feat: per-model system prompt suffix for Gemini runtime (ops-95)#193
Merged
feat: per-model system prompt suffix for Gemini runtime (ops-95)#193
Conversation
- Add systemPromptSuffix to GeminiConfig interface - buildPrompt() appends suffix after soul/Flair context - tps.ts wires agentCfg.gemini.systemPromptSuffix from agent.yaml - Default: 'Be concise. Output only your final answer. No narration.' - Sherlock's agent.yaml gets review-specific suffix with gh-as instructions Addresses Nathan's token efficiency concern — Gemini narration was output tokens already burned; per-model prompt tuning prevents it upstream. 496/496 tests.
tps-sherlock
approved these changes
Mar 8, 2026
Contributor
tps-sherlock
left a comment
tps-sherlock
left a comment
There was a problem hiding this comment.
No security vulnerabilities found. This change allows for user-controlled extension of the system prompt from an already-trusted configuration source. The implementation is safe.
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Addresses Nathan's token efficiency concern.
Root cause: Gemini outputs full thinking narration ("I'll do X...") before the final answer — those are output tokens already burned.
extractFinalAnswerstrips the display but can't recover spent tokens. Fix must be upstream in the prompt.Changes:
GeminiConfig.systemPromptSuffix: appended after soul/Flair context inbuildPrompt()tps.ts: wiresagentCfg.gemini.systemPromptSuffixfrom agent.yamlagent.yamlgets review-specific instructions includinggh-as sherlock pr review --approve496/496 tests.