Include all credentials and runtime config
Remove secret exclusions from .gitignore (local-only repo). Add openclaw runtime state: credentials, identity, devices, hooks, telegram, secrets, agent configs. Exclude noisy/binary data: sessions, sqlite, media, temp files. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"id": "36420c1a-ea13-4194-8143-57c02e289b12",
|
||||
"enqueuedAt": 1773072065232,
|
||||
"channel": "telegram",
|
||||
"to": "heartbeat",
|
||||
"payloads": [
|
||||
{
|
||||
"text": "Quick update: I couldn’t complete the best-practices sync this run.\n\nI was blocked by three things:\n- The target files weren’t present:\n- `skills/llm-tool-best-practices/hints/openai.md`\n- `skills/llm-tool-best-practices/hints/anthropic.md`\n- I couldn’t create the missing `skills/llm-tool-best-practices/hints/` directory/files in this environment.\n- I also couldn’t access web tooling here to verify the latest official OpenAI/Anthropic docs.\n\nSo no edits or commit were made.\n\nIf you want, I can do a follow-up run in a writable environment and create/populate those files.",
|
||||
"mediaUrls": []
|
||||
}
|
||||
],
|
||||
"threadId": null,
|
||||
"replyToId": null,
|
||||
"bestEffort": false,
|
||||
"retryCount": 1,
|
||||
"lastAttemptAt": 1773072065520,
|
||||
"lastError": "Telegram recipient @heartbeat could not be resolved to a numeric chat ID (Call to 'getChat' failed! (400: Bad Request: chat not found))"
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "53913bf6-0633-474c-86a4-3a2b50e88ac7",
|
||||
"enqueuedAt": 1772676377657,
|
||||
"channel": "telegram",
|
||||
"to": "heartbeat",
|
||||
"payloads": [
|
||||
{
|
||||
"text": "Now: P2 security audit has 2 warning(s) (plugin/tool policy allowlists need review).\n\nWatch:\n- ops-sentinel.sh — MONITOR, counts: p1=0 p2=1, artifact: /tmp/openclaw-healthcheck/2026-03-05/020608\n- mcp-smoke.sh — OK, counts: p1=0 p2=0, artifact: /tmp/openclaw-mcp-smoke/2026-03-05/020611\n\nNext actions:\n- Review plugin/tool policy allowlists.\n- Keep current MCP smoke baseline and run periodically."
|
||||
}
|
||||
],
|
||||
"threadId": null,
|
||||
"mirror": {
|
||||
"sessionKey": "agent:main:telegram:direct:heartbeat",
|
||||
"agentId": "main",
|
||||
"text": "Now: P2 security audit has 2 warning(s) (plugin/tool policy allowlists need review).\n\nWatch:\n- ops-sentinel.sh — MONITOR, counts: p1=0 p2=1, artifact: /tmp/openclaw-healthcheck/2026-03-05/020608\n- mcp-smoke.sh — OK, counts: p1=0 p2=0, artifact: /tmp/openclaw-mcp-smoke/2026-03-05/020611\n\nNext actions:\n- Review plugin/tool policy allowlists.\n- Keep current MCP smoke baseline and run periodically."
|
||||
},
|
||||
"retryCount": 1,
|
||||
"lastAttemptAt": 1772676378387,
|
||||
"lastError": "Telegram recipient @heartbeat could not be resolved to a numeric chat ID (Call to 'getChat' failed! (400: Bad Request: chat not found))"
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "8a0c6483-a339-4528-af49-182d594f8727",
|
||||
"enqueuedAt": 1772913441215,
|
||||
"channel": "telegram",
|
||||
"to": "8792219052",
|
||||
"payloads": [
|
||||
{
|
||||
"text": "Daily Infra Report (2026-03-07 11:57 AM PT)\n\nOverall verdict: **MONITOR** — p1: **0**, p2: **1**\n\nService summary:\n- **openclaw:** Gateway health OK\n- **backups:** Fresh (1h old, timestamp 20260307T181701Z)\n- **searxng:** Endpoint OK (HTTP 200)\n- **whisper:** Endpoint OK (HTTP 200)\n- **brave-mcp:** Endpoint responsive (HTTP 406 expected for base probe)\n- **ollama embeddings:** Up; `nomic-embed-text:latest` present\n- **llama.cpp:** Health endpoint responsive (HTTP 200)\n- **minio:** Live endpoint OK (HTTP 200)\n- **host resources:** Disk 40% used, memory 64% used (normal)\n\nActive issues:\n- **P2:** Security audit reports 1 warning.\n- **P3/info:** Local Docker checks did not find `searxng`, `whisper-server`, `brave-search` containers on this host (endpoints are still reachable).\n\nNext actions (max 3):\n1) Review plugin/tool policy allowlists (primary P2 follow-up).\n2) Confirm whether the three Docker services are intentionally hosted on another node.\n3) Keep monitoring resource trend; no immediate capacity action needed."
