* fix(agents): drop silent reasoning-only replay turns
Prevent NO_REPLY cleanup from leaving signed reasoning that merges into the next assistant tool-use turn and bricks strict-provider sessions.
Related: #99620
Co-authored-by: SunnyShu <shu.zongyu@xydigit.com>
* docs: refresh transcript hygiene map
Regenerate the docs map after documenting silent reasoning-only replay cleanup.
Co-authored-by: SunnyShu <shu.zongyu@xydigit.com>
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* refactor(ai): invert plugin coupling behind the transport host port
* fix(ai): queue custom transport registrations until the host is configured
* refactor(ai): remove relocated transport sources from src/agents
* fix(ai): source core stream types from canonical packages and fix tarball fixtures
* fix(ai): invert plugin transport host wiring
* fix(ai): harden managed transport projection
* test(ai): register synchronous stream in transport mock
* fix(ai): lazily install transport runtime host
* fix(ai): preserve completion compat detection
* feat(sessions): retain reset history in sqlite with physical disk budget
* fix(sessions): satisfy test-types, knip export scan, and docs map
* fix(sessions): align behavioral suites and flip proof with retained history, route-aware cleanup plans
* perf(sqlite): gate schema version before integrity scans and quarantine terminal open failures
* feat(gateway): refuse incompatible database schemas at boot and verify integrity in the background
* feat(update): refuse installing builds that cannot open the current databases
* docs: add database schema reference with version history and downgrade guidance
* test(update): tolerate optional runner options in git-mutation mocks
* refactor(update): split npm package-target metadata out of update-check
* chore: model verifier internals for knip and regenerate docs map
* chore(i18n): resync stale iOS localization catalog
* chore: allowlist read-only preflight and verifier raw SQLite access
* feat(onboarding): persist app recommendations once
* feat(onboarding): add self-naming birth sequence
* chore(wizard): hoist bootstrap-defer imports to the top of the module
* docs(bootstrap): persist agreed identity into IDENTITY.md and SOUL.md as well
* docs: regenerate docs map after onboarding plan merge
* fix(wizard): reuse a pending stored offer instead of rescanning apps
* fix(onboard): deduplicate bootstrap recommendations
* feat(slack): add user-identity config surface (session token/cookie)
Introduce an account-level identity discriminator ("bot" default | "user") for
the Slack channel, plus sessionToken/sessionCookie secret fields for the
browser-session (user) path. Schema enforces structural coupling only
(identity="user" rejects appToken/signingSecret/relay/non-default mode);
credential presence is deferred to runtime like bot/app tokens. Account entries
inherit the top-level identity. Adds env fallback (SLACK_SESSION_TOKEN/COOKIE,
default account only), secret-contract registration, provenance *Source fields,
and UI hints. Config surface only; resolver/transport are later phases.
* refactor(slack): identity-aware operation-token resolver + dedup
Route Slack read/write token selection through a single identity-aware
resolveSlackOperationToken: identity="user" selects the browser-session token
for both operations (companion cookie attached later at client construction),
identity="bot" keeps the exact userToken/botToken + userTokenReadOnly behavior.
Delete the duplicated token-selection gate in action-runtime and route direct
sends/DM opens through the shared resolver with identity-neutral error wording.
Behavior-neutral for bot identity; net non-test LOC -2.
* refactor(slack): retarget user identity to xoxp + companion app
Replace the abandoned browser-session (xoxc/xoxd) approach for identity="user"
with the official path: authenticate as the human via the existing userToken
(xoxp) while a companion app (appToken/socket or signingSecret/http) carries
events. Remove sessionToken/sessionCookie config, env vars, secret-contract
entries, resolver fields, and their tests. Invert the schema coupling so
identity="user" permits the companion-app transport credentials, and drop the
now-vestigial user-identity structural guard entirely (identity is a permissive
discriminator; credential presence is a runtime concern). Resolver returns the
user token for user-identity reads and writes. Behavior-neutral for bot
identity.
* feat(slack): user-identity provider transport (xoxp + companion app)
Wire the identity="user" event transport. The companion Slack app runs Socket
Mode (appToken) or HTTP (signingSecret) while Bolt authenticates as the human
via the user token (no bot token). Startup auth.test runs on the user token and
its user_id becomes the self/mention target and self-send dedupe id (Bolt's
lazy per-event authorize populates context.botUserId=user_id, so the existing
self-event middleware drops the human's own messages). Identity-aware token
requirements and diagnostics; the bot-token identity warning is suppressed for
user identity. Behavior-neutral for identity="bot".
