Why:
Membership could be revoked while a tool waited for confirmation or a queued
HITL reply waited for consumption. Publication replacement also crossed an
empty project scope or another plugin's source namespace for the same Ref.
Evidence:
SELF replay of all four independent review reproductions failed before the
fix and passed unchanged afterward. Committed regressions cover direct and
queued HITL, yes/session confirmation, direct artifact writes, protected vectors,
exact empty project scopes, literal wildcard IDs and unregistered compatibility.
SELF uncached go test ./..., isolated PostgreSQL Store tests and static build passed.
Impact:
Recheck trusted live owner/project authorization when HITL resumes and at write
boundaries. Registered publishers replace only exact owner/project/ref/plugin
rows and vectors; ordinary unregistered publication semantics are preserved.
Refs:
Dev project-member-access implementation plan r1 Task 1; independent Backend
review findings against b9bea5bee0
Why:
Higher-ranked private rows could exhaust SQL candidate limits and hide an
otherwise authorized published slice from a member's current-project search.
Evidence:
SELF TestAuthorizedKnowledgeFiltersBeforeTopK failed with no shared hits before
the change and passed after it. SELF go test ./... and the isolated PostgreSQL
Store suite passed; independent replay and current-HEAD CI remain owner gates.
Impact:
Scan the resource-authorized shared fulltext path until enough allowed results
are found. Preserve ordinary legacy retrieval candidate limits and semantics.
Refs:
Dev project-member-access plan r1 Task 1; R5 published knowledge availability
Why:
Shared project reads previously doubled as write permission, project mutations
bypassed the domain lifecycle, and coarse retrieval shared private resources.
Evidence:
SELF red-before-implementation logs cover projection, lifecycle, private work,
resource filtering, canonical retrieval scope, publication source and namespace.
SELF go test ./..., isolated PostgreSQL go test ./internal/store -count=1,
and CGO_ENABLED=0 go build ./cmd/agent-system passed; task owner owns replay/CI.
Impact:
Add optional actor-scoped projection/lifecycle capabilities; registered providers
control public lifecycle and live work. Preserve owned conversation history and
ordinary unregistered behavior. Authorize knowledge by stored ID/source, map
current host scopes through trusted service metadata, and filter artifact lists.
Refs:
Dev project-member-access implementation plan r1 Task 1; approved design r0.1;
2026-10-13 trusted publication Source hardening ruling
Why: The login recovery contract leftovers and KTD12/KTD14 require:
concurrent same-name account creation must not overwrite the winner,
first-admin bootstrap must serialize across processes, the redeem
endpoint backoff must be shared across instances, revoked API keys
must close established SSE streams, and CLI credentials need an
env-DSN path plus a non-interactive 0600 file delivery mode.
Evidence: go test ./... green; new tests cover 16-way concurrent
create (1 win/15 conflict, winner credentials intact), 8-way
concurrent bootstrap (single admin, refuse takeover after), redeem
guard shared across two store handles on one DB, SSE stream closed
after key revocation within the recheck window, and HTTP 429 after
the failure cap (SELF worktree run; CI is the GATE, PG via test-pg).
Impact: Migration v29 (redeem_attempts); CreateAccount becomes a
single-row INSERT with unique-violation conflict; BootstrapFirstAdmin
advisory-locks (PG) / rechecks (SQLite) and commits admin+key+audit in
one transaction; SSE revalidation covers API-key streams; redeem
backoff moves to the shared DB; CLI gains AGENT_SYSTEM_DSN fallback
and --out file delivery for create/reset-password/issue-login-key/
bootstrap-admin.
Refs: docs/svc-deploy/2026-10-13-login-recovery-contract.md leftovers;
proposal r2 KTD12/KTD14/R5/R11.
Why: Since the system-managed settings change (#188), runtime.* writes
at the user scope are rejected, so the mock startup flag failed with
"system-managed settings require admin" and the serve process never
became healthy - the Dev multi-instance integration regression.
Evidence: go build ok; internal/app and internal/settings suites green
(SELF); the Dev composite CI on the follow-up PR re-runs
make test-multi-instance against this fix (GATE).
Impact: The mock startup flag now seeds runtime.mock via MergeSystem
(trusted operator input, effective for every tenant through the
Effective merge chain); no HTTP surface changes.
Refs: Dev PR #508; backend #188.
Why: The 2026-10-13 login recovery contract (Dev docs/svc-deploy/
2026-10-13-login-recovery-contract.md, plan item 6.7) requires that
established SSE connections stop receiving private events once a
password write destroys their session.
Evidence: go test ./... green; TestSSESessionInvalidationClosesStream
streams over a real HTTP server, invalidates the session via
AdminResetUserPassword, and asserts the stream terminates with the
session-expired marker within the recheck window (SELF, worktree run).
