requestDetails
1,000 rows
This data as json, CSV (advanced)
Suggested facets: provider, model, connectionId, status, timestamp (date)
| id ▼ | timestamp | provider | model | connectionId | status | data |
|---|---|---|---|---|---|---|
| 1781010031865-ihui5wwtp | 2026-06-09T13:00:32.217Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010031865-ihui5wwtp","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:00:32.217Z","status":"success","latency":{"ttft":10962,"total":11310},"tokens":{"prompt_tokens":17573,"completion_tokens":310},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- se… |
| 1781010043815-0zexln910 | 2026-06-09T13:00:43.815Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010043815-0zexln910","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:00:43.815Z","status":"success","latency":{"ttft":0,"total":7640},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010043815-134bwyn2n | 2026-06-09T13:00:44.194Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010043815-134bwyn2n","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:00:44.194Z","status":"success","latency":{"ttft":7643,"total":8019},"tokens":{"prompt_tokens":18119,"completion_tokens":257},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sess… |
| 1781010056897-2b6ieg0fs | 2026-06-09T13:01:00.439Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010056897-2b6ieg0fs","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:01:00.439Z","status":"success","latency":{"ttft":7716,"total":11257},"tokens":{"prompt_tokens":21282,"completion_tokens":280,"cached_tokens":15872,"prompt_tokens_details":{"cached_tokens":15872}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-a… |
| 1781010056897-9vm1gz4m6 | 2026-06-09T13:00:56.897Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010056897-9vm1gz4m6","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:00:56.897Z","status":"success","latency":{"ttft":0,"total":7715},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010076817-79e97vxvw | 2026-06-09T13:01:16.817Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010076817-79e97vxvw","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:01:16.817Z","status":"success","latency":{"ttft":0,"total":9217},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010076817-td7ro102y | 2026-06-09T13:01:17.326Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010076817-td7ro102y","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:01:17.326Z","status":"success","latency":{"ttft":9220,"total":9726},"tokens":{"prompt_tokens":26644,"completion_tokens":209,"cached_tokens":18944,"prompt_tokens_details":{"cached_tokens":18944}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781010087726-74rjmv266 | 2026-06-09T13:01:27.726Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010087726-74rjmv266","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:01:27.726Z","status":"success","latency":{"ttft":0,"total":4544},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010087726-hyxy6dzqi | 2026-06-09T13:01:41.152Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010087726-hyxy6dzqi","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:01:41.152Z","status":"success","latency":{"ttft":4547,"total":17969},"tokens":{"prompt_tokens":34157,"completion_tokens":662},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- ses… |
| 1781010923764-9fw8bqi7v | 2026-06-09T13:15:28.636Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010923764-9fw8bqi7v","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:15:28.636Z","status":"success","latency":{"ttft":3772,"total":8639},"tokens":{"prompt_tokens":17647,"completion_tokens":313,"cached_tokens":14848,"prompt_tokens_details":{"cached_tokens":14848}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781010923764-l332r6rky | 2026-06-09T13:15:23.764Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010923764-l332r6rky","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:15:23.764Z","status":"success","latency":{"ttft":0,"total":3767},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010944785-648jiq0tw | 2026-06-09T13:15:44.785Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010944785-648jiq0tw","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:15:44.785Z","status":"success","latency":{"ttft":0,"total":12246},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_stat… |
| 1781010944785-abxedr745 | 2026-06-09T13:15:45.070Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010944785-abxedr745","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:15:45.070Z","status":"success","latency":{"ttft":12248,"total":12531},"tokens":{"prompt_tokens":18196,"completion_tokens":256,"cached_tokens":14848,"prompt_tokens_details":{"cached_tokens":14848}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-… |
