hermes - ✅(Solved) Fix [Bug]: api_key drift on provider switch — real Hermes bug [2 pull requests, 2 comments, 2 participants]
ON THIS PAGE
Recommended Tools
×6Utilities matched from this issue’s tags and category — try them while you read without losing context.
GitHub issue graph ai analysis
Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.
The report is written in English Markdown for sharing and archival.
Helpful · Quick feedback
Error Message
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with hermes model.
2026-04-22 05:20:36,354 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 07:59:09,453 INFO slack_bolt.AsyncApp: The old session (s_8691286481021) has been abandoned
2026-04-22 07:59:09,641 INFO slack_bolt.AsyncApp: A new session (s_8691270926317) has been established
2026-04-22 07:59:09,842 INFO slack_bolt.AsyncApp: The old session (s_8691270926317) has been abandoned
2026-04-22 07:59:09,955 INFO slack_bolt.AsyncApp: A new session (s_8691271701105) has been established
2026-04-22 07:59:10,445 INFO slack_bolt.AsyncApp: The old session (s_8691271701105) has been abandoned
2026-04-22 07:59:10,556 INFO slack_bolt.AsyncApp: A new session (s_8691271700633) has been established
2026-04-22 11:30:19,713 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (70 chars)
2026-04-22 11:30:19,715 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='the api key for ollama should be with the other keys in the env file ?'
2026-04-22 11:30:25,540 ERROR gateway.run: Agent error in session agent:main:telegram:dm:5192807992
Traceback (most recent call last):
File "/root/.hermes/hermes-agent/gateway/run.py", line 4409, in _handle_message_with_agent
agent_result = await self._run_agent(
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 10297, in _run_agent
response = _executor_task.result()
^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 8112, in _run_in_executor_with_context
return await loop.run_in_executor(None, ctx.run, func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 9680, in run_sync
agent = AIAgent(
^^^^^^^^
File "/root/.hermes/hermes-agent/run_agent.py", line 1217, in init
raise RuntimeError(
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with hermes model.
2026-04-22 11:30:25,544 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 11:38:16,164 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (98 chars)
2026-04-22 11:38:16,166 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='but you do have the local gemma 4 model via olamma installed on this device loca'
2026-04-22 11:38:21,502 ERROR gateway.run: Agent error in session agent:main:telegram:dm:5192807992
Traceback (most recent call last):
File "/root/.hermes/hermes-agent/gateway/run.py", line 4409, in _handle_message_with_agent
agent_result = await self._run_agent(
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 10297, in _run_agent
response = _executor_task.result()
^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 8112, in _run_in_executor_with_context
return await loop.run_in_executor(None, ctx.run, func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 9680, in run_sync
agent = AIAgent(
^^^^^^^^
File "/root/.hermes/hermes-agent/run_agent.py", line 1217, in init
raise RuntimeError(
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with hermes model.
2026-04-22 11:38:21,506 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 12:10:58,516 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (3 chars)
2026-04-22 12:10:58,517 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hey'
2026-04-22 12:10:59,339 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:10:59,382 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:10:59,399 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:10:59,482 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary flush_memories: using auto (google/gemini-3-flash-preview)
2026-04-22 12:11:02,029 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:11:02,055 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: using auto (minimax-m2.7) at http://localhost:11434/v1/
2026-04-22 12:11:03,393 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: connection error on auto (Connection error.), trying fallback
2026-04-22 12:11:03,451 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: connection error on auto — falling back to openrouter (google/gemini-3-flash-preview)
2026-04-22 12:11:41,897 INFO [20260422_043657_026972d3] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 12:12:03,086 INFO [20260422_043657_026972d3] gateway.run: Session split detected: 20260422_043657_026972d3 → 20260422_121111_9c914d (compression)
2026-04-22 12:12:03,122 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=64.6s api_calls=1 response=518 chars
2026-04-22 12:12:03,158 INFO gateway.platforms.base: [Telegram] Sending response (518 chars) to 5192807992
2026-04-22 12:35:35,933 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (54 chars)
2026-04-22 12:35:35,936 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u running on to generate this response?'
2026-04-22 12:35:37,280 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:35:37,323 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:35:37,339 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:36:07,707 INFO [20260422_121111_9c914d] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 12:36:15,775 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=39.8s api_calls=1 response=203 chars
2026-04-22 12:36:15,809 INFO gateway.platforms.base: [Telegram] Sending response (203 chars) to 5192807992
2026-04-22 12:39:20,019 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:43:28,461 INFO gateway.run: Stopping gateway for restart...
2026-04-22 12:43:29,018 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 12:43:29,034 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 12:43:29,040 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 12:43:29,060 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 12:43:29,061 INFO gateway.run: ✓ telegram disconnected
2026-04-22 12:43:29,123 INFO slack_bolt.AsyncApp: The current session (s_8691271700633) has been abandoned by disconnect() method call
2026-04-22 12:43:29,137 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 12:43:29,137 INFO gateway.run: ✓ slack disconnected
2026-04-22 12:43:29,204 INFO gateway.run: Gateway stopped
2026-04-22 12:43:29,205 INFO gateway.run: Cron ticker stopped
2026-04-22 12:44:03,123 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 12:44:03,123 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 12:44:05,230 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 12:44:05,231 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 12:44:05,275 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 12:44:05,647 INFO gateway.run: Connecting to telegram...
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 12:44:06,444 INFO apscheduler.scheduler: Scheduler started
2026-04-22 12:44:06,444 INFO telegram.ext.Application: Application started
2026-04-22 12:44:08,734 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 12:44:08,735 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 12:44:08,736 INFO gateway.run: ✓ telegram connected
2026-04-22 12:44:08,995 INFO gateway.run: Connecting to slack...
2026-04-22 12:44:09,360 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 12:44:09,363 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 12:44:09,364 INFO gateway.run: ✓ slack connected
2026-04-22 12:44:09,364 INFO gateway.run: 1 hook(s) loaded
2026-04-22 12:44:09,365 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 12:44:09,386 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 12:44:09,387 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 12:44:09,471 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 12:44:09,747 INFO slack_bolt.AsyncApp: A new session (s_8135995012657) has been established
2026-04-22 12:44:09,748 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 12:44:49,951 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:45:39,798 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:53:07,584 INFO slack_bolt.AsyncApp: The old session (s_8135995012657) has been abandoned
2026-04-22 12:53:07,778 INFO slack_bolt.AsyncApp: A new session (s_8135995002745) has been established
2026-04-22 12:53:08,007 INFO slack_bolt.AsyncApp: The old session (s_8135995002745) has been abandoned
2026-04-22 12:53:08,133 INFO slack_bolt.AsyncApp: A new session (s_8135994407801) has been established
2026-04-22 12:53:08,303 INFO slack_bolt.AsyncApp: The old session (s_8135994407801) has been abandoned
2026-04-22 12:53:08,427 INFO slack_bolt.AsyncApp: A new session (s_8135994407217) has been established
2026-04-22 12:55:14,440 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 12:56:14,708 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (54 chars)
2026-04-22 12:56:14,717 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u running on to generate this response?'
