docs: lessons learned from 2026-07-12 session

- gpu-fleet: Corrected architecture (direct GPU, no router in path). Updated context values (RTX 3090=256K, not 128K). Added api-key standardization requirement. - gpu-self-heal: Added Lessons Learned section with 5 critical findings: L1: API key standardization (RTX 5070 sk-loc...5678 vs not-needed) L2: Fallback chain cascading failure loop detection L3: Verify running state, not documentation L4: Infisical fallback requirement (.env must have uncommented key) L5: Zulip event queue can silently die after ~40 reconnects - litellm-self-heal: Updated status manual-only→deployed, cron schedule - litellm-api-keys: Added Infisical token expiry warning + .env fallback - hermes-config-template: Rule 3 updated with .env fallback requirement
2026-07-12 22:49:39 +00:00
parent 19b6db9891
commit 79d4a73895
14 changed files with 372 additions and 132 deletions
@@ -19,13 +19,53 @@ from datetime import datetime

 LITELLM = "http://192.168.68.116:80"

+def _get_agent_key(agent_name):
+    """Retrieve agent key from Infisical vault."""
+    try:
+        result = subprocess.run(
+            ["infisical", "secrets", "get", "LITELLM_API_KEY",
+             "--project=agents", "--env=production", "--plain"],
+            capture_output=True, text=True, timeout=10
+        )
+        if result.returncode == 0:
+            return result.stdout.strip()
+    except Exception:
+        pass
+
+    # Fallback: try exporting all secrets
+    try:
+        result = subprocess.run(
+            ["infisical", "export", "--project=agents", "--env=production",
+             "--format=dotenv"],
+            capture_output=True, text=True, timeout=10
+        )
+        if result.returncode == 0:
+            for line in result.stdout.splitlines():
+                if line.startswith(f"LITELLM_API_KEY_{agent_name.upper()}") or \
+                   (line.startswith("LITELLM_API_KEY=") and agent_name == os.uname().nodename):
+                    return line.split("=", 1)[1].strip().strip('"').strip("'")
+    except Exception:
+        pass
+
+    return None
+
+# Agent keys are pulled from Infisical vault at runtime.
+# The 'key' field is populated dynamically below.
 AGENTS = {
-    "tanko":   {"ct": 112, "host": "192.168.68.122", "key": "sk-CggiHWlamQyShxWC3Hx6uw", "user": "jerome"},
-    "mumuni":  {"ct": 114, "host": "192.168.68.123", "key": "sk-VrqCNlwUgzoNGOpikJ7nwQ", "user": "root"},
-    "tdunna":  {"ct": 111, "host": None,              "key": "sk-6sbCNjz2T6lTVDBdlNHXsA", "user": None},
-    "baggy":   {"ct": 113, "host": None,              "key": "sk-krnw_zGBwvvL5b7l2t-s-A", "user": None},
+    "tanko":   {"ct": 112, "host": "192.168.68.122", "user": "jerome"},
+    "mumuni":  {"ct": 114, "host": "192.168.68.123", "user": "root"},
+    "koby":    {"ct": 111, "host": None,              "user": None},
+    "koonimo": {"ct": 113, "host": None,              "user": None},
 }

+# Inject keys from vault
+for agent_name in AGENTS:
+    key = _get_agent_key(agent_name)
+    if key:
+        AGENTS[agent_name]["key"] = key
+    else:
+        AGENTS[agent_name]["key"] = None
+
 GPU_HOSTS = {
    "gpu-rtx3090 (.8)":     {"host": "192.168.68.8",   "port": 8080, "service": "llama-server"},
    "gpu-rtx5070 (.110)":   {"host": "192.168.68.110", "port": 8080, "service": "llama-server"},