Why: The backfill contract test used a fake PK-magic docx as its fixture;
the new registration structural gate correctly refuses that shape, so the
contract was no longer exercised.
Evidence: The three affected runmgr tests pass locally with -count=1;
the full combined suite receipt follows on the task card.
Impact: Test fixture only; the gate behavior under test is unchanged.
Refs: Dev task feature/pptx-register-structural-gate
Why: Account disable could be followed by late Backend business writes, API key creation could implicitly create users, account bootstrap locks could invert, and directory cursors were process-local or leaked out-of-scope changes.
Evidence: Local go test ./... and isolated PostgreSQL package suites passed on the staged candidate; exact committed-head SELF replay and stage 6 human review remain pending.
Impact: Adds final account transactions and external-effect checks across HTTP, Host, Bus and run manager; tightens API key issuance and persists versioned cursor signing. Delegated RDM rename still needs the separately proposed real-operator contract, so A1 and stage 6 are not complete.
Refs: Documents U3 r1, approved A1-A4 amendment fb3a821, pending delegated-projection amendment 5783940, Dev feature/iam-u3-account-directory-recovery.
Why: A disable could commit after the run manager checked account state but before its final business message was stored.
Evidence: SELF receipts /tmp/iam-u3-final-settle-sqlite.json, /tmp/iam-u3-final-settle-pg.json, /tmp/iam-u3-backend-settle-all.json, /tmp/iam-u3-backend-settle-pg.json, and /tmp/iam-u3-http-two-instance-pg.json.
Impact: The final run transaction locks and rechecks the account, rejects post-disable business output, and permits only an account-denial failure record. Auth-off implicit local ownership remains explicit.
Refs: IAM U3 r1 stages 4-5; Dev feature/iam-u3-account-directory-recovery
Why: Disabling an account must stop in-flight work as well as new HTTP requests.
Evidence: SELF receipts /tmp/iam-u3-u2-runtime-regression.json and /tmp/iam-u3-u2-app-compile.json.
Impact: Run start, tools, HITL, streaming output, child runs and final settlement recheck the account independently of project authorization.
Refs: IAM U3 r1 stages 4-5; Dev feature/iam-u3-account-directory-recovery
Why:
Legacy project streams replayed upload filenames and parser metadata to newly
authorized members even though the underlying cards remained owner-only.
Evidence:
SELF real HTTP red regressions exposed legacy replay, spoofed sharing claims,
private-history pagination, and live delivery after membership removal. The
affected packages, uncached full Backend suite, isolated PostgreSQL Store suite,
and agent-system build pass after applying the event boundary.
Impact:
Registered lifecycle streams resolve trusted resource ownership and require an
internal publication proof for cross-owner delivery. Event and proof commit in
one transaction; v30 adds an additive SQLite/PostgreSQL sidecar without granting
access to historical events. Seen and visible cursors remain separate, revoked
members leave live streams, and unregistered base behavior remains compatible.
The storage migration tool preserves the new proof rows.
Refs:
project-member-access-implementation-plan.md Task 1 / R5; authorized legacy SSE
privacy follow-up; project-member-composed-legacy-project-history.json
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:
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: 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: 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: 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: 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 U5 remainder (KTD5/KTD9 + exit criteria) - commands must commit atomically with business writes, artifacts need a shared object store for multi-instance, and the two-real-process acceptance matrix must run in CI.
Evidence: full suite green on SQLite and real PostgreSQL 18.6 (35 packages each tier) - outbox tx test (rollback removes the command, commit makes both visible, idempotent re-enqueue), S3 store tests (SigV4-signed round trip, 404 sentinel, idempotent delete, presigned GET, env fallback), real-process acceptance (testbinary self-spawn of two serve processes with per-process identity and command consumers against one schema: same-conversation contention, cross-instance cancel command claimed exactly once, stale-owner settle fenced with run unchanged).