| 1781010957058-6hbkpf5ik | 2026-06-09T13:15:57.058Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010957058-6hbkpf5ik","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:15:57.058Z","status":"success","latency":{"ttft":0,"total":7011},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010957058-99ww49i6v | 2026-06-09T13:15:57.239Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010957058-99ww49i6v","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:15:57.239Z","status":"success","latency":{"ttft":7013,"total":7192},"tokens":{"prompt_tokens":20026,"completion_tokens":158,"cached_tokens":15872,"prompt_tokens_details":{"cached_tokens":15872}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781010972897-9hnwcwodw | 2026-06-09T13:16:12.897Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010972897-9hnwcwodw","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:16:12.897Z","status":"success","latency":{"ttft":0,"total":9515},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010972897-v1u4badzs | 2026-06-09T13:16:13.356Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010972897-v1u4badzs","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:16:13.356Z","status":"success","latency":{"ttft":9518,"total":9974},"tokens":{"prompt_tokens":26437,"completion_tokens":149,"cached_tokens":17408,"prompt_tokens_details":{"cached_tokens":17408}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781010986491-0z2iuj2kz | 2026-06-09T13:16:26.491Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010986491-0z2iuj2kz","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:16:26.491Z","status":"success","latency":{"ttft":0,"total":6380},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781010986491-ntzdkwauq | 2026-06-09T13:16:32.230Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781010986491-ntzdkwauq","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-09T13:16:32.230Z","status":"success","latency":{"ttft":6385,"total":12119},"tokens":{"prompt_tokens":27185,"completion_tokens":305,"cached_tokens":15360,"prompt_tokens_details":{"cached_tokens":15360}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-a… |
| 1781096427977-vu8livbs0 | 2026-06-10T13:00:28.118Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096427977-vu8livbs0","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:00:28.118Z","status":"success","latency":{"ttft":7809,"total":7944},"tokens":{"prompt_tokens":20040,"completion_tokens":311},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sess… |
| 1781096427978-e64d38aeh | 2026-06-10T13:00:27.978Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096427978-e64d38aeh","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:00:27.978Z","status":"success","latency":{"ttft":0,"total":7804},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781096441357-kvocymjjh | 2026-06-10T13:00:41.501Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096441357-kvocymjjh","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:00:41.501Z","status":"success","latency":{"ttft":8968,"total":9107},"tokens":{"prompt_tokens":20586,"completion_tokens":258,"cached_tokens":17920,"prompt_tokens_details":{"cached_tokens":17920}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781096441358-9my6ab6ug | 2026-06-10T13:00:41.358Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096441358-9my6ab6ug","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:00:41.358Z","status":"success","latency":{"ttft":0,"total":8965},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781096452521-12hxubqvk | 2026-06-10T13:00:52.662Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096452521-12hxubqvk","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:00:52.662Z","status":"success","latency":{"ttft":5707,"total":5846},"tokens":{"prompt_tokens":21181,"completion_tokens":194},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sess… |
| 1781096452521-naqse9psj | 2026-06-10T13:00:52.521Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096452521-naqse9psj","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:00:52.521Z","status":"success","latency":{"ttft":0,"total":5705},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781096468993-cx5i4eka4 | 2026-06-10T13:01:09.185Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096468993-cx5i4eka4","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:01:09.185Z","status":"success","latency":{"ttft":9551,"total":9740},"tokens":{"prompt_tokens":27646,"completion_tokens":252,"cached_tokens":18944,"prompt_tokens_details":{"cached_tokens":18944}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781096468993-ftlap6wg7 | 2026-06-10T13:01:08.993Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096468993-ftlap6wg7","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:01:08.993Z","status":"success","latency":{"ttft":0,"total":9548},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781096485084-f9p9650z5 | 2026-06-10T13:01:32.025Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096485084-f9p9650z5","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:01:32.025Z","status":"success","latency":{"ttft":9083,"total":16013},"tokens":{"prompt_tokens":35088,"completion_tokens":614,"cached_tokens":25088,"prompt_tokens_details":{"cached_tokens":25088}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-a… |
| 1781096485085-gg5hg4eo7 | 2026-06-10T13:01:25.085Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781096485085-gg5hg4eo7","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:01:25.085Z","status":"success","latency":{"ttft":0,"total":9073},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781097329729-alg3fqg4b | 2026-06-10T13:15:30.538Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097329729-alg3fqg4b","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:15:30.538Z","status":"success","latency":{"ttft":9446,"total":10250},"tokens":{"prompt_tokens":20114,"completion_tokens":335},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- ses… |
