Why: The active secret_keys row overrides settings plaintext, so a replaced chat key kept returning 401. Migration also mutated the settings map in place, so clearing a matching plaintext never reached the database.
Evidence: go test ./internal/settings/ ./internal/runtime/ -count=1 (SELF, worktree).
Impact: System settings writes adopt a changed secret; conflicting plaintext is kept and logged; 401 errors name the key layer and an 8-hex fingerprint.
Refs: fix/model-key-secret-overlay
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the parent sync needs a backend commit that contains both vision routing and the current main pin.
Evidence: incoming pin 80bb123 is an ancestor of origin/main; merge keeps cfde38d.
Impact: backend gitlink can record one resolved commit.
Refs: feature/four-model-vision
Why: Uploaded images never reached the model, so a text-only chat model could be asked to read a picture it cannot see.
Evidence: go test ./internal/... passed locally before this commit. Image-link rejection is covered by vision package tests.
Impact: Current-turn attachments and fetched image links become image input. History keeps a text placeholder. Image turns swap to the configured vision model when the chat model is not in the capable list, and fallbacks are filtered the same way.
Refs: Agent-System-Dev feature/four-model-vision
Co-authored-by: Cursor <cursoragent@cursor.com>
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:
Nested unchanged credential masks left empty parents that looked like managed
subtree overwrites. Shared members also hit an owner-only upload guard, while
upload ingestion cards could disclose private filenames and parser metadata.
Evidence:
SELF independent nested-mask probe, HTTP nested/mixed writeback, member upload,
project card privacy and authorization-change regressions failed before each fix
and passed after it. Affected settings/server suite passed; exact final-object
build and independent replay remain delivery gates owned by the task coordinator.
Impact:
Prune only parents emptied by ignored masks; explicit empty/real managed writes
stay rejected. Registered uploads check live work and trusted project existence,
keep originals owned by the actor, and recheck before persistence. Suppress only
upload project cards when no private stream exists; explicit structure cards and
unregistered upload behavior remain available.
Refs:
Dev project-member-access plan r1 Task 1/R5; independent nested mask P2;
2026-10-13 composed member-upload and private project-stream acceptance findings
Why:
Legacy project metadata can contain credentials outside the settings scope table.
Sharing raw projection settings exposed them, and generic project PATCH bypassed
the system-managed path guard already enforced by project settings endpoints.
Evidence:
SELF member Host regression failed before the fix. The fixed 4f72aaf server
baseline overlay reproduced HTTP metadata leakage and managed PATCH returning 200.
SELF shared Host-to-HTTP, immutable mask, dotted/schema/fallback, public mutation
and atomic managed-write regressions passed; uncached full suite, isolated PG
Store suite and static build passed. Independent delta replay remains a gate.
Impact:
Registered lifecycle metadata returns detached credential-masked views while
preserving service/configuration keys and persisted data. Generic project PATCH
shares the existing managed validator before rename or settings mutation; allowed
metadata key shapes and raw owner-only management lookups remain available.
Refs:
Dev project-member-access plan r1 Task 1 and R5; approved hard secret boundary;
2026-10-13 shared project metadata review 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: 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: the dual-speed slow lane shipped as an observable capability plus soft
prompt guidance, but on the real (non-mock) path models routinely grind
through heavy document tasks synchronously for minutes with zero user-visible
output - the pattern only engages when the model happens to think of it.
Evidence: five new unit tests over an injected clock cover fire-after-threshold,
quiet-before-threshold, disabled-by-setting, and the replied/delegated guard
paths (reminders observed in the captured kernel requests); full go test
./... 32 pkgs green. Real-model run recorded in the Dev task card.
Impact: runDirect tracks run start, user-reply, and background-delegation
state; reminders() injects a one-shot dual-speed nudge (SR-B10) once elapsed
time crosses runtime.dualSpeedNudgeSeconds (default 75s, 0 disables) while
the user has neither a reply nor a background lane. New setting registered.
Refs: Dev task feature/dual-speed-real-path; SR-B10 (RDM requirements/01 V2.1).
