Repository navigation
chore(vendor): bump tinyagents to main (typed TerminalOutcome) - #7125
Merged
Merged
Conversation
Update the vendored tinyagents submodule to a newer commit. Auto-committed-on: dragonfly Co-authored-by: Medulla <medulla@tinyhumans.ai>
Add tests for the session host driver covering progress tracing and journal projection cost rollup, and adjust the driver so these paths are exercised correctly. Auto-committed-on: dragonfly Co-authored-by: Medulla <medulla@tinyhumans.ai>
Extend the stalled model stream test to check that the typed terminal outcome carries a ProviderFailed reason classified from the generation stall, so the failure path is verified rather than only the partial narration. Auto-committed-on: dragonfly Co-authored-by: Medulla <medulla@tinyhumans.ai>
Tiny Sweeper reviewTiny Sweeper reviewed this change across 6 lane(s) and found 1 active actionable finding(s). Detailed lane evidence and any incomplete work are listed below. State: Reviewing pending checks Review snapshot
Completeness: Complete What changedThe review could not produce a supported behavioral summary; inspect the cited changed surface and lane details below. FeaturesNone identified with supported citations. TestsNo supported feature-to-test mapping was produced. Test execution is not inferred. Findings
Resolved this pass
Pending checks: Rust E2E (mock backend), Build Playwright E2E Artifact, E2E (Playwright / web lane), Desktop E2E (full suite, 3 OS) Before merge
How this fits togetherflowchart LR
n0["..._usage_does_not_roll_into_the_parent_turn<br/>changed"]:::changed
n1["turn_with_usage<br/>changed"]:::changed
n2["...ide_a_subagent_projects_a_child_tool_span<br/>changed"]:::changed
n3["...own_tool_call_projects_a_failed_tool_span<br/>changed"]:::changed
n4["...cts_failed_subagent_from_child_run_failed<br/>changed"]:::changed
n5["projects_turn_content_from_root_model_io<br/>changed"]:::changed
n6["spans_from_observations"]:::impacted
n7["with_capture_content"]:::impacted
n8["vec"]:::impacted
n9["turn_span"]:::impacted
n10["ctx"]:::impacted
n0 -->|calls| n6
n0 -->|tests| n6
n0 -->|calls| n8
n0 -->|tests| n8
n0 -->|calls| n9
n0 -->|tests| n9
n1 -->|calls| n8
n2 -->|calls| n6
n2 -->|tests| n6
n2 -->|calls| n8
n2 -->|tests| n8
n3 -->|calls| n6
n3 -->|tests| n6
n3 -->|calls| n8
n3 -->|tests| n8
n4 -->|calls| n6
n4 -->|tests| n6
n4 -->|calls| n8
n4 -->|tests| n8
n4 -->|calls| n10
n4 -->|tests| n10
n5 -->|calls| n6
n5 -->|tests| n6
n5 -->|calls| n7
classDef changed fill:#0d4429,stroke:#238636,color:#e6edf3
classDef impacted fill:#161b22,stroke:#6e7681,color:#c9d1d9
classDef flagged fill:#5a1e02,stroke:#d93f0b,color:#ffffff
classDef blocking fill:#67060c,stroke:#f85149,color:#ffffff
Agent review detailscritique
security
tests
commits
description
e2e
Evidence and run details
|
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configuration
📒 Files selected for processing (1)
Included review availability: This review used your included allowance. Your plan provides up to 10 included reviews per hour; 8 remain after this review. 📝 WalkthroughWalkthroughThe driver now classifies chained typed errors and carries terminal outcomes on failures. Successful driver outcomes set the outcome to ChangesTerminal outcomes
Priority: ⬇️ Low Estimated code review effort: 2 (Simple) | ~15 minutes Change: Other Suggested reviewers: Merge Risk: ⚪ Minimal · up to The change adds typed terminal outcomes to driver failures and keeps successful runs unchanged. No actionable merge-blocking risk remains. Architecture SummaryArchitecture risk: 🔵 Low · up to The change affects 1 system. Changed systems: Architecture concerns Review detailsSystems and components
Before / after behavior
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
A rabbit checks the typed error trail, Comment |
![tinysweeper[bot]](https://avatars.githubusercontent.com/in/4526585?s=60&v=4){kind=small}
There was a problem hiding this comment.
tinysweeper found nothing blocking. Approving.