| 1781097329730-tqlz4k7g3 | 2026-06-10T13:15:29.730Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097329730-tqlz4k7g3","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:15:29.730Z","status":"success","latency":{"ttft":0,"total":9442},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781097341761-gbtx8ff9n | 2026-06-10T13:15:41.898Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097341761-gbtx8ff9n","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:15:41.898Z","status":"success","latency":{"ttft":7266,"total":7400},"tokens":{"prompt_tokens":20678,"completion_tokens":271,"cached_tokens":17408,"prompt_tokens_details":{"cached_tokens":17408}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781097341761-uidl892xm | 2026-06-10T13:15:41.761Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097341761-uidl892xm","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:15:41.761Z","status":"success","latency":{"ttft":0,"total":7263},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781097353204-52c3w1fvn | 2026-06-10T13:15:53.204Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097353204-52c3w1fvn","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:15:53.204Z","status":"success","latency":{"ttft":0,"total":6181},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781097353204-6dk5nlmux | 2026-06-10T13:15:55.578Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097353204-6dk5nlmux","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:15:55.578Z","status":"success","latency":{"ttft":6184,"total":8555},"tokens":{"prompt_tokens":21680,"completion_tokens":328},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sess… |
| 1781097366811-9nsifs2yj | 2026-06-10T13:16:06.988Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097366811-9nsifs2yj","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:16:06.988Z","status":"success","latency":{"ttft":5654,"total":5827},"tokens":{"prompt_tokens":26255,"completion_tokens":146,"cached_tokens":14848,"prompt_tokens_details":{"cached_tokens":14848}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-ag… |
| 1781097366812-cy1vot7zj | 2026-06-10T13:16:06.812Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097366812-cy1vot7zj","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:16:06.812Z","status":"success","latency":{"ttft":0,"total":5651},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781097379056-60sspihrs | 2026-06-10T13:16:19.056Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097379056-60sspihrs","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:16:19.056Z","status":"success","latency":{"ttft":0,"total":5244},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- session_statu… |
| 1781097379056-fwg48ud79 | 2026-06-10T13:16:24.333Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | gpt-5.5 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781097379056-fwg48ud79","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"gpt-5.5","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-10T13:16:24.333Z","status":"success","latency":{"ttft":5248,"total":10521},"tokens":{"prompt_tokens":36618,"completion_tokens":358,"cached_tokens":18432,"prompt_tokens_details":{"cached_tokens":18432}},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-a… |
| 1781182824120-fc975lnro | 2026-06-11T13:00:25.651Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182824120-fc975lnro","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:25.651Z","status":"success","latency":{"ttft":3623,"total":5150},"tokens":{"prompt_tokens":5673,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781182824121-8wp0hroi2 | 2026-06-11T13:00:24.121Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182824121-8wp0hroi2","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:24.121Z","status":"success","latency":{"ttft":0,"total":3620},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781182833564-1pvc40mvg | 2026-06-11T13:00:34.942Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182833564-1pvc40mvg","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:34.942Z","status":"success","latency":{"ttft":3915,"total":5286},"tokens":{"prompt_tokens":6346,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781182833565-v7jaovdzy | 2026-06-11T13:00:33.565Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182833565-v7jaovdzy","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:33.565Z","status":"success","latency":{"ttft":0,"total":3909},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781182840641-62osuycj8 | 2026-06-11T13:00:41.676Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182840641-62osuycj8","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:41.676Z","status":"success","latency":{"ttft":3456,"total":4488},"tokens":{"prompt_tokens":6744,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781182840642-8qkze3ot7 | 2026-06-11T13:00:40.642Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182840642-8qkze3ot7","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:40.642Z","status":"success","latency":{"ttft":0,"total":3454},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781182848265-bchlthb48 | 