Commit Graph

4 Commits

Author SHA1 Message Date
Urvish L.
44a2c30d5f feat: implement Hook Chains runtime integration for self-healing agent mesh MVP (#711)
* feat: implement Hook Chains runtime integration for self-healing agent mesh MVP

- Add Hook Chains config loader, evaluator, and dispatcher in src/utils/hookChains.ts
- Wire PostToolUseFailure hook dispatch in executePostToolUseFailureHooks()
- Wire TaskCompleted hook dispatch in executeTaskCompletedHooks()
- Integrate fallback-agent launcher with permission preservation (canUseTool threading)
- Add safety hardening for config-read errors (try-catch protection)
- Update docs with MVP runtime trigger explanation
- Add 10 unit tests and 4 integration tests covering config, rules, guards, and actions

This completes the self-healing agent mesh MVP by enabling declarative rule-based
responses to tool failures and task completions, with fallback agent spawning,
team notification, and capacity warming actions.

* Update docs/hook-chains.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update src/utils/hookChains.ts

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: address PR #711 review blockers for Hook Chains

- Gate hook-chain dispatch behind feature('HOOK_CHAINS') and default env gate to off
- Remove committed local artifact (agent.log) and ignore it in .gitignore
- Revert hook dispatcher signature threading changes for canUseTool
- Use ToolUseContext metadata hookChainsCanUseTool for fallback launch permissions
- Make spawn_fallback_agent fail explicitly when launcher context is unavailable
- Add config cache max age and guard map size limits to bound runtime memory
- Update docs and tests for default-off gating and explicit fallback failure

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-04-22 19:40:23 +08:00
JasonVon
fb32e3f829 feat: per-agent model routing — route different agents to different providers (#238)
* feat: add agentModels and agentRouting to SettingsSchema

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: add agentRouting module for per-agent provider resolution

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: thread providerOverride through OpenAI shim for per-agent routing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: getAnthropicClient accepts providerOverride for agent routing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: thread providerOverride through Options and queryModel calls

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: thread providerOverride through query loop and ToolUseContext

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: resolve agent routing in runAgent and inject providerOverride

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add Agent Routing configuration guide to README

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test: add unit tests for resolveAgentProvider + plaintext api_key note

- 15 tests covering priority chain (name > subagentType > default > null)
- normalize() case-insensitive and hyphen/underscore equivalence
- Edge cases: null settings, missing config sections, non-existent model
- README note about api_key stored in plaintext

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* security: address code review — SSRF, credential leak, key collision

- base_url schema now uses z.string().url() for SSRF mitigation
- Strip auth headers (Authorization, x-api-key, api-key) from
  defaultHeaders when providerOverride is active, preventing
  Anthropic credentials from leaking to third-party endpoints
- Warn on duplicate normalized routing keys to prevent silent shadowing
- providerOverride.apiKey is never logged (verified via grep)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: 冯俊辉 <fengjunhui@shiyanjia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-03 21:47:26 +08:00
sooth
5c4469fe81 fix: trim persisted tool results and sanitize MCP schemas 2026-04-02 09:20:40 -04:00
did:key:z6MkqDnb7Siv3Cwj7pGJq4T5EsUisECqR8KpnDLwcaZq5TPr
d2542c9a62 asdf
Squash the current repository state back into one baseline commit while
preserving the README reframing and repository contents.

Constraint: User explicitly requested a single squashed commit with subject "asdf"
Confidence: high
Scope-risk: broad
Reversibility: clean
Directive: This commit intentionally rewrites published history; coordinate before future force-pushes
Tested: git status clean; local history rewritten to one commit; force-pushed main to origin and instructkr
Not-tested: Fresh clone verification after push
2026-03-31 03:34:03 -07:00