Standardize eval policy, budgets, session metadata, traces, and cost accounting - #2902
Open
miguelg719 wants to merge 126 commits into
Open
miguelg719 wants to merge 126 commits into
miguelg719 wants to merge 126 commits into
Conversation
…solidation-04-cdp-diagnostics
…olidation-05-locator-wait-contract
…s/consolidation-06-frame-support
…solidation-04-cdp-diagnostics
…nsolidation-03-capture-recovery # Conflicts: # packages/integrations/core/src/facade/tools.ts # packages/integrations/core/tests/facade-tools.test.ts
…solidation-04-cdp-diagnostics
…/consolidation-08-native-routing
…idation-07-deepagents-lifecycle
# Conflicts: # packages/sdk-go/internal/extensionassets/stagehand-extension.zip
miguelg719
added this pull request to stack #2956
September 17, 2026 07:14
miguelg719
removed this pull request from stack #2956
September 17, 2026 07:15
miguelg719
changed the base branch from
evals/consolidation-11-verifier-results
to
main
September 17, 2026 07:23
miguelg719
changed the base branch from
main
to
evals/consolidation-11-verifier-results
September 17, 2026 07:24
miguelg719
force-pushed
the
evals/consolidation-11-verifier-results
branch
from
September 17, 2026 08:09
e9cf972 to
e0f2b1e
Compare
miguelg719
changed the base branch from
evals/consolidation-11-verifier-results
to
main
September 21, 2026 21:02
# Conflicts: # packages/integrations/core/tests/facade-tools.test.ts
This was referenced Sep 21, 2026
miguelg719
changed the base branch from
main
to
evals/consolidation-04-cdp-diagnostics
September 21, 2026 21:18
This was referenced Sep 21, 2026
This branch has not been deployed
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.
Defines one eval-owned autonomy policy and a shared result contract for external harnesses. Records policy channel/version, effective budget and unit, requested configuration, browser identity, execution reason, normalized usage and trace/timing metadata.
Unknown usage and subscription costs remain unavailable. Astra estimates also remain unavailable until per-request context-tier accounting exists. Other supported direct-provider estimates include the dated catalog source. Generic task JSON is preserved in results and verifier trajectories. Failed facade calls remain failures regardless of tool-output text; runner-owned telemetry determines run-level session loss. PR13 wires browser identity and budget helpers into existing adapters.
Validation: isolated shared-runner changes passed all 896 eval tests and eval typecheck. The complete repaired stack passed 30 build/typecheck tasks and 29 unit-test tasks, including 999 eval tests. Fresh CI passed on this PR’s current head.
Stack base:
evals/consolidation-04-cdp-diagnostics. Review this PR relative to its immediate predecessor.Reviewer entry points:
packages/evals/framework/evalSystemPrompt.tspackages/evals/framework/harnesses/externalRunner.tspackages/evals/framework/usageNormalization.tsReadiness: CI passed on
61aa53cfdb. Human review status is unchanged.Current open stack: #2893 → #2894 → #2902 → #2903 → #2889 → #2904 → #2905 → #2906 → #2907.