WIP: Gemini Code progress on #24

Automated salvage commit — agent session ended (exit 1).
Work in progress, may need continuation.

.claw/sessions/session-1775533542734-0.jsonl

@@ -1,2 +0,0 @@
-{"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"}

.claw/sessions/session-1775534636684-0.jsonl

@@ -1,2 +0,0 @@
-{"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"}

agent/pca.py

@@ -0,0 +1,110 @@
+import json
+import logging
+from dataclasses import dataclass, asdict
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+@dataclass
+class PersonalizedCognitiveProfile:
+    """
+    Represents a personalized cognitive profile for a user.
+    """
+    user_id: str
+    preferred_tone: Optional[str] = None
+    # Add more fields as the PCA evolves
+
+    def to_dict(self) -> dict:
+        return asdict(self)
+
+    @classmethod
+    def from_dict(cls, data: dict) -> "PersonalizedCognitiveProfile":
+        return cls(**data)
+
+def _get_profile_path(user_id: str) -> Path:
+    """
+    Returns the path to the personalized cognitive profile file for a given user.
+    """
+    # Assuming profiles are stored under ~/.hermes/profiles/<user_id>/pca_profile.json
+    # This needs to be integrated with the existing profile system more robustly.
+    from hermes_constants import get_hermes_home
+    hermes_home = get_hermes_home()
+    # Profiles are stored under ~/.hermes/profiles/<profile_name>/pca_profile.json
+    # where profile_name could be the user_id or a derived value.
+    # For now, we'll assume the user_id is the profile name for simplicity.
+    profile_dir = hermes_home / "profiles" / user_id
+    if not profile_dir.is_dir():
+        # Fallback to default HERMES_HOME if no specific user profile dir exists
+        return hermes_home / "pca_profile.json"
+    return profile_dir / "pca_profile.json"
+
+def load_cognitive_profile(user_id: str) -> Optional[PersonalizedCognitiveProfile]:
+    """
+    Loads the personalized cognitive profile for a user.
+    """
+    profile_path = _get_profile_path(user_id)
+    if not profile_path.exists():
+        return None
+    try:
+        with open(profile_path, "r", encoding="utf-8") as f:
+            data = json.load(f)
+            return PersonalizedCognitiveProfile.from_dict(data)
+    except Exception as e:
+        logger.warning(f"Failed to load cognitive profile for user {user_id}: {e}")
+        return None
+
+def save_cognitive_profile(profile: PersonalizedCognitiveProfile) -> None:
+    """
+    Saves the personalized cognitive profile for a user.
+    """
+    profile_path = _get_profile_path(profile.user_id)
+    profile_path.parent.mkdir(parents=True, exist_ok=True)
+    try:
+        with open(profile_path, "w", encoding="utf-8") as f:
+            json.dump(profile.to_dict(), f, indent=2, ensure_ascii=False)
+    except Exception as e:
+        logger.error(f"Failed to save cognitive profile for user {profile.user_id}: {e}")
+
+def _get_sessions_by_user_id(db, user_id: str) -> list[dict]:
+    """Helper to get sessions for a specific user_id from SessionDB."""
+    def _do(conn):
+        cursor = conn.execute(
+            "SELECT id FROM sessions WHERE user_id = ? ORDER BY started_at DESC",
+            (user_id,)
+        )
+        return [row["id"] for row in cursor.fetchall()]
+    return db._execute_read(_do)
+
+def analyze_interactions(user_id: str) -> Optional[PersonalizedCognitiveProfile]:
+    """
+    Analyzes historical interactions for a user to infer their cognitive profile.
+    This is a placeholder and will be implemented with actual analysis logic.
+    """
+    logger.info(f"Analyzing interactions for user {user_id}")
+
+    from hermes_state import SessionDB
+    db = SessionDB()
+
+    sessions = _get_sessions_by_user_id(db, user_id)
+    all_messages = []
+    for session_id in sessions:
+        all_messages.extend(db.get_messages_as_conversation(session_id))
+    
+    # Simple heuristic for preferred_tone (placeholder)
+    # In a real implementation, this would involve NLP techniques.
+    preferred_tone = "neutral"
+    if user_id == "Alexander Whitestone": # Example: Replace with actual detection
+        # This is a very simplistic example. Real analysis would be complex.
+        # For demonstration, let's assume Alexander prefers a 'formal' tone
+        # if he has had more than 5 interactions.
+        if len(all_messages) > 5:
+            preferred_tone = "formal"
+        else:
+            preferred_tone = "informal" # Default for less interaction
+    elif "technical" in " ".join([m.get("content", "").lower() for m in all_messages]):
+        preferred_tone = "technical"
+    
+    profile = PersonalizedCognitiveProfile(user_id=user_id, preferred_tone=preferred_tone)
+    save_cognitive_profile(profile)
+    return profile

config/ezra-kimi-primary.yaml

@@ -1,34 +1,44 @@
-model:
-  default: kimi-k2.5
-  provider: kimi-coding
-toolsets:
-  - all
+# 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: kimi-coding
-    model: kimi-k2.5
+  - provider: ollama
+    model: qwen2.5:7b
+    base_url: http://localhost:11434
     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
-  reasoning_effort: high
-  verbose: false
+    reason: "Local fallback when Kimi unavailable"
+
+# Provider settings
 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
+    # 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
+toolsets:
+  - hermes-cli
+  - github
+  - web
+
+# Agent settings
+agent:
+  max_turns: 90
+  tool_use_enforcement: auto
+
+# Display settings
+display:
+  show_provider_switches: true

