release: promote dev to main for v0.2.21 — forecast champion selector A–C#364
Merged
Conversation
chore(release): back-merge v0.2.20 into dev
…ful-skip-401 fix(api): skip showcase knowledge phase on embedding auth failure
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
…hots docs(docs): complete showcase dogfood screenshots
…tion fix(agents): persist pending_action for gated tool calls
fix(api): honor feature_frame_version >= 3 in ops + registry
fix(api): showcase agent step runs on local Ollama (no API key needed)
…lback fix(agents): non-streaming fallback for Ollama agent chat
Ollama's OpenAI-compatible /v1/chat/completions rejects any message whose content is JSON null and carries no tool_calls (400 'invalid message content type: <nil>'). A weak local model emits that shape for an empty assistant turn and PydanticAI replays it on retry, so every retry 400s and the run dies with FallbackExceptionGroup. Inject a sanitizing httpx transport into the OllamaProvider client that coerces outgoing content:null to content:"".
…344) A gated tool (create_alias/archive_run/save_scenario) records deps.pending_action the moment it fires, but does not halt the run. A weak model can ramble past the gate and exhaust its retry budget, so agent.run raises UnexpectedModelBehavior before returning and the post-run approval-surfacing path never runs. The captured approval is valid, so surface it: chat() and stream_chat()'s UnexpectedModelBehavior handlers now check deps.pending_action first and emit the approval (ChatResponse pending_approval / approval_required event) before falling back to the generic error.
) The chat Approve/Reject handlers awaited POST /approve but discarded the ApprovalResponse and only cleared the card, so a click produced no visible result — and a failed action execution (e.g. create_alias 'Run not found', returned as status=rejected + result.error) was silent. Capture the response and append a one-line report for every outcome (executed / approved-but-failed / rejected / expired) via a pure, unit-tested formatApprovalReport helper. Closes #346.
fix(agents,ui): Ollama chat HITL — null-content, pending-approval salvage, and approval report
fix(agents): constrain experiment read-only queries
fix(agents): stop experiment read-only tool-call loop
fix(agents): salvage experiment answer when weak model fails structured output
…or-backend feat(api,db): add forecast champion selector backend (#353)
…te-in-effect fix(ui): avoid setState-in-effect in RunHistoryStrip to unblock lint (#357)
feat(ui): add forecast champion selector foundation
feat(api,db,ui): forecast champion selector slice B — async comparison & results
feat(api,db,ui): forecast champion selector slice C — forecast decision, business summary & promotion (#362)
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Sorry @w7-mgfcode, your pull request is larger than the review limit of 150000 diff characters
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (5)
📒 Files selected for processing (118)
📝 WalkthroughWalkthroughAdds Champion Selector backend and frontend (Slices A–C): migrations, ORM, strict schemas, async runner, service, routes, UI, hooks, and types. Introduces config/env settings. Enhances agents HITL recovery and RAG embedding auth error handling. Updates docs and extensive unit/integration tests. ChangesChampion Selector End-to-End
Sequence Diagram(s)sequenceDiagram
participant UI (Champion Page)
participant Hooks
participant API
participant Service
participant DB
UI (Champion Page)->>Hooks: useSubmitSelectionRun(request)
Hooks->>API: POST /model-selection/runs
API->>Service: submit_run
Service->>DB: insert run+candidates (RUNNING/PENDING)
Service-->>API: 202 + monitor_url
API-->>Hooks: 202
Hooks-->>UI (Champion Page): selectionId
UI (Champion Page)->>Hooks: useSelectionRun(selectionId)
Hooks->>API: GET /model-selection/{id}
API->>Service: get_selection
Service->>DB: load run+children
Service-->>API: run with progress/ranking
API-->>Hooks: 200
Hooks-->>UI (Champion Page): render progress/results
Estimated code review effort🎯 5 (Critical) | ⏱️ ~120 minutes Possibly related issues
Possibly related PRs
Suggested labels
Suggested reviewers
Poem
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
|
This was referenced Jun 1, 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
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.
Release: promote
dev→mainfor v0.2.21Cuts the next pre-1.0 PATCH release (0.2.20 → 0.2.21). Merging this PR lets release-please open the
chore(main): release 0.2.21Release PR; merging that tagsv0.2.21.Headline — 🏆 Forecast Champion Selector (A → B → C)
model_selectionslice: candidate models, run lifecycle./visualize/champion.z·σ·√L), business summary, and champion promotion (registry run + alias with audit).Agents / Ollama hardening
pending_actionfor gated tool calls (fix(agents): persist pending_action for gated tool calls #336).RAG / Showcase
API / Ops / UI fixes
feature_frame_version >= 3in ops + registry (fix(ops,registry): honor feature_frame_version >= 3 (stop clamping to {1,2}) #338).RunHistoryStrip(fix(ui): RunHistoryStrip setState-in-effect lint failure blocks frontend lint gate #357).Validation
All five gates green on
devHEAD (ruff + format, mypy --strict, pyright --strict, pytest, migration-check). Alembic head:e4f5a6b7c8d9.Summary by CodeRabbit
New Features
Bug Fixes
Chores