2026-04-22 12:56:16,250 INFO agent.model_metadata: Cached context length gemma4:e4b@http://172.17.224.1:11434/v1 -> 131,072 tokens
2026-04-22 12:56:17,005 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 12:56:21,436 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (gemma4:e4b)
2026-04-22 12:56:21,830 INFO agent.model_metadata: Cached context length gemma4:e4b@http://172.17.224.1:11434/v1/ -> 131,072 tokens
2026-04-22 12:57:05,281 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=50.6s api_calls=1 response=47 chars
2026-04-22 12:57:05,335 INFO gateway.platforms.base: [Telegram] Sending response (47 chars) to 5192807992
2026-04-22 12:57:16,568 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (15 chars)
2026-04-22 12:57:16,570 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model name'
2026-04-22 12:57:44,957 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=28.4s api_calls=1 response=135 chars
2026-04-22 12:57:44,996 INFO gateway.platforms.base: [Telegram] Sending response (135 chars) to 5192807992
2026-04-22 12:57:58,474 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (46 chars)
2026-04-22 12:57:58,475 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='yes you do ... does the name gemma ring a bell'
2026-04-22 12:58:57,708 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=59.2s api_calls=2 response=158 chars
2026-04-22 12:58:57,765 INFO gateway.platforms.base: [Telegram] Sending response (158 chars) to 5192807992
2026-04-22 13:01:33,891 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:01:33,892 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='waht model are u using'
2026-04-22 13:01:36,251 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (openrouter/auto)
2026-04-22 13:01:49,715 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=15.8s api_calls=1 response=380 chars
2026-04-22 13:01:49,752 INFO gateway.platforms.base: [Telegram] Sending response (380 chars) to 5192807992
2026-04-22 13:02:16,475 INFO gateway.run: Stopping gateway for restart...
2026-04-22 13:02:19,884 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 13:02:19,885 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 13:02:19,895 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 13:02:19,902 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 13:02:19,902 INFO gateway.run: ✓ telegram disconnected
2026-04-22 13:02:19,944 INFO slack_bolt.AsyncApp: The current session (s_8135994407217) has been abandoned by disconnect() method call
2026-04-22 13:02:19,946 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 13:02:19,946 INFO gateway.run: ✓ slack disconnected
2026-04-22 13:02:19,962 INFO gateway.run: Gateway stopped
2026-04-22 13:02:19,962 INFO gateway.run: Cron ticker stopped
2026-04-22 13:02:51,459 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 13:02:51,459 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 13:02:53,473 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 13:02:53,473 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 13:02:53,521 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 13:02:53,919 INFO gateway.run: Connecting to telegram...
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 13:02:54,776 INFO apscheduler.scheduler: Scheduler started
2026-04-22 13:02:54,776 INFO telegram.ext.Application: Application started
2026-04-22 13:02:56,029 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 13:02:56,030 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 13:02:56,031 INFO gateway.run: ✓ telegram connected
2026-04-22 13:02:56,327 INFO gateway.run: Connecting to slack...
2026-04-22 13:02:56,670 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 13:02:56,672 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 13:02:56,673 INFO gateway.run: ✓ slack connected
2026-04-22 13:02:56,674 INFO gateway.run: 1 hook(s) loaded
2026-04-22 13:02:56,674 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 13:02:56,691 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 13:02:56,691 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 13:02:56,814 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 13:02:57,050 INFO slack_bolt.AsyncApp: A new session (s_8398139429125) has been established
2026-04-22 13:02:57,051 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 13:02:57,225 INFO slack_bolt.AsyncApp: The old session (s_8398139429125) has been abandoned
2026-04-22 13:02:57,353 INFO slack_bolt.AsyncApp: A new session (s_8398139510873) has been established
2026-04-22 13:02:57,537 INFO slack_bolt.AsyncApp: The old session (s_8398139510873) has been abandoned
2026-04-22 13:02:57,660 INFO slack_bolt.AsyncApp: A new session (s_8398135806557) has been established
2026-04-22 13:02:57,834 INFO slack_bolt.AsyncApp: The old session (s_8398135806557) has been abandoned
2026-04-22 13:02:57,957 INFO slack_bolt.AsyncApp: A new session (s_8398135196233) has been established
2026-04-22 13:02:58,128 INFO slack_bolt.AsyncApp: The old session (s_8398135196233) has been abandoned
2026-04-22 13:02:58,249 INFO slack_bolt.AsyncApp: A new session (s_8398135196529) has been established
2026-04-22 13:03:46,010 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:03:46,011 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='waht model are u using'
2026-04-22 13:03:47,637 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 13:03:49,901 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (openrouter/auto)
2026-04-22 13:03:59,633 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=13.6s api_calls=1 response=316 chars
2026-04-22 13:03:59,675 INFO gateway.platforms.base: [Telegram] Sending response (316 chars) to 5192807992
2026-04-22 13:04:13,254 WARNING gateway.run: Unrecognized slash command /models from telegram — replying with unknown-command notice
2026-04-22 13:04:13,255 INFO gateway.platforms.base: [Telegram] Sending response (132 chars) to 5192807992
2026-04-22 13:15:26,048 INFO hermes_cli.web_server: env/reveal: OPENROUTER_API_KEY
2026-04-22 13:15:45,569 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 13:16:10,564 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 13:17:42,533 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:17:42,535 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u using'
2026-04-22 13:17:43,446 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: marking OPENROUTER_API_KEY exhausted (status=401), rotating
2026-04-22 13:17:43,470 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:43,502 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:43,502 WARNING [20260422_121111_9c914d] agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:17:43,503 WARNING [20260422_121111_9c914d] root: Fallback to openrouter failed: provider not configured
2026-04-22 13:17:43,508 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:17:43,573 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=1.0s api_calls=1 response=75 chars
2026-04-22 13:17:43,597 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:17:43,608 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:17:52,835 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (1 chars)
2026-04-22 13:17:52,835 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='h'
2026-04-22 13:17:52,976 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,142 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,455 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,462 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:17:53,533 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=0.7s api_calls=1 response=75 chars
2026-04-22 13:17:53,558 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:17:53,572 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:19:45,170 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 13:19:45,172 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 13:19:45,425 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:45,645 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:46,099 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:46,105 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:19:46,170 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=1.0s api_calls=1 response=75 chars
2026-04-22 13:19:46,201 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:19:46,211 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:19:49,824 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 13:19:49,825 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 13:19:49,967 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,127 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,435 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,441 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:19:50,518 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=0.7s api_calls=1 response=75 chars
2026-04-22 13:19:50,546 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:19:50,556 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:21:51,623 INFO hermes_cli.web_server: env/reveal: OPENROUTER_API_KEY
2026-04-22 13:28:33,001 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (3 chars)
2026-04-22 13:28:33,002 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hey'
2026-04-22 13:28:33,141 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,317 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,705 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,705 WARNING [20260422_121111_9c914d] agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:28:33,734 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,916 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using openai-codex (gpt-5.2-codex) — skipped: openrouter, nous, local/custom
2026-04-22 13:28:43,806 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=10.8s api_calls=1 response=271 chars
2026-04-22 13:28:43,841 INFO gateway.platforms.base: [Telegram] Sending response (271 chars) to 5192807992
2026-04-22 13:28:57,989 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (19 chars)
2026-04-22 13:28:57,990 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u on now'
2026-04-22 13:28:58,124 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:58,287 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:29:09,017 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=11.0s api_calls=1 response=287 chars
2026-04-22 13:29:09,052 INFO gateway.platforms.base: [Telegram] Sending response (287 chars) to 5192807992
2026-04-22 13:29:30,917 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (39 chars)
2026-04-22 13:29:30,917 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='youre supposed to be on openrouter/auto'
2026-04-22 13:29:31,059 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:29:31,216 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:30:20,503 INFO gateway.platforms.telegram: Telegram button resolved 1 approval(s) for session agent:main:telegram:dm:5192807992 (choice=always, user=DocA)
2026-04-22 13:30:38,843 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=67.9s api_calls=4 response=953 chars
2026-04-22 13:30:38,891 INFO gateway.platforms.base: [Telegram] Sending response (953 chars) to 5192807992
2026-04-22 13:31:25,508 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (48 chars)
2026-04-22 13:31:25,509 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg="what file is the 'default model' settings in ..?"
