Why: native 855fe41 is the first head whose go.sum covers intent's NFKC import, so the later pins have to move with it.
Evidence: native go test of runtime, adapters, and exec passed; squad and backend vet passed on 855fe41 and 31ee395.
Impact: three gitlinks and the task card move. Product code in Dev is unchanged.
Refs: I4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev must record the intent, native, squad, and backend commits that close this batch so check-pins sees one tree.
Evidence: agent-intent 05e74d8, agent-native 11d1a76, agent-squad 1bb0c3a, and backend a494375 are the feature/agent-stack-r2 heads.
Impact: four gitlinks move and the task card records the batch scope.
Refs: R2 pin
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev must record the commits that contain the hold fixes, the offline pin check, and the CI checkout change.
Evidence: intent 7f7879b06b053f0a62746309b79e0e1b9a00f42d, native 91c155618487e21edeb4f1d3cc27e985aae2b0d2, squad e928ea3c0fa649cbbbad22a93a1bc0a12dee5f7d, backend ef0a1bef0f7bee626e59f160be51fb0e5f6aa692.
Impact: The four gitlinks match the open pull request heads. Other pins are unchanged.
Refs: feature/agent-stack-r0-r1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev could ship a combination whose nested gitlinks differed from the top-level pins, and make test never ran the three agent libraries.
Evidence: A go.work was measured and not adopted: workspace MVS selected newer golang.org/x crypto, exp, net, term, and text than backend with GOWORK=off. check-pins passes on the new pins and fails when backend's squad pin is 5cbac00.
Impact: make test adds pin checks and GOWORK=off vet/test for intent, native, and squad. make build still compiles inside backend; the pin check requires those gitlinks to match Dev.
Refs: R0
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The final reply still printed the artifact id and byte count.
Evidence: go test ./internal/runtime/ -run TestComposeReplyDropsInternalRefs
Impact: Backend gitlink moves to 46d5f7b.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The first composed reply still included the model's think block and the internal quality score.
Evidence: go test ./internal/runtime/ -run TestCompose
Impact: Backend gitlink moves to 1512ae5. No other module changes.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The work timeline was being shown as the answer, and file cards appeared before the run had a finished reply.
Evidence: make test
Impact: Gitlinks move to the final-reply branches. The timeline spec now includes the finalizing phase and delays deliverable cards until the reply is done.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Tool calls stayed invisible while arguments streamed, and a failed run hid the only reply inside the collapsed process block.
Evidence: make test in the worktree passed: boundaries, core, backend, frontend vitest 66, ui vitest 79, agent-command. Mock browser check showed the Chinese process summary, the reply outside the fold, a humanized error with 继续执行, and the back-to-bottom button.
Impact: Dev gitlinks move to the feature commits for core, agent-native, backend, ui, and frontend. DESIGN.md §9.6 describes individual tool blocks for exec, write, and delegate.
Refs: feature/stream-display-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: P4 is on main, and the shell pull request has to record UI and frontend commits that contain both the workflow contracts and the shell.
Evidence: submodule trees match the merged mains for core, backend, documents, ui, and frontend.
Impact: the shell branch now contains P4's example workflows and the combined pins.
Refs: feature/s4-shell-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The confirm card only folds after the client refetches the decision, so the parent pin has to include that frontend commit.
Evidence: make test passed; mock browser checked the shell, the pending filter, the blocked card, the folded row, and the molv theme.
Impact: task card records the result; modules/frontend moves to the refetch commit.
Refs: feature/s4-shell-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The molv theme and the rebuilt shell land together, so the design doc and the submodule pins stay in one change.
Evidence: UI npm test 79 passed; frontend tsc -b and npm test 61 passed.
Impact: DESIGN.md records the molv token table; modules/ui and modules/frontend point at the shell branches.
Refs: feature/s4-shell-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev should record the backend commit that runs a registered script from the launch of that call.
Evidence: go test ./internal/runtime/ -run TestRegisteredWorkflowUsesItsOwnScriptCopy passed.
