fix: persist runtime probe evidence#1213
Merged
Merged
Conversation
shaun0927
approved these changes
May 25, 2026
Collaborator
shaun0927
left a comment
There was a problem hiding this comment.
Cross-checked against #1190 (the L3-2 envelope + probe_runner contract) and #1181 (RuntimeEvidence substrate). Three things I verified:
- Persistence scope is correct —
state.runtime_probe_evidenceis per-session, hydrated at the start ofrun()and replaces the explicitself._last_probe_evidence = ()clear. This is not a "leak across AutoPipeline instances" regression because a freshAutoPipelineStatestill starts withruntime_probe_evidence=[]; the persistence only kicks in for resume/re-attach of the same logical session, which is exactly the gap #1190 acknowledged ("caches evidence... in the same run"). EnvRuntimeProbeRunneris strictly opt-in — returns()whenOUROBOROS_RUNTIME_PROBE_COMMANDis unset, so wiring it whenevercomplete_product=Trueis behaviorally identical to the previousprobe_runner=Nonedefault for any caller that doesn't set the env var. Aligns with #1190's "the caller decides".RuntimeEvidence.to_dict/from_dictround-trip is safe — explicit type validation for each field,_json_safe_payloadhandles non-JSON-safe values viadefault=strfallback, and_validate_loadedrejects malformed entries.from_dictdefaultingpayload.setdefault("runtime_probe_evidence", [])covers older state files cleanly.
No conflicts with the other open auto PRs since this touches auto/{pipeline,state,adapters}.py, mcp/tools/auto_handler.py, and orchestrator/runtime_evidence.py in additive places — verified against #1196 / #1194 line ranges. Safe to merge.
This was referenced May 25, 2026
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
Verification