Commit Graph

54 Commits

Author SHA1 Message Date
Vincent Koc
f16ecd1dac fix(ollama): unify context window handling across discovery, merge, and OpenAI-compat transport (#29205)
* fix(ollama): inject num_ctx for OpenAI-compatible transport

* fix(ollama): discover per-model context and preserve higher limits

* fix(agents): prefer matching provider model for fallback limits

* fix(types): require numeric token limits in provider model merge

* fix(types): accept unknown payload in ollama num_ctx wrapper

* fix(types): simplify ollama settled-result extraction

* config(models): add provider flag for Ollama OpenAI num_ctx injection

* config(schema): allow provider num_ctx injection flag

* config(labels): label provider num_ctx injection flag

* config(help): document provider num_ctx injection flag

* agents(ollama): gate OpenAI num_ctx injection with provider config

* tests(ollama): cover provider num_ctx injection flag behavior

* docs(config): list provider num_ctx injection option

* docs(ollama): document OpenAI num_ctx injection toggle

* docs(config): clarify merge token-limit precedence

* config(help): note merge uses higher model token limits

* fix(ollama): cap /api/show discovery concurrency

* fix(ollama): restrict num_ctx injection to OpenAI compat

* tests(ollama): cover ipv6 and compat num_ctx gating

* fix(ollama): detect remote compat endpoints for ollama-labeled providers

* fix(ollama): cap per-model /api/show lookups to bound discovery load
2026-02-27 17:20:47 -08:00
Marcus Widing
cbed0e065c fix: reject dmPolicy="allowlist" with empty allowFrom across all channels
When dmPolicy is set to "allowlist" but allowFrom is missing or empty,
all DMs are silently dropped because no sender can match the empty
allowlist. This is a common pitfall after upgrades that change how
allowlist files are handled (e.g., external allowlist-dm.json files
being deprecated in favor of inline allowFrom arrays).

Changes:
- Add requireAllowlistAllowFrom schema refinement (zod-schema.core.ts)
- Apply validation to all channel schemas: Telegram, Discord, Slack,
  Signal, IRC, iMessage, BlueBubbles, MS Teams, Google Chat, WhatsApp
- Add detectEmptyAllowlistPolicy to doctor-config-flow.ts so
  "openclaw doctor" surfaces a clear warning with remediation steps
- Add 12 test cases covering reject/accept for multiple channels

Fixes #27892
2026-02-26 22:04:16 +00:00
Peter Steinberger
344f54b84d refactor(config): dedupe model api definitions 2026-02-26 20:00:11 +01:00
AytuncYildizli
861b90f79c fix(config): add openai-codex-responses to ModelApiSchema
The config schema validates provider api fields against ModelApiSchema,
but openai-codex-responses was missing from the allowed values. This
forces users to set api: "openai-responses" for the openai-codex
provider, which routes requests to api.openai.com/v1/responses instead
of chatgpt.com/backend-api/codex/responses, causing HTTP 401 errors
because Codex OAuth tokens lack api.responses.write scope for the
standard OpenAI Responses endpoint.

The runtime already supports openai-codex-responses throughout: model
registry, stream dispatch (streamOpenAICodexResponses), and provider
detection (OPENAI_MODEL_APIS set). Only the config schema was missing
the literal.
2026-02-26 18:51:04 +00:00
joshavant
d879c7c641 fix(secrets): harden apply and audit plan handling 2026-02-26 14:47:22 +00:00
joshavant
f46b9c996f feat(secrets): allow opt-in symlink exec command paths 2026-02-26 14:47:22 +00:00
joshavant
06290b49b2 feat(secrets): finalize mode rename and validated exec docs 2026-02-26 14:47:22 +00:00
joshavant
8944b75e16 fix(secrets): align ref contracts and non-interactive ref persistence 2026-02-26 14:47:22 +00:00
joshavant
4e7a833a24 feat(security): add provider-based external secrets management 2026-02-26 14:47:22 +00:00
joshavant
d00ed73026 Config: enforce source-specific SecretRef id validation 2026-02-26 14:47:22 +00:00
joshavant
c3a4251a60 Config: add secret ref schema and redaction foundations 2026-02-26 14:47:22 +00:00
Peter Steinberger
0183610db3 refactor: de-duplicate channel runtime and payload helpers 2026-02-23 21:25:28 +00:00
Peter Steinberger
e029f78447 refactor(config): dedupe install and typing schema definitions 2026-02-22 21:19:09 +00:00
Peter Steinberger
34ea33f057 refactor: dedupe core config and runtime helpers 2026-02-22 17:11:54 +00:00
Peter Steinberger
6a19654c4a refactor(core): dedupe browser route signatures and cli watchdog schema 2026-02-18 14:15:20 +00:00
Onur
cd44a0d01e fix: codex and similar processes keep dying on pty, solved by refactoring process spawning (#14257)
* exec: clean up PTY resources on timeout and exit