Impact: EnqueueCommandInTx for in-transaction command outbox and AppendEvents now notifies in the same transaction (KTD6 front half); blobstore.S3 (SigV4, presign, prefix isolation) injected from BLOBSTORE_S3_* env when configured, local fallback otherwise; realproc_test provides the process-level multi-instance acceptance gate (PG-env gated, runs in CI test-pg job).
Refs: proposals/2026-10-11-collaboration-storage-and-distribution.md U5 KTD5/KTD9, section 5 exit criteria; R4/R7/R10.
Why: plan U5/KTD4+KTD5 - before a second instance may serve writes, conversation execution must have a single valid owner (DB lease, epoch increments on takeover), stale owners must not settle (in-transaction fence check), and cancel/HITL must reach the executing instance via a persistent command inbox.
Evidence: full suite green twice-relevant on SQLite and real PostgreSQL 18.6 (35 packages each tier) - lease tests (claim/contention/re-claim/renew fencing/expiry takeover/monotonic epoch, command inbox idempotent enqueue, atomic concurrent claim) and multi-instance tests (same-conversation contention rejected, stale-owner settle fenced with run unchanged, cross-instance cancel consumed exactly once by the owner instance, non-owner does not consume).
Impact: v23 migration (conversation_executions + run_commands); ClaimConversation stacks a DB lease on PG tiers (15min, release on conversation release); settle path fenced (fenced runs emit run.fenced, no terminal write); StartCommandConsumer polls the inbox for commands on locally-owned executions (cancel routes to local cascade or DB-level close-out; HITL revalidates gate and rejects expired explicitly); server cancel/HITL fall back to command enqueue with 202 when the run is not local; app wires instance identity (host:addr on PG tiers) and starts the consumer.
Refs: proposals/2026-10-11-collaboration-storage-and-distribution.md U5 KTD4/KTD5; R4/R10.
Why: Generative UI U3 - the agent needs a real submission path and the
next turn needs to see prior pages: a built-in in-process plugin
registers generative-ui.present (exposeAsTool) carrying the catalog
(prompt=validation single source) with a schema-repair strategy
measured against real MiniMax-M3 deviations; the command bus gains an
owner-scoped tool gate so a disabled plugin stops injecting its tool
(execution guard remains in surfacesvc); ctxasm projects saved surfaces
back into context so the model can revise existing structure; doc-refs
are authorized against the owner's real artifacts.
Evidence: unit suites green (genui guards/epoch/doc-ref, gate fail-closed,
projection content); full go test ./... green; cmdbus/ctxasm also green
under AGENT_PG_TEST_DSN; real-model closed loop (env-gated
TestRealModelSurfaceLoop) passes: task->spec->save->projection->revise
with revision 1->2 and structure change, CNY 0.08 total.
Impact: New internal/genui package; additive cmdbus/ctxasm/runmgr/
runtime hooks; no storage or contract changes (U2 layer untouched).
Refs: Documents proposal r2 U3; Core PR #25/#26; Backend #143; Dev task
feature/generative-ui-u3
Why: deliverNotices re-invoked itself synchronously from a defer after a failed startNoticeRun requeued the batch - a persistently failing delivery (busy conversation, missing row, slow DB) recursed without bound and overflowed the stack (real-PG CI job 2352, internal/runmgr).
Evidence: regression test TestNoticeDeliveryFailureIsBounded (missing conversation row) hangs on the old code and passes with the fix; full backend suite green on SQLite and against real PostgreSQL 18.6 + Redis; clean-HEAD reproduction isolated an unrelated count=2 admin-login artifact.
Impact: failed batches now return after requeue (retried on the next enqueue or restart); notices arriving during delivery are picked up by a bounded loop tail instead of defer recursion; no behavior change on the success path.
Refs: Dev PR #333; plan R8 real-database gate.
Why: plan U3 remainder (R8/KTD13) - execution admission must be bounded and shared (leases in the database, parents yield while waiting so budgets cannot deadlock parent-child), and project authorization must distinguish read/edit/approve/execute/admin with default-deny for unconfigured actions.