|
||||
}
|
||||
],
|
||||
"threadId": null,
|
||||
"mirror": {
|
||||
"sessionKey": "agent:main:telegram:direct:8792219052",
|
||||
"agentId": "main",
|
||||
"text": "Daily Infra Report (2026-03-07 11:57 AM PT)\n\nOverall verdict: **MONITOR** — p1: **0**, p2: **1**\n\nService summary:\n- **openclaw:** Gateway health OK\n- **backups:** Fresh (1h old, timestamp 20260307T181701Z)\n- **searxng:** Endpoint OK (HTTP 200)\n- **whisper:** Endpoint OK (HTTP 200)\n- **brave-mcp:** Endpoint responsive (HTTP 406 expected for base probe)\n- **ollama embeddings:** Up; `nomic-embed-text:latest` present\n- **llama.cpp:** Health endpoint responsive (HTTP 200)\n- **minio:** Live endpoint OK (HTTP 200)\n- **host resources:** Disk 40% used, memory 64% used (normal)\n\nActive issues:\n- **P2:** Security audit reports 1 warning.\n- **P3/info:** Local Docker checks did not find `searxng`, `whisper-server`, `brave-search` containers on this host (endpoints are still reachable).\n\nNext actions (max 3):\n1) Review plugin/tool policy allowlists (primary P2 follow-up).\n2) Confirm whether the three Docker services are intentionally hosted on another node.\n3) Keep monitoring resource trend; no immediate capacity action needed."
|
||||
},
|
||||
"retryCount": 5,
|
||||
"lastAttemptAt": 1773012334523,
|
||||
"lastError": "Call to 'sendMessage' failed! (403: Forbidden: bots can't send messages to bots)"
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "97d06aa5-7a46-498b-bbe0-bf1a212d8689",
|
||||
"enqueuedAt": 1772746155943,
|
||||
"channel": "telegram",
|
||||
"to": "heartbeat",
|
||||
"payloads": [
|
||||
{
|
||||
"text": "- Refined both hint files to align with current official guidance on strict schema usage, including explicit nullable-option patterns and required/additionalProperties behavior.\n- Tightened orchestration guidance: multi-call handling, `call_id`/`function_call_output` flow (OpenAI), and `tool_use` / `pause_turn` handling with `tool_result` loops (Anthropic).\n- Updated safety guidance to emphasize server-side argument validation, untrusted tool-output handling, and human confirmation for irreversible actions.\n- Clarified tool-surface design recommendations (small initial tool set, namespacing, deferred loading/tool search, high-signal outputs only).\n- Refreshed and normalized source link sections at the bottom of both files to point to canonical docs.\n\nSources:\n- https://developers.openai.com/api/docs/guides/function-calling\n- https://developers.openai.com/api/docs/guides/structured-outputs\n- https://developers.openai.com/api/docs/guides/tools-tool-search\n- https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview\n- https://platform.claude.com/docs/en/agents-and-tools/tool-use/implement-tool-use\n- https://platform.claude.com/docs/en/build-with-claude/structured-outputs\n- https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons"
|
||||
}
|
||||
],
|
||||
"threadId": null,
|
||||
"mirror": {
|
||||
"sessionKey": "agent:main:telegram:direct:heartbeat",
|
||||
"agentId": "main",
|
||||
"text": "- Refined both hint files to align with current official guidance on strict schema usage, including explicit nullable-option patterns and required/additionalProperties behavior.\n- Tightened orchestration guidance: multi-call handling, `call_id`/`function_call_output` flow (OpenAI), and `tool_use` / `pause_turn` handling with `tool_result` loops (Anthropic).\n- Updated safety guidance to emphasize server-side argument validation, untrusted tool-output handling, and human confirmation for irreversible actions.\n- Clarified tool-surface design recommendations (small initial tool set, namespacing, deferred loading/tool search, high-signal outputs only).\n- Refreshed and normalized source link sections at the bottom of both files to point to canonical docs.\n\nSources:\n- https://developers.openai.com/api/docs/guides/function-calling\n- https://developers.openai.com/api/docs/guides/structured-outputs\n- https://developers.openai.com/api/docs/guides/tools-tool-search\n- https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview\n- https://platform.claude.com/docs/en/agents-and-tools/tool-use/implement-tool-use\n- https://platform.claude.com/docs/en/build-with-claude/structured-outputs\n- https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons"
|
||||
},
|
||||
"retryCount": 1,
|
||||
"lastAttemptAt": 1772746157648,
|
||||
"lastError": "Telegram recipient @heartbeat could not be resolved to a numeric chat ID (Call to 'getChat' failed! (400: Bad Request: chat not found))"
|
||||
}
|
||||
Reference in New Issue
Block a user