$0.0064 · 90,328 in / 6,716 out · 12,086 cached (13%) · gpt-5.6-luna, glm-5.3-flash
critique: $0.0039 · 43,172 in / 2,129 out · 7,883 cached (18%) · gpt-5.6-luna
security: $0.0022 · 22,245 in / 655 out · 4,011 cached (18%) · gpt-5.6-luna
tests: $0.0001 · 6,323 in / 743 out · 64 cached (1%) · glm-5.3-flash
description: $0.0001 · 6,270 in / 191 out · 64 cached (1%) · glm-5.3-flash
e2e: $0.0001 · 7,191 in / 698 out · 64 cached (1%) · glm-5.3-flash
tinysweeper
Bot
added
the
priority: p2
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
…ilure Add a driver test asserting that a typed error still yields a terminal outcome when the transcript snapshot is empty, while an untyped error leaves the outcome unset. Auto-committed-on: dragonfly Co-authored-by: Medulla <medulla@tinyhumans.ai>
There was a problem hiding this comment.
tinysweeper found nothing blocking. Approving.
$0.0049 · 81,760 in / 4,607 out · 7,644 cached (9%) · gpt-5.6-luna, glm-5.3-flash
critique: $0.0025 · 27,616 in / 1,088 out · 4,066 cached (15%) · gpt-5.6-luna
security: $0.0022 · 26,393 in / 523 out · 3,578 cached (14%) · gpt-5.6-luna
tests: $0.0001 · 7,019 in / 308 out · 0 cached (0%) · glm-5.3-flash
description: $0.0001 · 7,055 in / 104 out · 0 cached (0%) · glm-5.3-flash
e2e: $0.0001 · 7,887 in / 856 out · 0 cached (0%) · glm-5.3-flash
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
vendor/tinyagentsto currentmain(c8b5c1f2, includes tinyagents#329).DriverOutcome/DriverFailurecarry an optional typedTerminalOutcome;AgentEvent::RunCompleted/RunFailedcarryoutcome: Option<TerminalOutcome>.TinyAgentsErrorin the error chain (stalled generation check, and aTerminalOutcomeattached to theDriverFailure) instead of matching rendered error text.Problem
tinyagents#329 changed public struct shapes (
DriverFailure,DriverOutcome,AgentEvent::RunFailed/RunCompleted), so the host no longer compiled against the new pin. The host also detected a stalled generation by substring-matching the error string.Solution
TerminalOutcome(reason, class, timeout phase,provider_started, message) onRunFailed/RunCompletedandAgentRun::terminal;DriverFailure.outcome/DriverOutcome.outcome; new lifecycle eventsTurnStarted,TurnCompletedandMessageAppended; a graph-driven agent loop driver; summarizer failures classified from their inner error; timeout phase backfill.outcome: Noneon successfulDriverOutcomes (runtime derives it frominterrupted), a typed outcome viaTerminalOutcome::from_erroron failures;journal_projectiontest literals updated. The new lifecycle events are not projected into spans by this PR.Submission Checklist
TerminalOutcome; existing literals updated)agent::session_host::driver_testsCloses #NNN: N/A, dependency bumpImpact
cargo check --tests(root andopenhuman-cliwith product features),openhuman-appcheck, clippy-D warnings,cargo fmt --check,pnpm rust:layout, feature-forwarding and submodule-monotonic checks,agent::lib tests (1792 passed,RUST_MIN_STACK=16777216).Related
Co-authored-by: Medulla medulla@tinyhumans.ai
Summary by CodeRabbit