Commit Graph

138 Commits

Author SHA1 Message Date
Peter Steinberger
538605ff44 [codex] Extract filesystem safety primitives (#77918)
* refactor: extract filesystem safety primitives

* refactor: use fs-safe for file access helpers

* refactor: reuse fs-safe for media reads

* refactor: use fs-safe for image reads

* refactor: reuse fs-safe in qqbot media opener

* refactor: reuse fs-safe for local media checks

* refactor: consume cleaner fs-safe api

* refactor: align fs-safe json option names

* fix: preserve fs-safe migration contracts

* refactor: use fs-safe primitive subpaths

* refactor: use grouped fs-safe subpaths

* refactor: align fs-safe api usage

* refactor: adapt private state store api

* chore: refresh proof gate

* refactor: follow fs-safe json api split

* refactor: follow reduced fs-safe surface

* build: default fs-safe python helper off

* fix: preserve fs-safe plugin sdk aliases

* refactor: consolidate fs-safe usage

* refactor: unify fs-safe store usage

* refactor: trim fs-safe temp workspace usage

* refactor: hide low-level fs-safe primitives

* build: use published fs-safe package

* fix: preserve outbound recovery durability after rebase

* chore: refresh pr checks
2026-05-06 02:15:17 +01:00
Peter Steinberger
aafdc5945a chore: delete stale memory host bridges 2026-05-02 18:15:26 +01:00
pashpashpash
563dca82f4 Add Codex happy path prompt snapshots (#75807)
* Add Codex prompt snapshots

