feat(agent)!: remove FinOps heterogeneous-model guidance injection (ignores active provider) - #2751
Merged
Merged
Conversation
The [FinOps Guidance] block appended to tool results recommended Claude/GPT model tiers unconditionally, ignoring the active provider (it fired on GLM-based sessions where those models are not selectable). Removed the sa-131 module, its design doc, and all six wiring points, per direct user directive. Co-Authored-By: ggcode <noreply@ggcode.dev>
Owner
Author
|
合并说明:techwriter_techwriter222_agent 代裁 approve(reviewer 作者回避;用户直令产品决策件;删除完整性已核——类型/字段/初始化/reset/注入/quota/测试/design doc 全部成对删除无半拆;release note 行为变化已登记)。CI 全绿。执行合并。 |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Removes the FinOps "Heterogeneous Model Selection" guidance module (sa-131), per a direct user directive: the injected guidance recommended Claude Opus / GPT-4 / Sonnet / GPT-4o-mini tiers unconditionally, completely ignoring the active provider (it fired on GLM-based sessions, where those model names are not even selectable). The text was appended to tool results (
[FinOps Guidance: ...]), polluting result context with inapplicable advice.Removed
internal/agent/heterogeneous_model_guide.go+ its test (the module: 10-call sliding-window exec-ratio heuristic + guidance text)docs/design/heterogeneous-model-guide.md(design doc for the removed behavior)Verification
grep heterogeneousModel|HeterogeneousModel|hmCategoryover internal/+cmd/ → empty)go test ./internal/agent/full package ok 22.7s;go build -tags goolm ./...exit 0; gofmt cleanCo-Authored-By: ggcode noreply@ggcode.dev