Evidence: full suite green on SQLite and against real PostgreSQL 18.6 + Redis (isolated instance); new tests - admission_pg_test (enforcement, per-user, concurrent no-oversell), runmgr admission tests (saturated-budget sync spawn progresses, background children share the budget, bounded queue 429), server action-matrix tests (default deny, legacy adapter read-only, action-aware authoritative + fail-closed).
Impact: admission_leases (v21) with atomic lease accounting under an advisory lock; runtime.execBudgetGlobal/PerUser/execQueueMax settings (all zero = off, historical behavior preserved); conversation turns, background and sync subagents share the pool, parents yield around synchronous children and HITL waits; queue-full rejects 429 before writing; server gains ProjectAction matrix + SetProjectActionAuthorizer with legacy EXT-8 read fallback.
Refs: proposals/2026-10-11-collaboration-storage-and-distribution.md U3 R8/KTD13; docs/guides/team-storage.md section 9.
Why: the approved plan U3 (KTD3/KTD7/KTD10 plus minimal recovery isolation) requires concurrent submits to not silently overwrite, unknown-side-effect runs to never auto-resume, and the shared rate limiter to degrade conservatively instead of failing open.
Evidence: full backend suite green twice-relevant paths against real PostgreSQL 18.6 and Redis (isolated instance) and on SQLite; new tests - card_version_test (concurrent single winner), recovery_hold_test + recovery_holds_test (skip/release/fail-closed CRUD), ratelimit atomic-window and degraded-fallback tests.
Impact: AppendMessageWithRequest now allocates seq under the conversation advisory lock in one transaction; activity_cards gain version (v19) with SaveCardVersioned/GetCardVersion/CardVersion and cardsvc user mutations (status/pin/action/resolve-by-ref) return 409-mapped conflicts while system mirrors keep blind writes; recovery_holds (v20) with admin list/release endpoints and fail-closed resume skip; Redis limiter uses one Lua INCR+PEXPIRE script and falls back to a per-instance limit with a Degraded counter.
Refs: proposals/2026-10-11-collaboration-storage-and-distribution.md U3 KTD3/KTD7/KTD10; R3/R6/R7/R8.
Why: the approved collaboration plan U2 (KTD1/KTD8/KTD12) requires an explicit fail-closed team deployment tier, DDL-and-ledger-atomic migrations serialized across migrators, and a configurable PG connection budget with sanitized effective values.
Evidence: real PostgreSQL 18.6 + pgvector + Redis 8.10.2 local gate - full backend suite green twice with AGENT_PG_TEST_DSN/AGENT_REDIS_TEST_ADDR (isolated svc.sh instance collabtest:8897, redis 6399); SQLite suite green without env.
Impact: config tier+pool keys and validation; store PoolOptions + statement_timeout DSN param + single-transaction migration with PG advisory lock and SQLite _txlock=immediate + unknown-schema-version refusal; app tier guard fail-closed (team requires DSN+auth, no SQLite fallback); CLI flags and explain rows; tests for tier/pool parsing, atomicity fault-injection, racing migrators, old-schema upgrade; fixed pre-existing real-PG test defects (blind &search_path= appends in runmgr/pgbus helpers, pg_trgm per-schema install race, exhausted seq-conflict retries).
Refs: proposals/2026-10-11-collaboration-storage-and-distribution.md U2, KTD1/KTD8/KTD12; R2/R3/R7.
Why: the round-6 real-model dual-speed run showed MiniMax writing its
reasoning as inline <think> blocks; finishChild's partsText fed them into
the background notice turn and the inbox result card verbatim.
Evidence: new runmgr test covers closed-block stripping with body preserved
and conservative handling of unclosed blocks; go test ./... 32 pkgs green.
Impact: partsText removes closed <think>...</think> spans before summary,
notice, and card assembly; unclosed blocks are kept as-is.
Refs: Dev task feature/dual-speed-real-path.
Why: SR-B10 (RDM requirements/01 V2.1, ruling J-03) defines the task-level
dual-speed pattern: a fast lane gives immediate feedback while deep work runs
in background with queryable progress and results posted back to the inbox.