* cli: harden resume cleanup and watchdog stalled runs

* cli: productionize PTY and resume reliability paths

* docs: add PTY process supervision architecture plan

* docs: rewrite PTY supervision plan as pre-rewrite baseline

* docs: switch PTY supervision plan to one-go execution

* docs: add one-line root cause to PTY supervision plan

* docs: add OS contracts and test matrix to PTY supervision plan

* docs: define process-supervisor package placement and scope

* docs: tie supervisor plan to existing CI lanes

* docs: place PTY supervisor plan under src/process

* refactor(process): route exec and cli runs through supervisor

* docs(process): refresh PTY supervision plan

* wip

* fix(process): harden supervisor timeout and PTY termination

* fix(process): harden supervisor adapters env and wait handling

* ci: avoid failing formal conformance on comment permissions

* test(ui): fix cron request mock argument typing

* fix(ui): remove leftover conflict marker

* fix: supervise PTY processes (#14257) (openclaw#14257) (thanks @onutc)
2026-02-16 02:32:05 +01:00
Peter Steinberger
747b11c83e refactor(config): share allow/deny channel policy schema 2026-02-14 15:39:45 +00:00
Cezar “ikari” Pokorski
d134c854a5 feat(config): expose full pi-ai model compat fields in config schema (openclaw#11063) thanks @ikari-pl
Verified:
- pnpm build
- pnpm check
- pnpm test (full run; transient lobster timeout rerun passed)

Co-authored-by: ikari-pl <811702+ikari-pl@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-13 18:47:18 -06:00
Sunwoo Yu
11702290ff feat(ollama): add native /api/chat provider for streaming + tool calling (#11853)
Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: 0a723f98e6
Co-authored-by: BrokenFinger98 <115936166+BrokenFinger98@users.noreply.github.com>
Co-authored-by: steipete <58493+steipete@users.noreply.github.com>
Reviewed-by: @steipete
2026-02-14 01:20:42 +01:00
Henry Loenwind
96318641d8 fix: Finish credential redaction that was merged unfinished (#13073)
* Squash

* Removed unused files

Not mine, someone merged that stuff in earlier.

* fix: patch redaction regressions and schema breakages

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-02-13 16:19:21 +01:00
Vignesh
fa906b26ad feat: IRC — add first-class channel support
Adds IRC as a first-class channel with core config surfaces (schema/hints/dock), plugin auto-enable detection, routing/policy alignment, and docs/tests.

Co-authored-by: Vignesh <vigneshnatarajan92@gmail.com>
2026-02-10 17:33:57 -06:00
max
223eee0a20 refactor: unify peer kind to ChatType, rename dm to direct (#11881)
* fix: use .js extension for ESM imports of RoutePeerKind

The imports incorrectly used .ts extension which doesn't resolve
with moduleResolution: NodeNext. Changed to .js and added 'type'
import modifier.

* fix tsconfig

* refactor: unify peer kind to ChatType, rename dm to direct

- Replace RoutePeerKind with ChatType throughout codebase
- Change 'dm' literal values to 'direct' in routing/session keys
- Keep backward compat: normalizeChatType accepts 'dm' -> 'direct'
- Add ChatType export to plugin-sdk, deprecate RoutePeerKind
- Update session key parsing to accept both 'dm' and 'direct' markers
- Update all channel monitors and extensions to use ChatType

BREAKING CHANGE: Session keys now use 'direct' instead of 'dm'.
Existing 'dm' keys still work via backward compat layer.

* fix tests

* test: update session key expectations for dmdirect migration

- Fix test expectations to expect :direct: in generated output
- Add explicit backward compat test for normalizeChatType('dm')
- Keep input test data with :dm: keys to verify backward compat

* fix: accept legacy 'dm' in session key parsing for backward compat

getDmHistoryLimitFromSessionKey now accepts both :dm: and :direct:
to ensure old session keys continue to work correctly.

* test: add explicit backward compat tests for dmdirect migration

- session-key.test.ts: verify both :dm: and :direct: keys are valid
- getDmHistoryLimitFromSessionKey: verify both formats work

* feat: backward compat for resetByType.dm config key

* test: skip unix-path Nix tests on Windows
2026-02-09 09:20:52 +09:00
cpojer
f06dd8df06 chore: Enable "experimentalSortImports" in Oxfmt and reformat all imorts. 2026-02-01 10:03:47 +09:00
cpojer
5ceff756e1 chore: Enable "curly" rule to avoid single-statement if confusion/errors. 2026-01-31 16:19:20 +09:00
Seb Slight
d4f60bf16a TTS: gate auto audio on inbound voice notes (#1667)
Co-authored-by: Sebastian <sebslight@gmail.com>
2026-01-25 04:35:20 +00:00
Peter Steinberger
fc0e303e05 feat: add edge tts fallback provider 2026-01-25 01:05:43 +00:00
Richard Pinedo
426168a338 Add link understanding tool support (#1637)
* Add