2026-06-11T13:00:48.265Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182848265-bchlthb48","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:48.265Z","status":"success","latency":{"ttft":0,"total":4047},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781182848265-yovkao88m | 2026-06-11T13:00:49.795Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182848265-yovkao88m","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:49.795Z","status":"success","latency":{"ttft":4050,"total":5577},"tokens":{"prompt_tokens":7354,"completion_tokens":1},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781182857655-s5dnrrzo4 | 2026-06-11T13:00:58.951Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182857655-s5dnrrzo4","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:58.951Z","status":"success","latency":{"ttft":3790,"total":5084},"tokens":{"prompt_tokens":7782,"completion_tokens":1},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781182857655-srgbm82ie | 2026-06-11T13:00:57.655Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182857655-srgbm82ie","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:00:57.655Z","status":"success","latency":{"ttft":0,"total":3788},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781182864778-vpv39ui0a | 2026-06-11T13:01:05.853Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182864778-vpv39ui0a","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:01:05.853Z","status":"success","latency":{"ttft":3186,"total":4260},"tokens":{"prompt_tokens":8294,"completion_tokens":1},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781182864778-zlkb27cni | 2026-06-11T13:01:04.778Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182864778-zlkb27cni","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:01:04.778Z","status":"success","latency":{"ttft":0,"total":3185},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781182875382-rlfqi5rx4 | 2026-06-11T13:01:37.066Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182875382-rlfqi5rx4","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:01:37.066Z","status":"success","latency":{"ttft":6950,"total":28632},"tokens":{"prompt_tokens":8995,"completion_tokens":9},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n… |
| 1781182875383-d4po2192t | 2026-06-11T13:01:15.383Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781182875383-d4po2192t","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:01:15.383Z","status":"success","latency":{"ttft":0,"total":6949},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781183724896-61bg0064q | 2026-06-11T13:15:26.725Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183724896-61bg0064q","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:15:26.725Z","status":"success","latency":{"ttft":5021,"total":6848},"tokens":{"prompt_tokens":5699,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781183724897-mtu9h3g4a | 2026-06-11T13:15:24.897Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183724897-mtu9h3g4a","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:15:24.897Z","status":"success","latency":{"ttft":0,"total":5020},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781183734155-awp1ro63r | 2026-06-11T13:15:35.693Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183734155-awp1ro63r","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:15:35.693Z","status":"success","latency":{"ttft":3348,"total":4884},"tokens":{"prompt_tokens":6383,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781183734155-iqqrrwo2o | 2026-06-11T13:15:34.155Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183734155-iqqrrwo2o","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:15:34.155Z","status":"success","latency":{"ttft":0,"total":3346},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781183746135-6buwx4cxq | 2026-06-11T13:15:46.136Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183746135-6buwx4cxq","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:15:46.136Z","status":"success","latency":{"ttft":0,"total":6830},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781183746135-x3qv1c34i | 2026-06-11T13:15:46.154Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183746135-x3qv1c34i","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:15:46.154Z","status":"success","latency":{"ttft":6833,"total":6849},"tokens":{"prompt_tokens":7363,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n-… |
| 1781183752058-jepks8x9m | 2026-06-11T13:16:10.446Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183752058-jepks8x9m","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:16:10.446Z","status":"success","latency":{"ttft":3309,"total":21696},"tokens":{"prompt_tokens":8128,"completion_tokens":10},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\… |
