted
run_shellreceipt names the command. All 129 tests pass.