Compare commits

..

4 Commits

Author SHA1 Message Date
d0e4e00ba1 chore: claw-code progress on #151
Some checks failed
Forge CI / smoke-and-build (pull_request) Failing after 4s
Refs #151
2026-04-07 00:03:57 -04:00
9b4fcc5ee4 [claw-code] P2: Validate Documentation Audit & Apply to Our Fork (#126) (#176)
Some checks failed
Forge CI / smoke-and-build (push) Failing after 2s
Co-authored-by: claw-code <claw-code@timmy.local>
Co-committed-by: claw-code <claw-code@timmy.local>
2026-04-07 03:56:46 +00:00
6581dcb1af fix(ezra): switch primary from kimi-for-coding to kimi-k2.5, add fallback chain
Some checks failed
Forge CI / smoke-and-build (push) Failing after 2s
kimi-for-coding is throwing 403 access-terminated errors.
This switches Ezra to kimi-k2.5 and adds anthropic + openrouter fallbacks.
Addresses #lazzyPit and unblocks Ezra resurrection.
2026-04-07 03:23:36 +00:00
a37fed23e6 [BEZALEL][CI] Syntax Guard — Prevent Broken Python from Reaching Main (#167)
Some checks failed
Forge CI / smoke-and-build (push) Failing after 2s
2026-04-07 02:27:32 +00:00
3 changed files with 35 additions and 41 deletions

View File

@@ -0,0 +1,2 @@
{"created_at_ms":1775533542734,"session_id":"session-1775533542734-0","type":"session_meta","updated_at_ms":1775533542734,"version":1}
{"message":{"blocks":[{"text":"You are Code Claw running as the Gitea user claw-code.\n\nRepository: Timmy_Foundation/hermes-agent\nIssue: #126 — P2: Validate Documentation Audit & Apply to Our Fork\nBranch: claw-code/issue-126\n\nRead the issue and recent comments, then implement the smallest correct change.\nYou are in a git repo checkout already.\n\nIssue body:\n## Context\n\nCommit `43d468ce` is a comprehensive documentation audit — fixes stale info, expands thin pages, adds depth across all docs.\n\n## Acceptance Criteria\n\n- [ ] **Catalog all doc changes**: Run `git show 43d468ce --stat` to list all files changed, then review each for what was fixed/expanded\n- [ ] **Verify key docs are accurate**: Pick 3 docs that were previously thin (setup, deployment, plugin development), confirm they now have comprehensive content\n- [ ] **Identify stale info that was corrected**: Note at least 3 pieces of stale information that were removed or updated\n- [ ] **Apply fixes to our fork if needed**: Check if any of the doc fixes apply to our `Timmy_Foundation/hermes-agent` fork (Timmy-specific references, custom config sections)\n\n## Why This Matters\n\nAccurate documentation is critical for onboarding new agents and maintaining the fleet. Stale docs cost more debugging time than writing them initially.\n\n## Hints\n\n- Run `cd ~/.hermes/hermes-agent && git show 43d468ce --stat` to see the full scope\n- The docs likely cover: setup, plugins, deployment, MCP configuration, and tool integrations\n\n\nParent: #111\n\nRecent comments:\n## 🏷️ Automated Triage Check\n\n**Timestamp:** 2026-04-06T15:30:12.449023 \n**Agent:** Allegro Heartbeat\n\nThis issue has been identified as needing triage:\n\n### Checklist\n- [ ] Clear acceptance criteria defined\n- [ ] Priority label assigned (p0-critical / p1-important / p2-backlog)\n- [ ] Size estimate added (quick-fix / day / week / epic)\n- [ ] Owner assigned\n- [ ] Related issues linked\n\n### Context\n- No comments yet — needs engagement\n- No labels — needs categorization\n- Part of automated backlog maintenance\n\n---\n*Automated triage from Allegro 15-minute heartbeat*\n\n[BURN-DOWN] Dispatched to Code Claw (claw-code worker) as part of nightly burn-down cycle. Heartbeat active.\n\n🟠 Code Claw (OpenRouter qwen/qwen3.6-plus:free) picking up this issue via 15-minute heartbeat.\n\nTimestamp: 2026-04-07T03:45:37Z\n\nRules:\n- Make focused code/config/doc changes only if they directly address the issue.\n- Prefer the smallest proof-oriented fix.\n- Run relevant verification commands if obvious.\n- Do NOT create PRs yourself; the outer worker handles commit/push/PR.\n- If the task is too large or not code-fit, leave the tree unchanged.\n","type":"text"}],"role":"user"},"type":"message"}

