harald/zeroclaw
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3
735 commits 1 branch 0 tags 7.8 MiB
Commit graph

2 commits

Author SHA1 Message Date
Edvard Schøyen
49bb20f961
fix(providers): use Bearer auth for Gemini CLI OAuth tokens 
* fix(providers): use Bearer auth for Gemini CLI OAuth tokens

When credentials come from ~/.gemini/oauth_creds.json (Gemini CLI),
send them as Authorization: Bearer header instead of ?key= query
parameter. API keys from env vars or config continue using ?key=.

Fixes #194

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(gemini): harden OAuth bearer auth flow and tests

* fix(gemini): granular auth source tracking and review fixes

Build on chumyin's auth model refactor with:
- Expand GeminiAuth to 4 variants (ExplicitKey/EnvGeminiKey/EnvGoogleKey/
  OAuthToken) so auth_source() uses stored discriminant without re-reading
  env vars at call time
- Add is_api_key()/credential() helpers on the enum
- Upgrade expired OAuth token log from debug to warn
- Add tests: provider_rejects_empty_key, auth_source_explicit_key,
  auth_source_none_without_credentials

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* style: apply rustfmt to fix CI lint failures

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: root <root@instance-20220913-1738.vcn09131738.oraclevcn.com>
Co-authored-by: argenis de la rosa <theonlyhennygod@gmail.com>
 2026-02-15 14:32:33 -05:00
Argenis
35b63d6b12
feat: SkillForge — automated skill discovery, evaluation & integration engine (#144) 
* feat: add SkillForge — automated skill discovery, evaluation, and integration engine

SkillForge adds a 3-stage pipeline for autonomous skill management:

- Scout: discovers candidate skills from GitHub (extensible to ClawHub, HuggingFace)
- Evaluate: scores candidates on compatibility, quality, and security (weighted 0.30/0.35/0.35)
- Integrate: generates standard SKILL.toml + SKILL.md manifests for approved candidates

Thresholds: >=0.7 auto-integrate, 0.4-0.7 manual review, <0.4 skip.
Uses only existing dependencies (reqwest, serde, tokio, tracing, chrono, anyhow).
Includes unit tests for all modules.

* fix: address code review feedback on SkillForge PR #115

- evaluate: whole-word matching for BAD_PATTERNS (fixes hackathon false positive)
- evaluate: guard against future timestamps in recency bonus
- integrate: escape URLs in TOML output via escape_toml()
- integrate: handle control chars (\n, \r, \t, \b, \f) in escape_toml()
- mod: redact github_token in Debug impl to prevent log leakage
- mod: fix auto_integrated count when auto_integrate=false
- mod: per-candidate error handling (single failure no longer aborts pipeline)
- scout: add 30s request timeout, remove unused token field
- deps: enable chrono serde feature for DateTime serialization
- tests: add hackathon/exact-hack tests, update escape_toml test coverage

* fix: address round-2 CodeRabbit review feedback

- integrate: add sanitize_path_component() to prevent directory traversal
- mod: GitHub scout failure now logs warning and continues (no pipeline abort)
- scout: network/parse errors per-query use warn+continue instead of ?
- scout: implement std::str::FromStr for ScoutSource (replaces custom from_str)
- tests: add path sanitization tests (traversal, separators, dot trimming)

---------

Co-authored-by: stawky <stakeswky@gmail.com>
 2026-02-15 09:26:13 -05:00