* Fix prompt snapshot scenario catalogs

* Harden prompt snapshot drift check

* Fix CLI compat build export

* fix: keep codex snapshots out of core plugin surface

* fix: harden prompt snapshot ci checks

* fix: accept readonly web search onboarding scopes

* fix: repair plugin sdk package boundary types

* fix: clear prompt snapshot ci regressions

* fix: clear latest main ci checks

* fix: resolve latest main discord helper overlap

* fix: refresh codex dynamic tool snapshots

* fix: align prompt snapshot branch with latest ci

* fix: isolate plugin auto enable tests

* test: refresh prompt dynamic tool snapshots

* fix: stabilize bundled channel auto enable

* fix: clean stale prompt snapshots
2026-05-03 00:59:55 +09:00
Peter Steinberger
99f1db33bf fix: include primary dreaming workspace 2026-05-02 09:25:19 +01:00
Peter Steinberger
85c29d1562 refactor: hide embedding input helper 2026-05-02 08:04:11 +01:00
Peter Steinberger
614a294afa refactor: trim contract helper exports 2026-05-02 05:03:37 +01:00
Peter Steinberger
e40c381fb8 refactor: trim model catalog exports 2026-05-02 00:19:13 +01:00
Peter Steinberger
e964f56735 refactor: remove unused memory runtime wrappers 2026-05-02 00:14:03 +01:00
Peter Steinberger
c7e3c68fde refactor: trim memory host wrappers 2026-05-02 00:11:10 +01:00
Peter Steinberger
bf1a8eebba fix(memory): preserve dreams path bridge behavior 2026-04-29 15:11:40 +01:00
Peter Steinberger
577438ca73 test: dedupe mirrored memory and deepseek tests 2026-04-29 15:11:39 +01:00
Peter Steinberger
1dd37f5c90 refactor(memory): bridge host sdk duplicates 2026-04-29 15:11:39 +01:00
Peter Steinberger
2b811fe6d9 fix(memory): make qmd gateway startup lazy 2026-04-29 08:45:19 +01:00
Vincent Koc
8b71d2347f docs(types): mark remaining deprecated aliases 2026-04-29 00:04:17 -07:00
Peter Steinberger
a6bb0265f0 test: speed up unit hotspot routing 2026-04-28 10:42:14 +01:00
Peter Steinberger
1089e8b9e0 fix: stabilize memory host ci tests 2026-04-28 06:00:21 +01:00
Peter Steinberger
dc3df62e67 refactor(memory-host): own package contract surface 2026-04-28 05:49:07 +01:00
Peter Steinberger
b1a36226b1 test: stabilize faster unit lanes 2026-04-28 04:09:41 +01:00
Peter Steinberger
a9648664c1 perf(test): route memory dreaming through unit-fast 2026-04-27 15:03:21 +01:00
Peter Steinberger
df65a75f92 fix(memory): avoid live embedding probes in status 2026-04-27 13:55:51 +01:00
Peter Steinberger
cae492374c test: reduce repeated test setup overhead 2026-04-27 13:33:05 +01:00
Peter Steinberger
7f3f108521 refactor(config): migrate plugin config access 2026-04-27 12:35:58 +01:00
Peter Steinberger
3bc29dd604 fix(sqlite): bound WAL sidecar growth 2026-04-27 12:25:10 +01:00
Peter Steinberger
775ed36c16 feat(memory): support asymmetric embedding input types 2026-04-27 11:25:40 +01:00
Peter Steinberger
f6ee2877e0 refactor: share memory dreaming cron constants 2026-04-27 11:19:09 +01:00
Peter Steinberger
4003e4389a fix(memory-core): support dreaming model override 2026-04-27 11:08:21 +01:00
Peter Steinberger
6df120fb39 fix: keep internal completion wakes out of chat memory 2026-04-26 04:01:45 +01:00
Peter Steinberger
1c6911c01f fix: ignore compaction checkpoints in session usage 2026-04-26 00:11:35 +01:00
Mara 🌿
7f5789575e fix(memory-wiki): skip bridge pruning when memory-core is not loaded (#71764)
When memory-core plugin is not registered (e.g. CLI context),
listActiveMemoryPublicArtifacts returns an empty array. The previous code
would then call pruneImportedSourceEntries with an empty activeKeys Set,
which removes ALL bridge-imported entries.

Now checks getMemoryCapabilityRegistration() instead of relying on artifact
count as a proxy, correctly distinguishing between 'plugin not loaded' and
'plugin loaded with no artifacts'.

Fixes #68373
2026-04-25 17:10:31 -04:00
Peter Steinberger
f34513ac66 perf(memory): avoid duplicate session store reads 2026-04-25 20:17:22 +01:00
Peter Steinberger
e1495c3372 test: streamline memory and tts suites 2026-04-25 19:23:51 +01:00
Peter Steinberger
8c93745f0f test(memory): speed up host fixture setup 2026-04-25 18:41:20 +01:00
Peter Steinberger
cd392b947c test: dedupe memory and context suites 2026-04-25 14:06:26 +01:00
Peter Steinberger
3db60f7eab perf: trim agent workspace imports 2026-04-25 14:06:26 +01:00
Peter Steinberger
4a76a66872 perf: slim memory host imports 2026-04-25 12:52:27 +01:00
Donetta Flatley
f408bba9de fix(memory-host-sdk): use TRUSTED_ENV_PROXY mode for remote embeddings in proxy environments (#71506)
* fix(memory-host-sdk): use TRUSTED_ENV_PROXY mode in withRemoteHttpResponse

When a HTTP/HTTPS proxy is configured via environment variables
(HTTPS_PROXY, HTTP_PROXY, ALL_PROXY), the withRemoteHttpResponse
function now passes mode=TRUSTED_ENV_PROXY to fetchWithSsrFGuard.

This causes DNS resolution to skip the local resolver and route
through the configured proxy, fixing 'fetch failed' errors for
remote memory embeddings (including GitHub Copilot embeddings) in
proxy environments (e.g. Clash TUN, corporate proxies).

Previously, without an explicit mode, fetchWithSsrFGuard defaulted
to STRICT mode which performs local DNS pre-resolution via
resolvePinnedHostnameWithPolicy(), failing in proxy environments
where DNS must go through the proxy.