* feat(slack): user-identity setup, doctor, and docs
Add the setup wizard, doctor/status, and documentation for identity="user".
The wizard collects a user token plus the companion-app transport credential
(app token for socket, signing secret for http) and only persists identity when
"user" so bot setups keep byte-identical generated config; doctor validates the
user token via auth.test and warns on a missing transport credential; account
inspection reports user-token status. Message actions are gated on the active
identity's credential so user accounts expose actions. Docs add the exact
companion-app recipe (user scopes, on-behalf-of-user message events, socket/http
examples, the DM/group-DM-only-via-user-scope note, and self-send dedupe).
Behavior-neutral for identity="bot".
* test(slack): isolate user-identity provider tests to fix parallel flake
The new user-identity provider tests shared the globalThis-stored Slack test
client/handlers across files under parallel isolate:false, so their reaction
closures could reference a prior file's state and intermittently fail sibling
monitor tests (monitor.tool-result reactions). Track started monitors and
abort/await them all in afterEach (even on failed assertions), reset the shared
auth.test/mock state, and dispose the global Slack test runtime per file via a
new disposeSlackTestRuntime helper. Full Slack suite green across repeated
parallel runs.
* fix(slack): regenerate channel config metadata after rebase
* fix(slack): resolve setup consistent-return and doctor dead-export lint
* style: format install script test
* docs(slack): regenerate docs map for user-identity section
* test(slack): use renamed createSlackBoltApp token param in interop test
The rebase folded main's new wrapReceiver test into the renamed
createSlackBoltApp signature (botToken -> token); update the call site.
Code mode previously suspended to the model with a waiting result for every
awaited tools.search/describe/call, forcing one wait tool turn per await
(turns = tool calls + 1). Bridge calls now resolve inline within the exec
deadline and resume the QuickJS snapshot host-side, matching the namespace
auto-drain path. Restart-safe runs keep their existing no-drain semantics.
Live proof across OpenAI/Anthropic/Google: ~45% fewer turns and ~45% fewer
input tokens at equal success rate.
Also landed with the same contract:
- one shared wall-clock deadline per exec/wait call (initial worker, inline
drain rounds, and resumed guest interrupt budget all share it)
- park the snapshot instead of resuming when the remaining budget could not
survive VM restore, so near-deadline settles stay recoverable
- abort now terminates the guest worker, skips resume, and drops suspended
runs instead of pinning process-global slots until TTL, reported with the
existing aborted failure code
- exec description omits API.list/MCP/namespace guidance when the run catalog
has no MCP tools or namespaces, so models stop probing an empty surface
- API.list tolerates a trailing-slash prefix like API.list("mcp/")
* fix(agents): map cacheRetention 'standard' to 'short' for Bedrock Claude models
* fix(agents): scope standard cacheRetention alias to Anthropic cache family only
* fix(agents): validate prompt cache retention
* chore: keep changelog release-owned
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Stops the legacy run-log dual-write, auto-imports remaining rows and drops
the table at state-DB open (table-presence guard: self-heals downgrade
round-trips), keeps the newest 2000 terminal runs per job in the ledger,
retires cron.runLog config via doctor, and moves live-run cancellation to
src/cron behind the shared task control seam.
Part 2 of 2 for #106041.
* fix(memory): scope qmd search deadline
Preserve the phase-scoped QMD timeout semantics on current main.
Co-authored-by: Peter Steinberger <58493+steipete@users.noreply.github.com>
* docs: refresh generated docs map
* test(memory): reconcile manager mock with current main
* test(memory): isolate deadline mock import
* style(memory): format search test mocks
* test(memory): decouple mock from deadline symbol
* chore(memory): refresh reviewed pull request head
---------
Co-authored-by: Benjamin Badejo <ben@benbadejo.com>
Co-authored-by: Peter Steinberger <58493+steipete@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: Peter Steinberger <peter@steipete.me>
* refactor(sessions): migrate runtime storage to sqlite
* test(sessions): fix sqlite CI regressions
* test(sessions): align remaining sqlite fixtures
* fix(codex): require sqlite trajectory recorder
* test(sessions): align orphan recovery sqlite fixture
* test(sessions): align sqlite rebase fixtures
* fix(sessions): finish current-main integration of the sqlite flip
Resolve the whole-store SDK removal across its owner boundary: drop the
loadSessionStore re-export and the registry whole-store wrappers, wire
hasTrackedActiveSessionRun into gateway chat, complete the
preserveLockedHarnessIds cleanup contract, flip the codex thread-history
import to storePath targets, and port remaining main-side tests from
file-store helpers to session accessor reads.
