* docs(gateway): document llamacpp toolSchemaProfile for custom llama.cpp endpoints
Custom openai-completions providers pointed at a llama.cpp / llama-server
endpoint bypass the GBNF-safe schema normalization that built-in llama-cpp,
ollama, and lmstudio providers apply automatically. The toolSchemaProfile:
"llamacpp" switch activates it, but the supported value was never named in
the docs, so users hit llama.cpp 400 'failed to parse grammar' on tools with
large minLength/maxLength (e.g. cron trigger.script, maxLength 65536).
- Expand the toolSchemaProfile row to name the values recognized on a model's
compat (llamacpp, gemini) and when llamacpp must be set explicitly;
cross-reference the unsupportedToolSchemaKeywords escape hatch.
- Add a 'Local models (llama.cpp / llama-server)' provider example showing
the required compat.toolSchemaProfile: "llamacpp" on a custom endpoint.
Related to #117070
Co-Authored-By: iCodeMate <noreply@anthropic.com>
* docs(gateway): describe llamacpp profile as stripping, not clamping
Address review feedback on #117120: the fallback sentence claimed the
llamacpp profile "also clamps" constraints, but cleanSchemaForLlamacppGbnf
only removes `pattern` outright and drops `maxLength` at or above the
2000-repetition threshold (LLAMACPP_GBNF_MAX_REPETITION_THRESHOLD). It
never clamps a value, and small bounds like `minLength: 1` are preserved
(confirmed by the projection test at src/plugin-sdk/provider-tools.test.ts).
Reword the escape-hatch sentence to describe the implemented stripping
behavior and contrast it with the unconditional keyword-list drops, so
operators do not expect a preserved bounded constraint.
No code or behavior changes; documentation only.
* docs(gateway): scope llamacpp profile description to its actual transformations
Address follow-up review on #117120: the toolSchemaProfile table row
described `llamacpp` as "rewriting tool schemas into the JSON Schema
subset llama.cpp can compile to GBNF," which overstates what
cleanSchemaForLlamacppGbnf does. The cleaner only removes `pattern`
outright and drops `maxLength` at or above the 2000-repetition threshold
(LLAMACPP_GBNF_MAX_REPETITION_THRESHOLD); it leaves every other keyword
and `minLength` untouched, and those are not guaranteed GBNF-safe.
Reword the row to state the exact transformation contract and explicitly
note it is a targeted compatibility cleaner, not a blanket GBNF-safety
guarantee. No code or behavior changes; documentation only.
Co-Authored-By: iCodeMate <noreply@anthropic.com>
* docs(gateway): tighten llama.cpp profile contract
* docs(gateway): order local model examples
---------
Co-authored-by: iCodeMate <noreply@anthropic.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(cli): update plugins doctor clean message (#115073)
Root cause: plugins doctor reports 'No plugin issues detected.' even when a selected context-engine plugin is quarantined at runtime, because doctor is a fast static control-plane check.
Architectural owner: plugins-cli.runtime.ts
Canonical fix: Change clean status message to direct operators to 'openclaw health' for active runtime quarantine/fallback status.
Production LOC delta: +2 LOC
* fix(cli): update plugins doctor clean message wording (#115073)
Root cause: Refine the diagnostic text message to run openclaw health directly.
Architectural owner: src/cli/plugins-cli.runtime.ts
* fix(cli): clarify plugin doctor scope
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(plugin-sdk): project recorded health facts through computed account status
* fix(plugin-sdk): regenerate API baseline and pin ingressUnavailable literal in test
* fix: gateway service commands refuse a named profile or relocated OPENCLAW_HOME
- Resolve the default install identity against the canonical state directory
for the active OpenClaw home and profile instead of the unprofiled OS
account default.
- `--profile <name>` / `--dev` project `.openclaw-<profile>` state and config
paths, so every named profile was classified as isolated state and refused
`install`, `start`, `stop`, `restart`, `uninstall`, Doctor service repair,
and self-update service handling.