Impact: Session-authenticated event streams revalidate at a 15s
heartbeat cadence (package var, shortened in tests) and terminate on
invalidation; API-key streams are unchanged (key revocation is separate).
EventSource reconnects are rejected by the auth middleware.
Refs: Dev PR #504; login recovery contract section 6.7.
Why: The login recovery contract (2026-10-13) requires admin-issued
one-time keys, in-transaction revalidation of restricted sessions, a
login race guard, and audited password writes; the previous
implementation validated sessions outside the change-password
transaction and let stale password verifications create sessions.
Evidence: go test ./... green (SQLite); store tests switch to
openTestStore so the CI test-pg job covers real PostgreSQL, including
100-way concurrent redeem single-winner and auth-version race cases
(SELF, local run).
Impact: New migration v28 (users/sessions.auth_version,
account_events). New admin endpoints POST/GET
/api/admin/users/{owner}/login-keys and DELETE
.../login-keys/{id}. Login binds session creation to the verified
auth version and creates restricted sessions for must-change accounts;
redeem gains per-IP backoff; cookies gain Secure under TLS; active
change-password and admin/CLI resets become single transactions that
bump auth_version, revoke keys and sessions, and write audit events.
Refs: modules/documents/docs/proposals/2026-10-12-svc-unified-deploy-and-login-key.md r2; Dev task feature/svc-login-recovery-flow
Why: an unset S3 client passed through the Store interface is not a nil interface, so uploads panic instead of using the local artifact directory.
Evidence: TestIsNil and TestFinishOpenTypedNilS3UsesLocalArtifacts failed before this change and pass after it. The PostgreSQL case skips unless AGENT_PG_TEST_DSN is set.
Impact: only an unset blob store falls back; a constructed S3 or local store is unchanged.
Refs: internal/blobstore/blobstore.go internal/store/store.go
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: a rollback can only be safe when the candidate says which schema it
will migrate to and whether older binaries can still read that schema.
A new migration that forgets to register that fact must fail the test.
Evidence: go test ./internal/store/ ./pkg/identity/ -run 'TestMigrationCompat|TestCapabilities' passed.
Impact: version --json and identity capabilities include schema.target and
schema.compatFloor. Every migration version is listed in
migrationBreaksOldReaders. Current versions do not break old readers, so
the floor stays 0.
Refs: recovery plan r3.1 D2
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: identity ensure/verify went through the normal store open, which
creates a database and runs migrations. A deploy gate that calls the
candidate before stopping the old service could migrate production
ahead of the switch, and a missing database was turned into an empty one.
Evidence: go test ./pkg/identity/ ./internal/store/ ./cmd/agent-system/ -run 'TestCapabilities|TestEnsure|TestVerify|TestDSN|TestUsage|TestSystemIdentity|TestOpenIdentity|TestUnknownSubcommand' passed in this worktree.
Impact: identity CLI refuses a missing file or a missing agent_system_identity table, does not migrate, reads DSN from the environment or a 0600 file, and version --json plus identity capabilities emit one capability document. Unknown top-level commands exit 2.
Refs: recovery plan r3.1 D1; Dev feature/svc-d1-identity-flow
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Stop showing raw task text as progress and stop lighting the
done lamp on failed background runs (U1 whitelist).
Evidence: go test ./internal/runmgr/ -count=1
Impact: create/promote/finish card bodies; material queue status text.
Refs: fast-slow-channel-display-u1-plan W2; Core ba289e7
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: TestMaterialIntakeAttachmentOnlyLifecycle flaked when waiting on
systemTexts; deliverNotices runs before defer materialKeyRelease, so
done-dedup still saw the in-memory key and returned pending.
Evidence: go test ./internal/runmgr/ -run TestMaterialIntakeAttachmentOnlyLifecycle -count=20
Impact: Aligns the wait with materialExisting gates; no production change.
Refs: fix/material-intake-lifecycle-flake
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: main #171 claimed migration v26; rebase conflict required
bumping the U1 I3 table and completing copyOrder for both new tables.
Evidence: go test ./internal/store/ ./cmd/storage-migrate/ -run
'SystemIdentity|CopyOrder'
Impact: migrate v27; copyOrder += login_keys + agent_system_identity.
Refs: Backend PR #170; conflict with main 1d9e8f4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: U1 I3 needs a DB-side instance identity anchor matching
manifest.instance_id so wrong/missing DB blocks startup (I4).
Evidence: go test ./internal/store/ ./internal/app/; CLI smoke
ensure/verify on SQLite temp dir.
Impact: migration v26; store Ensure/Verify; identity subcommand;
serve checks AGENT_SYSTEM_INSTANCE_ID when set.