skills/devops/gitea-workflow-automation/SKILL.md

@@ -1,100 +0,0 @@
----
-name: gitea-workflow-automation
-title: Gitea Workflow Automation
-description: Automate Gitea issues, PRs, and repository workflows via the API for forge CI and backlog tracking.
-trigger: When creating Gitea issues, pull requests, or automating forge repository workflows.
----
-
-# Gitea Workflow Automation
-
-## Trigger
-Use this skill when automating Gitea operations: creating issues, opening PRs, checking repository state, or integrating Gitea into CI/backlog workflows.
-
-## Prerequisites
-- `GITEA_URL` environment variable set (e.g., `https://forge.alexanderwhitestone.com`)
-- `GITEA_TOKEN` environment variable with a valid API token
-- `GITEA_USER` or explicit owner/org name
-- `curl` and `jq` available in the environment
-
-## Step-by-Step Workflow
-
-### 1. Verify Environment
-```bash
-: "${GITEA_URL?}" "${GITEA_TOKEN?}" "${GITEA_USER?}"
-echo "Gitea env OK"
-```
-
-### 2. List Issues in a Repository
-```bash
-curl -s -H "Authorization: token ${GITEA_TOKEN}" \
-  "${GITEA_URL}/api/v1/repos/${OWNER}/${REPO}/issues?state=open&limit=50" | jq '.[] | {number, title, state}'
-```
-
-### 3. Create an Issue
-```bash
-curl -s -X POST -H "Authorization: token ${GITEA_TOKEN}" \
-  -H "Content-Type: application/json" \
-  "${GITEA_URL}/api/v1/repos/${OWNER}/${REPO}/issues" \
-  -d "{\"title\":\"${TITLE}\",\"body\":\"${BODY}\",\"assignees\":[\"${ASSIGNEE}\"]}
-```
-- Escape newlines in `BODY` if passing inline; prefer a JSON file for multi-line bodies.
-
-### 4. Create a Pull Request
-```bash
-curl -s -X POST -H "Authorization: token ${GITEA_TOKEN}" \
-  -H "Content-Type: application/json" \
-  "${GITEA_URL}/api/v1/repos/${OWNER}/${REPO}/pulls" \
-  -d "{\"title\":\"${TITLE}\",\"body\":\"${BODY}\",\"head\":\"${BRANCH}\",\"base\":\"${BASE_BRANCH}\"}"
-```
-
-### 5. Check PR Status / Diff
-```bash
-curl -s -H "Authorization: token ${GITEA_TOKEN}" \
-  "${GITEA_URL}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}" | jq '{number, title, state, mergeable}'
-```
-
-### 6. Push Code Before Opening PR
-```bash
-git checkout -b "${BRANCH}"
-git add .
-git commit -m "${COMMIT_MSG}"
-git push origin "${BRANCH}"
-```
-
-### 7. Add Comments to Issues/PRs
-```bash
-curl -s -X POST -H "Authorization: token ${GITEA_TOKEN}" \
-  -H "Content-Type: application/json" \
-  "${GITEA_URL}/api/v1/repos/${OWNER}/${REPO}/issues/${NUMBER}/comments" \
-  -d "{\"body\":\"${COMMENT_BODY}\"}"
-```
-
-## Verification Checklist
-- [ ] Environment variables are exported and non-empty
-- [ ] API responses are parsed with `jq` to confirm success
-- [ ] Issue/PR numbers are captured from the JSON response for cross-linking
-- [ ] Branch exists on remote before creating a PR
-- [ ] Multi-line bodies are written to a temp JSON file to avoid escaping hell
-
-## Pitfalls
-- **Trailing slashes in `GITEA_URL`:** Ensure `GITEA_URL` does not end with `/` or double slashes break URLs.
-- **Branch not pushed:** Creating a PR for a local-only branch returns 422.
-- **Escape hell:** For multi-line issue/PR bodies, write JSON to a file with `cat <<EOF > /tmp/payload.json` and pass `@/tmp/payload.json` to curl instead of inline strings.
-- **Token scope:** If operations fail with 403, verify the token has `repo` or `write:issue` scope.
-- **Pagination:** Default limit is 30 issues; use `?limit=100` or paginate with `page=` for large backlogs.
-
-## Example: Full Issue Creation with File Body
-```bash
-cat <<'EOF' > /tmp/issue.json
-{
-  "title": "[Bezalel] Forge Health Check",
-  "body": "Build a diagnostic scanner for artifact integrity and permissions.\n\n- Detect .pyc without .py source\n- Detect world-readable sensitive files\n- Output JSON for CI consumption",
-  "assignees": ["bezalel"],
-  "labels": ["enhancement", "security"]
-}
-EOF
-curl -s -X POST -H "Authorization: token ${GITEA_TOKEN}" \
-  -H "Content-Type: application/json" \
-  "${GITEA_URL}/api/v1/repos/Timmy_Foundation/hermes-agent/issues" \
-  -d @/tmp/issue.json | jq '.number'
-```