Fixes: openclaw/openclaw#52162

* fix: harden memory env proxy guard (#71506) (thanks @DhtIsCoding)

---------

Co-authored-by: Dht <dht@openclaw.ai>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-04-25 12:24:09 +01:00
Peter Steinberger
e0beea97aa perf: speed up focused tests 2026-04-25 08:26:28 +01:00
Alex Fries
66e66f19c6 feat(memory-core): expose hybrid search component scores
Expose raw `vectorScore` and `textScore` alongside the combined hybrid memory search `score`.

- Preserve vector/text component scores from `mergeHybridResults` output.
- Add optional component-score fields to both memory host SDK type surfaces.
- Extend hybrid merge tests for vector-only, text-only, and overlapping result cases.
- Document that component scores remain raw retrieval diagnostics while temporal decay/MMR only adjust or reorder the combined ranking `score`.

Closes #68166.

Maintainer verification:
- `pnpm test extensions/memory-core/src/memory/hybrid.test.ts`
- `pnpm check:changed`
- Fresh GitHub checks passed.

Co-authored-by: Alex Fries <alex@engramlabs.io>
2026-04-25 01:46:03 -05:00
Michiel van den Donker
2c716f5677 fix: enforce memory search session visibility (#70761) (thanks @nefainl)
* [EV-001] memory-core: filter memory_search session hits by visibility

- Move session visibility + listSpawnedSessionKeys to plugin-sdk; sync test
  hook with sessions-resolution __testing.setDepsForTest
- Extract loadCombinedSessionStoreForGateway to config/sessions; re-export
  from gateway session-utils
- Add session-transcript-hit stem resolver for builtin + QMD paths
- Post-filter memory_search results before citations/recall; fail closed when
  requester session key missing; optional corpus=sessions
- Tests: stem extraction, visibility filter smoke, existing suites green

* chore: sync plugin-sdk exports for session-transcript-hit and session-visibility

Run pnpm plugin-sdk:sync-exports so package.json exports match
scripts/lib/plugin-sdk-entrypoints.json. Fixes contract tests and
lint:plugins:plugin-sdk-subpaths-exported for memory-core imports.

* fix(EV-001): cross-agent session memory hits + hoist combined store load

- resolveTranscriptStemToSessionKeys: stop filtering by requester agentId so
  keys from other agents reach createSessionVisibilityGuard (a2a + visibility=all).
- Re-export loadCombinedSessionStoreForGateway from session-transcript-hit;
  filterMemorySearchHitsBySessionVisibility loads the combined store once per pass.
- Drop unused agentId from filter params; extend tests (Greptile/Codex review).

* fix(memory_search): honor corpus=sessions before maxResults cap

Pass sources into MemoryIndexManager.search so FTS/vector queries add
source IN (...) before ranking and top-N slice (Codex: non-session hits
could fill the window).

QMD path: oversample fetch limit for single-source recall, filter by
source, then diversify/clamp to the requested maxResults.

Wire corpus=sessions from tools; extend MemorySearchManager opts and
wrappers.

* fix(memory_search): apply corpus=memory source filter like sessions

Pass sources: ["memory"] into manager.search so maxResults applies only
within the memory index; post-filter for defense in depth. Document
corpus=memory in the tool description.

* fix: scope qmd session memory search

* fix: enforce memory search session visibility (#70761) (thanks @nefainl)

---------

Co-authored-by: NefAI <info@nefai.nl>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
2026-04-25 09:30:21 +05:30
Patrick Erichsen
aca92b2906 memory/dreaming: decouple managed cron from heartbeat (#70737)
* Revert "fix(memory/dreaming): surface blocked status when heartbeat is disabled for main (#69875)"

This reverts commit 529577e045.