Refs: docs/recovery/u1-identity-manifest.md §5.2; Dev feature/recovery-u1-db-identity
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: system.intent ParamsSchema requires top-level text, but
SubmitAction only nested values under data, so button intent always
rejected missing text during prod acceptance.
Evidence: go test ./internal/surfacesvc/ -run TestSubmitActionFlattensDataIntoParams
Impact: B-class intent and other schema-required params work via actions;
submit still receives nested data.
Refs: GenUI prod deploy acceptance; fix track
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Async notice-run delivery raced with test teardown and in-flight
conversation runs (database closed / material lifecycle flakes).
Evidence: go test ./internal/runmgr/ -run Material
Impact: Reminders append as system messages only; material path still
inlines into startNoticeRun.
Refs: Dev PR #425 CI test-pg failure
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: lint-boundaries forbids backend/runmgr -> backend/genui; keep the
auto trigger as an injected interface with local reminder text.
Evidence: bash scripts/lint-boundaries.sh
Impact: No behavior change; wiring still via app.SetGenUIAuto(genui.NewAuto).
Refs: architecture boundaries
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: passwordless activation/recovery must redeem only into a
set-password session; account ops must not create empty stores.
Evidence: SELF go test store/server login-key and OpenExisting cases.
Impact: auth middleware gates; CLI user create defaults to activate key.
Refs: docs/svc-deploy/u4-one-time-login-key.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Generative UI U5 left the B-class action allowlist empty; owner
authorized first entries builtin.help and system.intent.
Evidence: go test ./internal/genui/ ./internal/surfacesvc/ ./internal/server/
Impact: Surface buttons may bind help/intent; button-entrance intent
matches only and does not nest-dispatch write commands.
Refs: docs/proposals/2026-10-12-generative-ui-bclass-help-intent.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: MiniMax-M3 emits XML-RPC-style {"item": ...} single-key wrappers on
array fields (kv/cells/items), bare scalar table cells, and page
submission delegated to the general sub-agent had no generative-ui
tool - observed live on dev (events seq 1395/1396/2171) where every
present with kv/table/list nodes failed invalid-spec and the delegated
retry reported the tool missing.
Evidence: red test reproducing the exact production error
(.nodes.1.kv of type [][2]string) goes green after the repair; full
genui/prompts/runtime/runmgr suites pass (SELF); mismatched-length
cells stay untouched by a dedicated guard test.
Impact: generative-ui pages with kv/table/list nodes save successfully
again; the general sub-agent can submit pages (tool resolves only when
the plugin exposes it, so absent plugins are unaffected).
Refs: dev task card feature/genui-spec-repair; dev conversation
激活验证-1012.
Why: the admin zone could not host plugin-declared partitions - KTD4
requires the RDM audit partition to be reachable by RDM domain admins and
base superadmins without hardcoding RDM into the base AdminZone.
Evidence: go test ./internal/app ./internal/server ./pkg/extension green
incl. new admin-zone recording/endpoint tests; surface snapshot test
green after surface.txt update; CI (Dev composite) is authoritative.
Impact: extension surface 2.8.0 -> 2.9.0 (Registry.AddAdminZone +
AdminZoneSpec, fail-closed on invalid specs); applyCompiled records
declarations into the plugin summary; new authenticated GET
/api/admin-zone/sections returns the flattened, ordered declaration list.
Entry visibility stays metadata-only - data capability remains enforced
by each section's own command surface (fail-closed).
Refs: WP3-I3/KTD4; task card feature-adminzone-plugin-sections.
Why: two-process HTTP acceptance (Dev tests/integration/multi-instance, added in
the matching Dev-side change) exposed three real cross-instance defects that the
U5 library-level tests bypassed via direct Manager calls, plus the U7 fault
matrix needs explicit disk-full rejection evidence.
Evidence: go test ./... green on SQLite and real PG (AGENT_PG_TEST_DSN);
new regressions TestCrossInstanceResolveDoesNotSettleCard (runmgr, PG-gated),
TestUploadRejectsCleanlyWhenObjectDirUnwritable and
TestArtifactOverwriteRejectsCleanlyWhenObjectDirUnwritable (server).
Impact: ResolveHITL no longer settles the card when the run executes on another
instance (command-bus fallback stays available); cancelRun enqueues the command
with the real conversation id and no longer reports a false local success;
object-store failures now provably leave zero DB/object residue.
Refs: collaboration storage proposal U7 (sections 3/5/7); task card
feature/u7-load-fault-release.
Why: U6 extends pages from conversations into the task/project
workspace - surfaces aggregate across conversations under the owner's
project scope (project resolved authoritatively from the conversation
row, never self-reported by the model), and the catalog guidance now
organizes pages by task phase (requirements/execution/acceptance)
while stating that task facts come only from real task records.