The base system had the background spawn/notice machinery but nothing the
user could see while it ran or collect afterwards, so heavy tasks just made
the user wait on a synchronous turn.
Evidence: go test ./... -count=1 green (32 pkgs); new runmgr tests cover the
card lifecycle on success (progress card -> done/ok with result summary and
artifact line, card.created/updated/status events) and on failure
(done/danger with the error), plus the cards==nil no-op path.
Impact: spawnBackground now registers an inbox progress card linked to the
child run and rewrites it with the result on completion; the delegate_task
description and base-method working prompt teach the fast-feedback-first
pattern; a #background mock demo exercises the whole path end to end.
Refs: RDM docs/requirements/01 UR-27/SR-B10; .tmp 03-V2 §任务快慢双速通用模式;
Dev task feature/dual-speed-tasks.
Why: the EXT-14 wiring made runmgr import cmdbus for the CommandSource
interface signatures, which adds a new edge backend/runmgr ->
backend/cmdbus outside the architecture baseline ratchet; the Dev
umbrella lint (lint-architecture) rejects the gitlink bump because of
it. The dependency direction was always meant to be inverted: runmgr
defines the port, the composition root adapts the bus.
Evidence: go build/vet clean; go test ./... 32/32 packages green;
grep confirms no internal/cmdbus import left in non-test runmgr files;
Dev-side lint re-run scheduled on the gitlink bump PR.
Impact: runmgr.CommandTool/CommandRequest/CommandResponse are local
view types; app.busAdapter now converts cmdbus types at the boundary
(Entrance still fixed to agent by runmgr). No behavior change; the
runmgr tests speak the view types instead of cmdbus ones.
Refs: Dev umbrella make test failure 'architecture: new dependency
edges backend/runmgr backend/cmdbus'; proposal 2026-10-09-ext-g1-b1-b3
(EXT-14); Backend #114.
Why: RDM's capabilities are rdm.* commands; the agent run has no bridge
to them, so the V0.1 end-to-end goal (full-conversation operation) and
the agent-driven two-trees-one-net access are unreachable (Q4 option A).
Evidence: SELF - red tests first: TestCommandToolsProjected and
TestCommandToolDispatchesThroughBus failed on undefined symbols, then
green; TestCommandToolsFiltering and TestCommandToolDispatchEnvelope
cover projection filtering (risk default low, description falls back to
title, unexposed commands absent) and the full dispatch receipt with
Entrance=agent preserved through CanonicalEntrance; go test ./... 32/32
packages ok.
Impact: agent-command pin cc1ad77 -> 5c6dd0c (library PRs #4/#5: optional
ExposeAsTool field + "agent" entrance). cmdbus gains CommandTool view and
Bus.CommandTools; runmgr gains SetCommandSource with projection into
runCtx.Tools (dedup: registry tools win) and routing in ExecuteTool -
model calls dispatch through the bus with Entrance=agent, Actor/Owner =
conversation owner, ConversationID set; high-danger commands keep the
inline-confirm-card flow via the bus; unregistered source = current
registry behavior. Composition root wires a busAdapter. No
pkg/extension change.
Refs: proposal 2026-10-09-ext-g1-b1-b3 section 2; Agent-Command #4/#5
Why: A member's agent cannot see published project knowledge inside a run
(runCtx.Retrieve and hostcaps.search are owner-only), and members can
neither see shared projects nor open conversations in them - both are P0
prerequisites for RDM G1 (EXT-13/EXT-15, proposal
2026-10-09-ext-g1-b1-b3-exec-backend).
Evidence: Red tests first - TestRunContextRetrieveShared (undefined
SetSharedKnowledgeAllow), TestInprocHostKnowledgeSearchShared (0 shared
hits), TestSharedProjectListAndConversation (empty list) all failed before
and pass after; go test ./... 32/32 packages ok.