2026-04-22 13:31:25,650 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:31:25,934 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:31:35,725 WARNING gateway.platforms.telegram_network: [Telegram] Primary api.telegram.org connection failed (); trying fallback IPs 149.154.167.220
2026-04-22 13:31:36,381 WARNING gateway.platforms.telegram_network: [Telegram] Primary api.telegram.org path unreachable; using sticky fallback IP 149.154.167.220
2026-04-22 13:31:53,362 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=27.9s api_calls=1 response=1259 chars
2026-04-22 13:31:53,398 INFO gateway.platforms.base: [Telegram] Sending response (1259 chars) to 5192807992
2026-04-22 13:32:21,546 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (85 chars)
2026-04-22 13:32:21,547 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='why are you using openclaw gateway config file when you are hermes and have your'
2026-04-22 13:32:21,691 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:32:21,851 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:32:46,831 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=25.3s api_calls=1 response=1672 chars
2026-04-22 13:32:46,864 INFO gateway.platforms.base: [Telegram] Sending response (1672 chars) to 5192807992
2026-04-22 13:34:08,776 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (150 chars)
2026-04-22 13:34:08,777 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='but im lookin at the config.yaml in root/.hermes and default models and fall b'
2026-04-22 13:34:08,909 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:09,063 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:11,550 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (16 chars)
2026-04-22 13:34:12,516 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:39,616 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=30.8s api_calls=2 response=1262 chars
2026-04-22 13:34:39,650 INFO gateway.platforms.base: [Telegram] Sending response (1262 chars) to 5192807992
2026-04-22 13:36:05,585 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (153 chars)
2026-04-22 13:36:05,586 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='find out what seeting and wwhat file is causing hermes to try to use openclaws c'
2026-04-22 13:36:05,735 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:36:05,895 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:37:50,669 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=105.1s api_calls=9 response=2995 chars
2026-04-22 13:37:50,758 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:37:50,758 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:37:50,770 INFO gateway.platforms.base: [Telegram] Sending response (2995 chars) to 5192807992
2026-04-22 13:39:56,734 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (139 chars)
2026-04-22 13:39:56,735 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what i want to know is why The actual runtime routing in this environment is gov'
2026-04-22 13:39:56,883 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:39:57,036 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:40:22,682 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=25.9s api_calls=1 response=3701 chars
2026-04-22 13:40:22,714 INFO gateway.platforms.base: [Telegram] Sending response (3701 chars) to 5192807992
2026-04-22 13:49:39,191 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (23 chars)
2026-04-22 13:49:39,193 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u using now?'
2026-04-22 13:49:39,476 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:39,642 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:47,341 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=8.1s api_calls=1 response=524 chars
2026-04-22 13:49:47,410 INFO gateway.platforms.base: [Telegram] Sending response (524 chars) to 5192807992
2026-04-22 13:49:47,421 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:47,422 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 14:00:59,033 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,168 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,168 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 14:01:05,196 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,402 INFO agent.auxiliary_client: Auxiliary auto-detect: using openai-codex (gpt-5.2-codex) — skipped: openrouter, nous, local/custom
2026-04-22 14:26:26,982 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (18 chars)
2026-04-22 14:26:26,984 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model you on?'
2026-04-22 14:26:37,029 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=10.0s api_calls=1 response=200 chars
2026-04-22 14:26:37,088 INFO gateway.platforms.base: [Telegram] Sending response (200 chars) to 5192807992
2026-04-22 14:26:41,079 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (29 chars)
2026-04-22 14:26:41,080 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='i dont believe that accurate.'
2026-04-22 14:27:41,358 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=60.3s api_calls=4 response=1910 chars
2026-04-22 14:27:41,457 INFO gateway.platforms.base: [Telegram] Sending response (1910 chars) to 5192807992
2026-04-22 14:53:23,489 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 14:53:26,349 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 14:53:55,467 INFO gateway.run: Stopping gateway for restart...
2026-04-22 14:53:55,997 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 14:53:56,001 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 14:53:56,012 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 14:53:56,022 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 14:53:56,022 INFO gateway.run: ✓ telegram disconnected
2026-04-22 14:53:56,060 INFO slack_bolt.AsyncApp: The current session (s_8398135196529) has been abandoned by disconnect() method call
2026-04-22 14:53:56,064 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 14:53:56,065 INFO gateway.run: ✓ slack disconnected
2026-04-22 14:53:56,080 INFO gateway.run: Gateway stopped
2026-04-22 14:53:56,080 INFO gateway.run: Cron ticker stopped
2026-04-22 14:54:30,726 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 14:54:30,726 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 14:54:32,952 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 14:54:32,952 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 14:54:32,993 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 14:54:33,330 INFO gateway.run: Connecting to telegram...
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 14:54:34,127 INFO apscheduler.scheduler: Scheduler started
2026-04-22 14:54:34,127 INFO telegram.ext.Application: Application started
2026-04-22 14:54:36,509 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 14:54:36,510 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 14:54:36,511 INFO gateway.run: ✓ telegram connected
2026-04-22 14:54:36,754 INFO gateway.run: Connecting to slack...
2026-04-22 14:54:37,142 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 14:54:37,145 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 14:54:37,146 INFO gateway.run: ✓ slack connected
2026-04-22 14:54:37,147 INFO gateway.run: 1 hook(s) loaded
2026-04-22 14:54:37,148 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 14:54:37,170 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 14:54:37,171 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 14:54:37,254 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 14:54:37,587 INFO slack_bolt.AsyncApp: A new session (s_8773147605217) has been established
2026-04-22 14:54:37,588 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 14:56:31,142 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 14:56:31,144 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model you on now?'
2026-04-22 14:56:32,646 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 14:56:36,396 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 14:56:37,543 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 14:56:52,194 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=21.0s api_calls=1 response=915 chars
2026-04-22 14:56:52,231 INFO gateway.platforms.base: [Telegram] Sending response (915 chars) to 5192807992
2026-04-22 14:57:11,059 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (6 chars)
2026-04-22 14:57:11,060 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='wrong.'