Impact: Only the backend pointer moves.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev should record the backend commit that makes planning return JSON and makes the critic reject a missing line.
Evidence: go test ./internal/runtime/ ./internal/prompts/ passed on that commit.
Impact: Only the backend pointer moves.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The step critic has to call the configured model, and Dev should record that backend commit.
Evidence: go test ./internal/runtime/ -run TestJudgeUsesConfiguredModel passed in the backend repo.
Impact: Only the backend pointer moves.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev has to record the Core, Backend, Frontend, UI, and Documents commits that implement intent-to-workflow.
Evidence: make test passed, including boundary lint, core, backend, frontend vitest, UI tsc and vitest, and agent-command.
Impact: agent-native stays at a34689c. The example plugin is already on this branch.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The combination has to move together so background subagents, review, and the notice row are the same build.
Evidence: Each module's own tests passed on its feature branch. agent-native stays at a34689c.
Impact: Dev does not merge this pin. The four module pull requests stay open until review.
Refs: feature/agent-harness-p3b
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Subagents now run a profile-scoped tool loop and stay out of the parent history. The Dev checkout has to build that backend.
Evidence: Backend 5051a06; go test ./... and make test passed in this checkout. The three agent-native gitlinks stay a34689c.
Impact: Only modules/backend moves. Squad, core, and the three agent-native pins stay put.
Refs: feature/agent-harness-p3
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Direct runs now check artifacts and run a fail-closed verifier before they stop. The Dev checkout has to build that backend.
Evidence: Backend a3ae1b9; go test ./... passed in that checkout. agent-native gitlinks stay a34689c.
Impact: Only modules/backend moves. Squad and the three agent-native pins stay put.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the direct chat path and both consumers must compile the same agent-native commit, or the new loop fields exist in only one replace target.
Evidence: make test passed (boundaries, core, backend, frontend 51, ui 71, agent-command). The three agent-native gitlinks are a34689c.
Impact: Dev pins deps/agent-native, deps/agent-squad, and modules/backend. Squad behavior stays on the zero-value kernel switches.
Refs: feature/agent-harness-p1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The model imitated flattened tool-call text and invented artifact ids. P0 stops that replay, and the proposal records the harness work that still sits in later phases.
Evidence: Documents PR 32 and Backend PR 42. Backend go test ./... passed. Dev make test passed (boundaries, core, backend, frontend 51, ui 71, agent-command).
Impact: Gitlinks move to feature/agent-harness-p0 on documents (a3f0b80) and backend (188c633). No other submodule changes. P1-P4 are not implemented.
Refs: feature/agent-harness-p0
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Downstream products need a published extension surface, contract checks, and a sample plugin that does not modify the base.
Evidence: scripts/lint-boundaries.sh printed boundaries ok. examples/downstream-rdm go test passed. Submodule pointers record the core, documents, backend, ui, and frontend commits for this roadmap.
Impact: make test runs the boundary lint first. make plugin-new scaffolds a declaration plugin. Version tags and remote downstream repositories are not created.
Refs: .task/feature-base-extension-roadmap.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev has to record the library commits the product now builds against.
Evidence: make test
Impact: runtime.entry stays direct. This commit only moves gitlinks.
Refs: feature/native-squad-full-upgrade
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The product needs the new content rules and the optional squad entry, while the library pins must match the kernel and router those paths compile against.
Evidence: Backend go test ./... -count=1 passed on 268f4a9. runtime.entry stays direct because no paired live scores exist.
Impact: Dev now points at the quality and squad-entry backend, agent-native cfc840c, and agent-squad d38f838. make eval-deliverables runs the scorecard tests.
Refs: deliverable-quality-system
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The deliverable standards landed in Agent-System-Backend and were
merged, so the Dev pin has to move to that commit before this branch
can be reviewed.
Evidence: Backend PR #38 merged as 2079b2dfa851bd4cbe8f399a015126c842c441ec.
make test passed on this worktree before the pin move; the pin itself
does not change Dev source.
Impact: modules/backend now points at the merged standards. No other
submodule moved.