Impact: runmgr gains SetSharedKnowledgeAllow and routes Retrieve through
RetrieveShared when the predicate is registered (nil = unchanged); hostcaps
search consults the same EXT-8 slot; GET /api/projects appends
adapter-authorized shared projects (projectView with shared flag, deduped);
POST /api/projects/{id}/conversations falls back to
CreateConversationInProject when the own-project path misses and the
adapter authorizes; store gains ListAllProjects (candidates only, callers
must filter through the adapter) and CreateConversationInProject.
Revocation takes effect immediately on both paths; absence of an adapter
is byte-for-byte the previous behavior. No pkg/extension surface change.
Refs: docs/proposals/2026-10-09-ext-g1-b1-b3-exec-backend.md (EXT-13, EXT-15)
Why: Real-run before/after evidence (phase01 card) showed later turns never
re-read the uploaded source (0 original reads in plan-followup) because the
attachment only existed in the current turn's injection and the context window
hard default was 32000 chars - a 25k-char transcript tripped the clear-on-first
request, replacing old tool results with a pointer the model has no tool to
follow. MiniMax is an interleaved-thinking model whose docs require <think>
blocks in assistant history; dropping them degrades later turns.
Evidence: SELF - new tests TestThinkReplayWrapsAssistantHistory,
TestContextWindowScalesFromTokens, TestThinkReplayEnabled,
TestPersistInputTextsAndListWorkspaceInputs; go test ./internal/... passes;
live before/after comparison on the golden task set recorded on the phase02
task card per the new policy clause.
Impact: models.chat.contextWindow/outputReserve/contextBuffer (tokens,
defaults 128k/16k/4k) drive the in-run clear threshold, converted to chars;
cleared tool results spill to <sandbox>/.agent/results with readable paths;
attachment parse text persists as inputs/<name>.md and the env section lists
all workspace inputs every turn; context.thinkReplay (auto|on|off, auto =
MiniMax) replays thinking blocks into request-side assistant history only.
Why: The DOCX parser only read w:r runs that were direct children of w:p, so
text inside w:ins, w:hyperlink and w:fldSimple was dropped with no warning,
violating the no-silent-degradation rule. Separately, runtime.exec is a
user-writable setting, so multi-user deployments could not reliably turn the
exec primitives off.
Evidence: SELF - red tests TestParseDocxTrackedChangesAndHyperlinks and
TestExecHardDisabledOverridesSettings failed before and pass after; backend
go test ./... (32 packages) passes; a mock-mode binary started with
--disable-exec-tools hides run_shell/run_python/register_artifact from
/api/tools even after the user sets runtime.exec=true.
Impact: DOCX paragraphs are decoded from the token stream at any depth;
deleted/moved-from text, field codes and mc:Fallback are excluded and
revised documents carry an explicit warning. New Options.DisableExecTools
(SurfaceVersion 2.5.0-experimental), CLI --disable-exec-tools, config key
disableExecTools and env AGENT_SYSTEM_DISABLE_EXEC_TOOLS; zero value keeps
current behavior.
Refs: Agent-System-RDM docs/proposals/2026-10-09-V22-review-and-implementation-plan.md (G0-7, B-5)
Why: Q3 WP2 retires the SpawnSubagent-compression execution path: all
WorkflowDef execution now goes through the wfcompile compiled graph, and
squad steps run on the agent-native kernel backend instead of the
agent-system step backend.
Evidence: runtime-level P4 parity tests (workflow_compiled_test.go):
registered branch lookup/errors, planned branch confirmation gate +
dynamic 8-step cap fail-closed before any HITL, model script switch
default-off, missing-slot HITL collection with compile-time rendering,
judge stream routed to the configured lightweight model (nil = fail-closed
verifier-unavailable). squadadapter TestOrchestrateRunsOnKernelStub:
four-phase skeleton runs end-to-end on the kernel stub (write_file
materialization, seeded skills, exec allowlist). server TestSquadOrchestration
reworked: kernel steps run in-process (no subagent child runs). Full
backend suite green; wfcompile/squadadapter/runmgr green with -race
(pre-existing llm_test fake race on main recorded as debt, CI does not
gate -race).