2026-04-22 14:57:11,576 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 14:57:12,004 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 14:58:08,933 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=57.9s api_calls=3 response=2496 chars
2026-04-22 14:58:08,973 INFO gateway.platforms.base: [Telegram] Sending response (2496 chars) to 5192807992
2026-04-22 15:08:54,457 INFO gateway.run: Stopping gateway for restart...
2026-04-22 15:08:55,018 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 15:08:55,019 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 15:08:55,029 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 15:08:55,033 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 15:08:55,033 INFO gateway.run: ✓ telegram disconnected
2026-04-22 15:08:55,070 INFO slack_bolt.AsyncApp: The current session (s_8773147605217) has been abandoned by disconnect() method call
2026-04-22 15:08:55,071 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 15:08:55,071 INFO gateway.run: ✓ slack disconnected
2026-04-22 15:08:55,075 INFO gateway.run: Gateway stopped
2026-04-22 15:08:55,076 INFO gateway.run: Cron ticker stopped
2026-04-22 15:09:27,183 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 15:09:27,183 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 15:09:29,281 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 15:09:29,281 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 15:09:29,338 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 15:09:29,666 INFO gateway.run: Connecting to telegram...
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 15:09:30,446 INFO apscheduler.scheduler: Scheduler started
2026-04-22 15:09:30,447 INFO telegram.ext.Application: Application started
2026-04-22 15:09:32,918 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 15:09:32,919 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 15:09:32,919 INFO gateway.run: ✓ telegram connected
2026-04-22 15:09:33,152 INFO gateway.run: Connecting to slack...
2026-04-22 15:09:33,503 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 15:09:33,504 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 15:09:33,505 INFO gateway.run: ✓ slack connected
2026-04-22 15:09:33,506 INFO gateway.run: 1 hook(s) loaded
2026-04-22 15:09:33,506 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 15:09:33,522 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 15:09:33,522 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 15:09:33,593 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 15:09:33,875 INFO slack_bolt.AsyncApp: A new session (s_7829486155165) has been established
2026-04-22 15:09:33,875 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 15:13:06,715 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:13:06,717 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:13:08,303 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 15:13:11,748 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:13:12,750 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:13:29,367 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=22.7s api_calls=1 response=878 chars
2026-04-22 15:13:29,408 INFO gateway.platforms.base: [Telegram] Sending response (878 chars) to 5192807992
2026-04-22 15:17:15,365 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (23 chars)
2026-04-22 15:17:15,367 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u running?hi'
2026-04-22 15:17:15,901 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:17:16,328 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:17:24,323 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.0s api_calls=1 response=738 chars
2026-04-22 15:17:24,359 INFO gateway.platforms.base: [Telegram] Sending response (738 chars) to 5192807992
2026-04-22 15:19:06,278 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:06,278 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:19:06,783 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:07,198 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:14,363 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:15,716 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:16,134 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:19,992 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:20,800 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:21,240 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:30,490 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=24.2s api_calls=1 response=777 chars
2026-04-22 15:19:30,526 INFO gateway.platforms.base: [Telegram] Sending response (777 chars) to 5192807992
2026-04-22 15:21:36,750 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:21:36,752 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:21:37,453 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 15:21:37,876 INFO [20260422_121111_9c914d] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 15:21:46,540 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.8s api_calls=1 response=680 chars
2026-04-22 15:21:46,616 INFO gateway.platforms.base: [Telegram] Sending response (680 chars) to 5192807992
2026-04-22 15:23:50,124 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:23:50,125 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:23:50,790 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (xiaomi/mimo-v2-pro)
2026-04-22 15:24:02,666 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=12.5s api_calls=1 response=498 chars
2026-04-22 15:24:02,711 INFO gateway.platforms.base: [Telegram] Sending response (498 chars) to 5192807992
2026-04-22 15:24:15,505 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (15 chars)
2026-04-22 15:24:15,505 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u on'
2026-04-22 15:24:25,097 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.6s api_calls=1 response=502 chars
2026-04-22 15:24:25,133 INFO gateway.platforms.base: [Telegram] Sending response (502 chars) to 5192807992
Root Cause
Root Cause Analysis (optional)
PR fix notes
PR #14370: fix: clear stale api_key on provider switch
- Repository: NousResearch/hermes-agent
- Author: aj-nt
- State: open | merged: False
- Link: https://github.com/NousResearch/hermes-agent/pull/14370
Description (problem / solution / changelog)
Summary
Fixes #14134 — stale api_key persists in model config when switching between built-in providers, causing credential drift (401 errors).
Red team revealed the bug was broader than the initial report: 10 built-in provider flows had the same issue, not just _model_flow_api_key_provider.
Root Cause
Each _model_flow_* function manually implemented the same boilerplate:
cfg = load_config()model = cfg.get("model")+ normalize to dict- Set
model["provider"],model["base_url"],model["api_mode"] - Missing:
model.pop("api_key", None)← the bug save_config(cfg)
Built-in providers get their keys from env vars / credential pool. A leftover model.api_key from a prior provider causes the new provider to use the wrong key.
Fix
Extract _set_builtin_provider_config() helper that:
- Normalizes model dict (bare string → dict)
- Sets provider / base_url / api_mode (or clears when empty)
- Always pops stale
api_key - Returns the model dict for further modification (e.g., bedrock region)
All 9 built-in flows now route through this helper:
_model_flow_openrouter_model_flow_ai_gateway_model_flow_nous(inline pop — uses_update_config_for_providerfirst)_model_flow_copilot_model_flow_copilot_acp_model_flow_kimi_model_flow_stepfun_model_flow_bedrock+_model_flow_bedrock_api_key_model_flow_anthropic_model_flow_api_key_provider
Custom provider flows (_model_flow_custom, _model_flow_named_custom) intentionally keep their api_key writes and are NOT affected.
Tests
- 8 direct unit tests for
_set_builtin_provider_config - 4 integration tests for
_model_flow_api_key_provider(the original reported flow) - All 2567 existing tests green (3 pre-existing failures unrelated to this change)
Pattern
Mirrors auth.py set_provider_in_config (~line 2764) which already correctly pops both api_key and api_mode.
Changed files
hermes_cli/main.py(modified, +72/-77)tests/hermes_cli/test_api_key_drift_provider_switch.py(added, +309/-0)
PR #14373: fix: clear stale api keys when switching API-key providers
- Repository: NousResearch/hermes-agent
- Author: LeonSGP43
- State: open | merged: False
- Link: https://github.com/NousResearch/hermes-agent/pull/14373
Description (problem / solution / changelog)
Summary
- clear stale inline
model.api_keyvalues when switching API-key providers inhermes model - keep provider/base URL updates while removing leftover credentials from the previous provider
- add a regression test covering a switch from OpenRouter to a generic API-key provider
Testing
- python3 -m pytest -o addopts= tests/hermes_cli/test_model_provider_persistence.py
Closes #14134.
Changed files
hermes_cli/main.py(modified, +1/-0)tests/hermes_cli/test_model_provider_persistence.py(modified, +32/-0)
Code Example
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with `hermes model`.