* chore: drop committed pebbles log, revert plugin-inspector bump, refresh generated docs
Remove the 1.8k-line .pebbles/events.jsonl work log from the branch, restore
the plugin-inspector advisory lane to main's pinned 0.3.10 so the supply-chain
bump gets its own review, and regenerate docs_map, the plugin SDK API baseline,
and the export-surface ratchet for the merged tree.
* feat(sessions): keep archived transcripts by default with zstd cold storage
Codex-style retention: deleting or resetting a session archives its
transcript as a zstd-compressed JSONL artifact (plain when the runtime
lacks node:zlib zstd) and keeps it until the disk budget evicts oldest
first. resetArchiveRetention now governs both deleted and reset archives
and defaults to keep; maxDiskBytes defaults to 2gb so retention stays
bounded, with archives evicted before live sessions. The cron reaper
follows the same knob instead of deleting archives on its own timer.
* fix(state): converge agent DB migration lineages and bound database growth
Merge coherence: run both structure-gated legacy memory-schema repairs
(flip-lineage drop, main-lineage identity rebuild) before the flip
migration so pre-flip v1/v2 and pre-merge flip v1/v4 databases all
converge, and hoist foreign_keys=OFF outside the schema transaction
where the pragma was silently ignored and the v1 sessions rebuild
cascade-deleted session_entries.
Growth guards: fresh agent DBs enable auto_vacuum=INCREMENTAL, WAL
maintenance releases freed pages in bounded passes (never a blocking
full VACUUM), and doctor reports state/agent DB bloat from freelist
stats.
* fix(codex): resolve the store path for thread-history import via the SDK
The supervision catalog passed the legacy sessionFile locator to the
storePath-targeted transcript mirror; resolve the agent store path with
the session-store SDK helper instead of a runtime-object seam so test
fakes and headless callers need no extra surface. Drop the obsolete
missing-session-id preprocessing case: sessions rows are NOT NULL on
session_id and upsert repairs id-less patches at write time.
* fix(sessions): fail safe on malformed disk-budget config and doctor stat errors
A malformed explicit maxDiskBytes disables the budget instead of
falling back to the destructive 2gb default the user never chose, and
the doctor bloat check skips databases whose paths stat-fail instead of
aborting doctor.
* fix(sessions): complete sqlite conflict translations
* test(sqlite): align hardening checks with maintenance
* test(sessions): inspect compressed transcript archives
* fix(tests): await session seeds and drop unused helpers flagged by CI lint
The five unawaited writeSessionStoreSeed calls raced their SQLite seeds
against the assertions, failing compact shards; the bloat probe drops a
useless initializer and the merged tests drop now-unused helpers.
* test(sessions): type legacy proof events directly
* test(sessions): align hardening contracts
* perf(sessions): read usage transcript sizes from SQL aggregates
Usage/cost scans walked every session and materialized every transcript
event just to re-stringify it for a byte estimate — the #86718 stall
class reborn on the DB. readTranscriptStatsSync sums stored JSON bytes
in SQLite without loading a single row.
* fix(sessions): re-root foreign-root transcript paths onto the current sessions dir
Restored backups, moved OPENCLAW_STATE_DIR, and rehearsal copies carry
absolute sessionFile paths from the old root; the containment fallback
kept those foreign paths, so migration read (and would archive) files in
the original root and reported local copies missing. Re-root the
canonical agents/<id>/sessions suffix onto the current dir when the file
exists there; genuine cross-root layouts still fall through unchanged.
* test(agents): seed harness admission through sqlite
* fix(sqlite): close agent db on pragma setup failure
* fix(doctor): compact and retrofit incremental auto-vacuum after session import
The migration is the sanctioned offline window: post-import compact
reclaims import churn and applies auto_vacuum=INCREMENTAL to databases
created before the fresh-DB pragma existed, so runtime maintenance can
release pages in bounded passes on every install.
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