Evidence: build/vet clean; surfacesvc suite green incl. the new
project-aggregation test (owner isolation, cross-owner zero, history
retained post-disable); genui/store suites green.
Impact: New endpoint GET /api/projects/{id}/surfaces; Submit resolves
project from conversation; catalog text guidance. Existing endpoints
unchanged.
Refs: proposal r2 U6; Dev task feature/generative-ui-u6
Why: compiled-in plugins (generative-ui, rdm) never appeared in the admin
plugins list: GET /api/plugins only scanned the directory host, so binary-
level capabilities were invisible to operators (user-reported gap).
Evidence: go test ./internal/app/ ./internal/server/ green locally incl.
new TestApplyCompiledRecordsSummary and TestListPluginsMergesCompiled;
CI (make test) is authoritative.
Impact: applyCompiled records each plugin's registered commands/intents/
skills into a summary handed to the server; /api/plugins merges synthesized
inproc entries (backend.mode=inproc, apiVersion=extension surface version,
provides from the registration record). Directory entries win on id
collision. No public extension-surface change.
Refs: WP3-I4; task card feature-plugins-compiled-listing.
Why: Live E2E on the dev instance - the model keyed section children
as an object map (children.item.*), the strict decode rejected it, and
the page fell back to a file artifact; the guidance fix made the model
call present, this closes the remaining shape gap.
Evidence: genui suite green incl. the reproduction case; post-deploy
E2E rerun recorded in the Dev task.
Impact: Repair strategy only; validation unchanged.
Refs: Dev task fix/genui-page-visibility (E2E follow-up)
Why: at the 3-per-conversation cap the guaranteed material task was dropped silently, and long deliverables stayed in chat because cardflow defaulted off (user ruling 2026-10-11).
Evidence: new queue lifecycle test (queued card, hard-reject for model path, FIFO start on release, card promote) passes; full go test ./... exit 0 (local, SELF).
Impact: queueable system spawns create a queued progress card at capacity and start FIFO when a slot frees (memory-only queue; restart limitation noted); model delegate_task still hard-rejects; ui.cardflow default true (EffectNewRun).
Refs: Dev task .task/feature-material-intake-flow.md I3.
Why: after material organization completes, weak models report and end the turn without offering the user a choice of formal deliverables, and even after a user picks one the model may close the turn without starting the background task.
Evidence: new tests (notice-choice chain, deliverable backstop, free-input path, invalid args, notice contract) pass; full go test ./... exit 0 (local, SELF).
Impact: new confirm_choice tool issues a HITL choice card and routes the answer into a hard delegate instruction; material notices instruct the model to report then offer choices; stop hook adds two one-shot backstops (choice not offered in material notice runs; choice made but no background delegation).
Refs: Dev task .task/feature-material-intake-flow.md I2.
Why: the dual-speed entry hint is advisory only; real runs (MiniMax, 3 attachments, no text) end with a clarifying question and zero delegation, so background cards and result backfill never start.
Evidence: new unit tests in runmgr/material_test.go and runtime/material_flow_test.go all pass; full go test ./... exit 0 (local, SELF).
Impact: attachment-carrying runs now guarantee a material-organization background task (pre-spawn on attachment-only/heavy sends, stop-hook backstop otherwise when the model did not delegate); subagent receives inline parsed text with budget plus knowledge_search guidance; content-key dedup prevents duplicate spawns (in-flight, completed, resend); model-authored delegate_task gains a materials appendix; settings runtime.materialIntake (default on) and runtime.materialIntakeChars added.
Refs: Dev task .task/feature-material-intake-flow.md I1; user ruling 2026-10-11.
Why: plan U6 vector slice (KTD11 correctness step) - same-dimension vectors from different models must never mix, and PG tiers should run filtered exact top-k in the database instead of scanning every row in-process.
Evidence: full suite green on SQLite and real PostgreSQL 18.6 with pgvector (35 packages each tier) - pgvector_test covers model-identity and dimension isolation, update/delete atomicity (BLOB and vec_pg swap together), shared top-5 with score monotonicity, Recall@10 = exact-scan parity, deny-all predicate leakage; storage-migrate tests green after excluding the derived vec_pg column.
Impact: v25 migration adds model/content_hash columns and (PG, best-effort DO block) the pgvector extension plus vec_pg column - absence degrades to in-process scan; UpsertKnowledgeVectorExt dual-writes BLOB (cross-tier authority) and vec_pg; SearchKnowledgeVectorsModel/SharedModel filter by model identity and use SQL exact top-k (ORDER BY vec_pg <=> q) with automatic degradation; embedders expose Model() and the rag pipeline threads it through indexing and both retrieve paths; storage-migrate excludes vec_pg as a derived column.
Refs: proposals/2026-10-11-collaboration-storage-and-distribution.md U6 slice 3, KTD11; R9.
weichen