Making way for the dreaming-vs-heartbeat decoupling from Josh's
josh/dreaming-isolated-cron-fix branch, which moves the managed dreaming
cron to isolated agent turns (sessionTarget: "isolated") so dreaming no
longer requires heartbeat to fire. Once the cron no longer rides the
heartbeat path, the blocked-reason observability has nothing left to
report — removing it cleanly here before the cherry-picks land.

* openclaw-3ba.1: move managed dreaming cron to isolated agent turns

* openclaw-46d: claim cron runs before embedded attempts

* openclaw-575: disable managed dreaming cron delivery

* openclaw-575: accept wrapped dreaming cron tokens

* openclaw-ccd: filter cron and wrapper transcript noise from dreaming corpus

* openclaw-cd9: filter archived, cron, and heartbeat transcript noise from dreaming corpus

* openclaw-cd9: suppress role-label reflection tags in rem dreaming

* openclaw-b49: stop narrative timeouts from blocking dreaming cron

* openclaw-b49: keep managed dreaming cron out of diary subagents

* openclaw-ff9: restore cron dream diary generation without serial waits

* openclaw-ff9: run dreaming narratives with lightweight isolated subagent lanes

* openclaw-ff9: detach cron dream diary generation from run completion

* openclaw-ff9: defer cron diary task startup until after cron completion

* doctor/cron: migrate stale managed dreaming jobs to isolated agent turns

After the dreaming cron moved off the heartbeat path to sessionTarget:
"isolated" + payload.kind: "agentTurn" (see the preceding memory-core
changes), users with existing ~/.openclaw/cron/jobs.json entries in the
old sessionTarget: "main" + payload.kind: "systemEvent" shape still
carry stale jobs until the gateway restart reconcile rewrites them.

Add a dreaming-specific cron migration to the existing
maybeRepairLegacyCronStore doctor path so "openclaw doctor" (and
"openclaw doctor --fix") rewrites those jobs without needing a gateway
restart. Match lives in a new doctor-cron-dreaming-payload-migration
helper alongside the existing legacy-delivery and store-migration files.

The matching uses the memory-core managed-job name and description tag
plus the short-term-promotion payload token. Constants are mirrored
from extensions/memory-core/src/dreaming.ts and commented so a future
rename in memory-core is a visible drift point here too.

* memory/dreaming: tighten cron-token match to known wrapper, not substring

The previous match relaxed the line check from 'trimmed line equals token'
to 'line contains token anywhere as a substring' to accept the
`[cron:<id>] <token>` wrapper that isolated-cron turns add. Substring
matching also let any user message embedding the token mid-sentence
trigger the dream-promotion hook, and was flagged by both Greptile and
Aisle on PR #70737.

Replace it with strip-the-known-prefix-then-exact-match: keep the
`[cron:<id>]` wrapper case working, reject every other variant. Add
focused unit coverage that the bare token, the wrapped token, and bare
multiline cases match while embedded / code-fenced / arbitrarily-wrapped
variants do not.

* memory/dreaming: drop assistant followup only on assistant-side signals

Per PR #70737 review (aisle-research-bot, Medium): the previous logic
suppressed the next assistant message whenever the prior user message
matched a 'generated prompt' pattern (`[cron:...]`,
`System (untrusted): ...`, heartbeat prompts, exec-completion events).
Real users can type those same patterns, which let a user exfiltrate
real assistant replies from the dreaming corpus by prefixing their own
prompt — the assistant's reply would be silently dropped.

Remove the cross-message coupling. Assistant-side machinery (silent
replies, system wrappers) is already dropped by sanitizeSessionText,
which is the right layer for that filter. Add an explicit assistant-side
HEARTBEAT_TOKEN check to keep the legitimate `HEARTBEAT_OK` ack drop
working without depending on the prior user message. Add a regression
test exercising the spoofing scenario.

* doctor/cron: assert mirrored dreaming constants stay in sync

Per PR #70737 review (greptile-apps): the doctor migration mirrors three
constants (MANAGED_DREAMING_CRON_NAME, MANAGED_DREAMING_CRON_TAG,
DREAMING_SYSTEM_EVENT_TEXT) from extensions/memory-core/src/dreaming.ts.
A future rename in either file would silently break the migration.