Why: Real runs were fully serial: the direct path never set the kernel's
parallel tool mode, delegate_task handed the parent only the child's
160-char summary (the full text was dropped), MiniMax streamed its
reasoning inside content <think> blocks, and the EXT-16 sandbox hid
~/.local so python-docx/openpyxl/pptx could not even import. All four
were measured defects (F1/F2/F3/F5) in the delegation/routing proposal.
Why: Serial-only mutual exclusion is not enough for order-sensitive
tools - the card-stream test failed with out-of-order appends - so the
ordering moved into the kernel (SerialTools partition, Agent-Native
#44); process events pair by CallID (#42) and tool results write back
through the injected call context (#43).
Evidence: go test ./... green, including new regression anchors:
TestDelegateToolReturnsFullText, TestToolEventsPairByCallID,
TestToolExecModeAndSerialSet, TestOpenLLMClientReasoningSplitAuto,
TestSandboxArgvDepsLayer, TestExecEnvJoinsPythonPath.
Impact: Direct runs now execute independent same-turn calls
(searches, reads, delegate_task, review_findings) concurrently by
default (runtime.parallelTools=false restores sequential); card flow,
plans, workflows, exec primitives and file edits keep model-declared
order. delegate_task returns the capped full child text. MiniMax-*
models get reasoning_split=true so thinking streams via
reasoning_content. --exec-deps-dir/AGENT_SYSTEM_EXEC_DEPS_DIR mounts a
read-only dependency layer into the sandbox and merges PYTHONPATH.
Bumps deps/agent-native to c348441.
Refs: proposal 2026-10-10-agent-delegation-routing-sandbox.md (E1,
F1-F5); Agent-Native #42/#43/#44; Dev task feature/agent-e1-parallel-fixes.
Why: User rulings 4/5 plus the P2-P4 live evidence. Keyword scoring dimensions
(readability, actionability) kept failing valid documents - normal Chinese
section headings flagged as column titles, loops of 4 corrections - because
they grade writing preferences, not verifiable facts. Unverified numbers
(~10-13 per run) remained the largest quality leak through every phase.
And the verifier runs on the same model as the worker (lightweight falls back
to chat), so "independent" verification was self-review. Separately, svc
seeding after boot never registered the tavily tools until a restart because
keys were snapshotted at startup.
Changes: quality.HardFacts (lint actually ran + zero errors) replaces the
full ScoreBytes projection in CheckArtifacts - keyword dimensions remain in
ScoreBytes for eval visibility only. New fact-consistency check
(runtime.factCheck, default on): extract percentages/dates/large numbers from
deliverable text, trace each against the material corpus (attachment text +
tool evidence); misses get exactly one correction round (fix, drop, or mark
as target/estimate), never a loop. runVerifier skips same-source model
verification unless runtime.verifierSameModel is set (hard facts + fact check
still run). Search tools now register lazily, reading tavily keys per call
(settings/seeding take effect immediately).
Evidence: SELF - TestHardFactsIgnoresKeywordDimensions,
TestHardFactsKeepsLintUnavailableBlocking, TestUnverifiedFactsAndNotice,
TestFactCheckContinuationOnce (fact note fires, corrected run passes);
go vet + go test ./... pass; live before/after on the golden task set
recorded on the phase05 task card per the policy clause.
Impact: Gate stops rejecting valid documents on stylistic grounds; invented
figures get one forced correction round; same-model verification no longer
pretends to be independent; tavily config is hot. No contract or storage
changes.
Why: User rulings 4 plus the P3 live evidence. The base library taught layout
standards but not how to work: no planning discipline (plan tool used in 2 of
31 tool runs), no retry-escalation rule (same failing call retried verbatim),
no check-API-first rule (phantom API calls), and nothing about edit
granularity - the P3 after-run showed one turn of 27 single-line edits plus a
self-review spiral (117 tools). The final-reply rewrite layer sees only
160-char summaries and fabricated chapters/promised unfinished work; with the
transcript now authoritative the working model already has full evidence, so
per ruling 4 the rewrite defaults off (kept as fallback when a work loop ends
with no user-facing text at all, plus opt-in setting).
