…aw#37867)

* fix(session): require strict direct key routing shapes

* test(session): cover direct route poisoning cases

…ge.py (openclaw#18706)

The MEDIA: output token must appear at line start with no space after
the colon for OpenClaw's splitMediaFromOutput parser to extract the
file path and auto-attach media on outbound chat channels (Discord,
Telegram, WhatsApp, etc.).

The script was printing 'MEDIA: /path' (with space), which while
tolerated by the regex, does not match the canonical 'MEDIA:/path'
format used by all other skills (e.g. openai-image-gen) and tested
in the codebase (pi-embedded-subscribe.tools.media.test.ts,
media/parse.test.ts).

Also updated the comment to clarify the format constraint.

…penclaw#36880)

* nano-banana-pro: respect explicit --resolution when editing images

* Changelog: note nano banana resolution fix

* Update CHANGELOG.md

---------

Co-authored-by: Vincent Koc <[email protected]>

* Telegram: default media cap to 100MB

* Telegram: honor outbound mediaMaxMb

* Discord: add shared media upload cap

* Discord: pass mediaMaxMb to outbound sends

* Telegram: cover outbound media cap sends

* Discord: cover media upload cap config

* Docs: update Telegram media cap guide

* Docs: update Telegram config reference

* Changelog: note media upload cap fix

* Docs: note Discord upload cap behavior

…#36762)

* openai-image-gen: validate --background and --style inputs

* Skills/openai-image-gen: warn on ignored background and style flags

* Skills/openai-image-gen: cover empty and warning cases

* Changelog: note openai image flag validation

* Skills/openai-image-gen: fix Python import order

---------

Co-authored-by: Vincent Koc <[email protected]>

* WhatsApp: add media cap helper

* WhatsApp: cap outbound media loads

* WhatsApp: align auto-reply media caps

* WhatsApp: add outbound media cap test

* WhatsApp: update auto-reply cap tests

* Docs: update WhatsApp media caps

* Changelog: note WhatsApp media cap fix

…38117)

* Infra: tighten npm registry spec parsing

* Infra: block implicit prerelease npm installs

* Plugins: cover prerelease install policy

* Infra: add npm registry spec tests

* Hooks: cover prerelease install policy

* Docs: clarify plugin guide version policy

* Docs: clarify plugin install version policy

* Docs: clarify hooks install version policy

* Docs: clarify hook pack version policy

)

* openai-image-gen: validate and normalize output format

* Skills/openai-image-gen: cover output-format edge cases

* Changelog: note openai image output format validation

---------

Co-authored-by: Vincent Koc <[email protected]>

* Media: normalize HEIC input images

* Gateway: accept HEIC image input schema

* Media: add HEIC input normalization tests

* Gateway: cover HEIC input schema parity

* Docs: document HEIC input image support

* Changelog: note HEIC input image fix

Fixes openclaw#7631

Fixes openclaw#28835

* Media: scope HEIC MIME sniffing

* Media: hermeticize HEIC input tests

* Gateway: fix HEIC image budget accounting

* Gateway: add HEIC image budget regression test

* Changelog: note HEIC follow-up fix

openclaw#38199)

* fix(gateway): keep probe routes reachable with root-mounted control ui

* Changelog: add root-mounted probe precedence fix entry

* Update CHANGELOG.md

* Changelog: add channel-backed readiness probe entry

* Gateway: add channel-backed readiness probes

* Docs: describe readiness probe behavior

* Gateway: add readiness probe regression tests

* Changelog: dedupe gateway probe entries

* Docs: fix readiness startup grace description

* Changelog: remove stale readiness entry

* Gateway: cover readiness hardening

* Gateway: harden readiness probes

The dashboard screenshot uses a relative path `src="whatsapp-openclaw.jpg"`
which resolves correctly on the English root page but produces 404 on
zh-CN and ja-JP pages because Mintlify prepends the language subdirectory
to the CDN path.

Change to absolute path `/whatsapp-openclaw.jpg` in all three index files,
consistent with other images on the same page that already use absolute
paths (e.g. `/assets/openclaw-logo-text-dark.png`).

…penclaw#38267)

The `timeout` property is not part of the Lark SDK method signatures,
causing TS2353 errors. The client-level `httpTimeoutMs` already applies
the timeout to all requests.

Co-authored-by: Claude Opus 4.6 <[email protected]>

…create auto-grant (openclaw#32915)

Merged via squash.

