Why: downstream parsers are unreachable via extension.Host and the base lacked xlsx/pptx parsers; MS1 needs Excel and PPT ingest (EXT-5 request, documents proposal 2026-10-06-ext-5-host-parse-document).
Evidence: local GOWORK=off go test ./... all 29 packages pass incl. new ooxml_test (hand-built parts), ooxml_python_test (openpyxl/python-pptx round-trip), inproc owner-scope and limit tests, xlsx upload e2e; go vet clean; recorded as SELF on the Dev task card, PR CI to confirm.
Impact: Host gains ParseDocument (pure compute; errors only on ctx cancel or >100MiB input); builtin:xlsx (sheet order via workbook.xml rels, rich-text shared strings, formula cache, 1900/1904 dates, sparse cells) and builtin:pptx (sldIdLst order, titles, group shapes, AlternateContent Choice, tables, notes) added with 200k-cell/64MiB-part caps; legacy doc/xls/ppt get an actionable hint; ParsersDescription gains xlsx/pptx and the missing text ext; surface snapshot now records exported interface methods; docx part reads share the 64MiB cap.
Refs: documents 2026-10-06-ext-5-host-parse-document.md; EXT-1 host.go precedent.
Why: GET /api/conversations on the default unarchived view appended
AND archived=0. PostgreSQL stores conversations.archived as BOOLEAN
and rejects boolean = integer (42883), so listTasks returned 500.
The previous dialect fix bound parameters and scans but left this literal.
Evidence: before the change, TestConversationFlagsAndTaskList against
pg1 failed with SQLSTATE 42883. After: AGENT_PG_TEST_DSN set to pg1,
go test ./internal/store -count=1 passed; go vet ./... && go test ./...
passed on SQLite.
Impact: the default task list works on the postgres tier. SQLite still
binds the bool as 0/1. openTestStore accepts URL and keyword DSNs and
keeps public on search_path so an existing pg_trgm extension stays visible.
Refs: Agent-System-Dev feature/store-pg-archived-literal
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: user create/reset-password and conversation flag updates wrote 1/0
literals and boolInt ints into BOOLEAN columns; SQLite tolerates it,
PostgreSQL rejects with 42804. The 10-04 user create on pg1 failed midway
(empty password_hash, is_admin=f), and password reset, user list (bool
scanned into int) and login (GetUserAuthState scan) were all broken on
the postgres tier.
Evidence: store tests green; against the live pg1 the fixed CLI completes
user reset-password and user list (isAdmin=true, mustChangePassword=true,
hasPassword=true).
Impact: auth/account management and conversation list/flag paths work on
postgres; SQLite unchanged (0/1 converts via driver.Bool). No schema
changes.
Refs: dev-repo PR for gitlink bump (feature/store-pg-bool-dialect)
Why: Dev and the backend checkout must name the same core commit, and the section type is no longer a separate export.
Evidence: modules/core is 0b5c774. The nested checkout is detached at that commit.
Impact: Backend still compiles the same Go observation type. Only the TypeScript export changed.
Refs: .task/feature-sillytavern-review.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The pin check requires Backend's squad gitlink to match Dev, and that squad commit must itself pin the message-shaping agent-native.
Evidence: Squad commit 5a57636 points agent-native at 3a110a7.
Impact: Backend and Dev resolve the same squad and native trees.
Refs: docs/records/2026-10-04-sillytavern-review.md
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: The embedded tier starts without auth, and nothing checked Origin or Host, so a public bind or a foreign page could call write APIs.
Evidence: go test ./internal/config ./internal/server covering listen policy, origin rejection, and response headers.
Impact: Non-loopback without auth exits before opening the database. HTML artifacts get a sandbox CSP. Reverse proxies must list their public host in allowedHosts.
Refs: feature/sillytavern-review
Co-authored-by: Cursor <cursoragent@cursor.com>
Why:
The dev runtime switched to the PostgreSQL tier and every conversation
endpoint started returning 500. Migrations define
conversations.pinned/archived/allow_cross_read/cross_private and
users.must_change_password/is_admin as BOOLEAN on PostgreSQL but
INTEGER on SQLite, while the store layer compared them with 0/1
literals, scanned them into int, and wrote them via boolInt().
Under pgx these fail with 42883 (operator does not exist: boolean =
integer), bool encode errors, or 42804 (column is of type boolean but
expression is of type integer).
Evidence:
- parent-repo main 4fd03ee with AGENT_PG_TEST_DSN:
TestConversationFlagsAndTaskList and TestAdminAccountsAndSessions
fail with the errors above; live GET /api/conversations returned
"operator does not exist: boolean = integer (SQLSTATE 42883)".
- this branch: full ./internal/store suite green on the PostgreSQL
tier (AGENT_PG_TEST_DSN against a scratch database), pgbus green,
make test-backend green on the SQLite tier.
- scan into *bool and Go bool parameters are cross-dialect: pgx encodes
bool natively; database/sql converts bool<->0/1 for SQLite.