Changes: new base.method module (plan-first for 3+ steps, switch approach
after two failures, check API signatures before scripting, batch edits with
multi_edit, persist to completion - never end on a promise, trace numbers/
dates/names back to source material or mark speculation, honest final
report); tool-description overrides for read_file/edit_file/grep/glob/
run_python/run_shell (dedicated tools over cat/sed, build pipeline for Word);
plan reminder now also nudges once when NO plan exists after several tool
turns (ignorable, once per run); runtime.composeFinal default true->false
with empty-body fallback.
Evidence: SELF - TestPlanlessNudgeFiresOnce (fires once, never repeats),
TestResolveSystemDefaultBase updated for the ninth base block; go vet +
go test ./... pass; live before/after on the golden task set recorded on the
phase04 task card per the policy clause.
Impact: Behavior-surface change only; no contract or storage changes.
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: spans now follow the OTel GenAI convention (Agent-Native#32); the
product needs the settings surface for the exporter, a meaningful
service.name, and per-profile agent names.
Evidence: go test -count=1 ./... green; TestTelemetryFlagsDefaults
(otlpEndpoint registered default empty = no export, serviceName
default agent-system-backend); nested pins carry the convention work.
Impact: nothing is exported unless telemetry.otlpEndpoint (or the env
var) is set; agent spans are named by profile id.
Refs: Agent-Native#32, Agent-Squad#36, N3 plan WP4
Why: I2 increments 1-2 shipped the agent-intent ports (SemanticScorer,
CommandGenerator); the backend still had no implementation, so the slow
lane could not be enabled in the product.
Evidence: go test ./... green; lint-boundaries ok; the two new
runtime.intentSemantic / runtime.intentGenerator flags are registered
with default false and the gate defaults to the I1 recognizer when both
are off (TestIntentSlowLaneFlagsDefaultOff, TestGate*).
Impact: no behavior change by default; enabling runtime.intentSemantic
routes ambiguous rule matches through embedding cosine scoring, and
runtime.intentGenerator lets the lightweight model propose commands on
fallback with library-side fail-closed validation. Nested agent-intent
pin moves to 343b1e6 (I2 increments 1-2).
Refs: I2 increment 3
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: A dotted-key PUT was stored beside the nested object and never read, so replacing a key kept the old pool. GET also returned tools.tavily.apiKeys in clear text, and saving settings would write the mask placeholder back over a real key.
Evidence: go test ./...
Impact: Dotted writes take effect on the next read. Startup expands stored dotted keys, and the existing nested value wins when both forms exist. GET masks schema secrets, including apiKeys. Writing the mask placeholder no longer overwrites a stored secret.
Refs: fix/settings-dotted-keys
Co-authored-by: Cursor <cursoragent@cursor.com>
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: The direct path never retried provider timeouts, so a single 429 failed the run.
Evidence: go test ./internal/settings/ ./internal/runtime/ passed. Default runtime.llmRetries is 2.
Impact: Retries happen only when the stream has not forwarded a delta. Injected test streams are not wrapped.
Refs: feature/llm-robustness
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: End-of-turn checks were injected as user messages, so the model answered the checker instead of the user, and the last draft was treated as the reply.
Evidence: go test ./internal/runtime/ ./internal/prompts/ ./internal/settings/ ./internal/ctxasm/
Impact: Rejections are system reminders. A main-model compose step writes the user-facing reply when tools were used. Deliverable cards stay after that reply.
Refs: feature/final-reply-compose
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: A direct run could stop on a missing file, a failed lint, or an unverified claim. The final turn now checks registered artifacts and asks a tool-less verifier, and nudges stale plans and todos.
Evidence: go test ./... passed. New runtime tests cover missing and empty artifacts, docx lint errors, verifier reject-then-pass, unparseable and failed verifier calls, nil verifier tools, todo reminders, and the false-deliverable fixture.
Impact: Direct runs with runtime.verify (default on for new runs) spend one extra lightweight call on every final turn. Setting it off keeps the previous stop behavior. Squad and SubLLMRunner are unchanged. The agent-native pin stays a34689c.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Squad steps previously ran without tools, and the product had no way to make the squad the conversation entry without losing streaming, cards, or the deliverable guard.