Refs: feature/agent-professional-deliverables
https: //git-home.u1680832.nyat.app:30319/weichen/Agent-System-Backend/pulls/38
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Main moved the backend pin to the B10 assembly after this branch
was opened, so the Dev pin has to follow the merged backend branch.
Evidence: modules/backend is b1fa89b, which contains origin/main and
the timeline changes. No other path conflicted.
Impact: This branch contains current main. The backend gitlink is the
merged feature tip.
Refs: feature/chat-timeline-preview
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Backend PR #36 closes the three open B10 sub-items (MCP config
injection, subagent bridge, explicit roles, skill-borne recipes); the
parent repo pins the new backend head.
Evidence: backend go vet + go test 21 packages ok; Dev make test all
green (core + backend 21 + frontend 42 + ui 68 + agent-command);
task card filled with per-item evidence.
Impact: modules/backend gitlink bump only; task card updated.
Refs: .task/feature-full-agent-b10-r2.md; Backend PR #36.
Why: Acceptance has to include the latest main, including the
agent-native kernel pin that landed in backend.
Evidence: Backend merge ca8aa5d contains both parents. go test passed
for runtime, tools, and squadadapter.
Impact: This branch now contains origin/main. The backend feature
branch includes that kernel pin.
Refs: feature/chat-timeline-preview
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The design system still described preview as a right-rail tab,
while the implementation now keeps a timeline in the transcript and
opens files in a closable pane beside the chat.
Evidence: make test passed (core, backend, frontend 51, ui 71, agent-command).
Impact: Dev pins core d437530, backend dab8f31, ui 8bfe8a8, frontend 0ed8ad3.
DESIGN.md §6, §9.3, and §9.6 match that layout.
Refs: feature/chat-timeline-preview
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the settled direction requires a complete agent kernel (web
search, code tooling, system tools, external tool calls, skills,
prompts) fused with squad orchestration; the three sub-repos landed
their batches and this bumps the gitlinks and records the task card.
Evidence: Agent-Native PR #3 (go vet + go test 15 pkgs ok), Agent-Squad
PR #3 (6 pkgs ok), Backend PR #35 (19 pkgs ok after rebasing onto the
concurrently merged #34); Dev make test all green (core + backend 19 +
frontend vitest 40 + ui vitest 68 + agent-command).
Impact: deps/agent-native -> f9ab2ef, deps/agent-squad -> 9a402e4,
modules/backend -> 87a3d0d; task card filled with per-PR evidence and
remaining-item notes (sandbox honesty, injection surfaces,
progressive enablement, deployment validation pending).
Refs: .task/feature-full-agent-r1.md batches B1-B10.
Why: The empty-create branch was synced onto frontend main after the input queue landed, so the parent gitlink must follow that tip.
Evidence: The synced tip 0cc0f40 is on frontend main, and vitest reported 42 passed with the default-project path still present.
Impact: Dev gitlink only.
Refs: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Frontend/pulls/29
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The input-queue branch was synced onto frontend main after the preview fallback landed, so the parent gitlink must follow that tip.
Evidence: Frontend main ba52fad contains aad5871, and vitest reported 42 passed on that tip.
Impact: Dev gitlink only. The queue and files tab stay, and the preview sniff changes remain in the pinned tree.
Refs: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Frontend/pulls/28
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The index branch was synced onto backend main after the interpreter merge, so the parent gitlink must follow that tip.
Evidence: Backend main 42fe619 contains 34be855, and go test of tools and runmgr passed on that tip.
Impact: Dev gitlink only. The write guard and text index stay, and the interpreter files remain in the pinned tree.
Refs: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Backend/pulls/34
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The first click on 新建任务 did nothing useful when the workspace had no project.
Evidence: Frontend 288d3ac; tsc -b passed and vitest reported 40 passed. A browser check on the dev server created 默认项目 and a conversation on the first click, and a second click added a conversation without a second project.
Impact: Dev gitlink only. Backend is unchanged.
Refs: modules/frontend fix/empty-create-task
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: follow-up messages were rejected while a run was in flight, and
the file list was only available from the workspace overlay.
