vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-15 11:11:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
29,858 Commits 1,302 Branches 108 Tags
0ebeee8b0de41611a59500d257ae78b513cbd2d4
Commit Graph

26 Commits

Author SHA1 Message Date
Peter Steinberger
9d4b0d551d fix: support inferrs string-only completions 2026-04-07 15:55:20 +01:00
Peter Steinberger
19de5d1b56 refactor: move provider discovery config into plugins 2026-04-05 09:55:55 +01:00
Peter Steinberger
455c642acb feat: add implicit discovery toggles 2026-04-05 09:27:48 +01:00
Peter Steinberger
58d2b9dd46 fix: add runtime model contextTokens caps 2026-04-04 09:36:53 +09:00
Vincent Koc
61f13173c2 feat(providers): add model request transport overrides (#60200) 
* feat(providers): add model request transport overrides

* chore(providers): finalize request override follow-ups

* fix(providers): narrow model request overrides
 2026-04-03 19:00:06 +09:00
Kunal Karmakar
34b0a19a16 fix: use azure-openai-responses for Azure custom providers (#50851) (thanks @kunalk16) 
* Add azure-openai-responses

* Unit tests update for updated API

* Add entry for PR #50851

* Add comma to address PR comment

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

* Address PR comment on sanitization of output

* Address review comment

* Revert commits

* Revert commit

* Update changelog stating Azure OpenAI only

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

* Add references

* Address PR comment on sanitization of output

* Address review comment

* Revert commits

* Revert commit

* Address PR comment on sanitization of output

* Address review comment

* Revert commits

* Revert commit

* Fix generated file

* Add azure openai responses to OPENAI_RESPONSES_APIS

* Add azure openai responses to createParallelToolCallsWrapper

* Adding azure openai responses to attempt.ts

* Add azure openai responses to google.ts

* Address PR comment on sanitization of output

* Revert commit

* Address PR comment on sanitization of output

* Revert commit

* Address PR comment on sanitization of output

* Revert commit

* Fix changelog

* Fix linting

* fix: cover azure responses wrapper path (#50851) (thanks @kunalk16)

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
 2026-03-30 16:17:03 +05:30
Peter Steinberger
b236f39104 refactor(agents): generalize tool schema compat cleanup 2026-03-28 05:42:46 +00:00
Peter Steinberger
ab2bd34b66 refactor(xai): split provider compat facades 
Co-authored-by: Harold Hunt <harold@pwrdrvr.com>
 2026-03-28 05:02:41 +00:00
Peter Steinberger
8e09568bc7 perf: expand base vitest thread lanes 2026-03-22 11:59:38 -07:00
Vincent Koc
b9e08a6839 Config: align model compat thinking format types 2026-03-18 02:45:15 -07:00
Josh Lehman
4ca87fa4b0 fix: restore main build (#49478) 
* Build: restore main build

* Config: align model compat schema
 2026-03-17 22:14:56 -07:00
Peter Steinberger
a8907d80dd feat: finish xai provider integration 2026-03-17 21:31:20 -07:00
Peter Steinberger
e5c06dd64a refactor: use model compat for anthropic tool payload normalization 2026-03-08 18:26:35 +00:00
Josh Avant
8e20dd22d8 Secrets: harden SecretRef-safe models.json persistence (#38955) 2026-03-07 11:28:39 -06:00
Vincent Koc
5320ee7731 fix(venice): harden discovery limits and tool support (#38306) 
* 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>
 2026-03-06 19:07:11 -05:00
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
Peter Steinberger
344f54b84d refactor(config): dedupe model api definitions 2026-02-26 20:00:11 +01:00
Peter Steinberger
ac03803d12 fix: align codex model api schema/type coverage (#27501) (thanks @AytuncYildizli) 2026-02-26 18:51:04 +00:00
joshavant
b50c4c2c44 Gateway: add eager secrets runtime snapshot activation 2026-02-26 14:47:22 +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
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
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
bcbfb357be refactor(src): split oversized modules 2026-01-14 01:17:56 +00:00