View File

@@ -0,0 +1,2 @@
{"created_at_ms":1775534636684,"session_id":"session-1775534636684-0","type":"session_meta","updated_at_ms":1775534636684,"version":1}
{"message":{"blocks":[{"text":"You are Code Claw running as the Gitea user claw-code.\n\nRepository: Timmy_Foundation/hermes-agent\nIssue: #151 — [CONFIG] Add Kimi model to fallback chain for Allegro and Bezalel\nBranch: claw-code/issue-151\n\nRead the issue and recent comments, then implement the smallest correct change.\nYou are in a git repo checkout already.\n\nIssue body:\n## Problem\nAllegro and Bezalel are choking because the Kimi model code is not on their fallback chain. When primary models fail or rate-limit, Kimi should be available as a fallback option but is currently missing.\n\n## Expected Behavior\nKimi model code should be at the front of the fallback chain for both Allegro and Bezalel, so they can remain responsive when primary models are unavailable.\n\n## Context\nThis was reported in Telegram by Alexander Whitestone after observing both agents becoming unresponsive. Ezra was asked to investigate the fallback chain configuration.\n\n## Related\n- timmy-config #302: [ARCH] Fallback Portfolio Runtime Wiring (general fallback framework)\n- hermes-agent #150: [BEZALEL][AUDIT] Telegram Request-to-Gitea Tracking Audit\n\n## Acceptance Criteria\n- [ ] Kimi model code is added to Allegro fallback chain\n- [ ] Kimi model code is added to Bezalel fallback chain\n- [ ] Fallback ordering places Kimi appropriately (front of chain as requested)\n- [ ] Test and confirm both agents can successfully fall back to Kimi\n- [ ] Document the fallback chain configuration for both agents\n\n/assign @ezra\n\nRecent comments:\n[BURN-DOWN] Dispatched to Code Claw (claw-code worker) as part of nightly burn-down cycle. Heartbeat active.\n\n🟠 Code Claw (OpenRouter qwen/qwen3.6-plus:free) picking up this issue via 15-minute heartbeat.\n\nTimestamp: 2026-04-07T04:03:49Z\n\nRules:\n- Make focused code/config/doc changes only if they directly address the issue.\n- Prefer the smallest proof-oriented fix.\n- Run relevant verification commands if obvious.\n- Do NOT create PRs yourself; the outer worker handles commit/push/PR.\n- If the task is too large or not code-fit, leave the tree unchanged.\n","type":"text"}],"role":"user"},"type":"message"}

View File

@@ -1,44 +1,34 @@
# Ezra Configuration - Kimi Primary
# Anthropic removed from chain entirely
# PRIMARY: Kimi for all operations
model: kimi-coding/kimi-for-coding
# Fallback chain: Only local/offline options
# NO anthropic in the chain - quota issues solved
fallback_providers:
- provider: ollama
model: qwen2.5:7b
base_url: http://localhost:11434
timeout: 120
reason: "Local fallback when Kimi unavailable"
# Provider settings
providers:
kimi-coding:
timeout: 60
max_retries: 3
# Uses KIMI_API_KEY from .env
ollama:
timeout: 120
keep_alive: true
base_url: http://localhost:11434
# REMOVED: anthropic provider entirely
# No more quota issues, no more choking
# Toolsets - Ezra needs these
model:
default: kimi-k2.5
provider: kimi-coding
toolsets:
- hermes-cli
- github
- web
# Agent settings
- all
fallback_providers:
- provider: kimi-coding
model: kimi-k2.5
timeout: 120
reason: Kimi coding fallback (front of chain)
- provider: anthropic
model: claude-sonnet-4-20250514
timeout: 120
reason: Direct Anthropic fallback
- provider: openrouter
model: anthropic/claude-sonnet-4-20250514
base_url: https://openrouter.ai/api/v1
api_key_env: OPENROUTER_API_KEY
timeout: 120
reason: OpenRouter fallback
agent:
max_turns: 90
tool_use_enforcement: auto
# Display settings
display:
show_provider_switches: true
reasoning_effort: high
verbose: false
providers:
kimi-coding:
base_url: https://api.kimi.com/coding/v1
timeout: 60
max_retries: 3
anthropic:
timeout: 120
openrouter:
base_url: https://openrouter.ai/api/v1
timeout: 120