* fix(active-memory): share one recall per run across retries
Register in-flight recalls per ctx.runId so overlapping or changed-prompt
attempts join a single execution, and gate replacement recalls on settled
timeout cleanup. Entries clear on agent_end. Fixes#106957.
* fix(active-memory): evict rejected recall entries
* test(active-memory): clarify run result retention
* test(active-memory): complete recall result fixture
* feat(memory): add provenance and recall metadata to the memory index
* feat(memory): provenance-gated promotion and capture hygiene
* feat(dreaming): LLM consolidation with deterministic gates, on by default
* feat(active-memory): deterministic recall lane with escalation default
* feat(memory): user model file and standing intents
* docs(memory): document the memory architecture
* fix(memory): live-QA fixes — metadata writers, provenance classes, intent scope, claim accumulation
Five session-store fixtures in index.test.ts still seeded the legacy flat
channel/origin fields. #113225 (73bba03e4c) moved the plugin's channel
resolution to canonical delivery state only, which broke two tests
(canonical session key by sessionId; resolved channel over wrapper hint)
and left three others passing vacuously (the #77396 colon-channel guard
and both weak-wrapper precedence tests no longer exercised their store
fixtures). Seed the canonical external delivery shape so all five tests
exercise the real read path again.
Test-only change; runtime behavior is untouched. Full suite:
extensions/active-memory 203/203 passing (was 201/203).
* refactor(prompt): plain inbound context labels with a provenance marker
Replaces trust-worded inbound context labels ("(untrusted metadata)",
"(untrusted, for context)") with plain labels plus a fixed provenance
marker suffix appended to every OpenClaw-injected context header.
Detection keys on the marker, not label text, so strippers stay correct
across UI, TUI, replay, /trace segmentation, memory recall, and the Swift
chat preprocessor. Drops sanitizeInboundSystemTags in favor of the marker
boundary plus trusted system-prompt narration.
Renames the untrusted-named plugin SDK context identifiers to
channel-provenance names, keeping deprecated aliases registered for
removal after 2026-09-08.
Adds `openclaw doctor --fix` migrations that rewrite legacy inbound
labels in stored SQLite transcripts and purge legacy envelope-
contaminated LanceDB recall rows.
* fix(ci): resolve gate failures for plain inbound context labels
- doctor sqlite readers: open read-only connections via openNodeSqliteDatabase
so the Kysely connection-boundary guardrail holds; unexport the now-internal
transcript snapshot type (Knip unused-export gate).
- compat registry: split the record table into registry-records.ts and
plugin-sdk-subpath-records.ts. The new compat record pushed registry.ts past
the 700-line oxlint cap; suppressions are disallowed, so follow the existing
sibling record-module pattern. Public exports and PluginCompatCode literals
unchanged.
- acp-runtime test: assert current finalization behavior (newline normalization
only). The bracket de-fang and System: rewrite it expected were removed with
sanitizeInboundSystemTags; forged system lines are neutralized at the
system-event queue, the single chokepoint feeding the System:-per-line render.
- regenerate docs_map and the plugin SDK API baseline manifest.
* fix(prompt): harden inbound context label migration and drop in-band sanitizer
Review follow-ups on the plain-label + provenance-marker change:
- Remove src/security/system-tags.ts. Rewriting inbound text to neutralize
look-alike `System:`/`[System]` markers corrupted legitimate user text and is
not a real injection boundary; role separation plus external-content wrapping
is. Explicit product decision, recorded at the system-event queue.
- Narrow the LanceDB legacy-row purge so it cannot delete benign memories. It
now requires a complete known legacy sentinel line, a legacy label followed by
a fenced JSON body, or the complete legacy external-content header. The prior
predicates matched ordinary prose such as `Notes (untrusted metadata):`, and
deletion is irreversible.
- Make explicit-empty canonical ChannelStructuredContext win over the deprecated
alias via a present/absent result instead of collapsing `[]` to undefined.
- Keep `\r?` in the active-memory doctor rule. It is the only rule spanning the
header's line break, migrated assistant rows skip newline normalization, and
without it the marked-header replace wins and the body strips to empty. Added
a CRLF regression test.
- Fix stale comments that described removed behavior, and cover the Swift
prose-block strip path.
Claude-Session: https://claude.ai/code/session_01WNzsPddQmxy9Y7jKD4wAxH
Embedded runs targeting a CLI runtime provider fall through to the openclaw
harness and call the provider API directly with the runtime's credentials
(cli_runtime_passthrough_openclaw). Anthropic routes direct anthropic-messages
calls on subscription OAuth tokens to metered extra-usage billing — this is
long-standing behavior, not a recent change. Without extra-usage balance,
every such run (e.g. active-memory recall) fails with a billing error; with
extra-usage enabled, the run silently draws paid metered usage instead of the
plan limits the CLI runtime was configured for. Only CLI-backed execution
runs on plan limits for those credentials.