Impact: DELETED runtime/workflow.go + workflow_script.go (legacy step loop,
critic, script host) and their tests; squadadapter stepBackend
'agent-system' + profileForRole deleted; BuildBackends exported and
registers only agent-native; Orchestrate DefaultBackend -> agent-native;
builtin roles declare agent-native with write_file added to allowlists and
writer run_shell -> run_command (kernel tool name); runmgr default workflow
runner -> CompiledWorkflowRunner; mock #workflow demo runs compiled
(host-only steps). Model script branch keeps the single script-level
confirmation (no extra plan confirmation), matching legacy.
Refs: Q3 plan WP2 (2026-10-07-agent-stack-q2q3-plans.md); task card
.task/feature-agent-stack-q3.md
Why: subagent runs recorded zero tokens, cache hits were invisible in
run records, the usage event skipped terminal paths, and stream retry
existed only on the direct-chat path (audit N20 residual).
Evidence: go test -count=1 ./... green; TestRetryAttemptsMapping
(setting 0=off→-1, N→N), TestDirectRunUsageSplitOnRecord (Last* and
cache land in the run usage), TestSubRunAccountsTokens (subagent
accounting), TestAddUsageAccumulatesSplitFields (handle chain); pins
carry Agent-Native#35/#37/#38/#39, Agent-Squad#41, Core Usage fields.
Impact: run.Usage carries Last*/cache on every path; subagent runs are
accounted; runtime.llmRetries maps onto the library default (setting 0
disables via -1); the verifier wraps retry+fallback explicitly; retry
events surface as process parts.
Refs: Agent-Native#35-#39, Agent-Squad#41, N3 plan WP6
Why: memory recall lived as a product-side interface assertion with no
library port, AgentSpec.MemoryScope had no consumer, and the model had
no write-back path. The port (Agent-Native#34) now exists; the product
adapts it over memory_entries.
Evidence: go test -count=1 ./... green; TestStoreMemoryRecallScopeAndLimit
(scope filters and limit), TestStoreMemoryAppendRoundtrip (project
context inheritance), TestRunCtxStoreMemory (runCtx outlet),
TestDirectRunInjectsMemoryBlock (the [记忆] block reaches the request
with the pre-migration text shape and deterministic order).
Impact: assembly-side injection removed (the loop injects per request
— same text, no duplication); memory_write available on the kernel
path; recall defaults to all scopes (pre-migration semantics), with
AgentSpec.MemoryScope narrowing where hosts pass it.
Refs: Agent-Native#34, Agent-Squad#38, N3 plan WP5
Why: the library now pins eligibility, guards symlinks, reports partial
restores, and bounds the log (Agent-Native#33); the product wires
retention after successful rewinds and needed the HTTP-layer and
eligibility evidence.
Evidence: go test -count=1 ./... green; TestRewindFilesHTTPHappy and
TestRewindFilesHTTPBusy409 (HTTP happy + conflict),
TestBackendCheckpointEligibilityIsWriteFileOnly (the product surface
checkpoints exactly {fs_write_file}).
Impact: checkpoints.jsonl is compacted to the latest 200 anchors after
each successful rewind.
Refs: Agent-Native#33, Agent-Squad#37, N3 plan WP3
Why: InterruptRunning wrote done.json{status:interrupted} for every
child, and ResumeInterruptedChildren skipped anything with done.json —
graceful shutdowns never resumed (only SIGKILL-style deaths did). done
markers now split by status: terminal states block resume, interrupted
does not. Nested pins carry repairOrphanTail and the N6 fix.
Evidence: go test -count=1 ./... green; TestResumeAfterGracefulInterruptMarker
(resumed once and only once), TestResumeSkipsCompletedMarker (terminal
states still block).
Impact: after any restart, interrupted children with a stored request
re-spawn exactly once regardless of how the process stopped.
Refs: Agent-Native#30, Agent-Squad#34, N3 plan WP1
Why: child runs had no independent transcript, no resume path (sealed
interrupted only), in-memory completion notices lost on restart, and
the subagent Background declaration had no consumer.
