gitops/optimclaw
1
0
Fork 0
mirror of https://github.com/outbackdingo/optimclaw.git synced 2026-08-26 15:40:18 +00:00
Code Issues Packages Projects Releases Wiki Activity
907 Commits 115 Branches 33 Tags
7d31d68f6f08c95c86c187fbb297f060aaf064d9
Commit Graph
3 Commits
Author SHA1 Message Date
[email protected]andClaude Opus 4.6 7d31d68f6f feat(skills): add 245 Pica integration skills covering full catalog 
Add SKILL.md files for all 252 Pica platform integrations (245 new,
7 internal skills already existed). Covers the full Pica catalog:

- CRM: attio, close, freshdesk, gorgias, hubspot, intercom, klaviyo, zoho, etc.
- Communication: bluesky, linked-in, meta, x, teams, twilio, ring-central, etc.
- DevOps: git-lab, circle-ci, netlify, render, n8n, neon, ngrok, posthog, etc.
- AI/LLM: anthropic, deep-seek, gemini, perplexity, open-router, x-ai
- E-commerce: big-commerce, shopify-admin, shopify-storefront, square, woocommerce
- Payments: chargebee, paystack, square, stripe
- Email: sendgrid, mailchimp-marketing, mailgun, loops
- And 190+ more across all categories

~83 skills have detailed API docs (base URLs, example http() calls, notes).
~122 skills have auth setup and credential config from Pica metadata.

Skills are embedded into the binary at compile time via the bundling
infrastructure added to v2-architecture, making them available on
every IronClaw install without needing ClawHub.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
 2026-03-27 20:16:12 -07:00
[email protected]andClaude Opus 4.6 96266cb46d feat(skills): credential specs in skill frontmatter, HTTP tool hardening, mission leases 
Skills can now declare API credentials in YAML frontmatter (SkillCredentialSpec,
SkillCredentialLocation, SkillOAuthConfig, ProviderRefreshStrategy). Valid specs
are registered into SharedCredentialRegistry at startup; the HttpTool auto-injects
credentials for matching hosts — same zero-exposure model as WASM tools.

HTTP tool security hardening:
- Block LLM-provided auth headers for hosts with registered credentials
- Return structured authentication_required error for missing credentials
- Strip sensitive response headers (Set-Cookie, WWW-Authenticate, Authorization)
- Scan response body through LeakDetector before returning to LLM

Mission capability leases: registered mission_create/list/fire/pause/resume/delete
as a "missions" capability so threads receive leases. Removed routine_* aliases
from effect adapter — descriptions mention "routine" for LLM intent mapping.

Includes 10 integration tests (tests/skill_credential_injection.rs) covering
the full pipeline: YAML parsing → validation → registry → HttpTool wiring →
per-user isolation.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
 2026-03-27 19:33:58 -07:00
[email protected]andClaude Opus 4.6 8e2349d12e feat(skills): extract ironclaw_skills crate and integrate with v2 engine 
Extract the skills system into a standalone `ironclaw_skills` crate
(following the ironclaw_safety pattern) and wire it into the v2 engine
for deterministic skill selection, CodeAct code injection, and
confidence tracking.

**ironclaw_skills crate** (94 tests):
- Core types: SkillManifest, ActivationCriteria, LoadedSkill, SkillTrust
- V2 types: V2SkillMetadata, CodeSnippet, SkillMetrics, V2SkillSource
- Deterministic 4-phase selector (gating→scoring→budget→attenuation)
- apply_confidence_factor() for extracted skill scoring
- SKILL.md parser, validation/escaping, gating, registry, catalog
- Feature-gated: catalog (reqwest), registry (filesystem)

**Engine integration** (14 new tests):
- DocType::Skill with retrieval weight 0.45
- SkillSelector bridges MemoryDoc→LoadedSkill for shared scoring
- SkillTracker for usage/version/rollback confidence tracking
- System prompt injection via <skill> XML blocks
- CodeAct snippet injection via Monty NameLookup
- Skill extraction mission replaces playbook extraction
- ThreadManager.set_skill_selector() for runtime wiring

**Bridge + migration**:
- skill_migration.rs: v1 SKILL.md → v2 MemoryDoc (idempotent)
- init_engine() migrates v1 skills, builds SkillSelector
- src/skills/mod.rs → re-export shim

**E2E test** (tests/engine_v2_skill_codeact.rs):
- Full CodeAct loop: skill selected → LLM returns Python code →
  Monty executes http() → mock returns canned GitHub JSON →
  FINAL() terminates → thread completes with canned data
- GitHub SKILL.md in skills/github/ as reference implementation

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
 2026-03-27 16:24:07 -07:00