* Fix

---------

Co-authored-by: Richard <dasilva333@DESKTOP-74E3GJO.localdomain>
2026-01-25 00:15:54 +00:00
Peter Steinberger
5ad203e47b fix: default custom provider model fields 2026-01-25 00:02:53 +00:00
Peter Steinberger
6765fd15eb feat: default TTS model overrides on (#1559) (thanks @Glucksberg)
Co-authored-by: Glucksberg <80581902+Glucksberg@users.noreply.github.com>
2026-01-24 09:42:32 +00:00
Peter Steinberger
d9a467fe3b feat: move TTS into core (#1559) (thanks @Glucksberg) 2026-01-24 08:00:44 +00:00
Peter Steinberger
4e77483051 fix: refine bedrock discovery defaults (#1543) (thanks @fal3) 2026-01-24 01:18:33 +00:00
Alex Fallah
8effb557d5 feat: add dynamic Bedrock model discovery
Add automatic discovery of AWS Bedrock models using ListFoundationModels API.
When AWS credentials are detected, models that support streaming and text output
are automatically discovered and made available.

- Add @aws-sdk/client-bedrock dependency
- Add discoverBedrockModels() with caching (default 1 hour)
- Add resolveImplicitBedrockProvider() for auto-registration
- Add BedrockDiscoveryConfig for optional filtering by provider/region
- Filter to active, streaming, text-output models only
- Update docs/bedrock.md with auto-discovery documentation
2026-01-24 01:15:06 +00:00
Peter Steinberger
b77e730657 fix: add per-channel markdown table conversion (#1495) (thanks @odysseus0) 2026-01-23 18:39:25 +00:00
Dominic Damoah
fe77d3eb56 Merge branch 'main' into feat/mattermost-channel 2026-01-22 02:49:17 -05:00
Peter Steinberger
a2bea8e366 feat: add agent avatar support (#1329) (thanks @dlauer) 2026-01-22 04:00:07 +00:00
Dominic Damoah
bf6df6d6b7 feat: add Mattermost channel support
Add Mattermost as a supported messaging channel with bot API and WebSocket integration. Includes channel state tracking (tint, summary, details), multi-account support, and delivery target routing. Update documentation and tests to include Mattermost alongside existing channels.
2026-01-21 18:40:56 -05:00
Peter Steinberger
32550154f9 feat(queue): add per-channel debounce overrides 2026-01-21 18:50:55 +00:00
Peter Steinberger
d69f246ba7 chore: fix lint/format 2026-01-20 13:52:59 +00:00
Peter Steinberger
a5adedea91 refactor: add aws-sdk auth mode and tighten provider auth 2026-01-20 08:28:40 +00:00
Andrew Lauppe
a793523b74 feat(models): add bedrock-converse-stream API type
Add AWS Bedrock Converse Stream API to the list of supported model APIs,
enabling custom provider configurations for Amazon Bedrock endpoints.

This allows users to configure Bedrock models in their clawdbot.json:

  "models": {
    "providers": {
      "amazon-bedrock": {
        "baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
        "api": "bedrock-converse-stream",
        "models": [...]
      }
    }
  }

The underlying adapter already exists; this change exposes it as a valid
configuration option.
2026-01-20 01:28:07 -05:00
Peter Steinberger
2dc9c95530 style: oxfmt core files 2026-01-19 05:59:29 +00:00
Peter Steinberger
d1e9490f95 fix: enforce strict config validation 2026-01-19 03:39:25 +00:00
Peter Steinberger
d66bc65ca6 refactor: unify media provider options 2026-01-17 09:28:05 +00:00
Peter Steinberger
ae6792522d feat: add deepgram audio options 2026-01-17 08:53:42 +00:00
Peter Steinberger
7cebe7a506 style: run oxfmt 2026-01-17 08:00:05 +00:00
Peter Steinberger
e59d8c5436 style: oxfmt format 2026-01-17 05:48:56 +00:00
Peter Steinberger
8b42902cee refactor: drop legacy room chatType 2026-01-17 05:46:40 +00:00
Peter Steinberger
fcb7c9ff65 refactor: unify media understanding pipeline 2026-01-17 04:39:00 +00:00
Peter Steinberger
87cecd0268 refactor: align channel chatType 2026-01-17 04:13:06 +00:00
Peter Steinberger
1b973f7506 feat: add inbound media understanding
Co-authored-by: Tristan Manchester <tmanchester96@gmail.com>
2026-01-17 03:54:46 +00:00