Evidence: go test -count=1 ./... green; TestSubagentTranscriptFilesWritten
(request/transcript/done files), TestResumeInterruptedChildrenRespawns
(re-spawn with original task + transcript-path hint, resumed.json
idempotent), TestNoticesPersistAndRedeliverAfterRestart (persist →
reload → deliver → delete), migration v17 pending_notices with up/down
on both dialects.
Impact: per-run transcript dirs under the workspace root (auxiliary,
write failures never abort spawns); interrupted children with a stored
request re-spawn as background runs at startup (pre-WP5 runs stay
sealed); notices survive restart; delegate factory honors
Request.Background with a sync fallback when the host lacks background
support.
Refs: Agent-Native#29, Agent-Squad#33, N2 plan WP5
Why: I1 WP3 - chat routing and the HITL free-text pivot now share one
router consuming the library's command list, and both intent hosts
fold compatibility-equivalent input.
Evidence: go vet clean; go test ./... 30 packages ok, including the
existing workflow-route and server e2e suites unchanged (behavior
parity) and the new route package tests.
Impact: new internal/route package (unique router with explicit
priority rules); intentgate carries Commands and folds NFKC;
server.go and runmgr.go route through it; nested pins at intent
2554b50 and squad 6b7a991. Blueprint actions resolve to a squad
decision at the router level; per-run squad entry stays a recorded
follow-up (no silent misrouting).
Refs: Documents proposal 2026-10-07-agent-stack-n1q1i1-plans.md I1 WP3/WP4
Why: N1 WP2/WP3 host side - the kernel ask loop must reach the HITL
confirm card, and tool gating should run through the typed Policy with
the session-allow store port instead of a hand-built Request.
Evidence: go vet clean; go test ./... all packages ok, including new
TestConvAllowStoreKeysByName, TestPermissionAskRoutesToHITL, and
permissionAskOf tests. Nested agent-native pin at 9758a8d (PR #17).
Impact: runmgr.ExecuteTool decides via agentpolicy.Policy with
convAllowStore (keying unchanged: conversation x tool name);
runCtx.PermissionAsk routes kernel asks to the shared toolConfirmCard
HITL; direct and subagent loops pass PermissionAsk into the kernel
config (nil for hosts without the method, preserving legacy ask=reject).
Refs: Documents proposal 2026-10-07-agent-stack-n1q1i1-plans.md WP2/WP3; Agent-Native PR #17
Why: Masks must not be the only copy of a key, and personal instructions, lore hits, and candidate replies have to reach the model without rewriting the system prefix or deleting history.
Evidence: go test ./internal/store ./internal/ctxasm ./internal/settings ./internal/runtime ./internal/server. Migration v16 upgrades and rolls back. Startup snapshots settings before moving raw keys.
Impact: One labeled key is active per service. Excluding a message hides its whole run from the model. Regenerating appends another candidate and rewinds files to the user turn. User slash commands expand to prompt text and do not fire on their own.
Refs: docs/records/2026-10-04-sillytavern-review.md
Why: workflow scripts and run_tool_script should share one Python host, while a slow MCP server must not block the first prompt.
Evidence: GOWORK=off go test ./internal/runtime/ ./internal/app/ ./internal/settings/ ./internal/tools/ ./internal/runmgr/
Impact: runtime.codeOrchestration defaults to false, so the tool stays hidden. Workflow script confirmation and its longer timeout cap stay as they were.
Refs: feature/code-orchestration
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: workspace writes had no checkpoint, and a 5xx before any output stopped the turn instead of trying the next configured model.
Evidence: GOWORK=off go test ./internal/runtime/ ./internal/runmgr/ ./internal/tools/ ./internal/settings/ ./internal/server/ ./internal/app/
Impact: models.chat.fallbacks defaults to empty, so existing runs keep their model. Rewind restores only tracked writes and appends a system note. Usage records the model that served.