2026-04-22 05:20:36,354 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 07:59:09,453 INFO slack_bolt.AsyncApp: The old session (s_8691286481021) has been abandoned
2026-04-22 07:59:09,641 INFO slack_bolt.AsyncApp: A new session (s_8691270926317) has been established
2026-04-22 07:59:09,842 INFO slack_bolt.AsyncApp: The old session (s_8691270926317) has been abandoned
2026-04-22 07:59:09,955 INFO slack_bolt.AsyncApp: A new session (s_8691271701105) has been established
2026-04-22 07:59:10,445 INFO slack_bolt.AsyncApp: The old session (s_8691271701105) has been abandoned
2026-04-22 07:59:10,556 INFO slack_bolt.AsyncApp: A new session (s_8691271700633) has been established
2026-04-22 11:30:19,713 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (70 chars)
2026-04-22 11:30:19,715 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='the api key for ollama should be with the other keys in the env file ?'
2026-04-22 11:30:25,540 ERROR gateway.run: Agent error in session agent:main:telegram:dm:5192807992
Traceback (most recent call last):
File "/root/.hermes/hermes-agent/gateway/run.py", line 4409, in _handle_message_with_agent
agent_result = await self._run_agent(
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 10297, in _run_agent
response = _executor_task.result()
^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 8112, in _run_in_executor_with_context
return await loop.run_in_executor(None, ctx.run, func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 9680, in run_sync
agent = AIAgent(
^^^^^^^^
File "/root/.hermes/hermes-agent/run_agent.py", line 1217, in __init__
raise RuntimeError(
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with `hermes model`.
2026-04-22 11:30:25,544 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 11:38:16,164 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (98 chars)
2026-04-22 11:38:16,166 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='but you do have the local gemma 4 model via olamma installed on this device loca'
2026-04-22 11:38:21,502 ERROR gateway.run: Agent error in session agent:main:telegram:dm:5192807992
Traceback (most recent call last):
File "/root/.hermes/hermes-agent/gateway/run.py", line 4409, in _handle_message_with_agent
agent_result = await self._run_agent(
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 10297, in _run_agent
response = _executor_task.result()
^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 8112, in _run_in_executor_with_context
return await loop.run_in_executor(None, ctx.run, func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 9680, in run_sync
agent = AIAgent(
^^^^^^^^
File "/root/.hermes/hermes-agent/run_agent.py", line 1217, in __init__
raise RuntimeError(
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with `hermes model`.
2026-04-22 11:38:21,506 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 12:10:58,516 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (3 chars)
2026-04-22 12:10:58,517 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hey'
2026-04-22 12:10:59,339 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:10:59,382 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:10:59,399 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:10:59,482 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary flush_memories: using auto (google/gemini-3-flash-preview)
2026-04-22 12:11:02,029 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:11:02,055 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: using auto (minimax-m2.7) at http://localhost:11434/v1/
2026-04-22 12:11:03,393 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: connection error on auto (Connection error.), trying fallback
2026-04-22 12:11:03,451 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: connection error on auto — falling back to openrouter (google/gemini-3-flash-preview)
2026-04-22 12:11:41,897 INFO [20260422_043657_026972d3] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 12:12:03,086 INFO [20260422_043657_026972d3] gateway.run: Session split detected: 20260422_043657_026972d3 → 20260422_121111_9c914d (compression)
2026-04-22 12:12:03,122 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=64.6s api_calls=1 response=518 chars
2026-04-22 12:12:03,158 INFO gateway.platforms.base: [Telegram] Sending response (518 chars) to 5192807992
2026-04-22 12:35:35,933 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (54 chars)
2026-04-22 12:35:35,936 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u running on to generate this response?'
2026-04-22 12:35:37,280 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:35:37,323 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:35:37,339 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:36:07,707 INFO [20260422_121111_9c914d] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 12:36:15,775 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=39.8s api_calls=1 response=203 chars
2026-04-22 12:36:15,809 INFO gateway.platforms.base: [Telegram] Sending response (203 chars) to 5192807992
2026-04-22 12:39:20,019 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:43:28,461 INFO gateway.run: Stopping gateway for restart...
2026-04-22 12:43:29,018 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 12:43:29,034 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 12:43:29,040 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 12:43:29,060 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 12:43:29,061 INFO gateway.run: ✓ telegram disconnected
2026-04-22 12:43:29,123 INFO slack_bolt.AsyncApp: The current session (s_8691271700633) has been abandoned by disconnect() method call
2026-04-22 12:43:29,137 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 12:43:29,137 INFO gateway.run: ✓ slack disconnected
2026-04-22 12:43:29,204 INFO gateway.run: Gateway stopped
2026-04-22 12:43:29,205 INFO gateway.run: Cron ticker stopped
2026-04-22 12:44:03,123 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 12:44:03,123 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 12:44:05,230 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 12:44:05,231 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 12:44:05,275 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 12:44:05,647 INFO gateway.run: Connecting to telegram...
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 12:44:06,444 INFO apscheduler.scheduler: Scheduler started
2026-04-22 12:44:06,444 INFO telegram.ext.Application: Application started
2026-04-22 12:44:08,734 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 12:44:08,735 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 12:44:08,736 INFO gateway.run: ✓ telegram connected
2026-04-22 12:44:08,995 INFO gateway.run: Connecting to slack...
2026-04-22 12:44:09,360 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 12:44:09,363 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 12:44:09,364 INFO gateway.run: ✓ slack connected
2026-04-22 12:44:09,364 INFO gateway.run: 1 hook(s) loaded
2026-04-22 12:44:09,365 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 12:44:09,386 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 12:44:09,387 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 12:44:09,471 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 12:44:09,747 INFO slack_bolt.AsyncApp: A new session (s_8135995012657) has been established
2026-04-22 12:44:09,748 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 12:44:49,951 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:45:39,798 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:53:07,584 INFO slack_bolt.AsyncApp: The old session (s_8135995012657) has been abandoned
2026-04-22 12:53:07,778 INFO slack_bolt.AsyncApp: A new session (s_8135995002745) has been established
2026-04-22 12:53:08,007 INFO slack_bolt.AsyncApp: The old session (s_8135995002745) has been abandoned
2026-04-22 12:53:08,133 INFO slack_bolt.AsyncApp: A new session (s_8135994407801) has been established
2026-04-22 12:53:08,303 INFO slack_bolt.AsyncApp: The old session (s_8135994407801) has been abandoned
2026-04-22 12:53:08,427 INFO slack_bolt.AsyncApp: A new session (s_8135994407217) has been established
2026-04-22 12:55:14,440 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 12:56:14,708 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (54 chars)
2026-04-22 12:56:14,717 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u running on to generate this response?'
