chore: tighten uniform_failure suggestions after prefix-routing fix#67
Merged
Merged
Conversation
The "validator appears too weak" suggestion was actively misleading historically: hermes -m treated LiteLLM provider prefixes as openrouter routing, breaking auth and returning 0-turn sessions that the framework counted as task failures. Users (and reviewers) followed the suggestion to bump model strength when the actual fix was routing. Now that the routing bug is fixed (#66), the residual uniform_failure cases are more likely to be misconfiguration than capability. Lead the suggestion list with "first check the validator actually ran" and point users at the run.log line that confirms routing. Panel title softened from "validator too weak" to "closed-loop scored zero on every task" — observation, not diagnosis.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Loop-close on PR #66. The saturation pre-flight's
uniform_failurepanel was telling users "validator appears too weak — try a stronger --closed-loop-agent-model" when the actual cause was usually the silent prefix-routing bug PR #66 just fixed. Now that the routing bug is fixed, the residualuniform_failurecases are more likely to be misconfiguration than capability, and the suggestion ordering should reflect that.Changes
Suggestion list reordered:
Baseline scored 0 on every behavioral task — GEPA has nothing to optimize for)Stripped LiteLLM provider prefixrun.log line (the exact signal PR fix: strip LiteLLM provider prefix before hermes -m #66 added)Panel title:
Uniform failure — validator too weak→Uniform failure — closed-loop scored zero on every task. Observation, not diagnosis.Test plan
uv run pytest tests/core/test_saturation_check.py -q— expect 33 passed.uv run pytest -q— expect 1090 passed (no regressions).