Refs: feature/durable-rewind
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Plan mode has to block writes, confirmations dropped the argument preview, and direct chat did not share its stop gate with squad members.
Evidence: GOWORK=off go test ./internal/store/ ./internal/tools/ ./internal/runmgr/ ./internal/runtime/ ./internal/server/ passed. Default mode still runs write_artifact; plan mode rejects it.
Impact: Empty permission mode keeps the profile allow, deny, and confirm lists. High-risk shell commands now ask. There is no bypass-all mode.
Refs: feature/permission-hooks
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Byte truncation split UTF-8, subagent results could return unbounded text, and a write could overwrite a file that changed after it was read.
Evidence: cutRunes keeps a two-character Chinese prefix; tool selection honors -name; checklist reminders go through the reminder bus.
Impact: Tool output limits count characters. A subagent result over 32000 characters is stored as an artifact and the parent sees the path. fs_write_file rejects an existing file that was not read in this run.
Refs: feature/context-engineering
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: A hard kill left runs in pending, running, or waiting_hitl, a busy send stored a message before the 409, finishRun could mark a run completed without an assistant message, and a full SSE buffer dropped events without closing the stream.
Evidence: GOWORK=off go vet ./... and GOWORK=off go test -count=1 ./... passed, including store, runmgr, bus, and server recovery tests.
Impact: Migration v14 adds runs.instance_id and messages.request_id. Startup reconciliation and shutdown share one seal. Turn and workflow sends claim a slot before writing. Duplicate request ids return the existing message. SettleRun updates the run and appends the assistant message in one transaction. A full subscriber buffer closes the channel so SSE can replay from the cursor.
Refs: Dev feature/pi-durable-borrow
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Tool calls stayed invisible until execution finished, and turn, tool, timeout, and output caps stopped long tasks early.
Evidence: go test ./internal/runtime/ ./internal/tools/ ./internal/prompts/ ./internal/squadadapter/ ./internal/runmgr/ ./internal/app/ ./internal/settings/
Impact: tool.call.delta and tool.output reach the client; default profile, subagents, and squad no longer cap turns or tool calls; exec timeout defaults to 600s with no hard ceiling. A profile or subagent maxTurns above 0 still applies.
Refs: feature/stream-display-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Plugin scripts and model-written scripts need the same step runner, without giving the script a way to call interpreters or start another workflow.
Evidence: go test ./... passed. Callbacks, denied tools, the 50-call cap, a 1MB line, and cancel-kills-the-process are covered. A model script does not run until the switch is on and the user confirms.
Impact: runtime.workflowScripts stays off by default. Plugin script bodies are copied into the launch. Squad entry still has no run_workflow.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: A matched intent needs to run the copied definition, ask for missing slots, and stop when a step or the whole workflow exceeds its retry cap.
Evidence: go test ./internal/runtime/ ./internal/runmgr/ ./internal/server/ ./internal/prompts/ passed. The five step kinds update the plan, an unparseable critic counts as a failure, and run_workflow by id runs the registered definition.
Impact: Squad entry does not declare run_workflow. Script steps still return an error until the script host lands. Goal and script arguments are rejected for now.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: A hit intent should start the bound workflow, and a command that shares the same id still has to win.
Evidence: go test ./internal/intentgate/ ./internal/runmgr/ ./internal/server/ passed. Recognize keeps slots and the missing-slot question. StartWorkflowRun copies the definition and selects the workflow runner even when mock is on.
Impact: Ordinary turns are unchanged. The workflow runner body is still a stub until the executor lands.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: A parent turn should be able to finish while children keep working, and a review should keep only findings that a second pass confirms. Users also need to override a profile's tools, model, and turn cap without adding dispatch tools.
Evidence: go test ./... passed. New cases cover overlay rejection, role mapping, queued notices, and dropping FAIL or unparsed findings.
Impact: Notices live only in memory, and each conversation allows three background children. Squad writer steps now use the writer profile.
Refs: feature/agent-harness-p3b
Co-authored-by: Cursor <cursoragent@cursor.com>
weichen