2026-04-22 12:56:16,250 INFO agent.model_metadata: Cached context length gemma4:e4b@http://172.17.224.1:11434/v1 -> 131,072 tokens
2026-04-22 12:56:17,005 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 12:56:21,436 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (gemma4:e4b)
2026-04-22 12:56:21,830 INFO agent.model_metadata: Cached context length gemma4:e4b@http://172.17.224.1:11434/v1/ -> 131,072 tokens
2026-04-22 12:57:05,281 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=50.6s api_calls=1 response=47 chars
2026-04-22 12:57:05,335 INFO gateway.platforms.base: [Telegram] Sending response (47 chars) to 5192807992
2026-04-22 12:57:16,568 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (15 chars)
2026-04-22 12:57:16,570 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model name'
2026-04-22 12:57:44,957 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=28.4s api_calls=1 response=135 chars
2026-04-22 12:57:44,996 INFO gateway.platforms.base: [Telegram] Sending response (135 chars) to 5192807992
2026-04-22 12:57:58,474 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (46 chars)
2026-04-22 12:57:58,475 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='yes you do ... does the name gemma ring a bell'
2026-04-22 12:58:57,708 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=59.2s api_calls=2 response=158 chars
2026-04-22 12:58:57,765 INFO gateway.platforms.base: [Telegram] Sending response (158 chars) to 5192807992
2026-04-22 13:01:33,891 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:01:33,892 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='waht model are u using'
2026-04-22 13:01:36,251 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (openrouter/auto)
2026-04-22 13:01:49,715 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=15.8s api_calls=1 response=380 chars
2026-04-22 13:01:49,752 INFO gateway.platforms.base: [Telegram] Sending response (380 chars) to 5192807992
2026-04-22 13:02:16,475 INFO gateway.run: Stopping gateway for restart...
2026-04-22 13:02:19,884 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 13:02:19,885 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 13:02:19,895 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 13:02:19,902 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 13:02:19,902 INFO gateway.run: ✓ telegram disconnected
2026-04-22 13:02:19,944 INFO slack_bolt.AsyncApp: The current session (s_8135994407217) has been abandoned by disconnect() method call
2026-04-22 13:02:19,946 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 13:02:19,946 INFO gateway.run: ✓ slack disconnected
2026-04-22 13:02:19,962 INFO gateway.run: Gateway stopped
2026-04-22 13:02:19,962 INFO gateway.run: Cron ticker stopped
2026-04-22 13:02:51,459 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 13:02:51,459 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 13:02:53,473 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 13:02:53,473 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 13:02:53,521 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 13:02:53,919 INFO gateway.run: Connecting to telegram...
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 13:02:54,776 INFO apscheduler.scheduler: Scheduler started
2026-04-22 13:02:54,776 INFO telegram.ext.Application: Application started
2026-04-22 13:02:56,029 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 13:02:56,030 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 13:02:56,031 INFO gateway.run: ✓ telegram connected
2026-04-22 13:02:56,327 INFO gateway.run: Connecting to slack...
2026-04-22 13:02:56,670 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 13:02:56,672 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 13:02:56,673 INFO gateway.run: ✓ slack connected
2026-04-22 13:02:56,674 INFO gateway.run: 1 hook(s) loaded
2026-04-22 13:02:56,674 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 13:02:56,691 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 13:02:56,691 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 13:02:56,814 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 13:02:57,050 INFO slack_bolt.AsyncApp: A new session (s_8398139429125) has been established
2026-04-22 13:02:57,051 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 13:02:57,225 INFO slack_bolt.AsyncApp: The old session (s_8398139429125) has been abandoned
2026-04-22 13:02:57,353 INFO slack_bolt.AsyncApp: A new session (s_8398139510873) has been established
2026-04-22 13:02:57,537 INFO slack_bolt.AsyncApp: The old session (s_8398139510873) has been abandoned
2026-04-22 13:02:57,660 INFO slack_bolt.AsyncApp: A new session (s_8398135806557) has been established
2026-04-22 13:02:57,834 INFO slack_bolt.AsyncApp: The old session (s_8398135806557) has been abandoned
2026-04-22 13:02:57,957 INFO slack_bolt.AsyncApp: A new session (s_8398135196233) has been established
2026-04-22 13:02:58,128 INFO slack_bolt.AsyncApp: The old session (s_8398135196233) has been abandoned
2026-04-22 13:02:58,249 INFO slack_bolt.AsyncApp: A new session (s_8398135196529) has been established
2026-04-22 13:03:46,010 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:03:46,011 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='waht model are u using'
2026-04-22 13:03:47,637 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 13:03:49,901 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (openrouter/auto)
2026-04-22 13:03:59,633 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=13.6s api_calls=1 response=316 chars
2026-04-22 13:03:59,675 INFO gateway.platforms.base: [Telegram] Sending response (316 chars) to 5192807992
2026-04-22 13:04:13,254 WARNING gateway.run: Unrecognized slash command /models from telegram — replying with unknown-command notice
2026-04-22 13:04:13,255 INFO gateway.platforms.base: [Telegram] Sending response (132 chars) to 5192807992
2026-04-22 13:15:26,048 INFO hermes_cli.web_server: env/reveal: OPENROUTER_API_KEY
2026-04-22 13:15:45,569 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 13:16:10,564 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 13:17:42,533 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:17:42,535 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u using'
2026-04-22 13:17:43,446 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: marking OPENROUTER_API_KEY exhausted (status=401), rotating
2026-04-22 13:17:43,470 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:43,502 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:43,502 WARNING [20260422_121111_9c914d] agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:17:43,503 WARNING [20260422_121111_9c914d] root: Fallback to openrouter failed: provider not configured
2026-04-22 13:17:43,508 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:17:43,573 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=1.0s api_calls=1 response=75 chars
2026-04-22 13:17:43,597 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:17:43,608 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:17:52,835 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (1 chars)
2026-04-22 13:17:52,835 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='h'
2026-04-22 13:17:52,976 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,142 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,455 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,462 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:17:53,533 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=0.7s api_calls=1 response=75 chars
2026-04-22 13:17:53,558 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:17:53,572 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:19:45,170 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 13:19:45,172 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 13:19:45,425 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:45,645 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:46,099 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:46,105 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:19:46,170 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=1.0s api_calls=1 response=75 chars
2026-04-22 13:19:46,201 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:19:46,211 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:19:49,824 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 13:19:49,825 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 13:19:49,967 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,127 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,435 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,441 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:19:50,518 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=0.7s api_calls=1 response=75 chars
2026-04-22 13:19:50,546 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:19:50,556 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:21:51,623 INFO hermes_cli.web_server: env/reveal: OPENROUTER_API_KEY
2026-04-22 13:28:33,001 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (3 chars)
2026-04-22 13:28:33,002 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hey'
2026-04-22 13:28:33,141 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,317 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,705 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,705 WARNING [20260422_121111_9c914d] agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:28:33,734 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,916 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using openai-codex (gpt-5.2-codex) — skipped: openrouter, nous, local/custom
2026-04-22 13:28:43,806 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=10.8s api_calls=1 response=271 chars
2026-04-22 13:28:43,841 INFO gateway.platforms.base: [Telegram] Sending response (271 chars) to 5192807992
2026-04-22 13:28:57,989 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (19 chars)
2026-04-22 13:28:57,990 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u on now'
2026-04-22 13:28:58,124 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:58,287 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:29:09,017 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=11.0s api_calls=1 response=287 chars
2026-04-22 13:29:09,052 INFO gateway.platforms.base: [Telegram] Sending response (287 chars) to 5192807992
2026-04-22 13:29:30,917 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (39 chars)
2026-04-22 13:29:30,917 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='youre supposed to be on openrouter/auto'
2026-04-22 13:29:31,059 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:29:31,216 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:30:20,503 INFO gateway.platforms.telegram: Telegram button resolved 1 approval(s) for session agent:main:telegram:dm:5192807992 (choice=always, user=DocA)
2026-04-22 13:30:38,843 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=67.9s api_calls=4 response=953 chars
2026-04-22 13:30:38,891 INFO gateway.platforms.base: [Telegram] Sending response (953 chars) to 5192807992
2026-04-22 13:31:25,508 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (48 chars)
2026-04-22 13:31:25,509 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg="what file is the 'default model' settings in ..?"