- `OPENCLAW_HOME` relocates all OpenClaw path defaults and is documented for
running as a dedicated service user; a relocated home is now an install
identity. `HOME` alone still is not.
- An `OPENCLAW_STATE_DIR` or `OPENCLAW_CONFIG_PATH` pointing outside those
canonical paths is still treated as isolated state.
- Recovery guidance in the refusal message now names the paths that must match.
Verified: focused vitest shards for the changed suites plus the daemon, CLI,
and doctor suites that consume the identity check; tsgo core and core-test
lanes; oxlint; docs format, MDX, link, and map checks.
* fix(gateway): keep relocated homes isolated
* fix(config): validate service profile identity
* fix(daemon): enforce named-profile service ownership
* fix(update): reject drifted service selectors before probes
* test(windows): prove scheduled task lifecycle
* test(windows): harden scheduled task proof cleanup
* test(windows): bind lifecycle proof to checkout
* test(windows): normalize cleanup exit status
* test(windows): verify effective task privilege
* test(windows): protect scheduled task proof roots
* test(windows): prove listener-owned task lifecycle
* test(windows): fix scheduled task proof contracts
* test(windows): remove redundant mock coercions
* test(windows): measure fallback before task probes
* test(windows): prove scheduled task process origin
* fix(gateway): preserve unmanaged restart fallback
* test(gateway): cover denied restart ownership
* test(gateway): keep restart helper types private
* test(gateway): classify lifecycle helpers as test code
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* docs(config-channels): replace legacy allow:true with enabled:true for Discord, Slack, and Google Chat config examples
* docs(config-channels): repair channel configuration examples
Make the complete Discord, Slack, and Google Chat setup examples valid and keep Slack channel routing on stable IDs.
Co-authored-by: 赵旺0668001248 <zhao.wang1@xydigit.com>
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
The gateway.reload documentation advertised four settings the shipped
build rejects. gateway.reload is a strictObject accepting only `mode`,
and `mode` is a union of "off" | "hybrid", so a config written from the
docs fails validation and the gateway fails closed on the unknown keys.
Retired but still documented:
- `debounceMs` and `deferralTimeoutMs` (RETIRED_TUNING_PATHS; stripped by
`openclaw doctor --fix` via stripRetiredTuningKnobs)
- `mode: "restart"` and `mode: "hot"` (mapped to "hybrid" by
`openclaw doctor --fix`)
Correct all four docs pages that still describe them, and say what
replaced them: debounce and active-work deferral now run behind built-in
defaults rather than config keys.
Refs #116973
Reject symlinked generated-output roots before build and postbuild mutation paths can recurse into unrelated targets. Cover aggregate, UI, export-template, bundled-plugin, Docker-prune, and plugin-runtime entry points with regression tests and migration guidance.
Closes#116498
Co-authored-by: WangYan <wang.yan29@xydigit.com>
* fix(memory-wiki): preserve user edits when rolling back ChatGPT imports
Rollback deleted created pages and overwrote updated pages unconditionally,
destroying content the user added after the import with no recovery copy.
Import runs now record a content hash of each written page after vault
compile, and rollback preserves any page whose current content no longer
matches into the run's recovered directory before deleting or restoring.
Legacy run records without hashes preserve unconditionally.
Fixes#116457
* fix(memory-wiki): move pages aside atomically during rollback
Rollback now renames the live page into the recovery location before
inspecting it, so a concurrent external save cannot land between the
content read and the delete or snapshot restore. Matching pages drop
the moved copy; mismatching pages keep it as the recovery file.
* fix(memory-wiki): make rollback snapshot restore collision-safe
The snapshot restore wrote directly to the page path after the
move-aside, so a page recreated by an editor in that window was
overwritten with no recovery copy. Restore now creates the snapshot
exclusively and on collision moves the recreated page aside and
retries; recovery filenames are uniqued so a second move-aside cannot
clobber an earlier preserved copy.
* fix(memory-wiki): record rollback hashes at write time
* fix(memory-wiki): make ChatGPT rollback retry-safe
* fix(memory-wiki): fence ChatGPT rollback phases
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