| 1781183752058-lx954eq5l | 2026-06-11T13:15:52.058Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781183752058-lx954eq5l","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-11T13:15:52.058Z","status":"success","latency":{"ttft":0,"total":3308},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"You are a personal assistant running inside OpenClaw.\n## Tooling\nAvailable tools are policy-filtered. Names are case-sensitive; call exactly as listed.\n- read: Read file contents\n- write: Create or overwrite files\n- edit: Make precise edits to files\n- exec: Run shell commands (pty available for TTY-required CLIs)\n- process: Manage background exec sessions\n- web_search: Search the web using the configured provider\n- web_fetch: Fetch and extract readable content from a URL\n- browser: Control web browser\n- canvas: Present/eval/snapshot the Canvas\n- nodes: List/describe/notify/camera/screen on paired nodes\n- cron: Manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)\n- message: Send messages and channel actions\n- gateway: Restart, apply config, or run updates on the running OpenClaw process\n- agents_list: List OpenClaw agent ids allowed for sessions_spawn\n- sessions_list: List other sessions (incl. sub-agents) with filters/last\n- sessions_history: Fetch history for another session/sub-agent\n- sessions_send: Send a message to another session/sub-agent\n- sessions_spawn: Spawn an isolated sub-agent session; use context=\"fork\" only when current transcript context is required\n- sessions_yield: End this turn and wait for spawned sub-agent completion events\n- subagents: On-demand list, steer, or kill sub-agent runs for this requester session; do not use for wait loops\n- sessi… |
| 1781237462160-282ci2q6u | 2026-06-12T04:11:02.160Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237462160-282ci2q6u","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:11:02.160Z","status":"success","latency":{"ttft":0,"total":3223},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237462160-68md4hmwg | 2026-06-12T04:11:02.446Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237462160-68md4hmwg","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:11:02.446Z","status":"success","latency":{"ttft":3226,"total":3509},"tokens":{"prompt_tokens":4642,"completion_tokens":5},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781237500421-akot3z7yh | 2026-06-12T04:11:48.286Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237500421-akot3z7yh","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:11:48.286Z","status":"success","latency":{"ttft":4966,"total":12827},"tokens":{"prompt_tokens":4748,"completion_tokens":292},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user… |
| 1781237500422-wdnl1anj2 | 2026-06-12T04:11:40.422Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237500422-wdnl1anj2","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:11:40.422Z","status":"success","latency":{"ttft":0,"total":4963},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237563668-gqjsc1mzx | 2026-06-12T04:12:56.019Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237563668-gqjsc1mzx","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:12:56.019Z","status":"success","latency":{"ttft":2822,"total":15170},"tokens":{"prompt_tokens":4868,"completion_tokens":298},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user… |
| 1781237563669-bjdl4dhow | 2026-06-12T04:12:43.669Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237563669-bjdl4dhow","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:12:43.669Z","status":"success","latency":{"ttft":0,"total":2820},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237646255-cf2h2pw2v | 2026-06-12T04:14:06.255Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237646255-cf2h2pw2v","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:14:06.255Z","status":"success","latency":{"ttft":0,"total":5058},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237646255-w1cx93tei | 2026-06-12T04:14:11.788Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237646255-w1cx93tei","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:14:11.788Z","status":"success","latency":{"ttft":5061,"total":10591},"tokens":{"prompt_tokens":4930,"completion_tokens":153},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user… |
| 1781237707633-lqv9rmeoi | 2026-06-12T04:15:07.929Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237707633-lqv9rmeoi","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:15:07.929Z","status":"success","latency":{"ttft":3652,"total":3944},"tokens":{"prompt_tokens":4950,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781237707634-xialb5067 | 2026-06-12T04:15:07.634Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237707634-xialb5067","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:15:07.634Z","status":"success","latency":{"ttft":0,"total":3649},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237713287-mbfq6toro | 2026-06-12T04:15:20.795Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237713287-mbfq6toro","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:15:20.795Z","status":"success","latency":{"ttft":5024,"total":12529},"tokens":{"prompt_tokens":8014,"completion_tokens":251},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user… |
| 1781237713288-qsd172z41 | 2026-06-12T04:15:13.288Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237713288-qsd172z41","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:15:13.288Z","status":"success","latency":{"ttft":0,"total":5022},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237812138-n5otxj4qc | 2026-06-12T04:16:56.819Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237812138-n5otxj4qc","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:16:56.819Z","status":"success","latency":{"ttft":2962,"total":7641},"tokens":{"prompt_tokens":8067,"completion_tokens":97},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user).… |