Evidence: frontend 3c81525; tsc clean; vitest 42 tests.
Impact: gitlink only. Backend conversation serialization is unchanged.
Refs: task feature/input-queue
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: pseudo-binary Office writes and unsearchable generated documents
were the two pieces of the closed docx PR that main still needs.
Evidence: backend 3e5699c; go test ./... 19 packages ok. Dev #99 and
Backend #27 are closed as superseded.
Impact: gitlink only. Merge after Dev #113 so the refusal text names
tools that are already on main.
Refs: task feature/binary-doc-index
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the preview sniff branch predated the shell redesign and could not
merge. Module gitlinks now include current main plus ZIP fallback for
docx, xlsx, and pptx.
Evidence: conflict was only the shared sync-log card; both sides' rows
kept. UI and Frontend tests passed on the updated module SHAs.
Impact: parent branch contains origin/main. .mimosa/ ignore stays.
Refs: task feature/preview-sniff-fallback, Dev PR #96
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the open preview-sniff PRs were cut before the shell redesign, so
they could not merge. UI and Frontend now contain origin/main plus the
ZIP sniff, including xlsx and pptx text fallback.
Evidence: UI vitest 68 and tsc clean; Frontend vitest 40 and tsc clean.
UI pulls/21 and Frontend pulls/22 updated.
Impact: gitlinks only. Dev still needs to merge origin/main before the
parent PR can land.
Refs: task feature/preview-sniff-fallback
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the deliverable workflow prompts call run_shell and run_python, but
those tools were not in the registered binary, so generation fell back
to text-only write_artifact.
Evidence: backend feature/exec-interpreters 2880b58; go test ./... 19
packages ok in modules/backend.
Impact: Dev gitlink moves to the interpreter commit. Merge the backend
PR before this one so the recorded SHA is on backend main.
Refs: task feature/exec-interpreters
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the card was folded into PR #109 already marked complete, so
task-close skipped it; archive it manually per the no-open-cards rule
and advance the frontend gitlink past the mimosa-ignore chore (#26).
Evidence: .task has no deliverable-docx-r1.md left; precheck [cards]
to be re-run after merge; frontend -> de38791 (chore #26 merged).
Impact: housekeeping only; no code paths touched.
Refs: task feature/deliverable-docx-r1 (PR #109), frontend PR #26
Why: users received plain-text .docx files and had to dig through the
process collapse or workspace panel to find deliverables; deliverables
must appear directly in the conversation and open with real formatting.
Evidence: module PRs merged — Agent-System-Backend#31 (docgen Markdown
to styled OOXML, write_docx tool, artifact_ref pinned as content after
final text, prompt routing, mock #doc dogfood) and
Agent-System-Frontend#25 (deliverable card renderer, live projection
pinned tail). Combination `make test` green in this worktree: backend
go test 19 pkgs, frontend vitest 40/40 + tsc clean, ui tsc + vitest
68/68 incl design-guard, agent-command ok. Task card records scope,
sync nodes and leftovers.
Impact: gitlinks backend -> 8550bb0, frontend -> b048d90; core/ui
unchanged.
Refs: task feature/deliverable-docx-r1
Why: Submodule branches merged their origin/main (CF3) and were pushed;
record the new heads so the parent sync merges cleanly.
Evidence: submodules green post-merge (ui 68 / frontend 39 tests, tsc
clean); parent task-sync re-run follows this commit.
Impact: gitlinks only.
Refs: task feature/ui-tokens-v3.
Why: Land phase 4 of the UI redesign in the parent repo: ToolBlock chat
contract, Collapsible migration of all folds, live sweep with worked-time,
and the honest in-progress input hint. Completes the four-phase plan on
this branch (deviation recorded in the task card).
Evidence: combined make test -> go core/backend/agent-command ok, frontend
39 vitest passed, ui 66 vitest passed; tsc clean in both submodules.
Impact: modules/ui and modules/frontend gitlinks move to their
feature/ui-tokens-v3 heads; task card records results and remaining items.
Refs: task feature/ui-tokens-v3.
weichenandCursor