2026-04-22 13:31:25,650 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:31:25,934 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:31:35,725 WARNING gateway.platforms.telegram_network: [Telegram] Primary api.telegram.org connection failed (); trying fallback IPs 149.154.167.220
2026-04-22 13:31:36,381 WARNING gateway.platforms.telegram_network: [Telegram] Primary api.telegram.org path unreachable; using sticky fallback IP 149.154.167.220
2026-04-22 13:31:53,362 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=27.9s api_calls=1 response=1259 chars
2026-04-22 13:31:53,398 INFO gateway.platforms.base: [Telegram] Sending response (1259 chars) to 5192807992
2026-04-22 13:32:21,546 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (85 chars)
2026-04-22 13:32:21,547 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='why are you using openclaw gateway config file when you are hermes and have your'
2026-04-22 13:32:21,691 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:32:21,851 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:32:46,831 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=25.3s api_calls=1 response=1672 chars
2026-04-22 13:32:46,864 INFO gateway.platforms.base: [Telegram] Sending response (1672 chars) to 5192807992
2026-04-22 13:34:08,776 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (150 chars)
2026-04-22 13:34:08,777 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='but im lookin at the config.yaml in root/.hermes and default models and fall b'
2026-04-22 13:34:08,909 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:09,063 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:11,550 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (16 chars)
2026-04-22 13:34:12,516 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:39,616 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=30.8s api_calls=2 response=1262 chars
2026-04-22 13:34:39,650 INFO gateway.platforms.base: [Telegram] Sending response (1262 chars) to 5192807992
2026-04-22 13:36:05,585 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (153 chars)
2026-04-22 13:36:05,586 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='find out what seeting and wwhat file is causing hermes to try to use openclaws c'
2026-04-22 13:36:05,735 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:36:05,895 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:37:50,669 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=105.1s api_calls=9 response=2995 chars
2026-04-22 13:37:50,758 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:37:50,758 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:37:50,770 INFO gateway.platforms.base: [Telegram] Sending response (2995 chars) to 5192807992
2026-04-22 13:39:56,734 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (139 chars)
2026-04-22 13:39:56,735 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what i want to know is why The actual runtime routing in this environment is gov'
2026-04-22 13:39:56,883 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:39:57,036 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:40:22,682 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=25.9s api_calls=1 response=3701 chars
2026-04-22 13:40:22,714 INFO gateway.platforms.base: [Telegram] Sending response (3701 chars) to 5192807992
2026-04-22 13:49:39,191 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (23 chars)
2026-04-22 13:49:39,193 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u using now?'
2026-04-22 13:49:39,476 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:39,642 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:47,341 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=8.1s api_calls=1 response=524 chars
2026-04-22 13:49:47,410 INFO gateway.platforms.base: [Telegram] Sending response (524 chars) to 5192807992
2026-04-22 13:49:47,421 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:47,422 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 14:00:59,033 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,168 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,168 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 14:01:05,196 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,402 INFO agent.auxiliary_client: Auxiliary auto-detect: using openai-codex (gpt-5.2-codex) — skipped: openrouter, nous, local/custom
2026-04-22 14:26:26,982 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (18 chars)
2026-04-22 14:26:26,984 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model you on?'
2026-04-22 14:26:37,029 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=10.0s api_calls=1 response=200 chars
2026-04-22 14:26:37,088 INFO gateway.platforms.base: [Telegram] Sending response (200 chars) to 5192807992
2026-04-22 14:26:41,079 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (29 chars)
2026-04-22 14:26:41,080 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='i dont believe that accurate.'
2026-04-22 14:27:41,358 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=60.3s api_calls=4 response=1910 chars
2026-04-22 14:27:41,457 INFO gateway.platforms.base: [Telegram] Sending response (1910 chars) to 5192807992
2026-04-22 14:53:23,489 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 14:53:26,349 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 14:53:55,467 INFO gateway.run: Stopping gateway for restart...
2026-04-22 14:53:55,997 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 14:53:56,001 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 14:53:56,012 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 14:53:56,022 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 14:53:56,022 INFO gateway.run: ✓ telegram disconnected
2026-04-22 14:53:56,060 INFO slack_bolt.AsyncApp: The current session (s_8398135196529) has been abandoned by disconnect() method call
2026-04-22 14:53:56,064 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 14:53:56,065 INFO gateway.run: ✓ slack disconnected
2026-04-22 14:53:56,080 INFO gateway.run: Gateway stopped
2026-04-22 14:53:56,080 INFO gateway.run: Cron ticker stopped
2026-04-22 14:54:30,726 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 14:54:30,726 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 14:54:32,952 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 14:54:32,952 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 14:54:32,993 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 14:54:33,330 INFO gateway.run: Connecting to telegram...
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 14:54:34,127 INFO apscheduler.scheduler: Scheduler started
2026-04-22 14:54:34,127 INFO telegram.ext.Application: Application started
2026-04-22 14:54:36,509 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 14:54:36,510 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 14:54:36,511 INFO gateway.run: ✓ telegram connected
2026-04-22 14:54:36,754 INFO gateway.run: Connecting to slack...
2026-04-22 14:54:37,142 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 14:54:37,145 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 14:54:37,146 INFO gateway.run: ✓ slack connected
2026-04-22 14:54:37,147 INFO gateway.run: 1 hook(s) loaded
2026-04-22 14:54:37,148 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 14:54:37,170 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 14:54:37,171 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 14:54:37,254 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 14:54:37,587 INFO slack_bolt.AsyncApp: A new session (s_8773147605217) has been established
2026-04-22 14:54:37,588 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 14:56:31,142 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 14:56:31,144 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model you on now?'
2026-04-22 14:56:32,646 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 14:56:36,396 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 14:56:37,543 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 14:56:52,194 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=21.0s api_calls=1 response=915 chars
2026-04-22 14:56:52,231 INFO gateway.platforms.base: [Telegram] Sending response (915 chars) to 5192807992
2026-04-22 14:57:11,059 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (6 chars)
2026-04-22 14:57:11,060 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='wrong.'
2026-04-22 14:57:11,576 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 14:57:12,004 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 14:58:08,933 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=57.9s api_calls=3 response=2496 chars
2026-04-22 14:58:08,973 INFO gateway.platforms.base: [Telegram] Sending response (2496 chars) to 5192807992
2026-04-22 15:08:54,457 INFO gateway.run: Stopping gateway for restart...