Add a vitest unit that reads both files and asserts the literals match.
Manually verified the assertion fires with a clear error when one side
diverges. Adds no runtime cost; sits in the regular test pipeline.

* fix(memory): stabilize dreaming CI checks

* memory/dreaming: skip eager narrative session cleanup when detached

Per PR #70737 review (chatgpt-codex-connector, P2): runDreamingSweepPhases
called deleteNarrativeSessionBestEffort synchronously right after each
phase. Once narrative generation moved to detached mode (queued via
queueMicrotask), the eager cleanup races the writer: the session is
deleted before the queued subagent run reads it, silently dropping cron
diary entries.

Skip the eager cleanup branch when params.detachNarratives is true.
generateAndAppendDreamNarrative still runs its own deleteSession in the
finally{} block, so the cleanup intent is preserved without the race.
Heartbeat-driven (non-detached) runs keep the original eager-cleanup
behavior.

* fix(plugin-sdk): restore heartbeat-summary re-export

Per PR #70737 review (chatgpt-codex-connector, P1): the revert of
PR #69875 dropped the `heartbeat-summary` re-export from
`openclaw/plugin-sdk/infra-runtime`. That subpath shipped publicly two
days earlier, so removing it is technically a breaking change to a
public SDK surface — third-party plugins importing
`isHeartbeatEnabledForAgent` / `resolveHeartbeatIntervalMs` from this
path would fail with no replacement contract introduced.

Restore the re-export. Costs nothing to keep; the helpers are already
public via `../infra/heartbeat-summary.ts`. SDK additions are by
default backwards-compatible (CLAUDE.md), so removing within days of
introduction violates that intent.

* changelog: note dreaming decoupling from heartbeat

Refs PR #70737.

---------

Co-authored-by: Josh Lehman <josh@martian.engineering>
2026-04-23 22:23:19 -07:00
aalekh-sarvam
d40dd9088e feat(memory): configurable local embedding contextSize (default 4096) (#70544)
node-llama-cpp defaults contextSize to "auto", which on large embedding
models like Qwen3-Embedding-8B (trained context 40,960) inflates gateway
VRAM from ~8.8 GB to ~32 GB and causes OOM on single-GPU hosts that share
the gateway with an LLM runtime.

Expose memorySearch.local.contextSize in openclaw.json (number | "auto"),
default to 4096 which comfortably covers typical memory-search chunks
(128–512 tokens) while keeping non-weight VRAM bounded.

Closes #69667.
2026-04-23 14:21:53 -07:00
Peter Steinberger
5ebef46183 perf: speed up hot test paths 2026-04-23 18:17:09 +01:00
Peter Steinberger
deb1364dfb refactor: centralize root memory file policy 2026-04-23 16:40:41 +01:00
Mariano
10a9acbf29 fix: keep root memory uppercase (#70621)
Thanks @mbelinky.
2026-04-23 16:10:36 +01:00
Peter Steinberger
b2472d6560 build: migrate schema deps to typebox 2026-04-23 04:59:42 +01:00
Bek
1acb094579 fix: wrap oversized session lines before JSONL write (#64494)
updates the real session-export path so pathological transcript messages no longer become a single toxic export line for downstream indexing.
2026-04-21 18:18:22 -04:00
Peter Steinberger
66665eea6d test: use synthetic status session fixtures 2026-04-21 01:40:29 +01:00
Peter Steinberger
da5a6b68bd refactor: share ssrf base url policy 2026-04-20 23:15:58 +01:00
Peter Steinberger
e0c01bf956 perf: trim hot path allocations 2026-04-20 23:13:20 +01:00
Peter Steinberger
59657913fd perf(test): prune duplicate memory host tests 2026-04-20 20:05:37 +01:00