23 Commits

Author SHA1 Message Date
Peter Steinberger
2dfa4b082a docs: sync docs with source truth 2026-05-02 21:45:03 +01:00
Peter Steinberger
99f1db33bf fix: include primary dreaming workspace 2026-05-02 09:25:19 +01:00
Peter Steinberger
78a12706ec fix(docs): make docs formatter mintlify-safe 2026-04-28 08:13:21 +01:00
Peter Steinberger
a644e30245 fix(memory-core): retry unavailable dreaming model 2026-04-28 06:15:28 +01:00
Peter Steinberger
4003e4389a fix(memory-core): support dreaming model override 2026-04-27 11:08:21 +01:00
Vincent Koc
2a5d3ad5b9 docs(dreaming): rewrite with AccordionGroup for phases and backfill, Tabs for quick start and CLI workflow, ParamField for dreaming defaults 2026-04-26 04:04:09 -07:00
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
Vincent Koc
c5c163d078 docs: standardize frontmatter field order (summary before title) 2026-04-23 13:18:17 -07:00
Vincent Koc
4a2cd533ac docs: remove duplicate H1 where frontmatter title already sets it 2026-04-23 13:11:14 -07:00
Peter Steinberger
834fdc4832 docs: align documentation with current surfaces 2026-04-23 07:25:06 +01:00
Patrick Erichsen
529577e045 fix(memory/dreaming): surface blocked status when heartbeat is disabled for main (#69875)
* fix(memory/dreaming): surface blocked status in memory status when heartbeat disabled for main

Replace the hand-rolled heartbeat-rules logic in resolveDreamingBlockedReason
with the shared resolveHeartbeatSummaryForAgent helper, promoted from core to
the plugin-sdk via infra-runtime. Collapses the two disabled-reason branches
into a single message that points at a new Troubleshooting section in the
dreaming docs, so the silent-failure mode described in openclaw/openclaw#69843
becomes legible without the extension re-encoding heartbeat-enablement rules.

Refs openclaw/openclaw#69843, openclaw/openclaw#46046.

* refactor(memory/dreaming): share resolveDreamingBlockedReason across cli and /dreaming surfaces

- Move resolveDreamingBlockedReason from cli.runtime.ts into dreaming.ts as an exported helper and pin its heartbeat check to DEFAULT_AGENT_ID (now exported from plugin-sdk/routing) so the status-line check agrees with the cron's hardcoded sessionTarget even when the configured default agent is not main.
- Render the blocked reason from formatStatus in dreaming-command.ts directly under the enabled line, so /dreaming status, /dreaming on, /dreaming off, and bare /dreaming all flag that the cron is blocked instead of implying dreaming is healthy.
- Tighten the blocked-reason text to lead with user impact ('dreaming is enabled but will not run because heartbeat is disabled for main'), so operators immediately understand the config is toggled on but nothing is actually running.
- Tighten the dreaming Troubleshooting copy to name main explicitly and mention both surfaces.
- Add tests locking the new behavior across cli.test.ts (default-agent=ops still reports blocked for main) and dreaming-command.test.ts (/dreaming status ordering, /dreaming on surfacing, healthy-heartbeat omission).

Refs openclaw/openclaw#69843, openclaw/openclaw#46046.

* fix(memory/dreaming): check heartbeat for the resolved default agent, not the literal 'main'

sessionTarget: 'main' is a cron session-type enum variant meaning 'the default agent's main session', not an agent id (see src/cron/service/jobs.ts). buildManagedDreamingCronJob does not set agentId, and cron runtime resolves the missing agentId through resolveDefaultAgentId(cfg) before enqueuing or waking. The previous pin to DEFAULT_AGENT_ID could produce a false 'blocked' reading when a configured default agent is not 'main' and its heartbeat is fine, and could miss a real block when the default agent is not 'main' and that agent's heartbeat is actually off.

Switch resolveDreamingBlockedReason to resolveDefaultAgentId(cfg) and interpolate the resolved agent id into the message so the blocked line names the agent whose heartbeat is the blocker. Introduce a narrow local CRON_SESSION_TARGET_MAIN constant for the cron session-type enum variant (used by the sessionTarget type and value) so the remaining 'main' literal is semantically distinct from any agent id. Revert the DEFAULT_AGENT_ID export addition on plugin-sdk/routing; memory-core no longer needs it. Update the Troubleshooting doc wording and the cli test that was locking the wrong behaviour.

Refs openclaw/openclaw#69843, openclaw/openclaw#46046.

* fix(memory/dreaming): align blocked check with server-cron wake's defaults-only heartbeat

resolveDreamingBlockedReason was using resolveHeartbeatSummaryForAgent, which merges agents.defaults.heartbeat with agents.list[].heartbeat. The managed dreaming cron leaves job.agentId and job.sessionKey unset, so server-cron's wake wrapper cannot look up a per-agent entry and calls runHeartbeatOnce with agents.defaults.heartbeat only. Using the summary helper would disagree with the actual wake when the default agent overrides heartbeat.every differently from the defaults (either direction — false blocked when the override would run, or false healthy when defaults block).

Mirror the wake path explicitly: rule-1 enablement via isHeartbeatEnabledForAgent against the default agent, rule-3 interval via resolveHeartbeatIntervalMs with defaults-only heartbeat config. Comment points at server-cron so a future cleanup of that latent override-propagation gap sees the coupling.

Refs openclaw/openclaw#69843.
2026-04-21 18:51:43 -07:00
Vincent Koc
a780151fd1 docs: add experimental-features page and de-experimentalize dreaming 2026-04-15 11:46:25 +01:00
Gustavo Madeira Santana
0c4e0d7030 memory: block dreaming self-ingestion (#66852)
Merged via squash.

Prepared head SHA: 4742656a0d
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-14 20:29:12 -04:00
Mariano
d514f4de83 Dreaming: surface grounded scene lane (#63395)
Merged via squash.

Prepared head SHA: 0c7f586f32
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-04-09 00:24:47 +02:00
Mariano Belinky
a71ad12044 Memory/dreaming: harden grounded backfill follow-ups 2026-04-08 23:43:39 +02:00
Vincent Koc
3e7e6f2f60 docs: cover 2026.4.7 changelog gaps 2026-04-08 07:26:56 +01:00
Vincent Koc
1835493aa5 docs(memory): add promote-explain and rem-harness CLI reference 2026-04-06 05:10:15 +01:00
Vignesh Natarajan
61e61ccc18 Dreaming: simplify sweep flow and add diary surface 2026-04-05 17:18:54 -07:00
Vincent Koc
0e85343b6c docs: update Lobster in-process mode and REM preview tooling 2026-04-06 00:40:21 +01:00
Vincent Koc
a9dbaa1124 fix(memory): standardize DREAMS trail path 2026-04-05 23:35:44 +01:00
Vincent Koc
367f52f483 docs(memory): point dreaming trail docs to dreams.md 2026-04-05 23:35:44 +01:00
Vincent Koc
a1c1598742 docs: rewrite dreaming docs for 3-phase architecture 2026-04-05 18:42:06 +01:00
Peter Steinberger
6e3155ca84 feat(memory-core): add dreaming aging controls 2026-04-05 15:59:06 +01:00