feat(seer): Plumb reasoning_effort through trigger_autofix_explorer#114357
Merged
feat(seer): Plumb reasoning_effort through trigger_autofix_explorer#114357
Conversation
trigger_autofix_explorer previously hardcoded reasoning_effort to STEP_CONFIGS[step].reasoning_effort, leaving callers no way to override it. Add an optional reasoning_effort parameter that overrides the step default when provided, and forward the night-shift run's options["reasoning_effort"] through to it. Co-Authored-By: Claude <noreply@anthropic.com>
github-actions
Bot
added
the
Scope: Backend
…xplorer Add three regression tests: - trigger_autofix_explorer falls back to STEP_CONFIGS[step].reasoning_effort when no override is supplied - An explicit reasoning_effort kwarg wins over the step default - The night-shift cron forwards options["reasoning_effort"] into trigger_autofix_explorer Co-Authored-By: Claude <noreply@anthropic.com>
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit eb49649. Configure here.
…low" The override test asserts the explicit "low" reasoning_effort wins over the step default. If STEP_CONFIGS[ROOT_CAUSE].reasoning_effort ever changed to "low", the assertion would pass coincidentally even if the override plumbing broke. Assert the step default is not "low" so the test fails loudly if that happens. Co-Authored-By: Claude <noreply@anthropic.com>
rbro112
approved these changes
Apr 29, 2026
Use a module-level _UNSET sentinel as the default for the reasoning_effort parameter so callers can distinguish three cases: - not passed → fall back to STEP_CONFIGS[step].reasoning_effort - "low" / "medium" / "high" → use that value - None → bypass the step default and let the explorer client decide This mirrors the pattern already in src/sentry/integrations/vsts/client.py. Co-Authored-By: Claude <noreply@anthropic.com>
test_explicit_none_reasoning_effort_bypasses_step_default is strictly more sensitive than the "low" override test — it catches every regression the "low" test would, plus reintroductions of an is-not-None or truthiness fallback. Co-Authored-By: Claude <noreply@anthropic.com>
3 tasks
cleptric
pushed a commit
that referenced
this pull request
May 5, 2026
…114357) `trigger_autofix_explorer` previously hardcoded `reasoning_effort` to `STEP_CONFIGS[step].reasoning_effort`, so callers couldn't override it. Adds an optional `reasoning_effort` parameter that wins over the step default when provided, and threads the night-shift run's `options["reasoning_effort"]` through to it so per-run tweaks actually take effect. Note: this PR also forwards `options["intelligence_level"]` through to `trigger_autofix_explorer`. That intentionally changes the effective default for cron-triggered night-shift runs from `"medium"` (the `trigger_autofix_explorer` parameter default) to `"high"` (`DEFAULT_INTELLIGENCE_LEVEL`). The night-shift options are now the single source of truth for both knobs. --------- Co-authored-by: Claude <noreply@anthropic.com>
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
2 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.
trigger_autofix_explorerpreviously hardcodedreasoning_efforttoSTEP_CONFIGS[step].reasoning_effort, so callers couldn't override it.Adds an optional
reasoning_effortparameter that wins over the step default when provided, and threads the night-shift run'soptions["reasoning_effort"]through to it so per-run tweaks actually take effect.Note: this PR also forwards
options["intelligence_level"]through totrigger_autofix_explorer. That intentionally changes the effective default for cron-triggered night-shift runs from"medium"(thetrigger_autofix_explorerparameter default) to"high"(DEFAULT_INTELLIGENCE_LEVEL). The night-shift options are now the single source of truth for both knobs.