Add an opt-in RunEmbeddedAgentParams.cliBackendDispatch: "subscription-auth"
that dispatches the run through runCliAgent as a one-shot turn when the
provider is claude-cli, a CLI backend is registered, and the ordered auth
profile selection for the passthrough resolves to a subscription (oauth/token)
credential or nothing rather than an API key; resolution stays on stored
credential metadata, with no credential materialization or refresh on the
per-turn path. The dispatch translates toolsAllow into the selectable-backend
surface (native: [], allowlisted loopback MCP tools; wildcard allowlists stay
MCP-only), runs with a fresh CLI process (no live-session reuse; session-
scoped bundle-MCP retirement on run end rather than the process-wide loopback
close), bridges CLI tool result events to onAgentToolResult with native-path
semantics (normalizeToolName + isToolResultError), and drops CLI session
bindings from the result.
The selectable-backend MCP list now also bounds the loopback MCP grant
server-side: the grant carries a per-run gateway tool allowlist enforced in
scoped tool resolution, so tools outside the run's allowlist can be neither
listed nor called even under CLI bypass permission modes where
--allowedTools is advisory.
active-memory recall opts in so recall works on claude-cli subscription-only
instances and stops drawing metered extra usage where it previously could.
Scoped to claude-cli; other CLI runtimes keep the passthrough until their
direct-API contract is verified.
The dispatch also mirrors the run into the run's session transcript through the session
accessor (user turn, tool call/result records as they stream, final assistant
snapshot at run end) so transcript consumers keep parity with embedded runs:
active-memory's persistTranscripts, timeout partial-text salvage, and the
live terminal-search watcher that polls the session file mid-run.
Post-review hardening: canonical anthropic/<model> refs whose configured
agentRuntime is claude-cli resolve through the runtime policy before the
dispatch gate (they previously stayed on the failing passthrough); restricted
dispatches serve an exclusive loopback-only MCP bundle so user/plugin MCP
servers stay outside the run's tool universe; and the transcript recorder
flushes the latest assistant snapshot the moment the run aborts, so timeout
salvage sees partial text even while the killed CLI child is still settling.
Recalls routed to the claude-cli runtime default to a 45s budget (measured
CLI-dispatched runs take 14-20s, over the plain 15s default); explicit
timeoutMs config always wins.
Transcript mirror keeps bare-array tool_result content (claude stream-json
echoes MCP results without a {content} wrapper); dropping it classified every
successful recall as no_relevant_memory.
CLI dispatch resolves inside session/global lane admission so dispatched
runs obey the same lifecycle, placement, and concurrency gates as native
embedded runs.
LOC-ratchet offsets move the loopback grant-context builders to
cli-runner/mcp-grant-context.ts and dedupe the run/prep stage-summary
emitters into attempt-stage-timing.ts; unused type exports dropped and the
now-used stream-message baseline entry removed.
The recall timeout default now consumes the runner's own dispatch
eligibility through a new plugin-runtime seam
(agent.resolveCliBackendDispatchEligibility): API-key and missing-backend
routes keep the passthrough and its plain 15s default.
Eligibility honors an explicitly pinned authProfileId (the credential the
run executes on) before ordered profile selection, in both directions.
Transcript mirror composes buildAssistantMessage + buildUsageWithNoCost
directly; main trimmed the zero-usage wrapper export (ab0ccc244b) before
this branch's usage landed.
Dispatch eligibility is provider-owned: the anthropic plugin's claude-cli
backend declares CliBackendPlugin.subscriptionAuthDispatch and core reads
the registered descriptor instead of a core provider allowlist.
Dispatch fails closed on tool policy (only non-empty named allowlists are
expressible on the CLI surface; deny-all, wildcards, absent allowlists, and
disableTools/modelRun keep the passthrough), threads the pinned
authProfileId into CLI runtime resolution, and emits onExecutionStarted at
the admitted dispatch boundary.
* 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>
* fix(active-memory): use truncateUtf16Safe for log value truncation
* fix(active-memory): use truncateUtf16Safe for log value truncation
* test(active-memory): cover UTF-16-safe log limits
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Fixes#89691.
Memory search now treats explicitly configured non-local embedding providers as required. When that provider is unavailable, search and sync surface an unavailable memory-search result instead of silently returning FTS-only recall.
Unset/default/local/none-style paths keep FTS fallback so existing workflows do not lose keyword recall entirely. The fallback state is now surfaced in diagnostics/status instead of being hidden.
Maintainer merge note: current CI still has unrelated baseline boundary failures in extensions/google/google.live.test.ts and extensions/minimax/minimax.live.test.ts. This PR does not touch those files; the PR-specific memory, docs, lint, type, security, and ClawSweeper checks were reviewed before merge.