- pre-existing and out of scope: ./internal/runmgr PG integration tests
fail on main too (gin_trgm_ops invisible inside the search_path
isolation schema, 42704).
Impact:
Conversations list/detail/flags and user auth-state reads/writes now
work identically on both storage tiers; SQLite behavior is unchanged.
Refs: Dev task .task/fix-pg-boolean-columns.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: Those three branches were replayed onto origin/main after the first pin.
Evidence: native 0a52d9f, squad beea97e, and core cf7df54 each contain origin/main.
Impact: The backend build uses the same commits that will be merged.
Refs: feature/permission-hooks
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: A dropped subscription had no retry hint, and a reconnect had no test that the gap is filled from the cursor.
Evidence: The stream starts with retry: 1000. A live publish is delivered, and Last-Event-ID after an overflow replay skips events the client already has.
Impact: EventSource waits one second before reconnecting. Persisted events are unchanged.
Refs: feature/runstate-shell
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The pin check requires backend's squad gitlink to match the Dev pin, and that squad commit carries the native context-engineering loop.
Evidence: deps/agent-squad is 4d53450, whose agent-native gitlink is 6fd1d44.
Impact: No backend behavior change beyond the shared native loop.
Refs: feature/context-engineering
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: 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: The pull request cannot merge while the head is behind main.
Evidence: origin/main is 5d59ee9, one commit ahead of this branch.
Impact: Keeps the resume cursor and the interrupted-run recovery together.
Refs: Backend #54
Why: Refreshing or switching back only knew the latest event cursor, so process that had already happened was missing until the run finished.
Evidence: GOWORK=off go test -count=1 -run TestConversationResumeSeq ./internal/server passed. While a hitl run waits, resumeSeq is the run's first seq minus one and is less than lastSeq; after the run completes the two cursors match.
Impact: Conversation detail gains resumeSeq beside lastSeq. No core contract change. Clients that ignore the field keep the old cursor.
Refs: Dev fix/live-run-visibility
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: Backend's nested checkouts have to match the native head that treats a cancelled stream as aborted.
Evidence: gitlinks only. The race test passed on d84a67c.
Impact: no Backend source change.
Refs: D1
Why: Backend's nested checkouts have to match the intent, native, and squad commits Dev will pin.
Evidence: gitlinks only. Internal package tests passed before this pointer move.
Impact: no Backend source change.
Refs: D1
Why: Backend must build against the squad head that keeps agent-intent inside adapters/intent.
Evidence: the previous internal package tests passed on a182d76; this commit only moves the gitlink to f68e5bd.
Impact: no Backend source change.
Refs: D1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Backend has to keep the same squad runs after the core stopped importing agent-native. The adapter module owns the concrete client.
Evidence: GOWORK=off go test -count=1 ./internal/... passed.
Impact: AgentNativeOptions now returns the adapter config. Default roles still use the agent-system backend.
Refs: D1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: native 855fe41 records the golang.org/x/text sum that intent's NFKC import needs, and squad 31ee395 pins that native commit.
Evidence: GOWORK=off go vet ./internal/squadadapter/ ./internal/app/ passed against these heads.
Impact: two gitlinks move. Backend product code is unchanged.
Refs: I4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: backend must run against the intent, native, and squad commits that close this batch.
Evidence: agent-intent 05e74d8, agent-native 11d1a76, and agent-squad 1bb0c3a are the feature/agent-stack-r2 heads.
Impact: gitlinks move; backend product code is unchanged.
Refs: R2 pin
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: TestLintErrorContinues imports the house-style linter, which needs python-docx, python-pptx, and openpyxl.
Evidence: Actions run 678 failed that test with ModuleNotFoundError: No module named docx after submodules checked out.
Impact: The packages come from the Tsinghua PyPI mirror. The test command is unchanged.
Refs: feature/agent-stack-r0-r1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The runner cannot reach github.com, so a checkout action would time out before vet or test.
Evidence: The Go 1.27.1 tarball is available from mirrors.aliyun.com. Checkout uses the job token and GITHUB_SHA.
Impact: Submodule checkout still requires SUBMODULE_TOKEN. A missing secret fails the job with that message.
Refs: feature/agent-stack-r0-r1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Backend must call the library commits that include the hold fixes and the CI checkout change.
Evidence: intent 7f7879b06b053f0a62746309b79e0e1b9a00f42d, native 91c155618487e21edeb4f1d3cc27e985aae2b0d2, squad e928ea3c0fa649cbbbad22a93a1bc0a12dee5f7d.
Impact: The three 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: This repo had no workflow, so pull requests could not show a vet or test result.
Evidence: The job checks out submodules over HTTPS and runs GOWORK=off go vet ./... && GOWORK=off go test -count=1 ./... on Go 1.27 with GOPROXY=https://goproxy.cn,direct.
Impact: SUBMODULE_TOKEN must be set by the owner before checkout can succeed.
Refs: feature/agent-stack-r0-r1
Co-authored-by: Cursor <cursoragent@cursor.com>
weichen