| 1781237812138-v9u9ts6va | 2026-06-12T04:16:52.138Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237812138-v9u9ts6va","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:16:52.138Z","status":"success","latency":{"ttft":0,"total":2960},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237823361-0pskdcoz3 | 2026-06-12T04:17:03.361Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237823361-0pskdcoz3","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:17:03.361Z","status":"success","latency":{"ttft":0,"total":3497},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237823361-jxdmt0srk | 2026-06-12T04:17:03.965Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237823361-jxdmt0srk","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:17:03.965Z","status":"success","latency":{"ttft":3500,"total":4101},"tokens":{"prompt_tokens":8092,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781237827850-7s11ocnog | 2026-06-12T04:17:08.707Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237827850-7s11ocnog","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:17:08.707Z","status":"success","latency":{"ttft":3545,"total":4398},"tokens":{"prompt_tokens":8138,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781237827850-84bopi9sw | 2026-06-12T04:17:07.851Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237827850-84bopi9sw","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:17:07.851Z","status":"success","latency":{"ttft":0,"total":3541},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237831954-jnm46rxrc | 2026-06-12T04:17:11.954Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237831954-jnm46rxrc","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:17:11.954Z","status":"success","latency":{"ttft":0,"total":2817},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237831954-k7lyo3i5i | 2026-06-12T04:17:20.214Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237831954-k7lyo3i5i","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:17:20.214Z","status":"success","latency":{"ttft":2820,"total":11077},"tokens":{"prompt_tokens":8247,"completion_tokens":236},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user… |
| 1781237944905-8sobhvnh1 | 2026-06-12T04:19:04.905Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237944905-8sobhvnh1","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:19:04.905Z","status":"success","latency":{"ttft":0,"total":2853},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781237944905-pocpoy67e | 2026-06-12T04:19:05.164Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781237944905-pocpoy67e","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:19:05.164Z","status":"success","latency":{"ttft":2855,"total":3112},"tokens":{"prompt_tokens":4647,"completion_tokens":7},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781238003825-8w71y40rh | 2026-06-12T04:20:04.079Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238003825-8w71y40rh","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:04.079Z","status":"success","latency":{"ttft":3127,"total":3376},"tokens":{"prompt_tokens":4668,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781238003825-ouw3wbr8c | 2026-06-12T04:20:03.825Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238003825-ouw3wbr8c","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:03.825Z","status":"success","latency":{"ttft":0,"total":3122},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238007858-7nma4sgni | 2026-06-12T04:20:07.858Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238007858-7nma4sgni","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:07.858Z","status":"success","latency":{"ttft":0,"total":3299},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238007858-rr4w4g8b8 | 2026-06-12T04:20:08.088Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238007858-rr4w4g8b8","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:08.088Z","status":"success","latency":{"ttft":3302,"total":3529},"tokens":{"prompt_tokens":4829,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781238012008-2a7s63g9f | 2026-06-12T04:20:12.008Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238012008-2a7s63g9f","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:12.008Z","status":"success","latency":{"ttft":0,"total":3562},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238012008-tog9m0j71 | 2026-06-12T04:20:12.469Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238012008-tog9m0j71","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:12.469Z","status":"success","latency":{"ttft":3565,"total":4023},"tokens":{"prompt_tokens":6494,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). … |
| 1781238016272-sq66afsdi | 2026-06-12T04:20:42.329Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238016272-sq66afsdi","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:42.329Z","status":"success","latency":{"ttft":3498,"total":29552},"tokens":{"prompt_tokens":7327,"completion_tokens":811},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user… |