Prepared head SHA: efb2293
Co-authored-by: cszhouwei <[email protected]>
Co-authored-by: jalehman <[email protected]>
Reviewed-by: @jalehman

* fix(agents): skip auth-profile failure on overload

* fix(agents): note overload auth-profile fallback fix

* fix(agents): classify overloaded failures separately

* fix(agents): back off before overload failover

* fix(agents): tighten overload probe and backoff state

* fix(agents): persist overloaded cooldown across runs

* fix(agents): tighten overloaded status handling

* test(agents): add overload regression coverage

* fix(agents): restore runner imports after rebase

* test(agents): add overload fallback integration coverage

* fix(agents): harden overloaded failover abort handling

* test(agents): tighten overload classifier coverage

* test(agents): cover all-overloaded fallback exhaustion

* fix(cron): retry overloaded fallback summaries

* fix(cron): treat HTTP 529 as overloaded retry

* Dead code: remove unused provider runtime policy helper

* Dead code: remove unused shared env writer

* Dead code: remove unused auth store path collector

…penclaw#34556)

Merged via squash.

Prepared head SHA: 491bb28
Co-authored-by: efe-arv <[email protected]>
Co-authored-by: jalehman <[email protected]>
Reviewed-by: @jalehman

…aw#36280) (openclaw#36316)

* fix: strip skill-injected env vars from ACP harness spawn env

Skill apiKey entries (e.g., openai-image-gen with primaryEnv=OPENAI_API_KEY)
are set on process.env during agent runs and only reverted after the run
completes. ACP harnesses like Codex CLI inherit these vars, causing them
to silently use API billing instead of their own auth (e.g., OAuth).

The fix tracks which env vars are actively injected by skill overrides in
a module-level Set (activeSkillEnvKeys) and strips them in
resolveAcpClientSpawnEnv() before spawning ACP child processes.

Fixes openclaw#36280

* ACP: type spawn env for stripped keys

* Skills: cover active env key lifecycle

* Changelog: note ACP skill env isolation

* ACP: preserve shell marker after env stripping

---------

Co-authored-by: Vincent Koc <[email protected]>

…ools (openclaw#26331)

Merged via squash.

Prepared head SHA: 1fbe1c7
Co-authored-by: widingmarcus-cyber <[email protected]>
Co-authored-by: jalehman <[email protected]>
Reviewed-by: @jalehman

openclaw#34977)

Merged via squash.

Prepared head SHA: 1c14094
Co-authored-by: sp-hk2ldn <[email protected]>
Co-authored-by: jalehman <[email protected]>
Reviewed-by: @jalehman

* Config: add supportsTools compat flag

* Agents: add model tool support helper

* Venice: sync discovery and fallback metadata

* Agents: skip tools for unsupported models

* Changelog: note Venice provider hardening

* Update CHANGELOG.md

* Venice: cap degraded discovery metadata

* Apply suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Venice: tolerate partial discovery capabilities

* Venice: tolerate missing discovery specs

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

…mplifying NO_REPLY into queue overflow (openclaw#33295)

* fix(imessage): prevent echo loop from leaking internal metadata and amplifying NO_REPLY into queue overflow

- Add outbound sanitization at channel boundary (sanitize-outbound.ts):
  strips thinking/reasoning tags, relevant-memories tags, model-specific
  separators (+#+#), and assistant role markers before iMessage delivery

- Add inbound reflection guard (reflection-guard.ts): detects and drops
  messages containing assistant-internal markers that indicate a reflected
  outbound message, preventing recursive echo amplification

- Harden echo cache: increase text TTL from 5s to 30s to catch delayed
  reflections that previously expired before the echo could be detected

- Add loop rate limiter (loop-rate-limiter.ts): per-conversation rapid-fire
  detection that suppresses conversations exceeding threshold within a
  time window, acting as a safety net against amplification

Closes openclaw#33281

* fix(imessage): address review — stricter reflection regex, loop-aware rate limiter

- Reflection guard: require closing > bracket on thinking/final/memory
  tag patterns to prevent false-positives on user phrases like
  '<final answer>' or '<thought experiment>' (openclaw#33295 review)

- Rate limiter: only record echo/reflection/from-me drops instead of
  all dispatches, so the limiter acts as a loop-specific escalation
  mechanism rather than a general throttle on normal conversation
  velocity (openclaw#33295 review)

* Changelog: add iMessage echo-loop hardening entry

* iMessage: restore short echo-text TTL

* iMessage: ignore reflection markers in code

---------

Co-authored-by: Vincent Koc <[email protected]>

* Docs: refresh Venice default model guidance

* Venice: switch default model to Kimi K2.5

* Changelog: credit Venice default refresh

…essing

Fixes openclaw#37844

The debounce key was missing messageId, causing duplicate message
processing when Discord Gateway reconnects or retries delivery.
Key now includes messageId: discord:{accountId}:{channelId}:{authorId}:{messageId}