Evidence: go test ./... -count=1 passed, including streaming, cardflow, false-deliverable rejection, tool allowlist, model routing, usage, cancel, and turn and tool budgets.
Impact: runtime.entry defaults to direct. squad uses one kernel step for simple work and the leader for the rest. squad_orchestrate is hidden in that mode. The default is not switched.
Refs: deliverable-quality-system B3-B5
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Generated files kept Word's default theme, US Letter pages,
hand-typed bullets and empty sections. Recipes only showed library
calls, the prompt had no craft standard, and seeded skills could not
be upgraded once written.
Evidence: go test ./... passed. The house-style suite covers three
themes across docx, pptx and xlsx, and rejects a document that repeats
the diagnosed layout failures. lint on the sample minutes exits 1.
Impact: Every run gets a resident quality standard. Office files use
house-style (switchable themes, templates, imitation) and must pass
lint. Skill seeding upgrades untouched builtins and keeps user edits.
Uploads land in inputs/, and the default style is a setting.
Refs: feature/agent-professional-deliverables
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: conversation transcripts were the only project channel not
readable across sessions (artifacts/knowledge are already shared),
which caused duplicate parallel work; see proposal
2026-09-30-cross-session-reading.
Evidence: runmgr/crossread_test.go covers the full gate matrix
(project gate on/off x outbound flag x private target x cross-project
x cross-tenant x self-read x archived x limit clamping) against a real
store + settings chain; store tests cover migration v11, flag
persistence and tenant isolation; tools/peers_test.go covers args
validation, transcript rendering and the untrusted-content banner;
go test ./... green.
Impact: setting crossSession.read (default off, schema-driven);
conversation columns allow_cross_read (default true) and cross_private
(default false) with PATCH support; builtin tools list_conversations
and read_conversation gated fail-closed in runmgr toolCtx; nested
agent-system-core pin bumped to fd44179 (Core PR #6).
Refs: Agent-System-Documents proposals/2026-09-30-cross-session-reading.md
(Dev task feature/cross-session-reading).
Why: the user ruled out self-registration (2026-09-30): accounts are
created only by admins who set an initial password; first login (and
first login after any admin reset) must force a password change.
Evidence:
- migration v10 auth_accounts (users password/must_change/is_admin +
sessions table; upgrade test walks v1<->v10 both directions).
- argon2id hash/verify with PHC encoding; store tests cover hash
roundtrip, duplicate-owner conflict, must-change lifecycle, session
keep/except semantics.
- e2e TestAdminAccountFlow: static login page reachable without auth,
wrong password 401, login sets HttpOnly cookie + mustChangePassword,
admin creates user (409 on duplicate), non-admin create 403, forced
change clears flag and old password dies, admin reset revokes sessions
and re-arms forced change, API-key channel untouched, 5-fail backoff
429, logout kills session. Full go test ./... green.
Impact: middleware now accepts Bearer key OR session cookie and exempts
static + /api/auth/login (also fixes the latent case where the login
page itself could 401). Embedded no-auth mode unchanged.
Refs: proposal 2026-09-30-ui-redesign-and-auth.md section 5 (admin-issued
variant, user decision 2026-09-30)
Why: Agent-Native ships a Tavily integration (key-pool rotation,
markdown output, fallback copy) that the backend never registered, so
the catalog's WebSearch prompt had no carrier; wiring the tool gives it
one and gives the agent live-web reach.
Evidence: 4 new tool tests (registration, markdown formatting, empty
query, failure fallback carried inside the error to match registry
replay semantics); go test ./... 16 packages ok; live boot check - no
keys means not registered, two keys log registration with both tools
in /api/tools and 46 library modules in /api/prompts.
Impact: tools.tavily.apiKeys/endpoint settings (restart effect; empty
pool means the tool is absent, no silent degradation); tool.tavily_search
and tool.web_search prompt modules inject citation discipline (cite
sources, keep inference separate, fall back to workspace materials on
failure); library floor raised to 46.
Refs: feature/tavily-search-tool task card; guide disposition table in
Documents.
weichenandCursor