| 1781238016273-j3f6hu2pu | 2026-06-12T04:20:16.273Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238016273-j3f6hu2pu","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:20:16.273Z","status":"success","latency":{"ttft":0,"total":3496},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238592177-6y9e3xuaf | 2026-06-12T04:30:23.932Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238592177-6y9e3xuaf","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:30:23.932Z","status":"success","latency":{"ttft":3100,"total":34850},"tokens":{"prompt_tokens":7689,"completion_tokens":113},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user… |
| 1781238592177-brkgiqwnp | 2026-06-12T04:29:52.177Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238592177-brkgiqwnp","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:29:52.177Z","status":"success","latency":{"ttft":0,"total":3095},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238627885-kxxefh9j5 | 2026-06-12T04:31:22.361Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238627885-kxxefh9j5","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:31:22.361Z","status":"success","latency":{"ttft":3596,"total":58068},"tokens":{"prompt_tokens":8241,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user).… |
| 1781238627886-4eu3562b0 | 2026-06-12T04:30:27.886Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238627886-4eu3562b0","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:30:27.886Z","status":"success","latency":{"ttft":0,"total":3593},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238688246-22aybed6t | 2026-06-12T04:32:22.106Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238688246-22aybed6t","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:32:22.106Z","status":"success","latency":{"ttft":5521,"total":59378},"tokens":{"prompt_tokens":8824,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user).… |
| 1781238688246-xshajg4jd | 2026-06-12T04:31:28.246Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238688246-xshajg4jd","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:31:28.246Z","status":"success","latency":{"ttft":0,"total":5518},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238745608-l6kh0d8sd | 2026-06-12T04:32:25.608Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238745608-l6kh0d8sd","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:32:25.608Z","status":"success","latency":{"ttft":0,"total":3182},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238809893-13r1qhdwc | 2026-06-12T04:33:29.893Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238809893-13r1qhdwc","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:33:29.893Z","status":"success","latency":{"ttft":0,"total":3730},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
| 1781238873600-epva102dl | 2026-06-12T04:34:33.600Z | openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b | claude-opus-4.6 | 48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66 | success | {"id":"1781238873600-epva102dl","provider":"openai-compatible-chat-4171ac94-9183-4a44-9d1c-28870ef7bf2b","model":"claude-opus-4.6","connectionId":"48ca2d8c-2e06-4a5c-859f-8fa4a9c4db66","timestamp":"2026-06-12T04:34:33.600Z","status":"success","latency":{"ttft":0,"total":3059},"tokens":{"prompt_tokens":0,"completion_tokens":0},"request":{"messages":[{"role":"system","content":"# Hermes Agent Persona\n\n<!--\nThis file defines the agent's personality and tone.\nThe agent will embody whatever you write here.\nEdit this to customize how Hermes communicates with you.\n\nExamples:\n - \"You are a warm, playful assistant who uses kaomoji occasionally.\"\n - \"You are a concise technical expert. No fluff, just facts.\"\n - \"You speak like a friendly coworker who happens to know everything.\"\n\nThis file is loaded fresh each message -- no restart needed.\nDelete the contents (or this file) to use the default personality.\n-->\n\nYou run on Hermes Agent (by Nous Research). When the user needs help with Hermes itself — configuring, setting up, using, extending, or troubleshooting it — or when you need to understand your own features, tools, or capabilities, the documentation at https://hermes-agent.nousresearch.com/docs is your authoritative reference and always holds the latest, most up-to-date information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') for additional guidance and proven workflows, but treat the docs as the source of truth when the two differ.\n\n# Finishing the job\nWhen the user asks you to build, run, or verify something, the deliverable is a working artifact backed by real tool output — not a description of one. Do not stop after writing a stub, a plan, or a single command. Keep working until you have actually exercised the code or produced the requested result, then report what real execution returned.\nIf a tool, install, or network call fails and blocks the real path, say so directly and try an alternative (different package manager, different approach, ask the user). NEVER … |
Advanced export
JSON shape: default, array, newline-delimited, object
CREATE TABLE requestDetails (id TEXT PRIMARY KEY, timestamp TEXT NOT NULL, provider TEXT, model TEXT, connectionId TEXT, status TEXT, data TEXT NOT NULL); CREATE INDEX idx_rd_ts ON requestDetails(timestamp DESC); CREATE INDEX idx_rd_provider ON requestDetails(provider); CREATE INDEX idx_rd_model ON requestDetails(model); CREATE INDEX idx_rd_conn ON requestDetails(connectionId);