2026-04-22 15:08:55,018 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 15:08:55,019 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 15:08:55,029 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 15:08:55,033 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 15:08:55,033 INFO gateway.run: ✓ telegram disconnected
2026-04-22 15:08:55,070 INFO slack_bolt.AsyncApp: The current session (s_8773147605217) has been abandoned by disconnect() method call
2026-04-22 15:08:55,071 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 15:08:55,071 INFO gateway.run: ✓ slack disconnected
2026-04-22 15:08:55,075 INFO gateway.run: Gateway stopped
2026-04-22 15:08:55,076 INFO gateway.run: Cron ticker stopped
2026-04-22 15:09:27,183 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 15:09:27,183 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 15:09:29,281 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 15:09:29,281 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 15:09:29,338 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 15:09:29,666 INFO gateway.run: Connecting to telegram...
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 15:09:30,446 INFO apscheduler.scheduler: Scheduler started
2026-04-22 15:09:30,447 INFO telegram.ext.Application: Application started
2026-04-22 15:09:32,918 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 15:09:32,919 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 15:09:32,919 INFO gateway.run: ✓ telegram connected
2026-04-22 15:09:33,152 INFO gateway.run: Connecting to slack...
2026-04-22 15:09:33,503 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 15:09:33,504 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 15:09:33,505 INFO gateway.run: ✓ slack connected
2026-04-22 15:09:33,506 INFO gateway.run: 1 hook(s) loaded
2026-04-22 15:09:33,506 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 15:09:33,522 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 15:09:33,522 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 15:09:33,593 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 15:09:33,875 INFO slack_bolt.AsyncApp: A new session (s_7829486155165) has been established
2026-04-22 15:09:33,875 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 15:13:06,715 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:13:06,717 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:13:08,303 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 15:13:11,748 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:13:12,750 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:13:29,367 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=22.7s api_calls=1 response=878 chars
2026-04-22 15:13:29,408 INFO gateway.platforms.base: [Telegram] Sending response (878 chars) to 5192807992
2026-04-22 15:17:15,365 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (23 chars)
2026-04-22 15:17:15,367 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u running?hi'
2026-04-22 15:17:15,901 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:17:16,328 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:17:24,323 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.0s api_calls=1 response=738 chars
2026-04-22 15:17:24,359 INFO gateway.platforms.base: [Telegram] Sending response (738 chars) to 5192807992
2026-04-22 15:19:06,278 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:06,278 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:19:06,783 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:07,198 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:14,363 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:15,716 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:16,134 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:19,992 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:20,800 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:21,240 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:30,490 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=24.2s api_calls=1 response=777 chars
2026-04-22 15:19:30,526 INFO gateway.platforms.base: [Telegram] Sending response (777 chars) to 5192807992
2026-04-22 15:21:36,750 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:21:36,752 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:21:37,453 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 15:21:37,876 INFO [20260422_121111_9c914d] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 15:21:46,540 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.8s api_calls=1 response=680 chars
2026-04-22 15:21:46,616 INFO gateway.platforms.base: [Telegram] Sending response (680 chars) to 5192807992
2026-04-22 15:23:50,124 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:23:50,125 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:23:50,790 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (xiaomi/mimo-v2-pro)
2026-04-22 15:24:02,666 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=12.5s api_calls=1 response=498 chars
2026-04-22 15:24:02,711 INFO gateway.platforms.base: [Telegram] Sending response (498 chars) to 5192807992
2026-04-22 15:24:15,505 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (15 chars)
2026-04-22 15:24:15,505 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u on'
2026-04-22 15:24:25,097 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.6s api_calls=1 response=502 chars
2026-04-22 15:24:25,133 INFO gateway.platforms.base: [Telegram] Sending response (502 chars) to 5192807992
---RAW_BUFFERClick to expand / collapse
Bug Description
Bug 1: api_key drift on provider switch — real Hermes bug
The hermes model picker for API-key providers (Ollama Cloud, MiniMax, Z.AI, Kimi via the generic path) routes through _model_flow_api_key_provider() in hermes_cli/main.py:3736. When it saves config, lines 3886–3892 do this:
model["provider"] = provider_id # updates
model["base_url"] = effective_base # updates
model.pop("api_mode", None) # clears (good)
save_config(cfg) # writes file
api_key is NEVER touched
It updates provider, base_url, and api_mode — but never clears or rewrites api_key. So whatever key the previous provider wrote stays put. Switch OpenRouter → Ollama Cloud, and the OpenRouter key hitches a ride into Ollama Cloud's slot. Switch back → the Ollama Cloud key hitches a ride into OpenRouter's slot. That's the exact pattern you observed.
Steps to Reproduce
_model_flow_api_key_provider() in main.py:3891 forgets to pop("api_key") on provider switch. Sister function in auth.py:2752 does it correctly. One-line upstream fix
Expected Behavior
new model selected api key should auto update on the config yaml
Actual Behavior
its leaving the stale key from the prior selected primary model.
Affected Component
Configuration (config.yaml, .env, hermes setup)
Messaging Platform (if gateway-related)
No response
Debug Report
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with `hermes model`.
2026-04-22 05:20:36,354 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 07:59:09,453 INFO slack_bolt.AsyncApp: The old session (s_8691286481021) has been abandoned
2026-04-22 07:59:09,641 INFO slack_bolt.AsyncApp: A new session (s_8691270926317) has been established
2026-04-22 07:59:09,842 INFO slack_bolt.AsyncApp: The old session (s_8691270926317) has been abandoned
2026-04-22 07:59:09,955 INFO slack_bolt.AsyncApp: A new session (s_8691271701105) has been established
2026-04-22 07:59:10,445 INFO slack_bolt.AsyncApp: The old session (s_8691271701105) has been abandoned
2026-04-22 07:59:10,556 INFO slack_bolt.AsyncApp: A new session (s_8691271700633) has been established
2026-04-22 11:30:19,713 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (70 chars)
2026-04-22 11:30:19,715 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='the api key for ollama should be with the other keys in the env file ?'
2026-04-22 11:30:25,540 ERROR gateway.run: Agent error in session agent:main:telegram:dm:5192807992
Traceback (most recent call last):
File "/root/.hermes/hermes-agent/gateway/run.py", line 4409, in _handle_message_with_agent
agent_result = await self._run_agent(
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 10297, in _run_agent
response = _executor_task.result()
^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 8112, in _run_in_executor_with_context
return await loop.run_in_executor(None, ctx.run, func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 9680, in run_sync
agent = AIAgent(
^^^^^^^^
File "/root/.hermes/hermes-agent/run_agent.py", line 1217, in __init__
raise RuntimeError(
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with `hermes model`.
2026-04-22 11:30:25,544 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 11:38:16,164 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (98 chars)
2026-04-22 11:38:16,166 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='but you do have the local gemma 4 model via olamma installed on this device loca'
2026-04-22 11:38:21,502 ERROR gateway.run: Agent error in session agent:main:telegram:dm:5192807992
Traceback (most recent call last):
File "/root/.hermes/hermes-agent/gateway/run.py", line 4409, in _handle_message_with_agent
agent_result = await self._run_agent(
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 10297, in _run_agent
response = _executor_task.result()
^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 8112, in _run_in_executor_with_context
return await loop.run_in_executor(None, ctx.run, func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.hermes/hermes-agent/gateway/run.py", line 9680, in run_sync
agent = AIAgent(
^^^^^^^^
File "/root/.hermes/hermes-agent/run_agent.py", line 1217, in __init__
raise RuntimeError(
RuntimeError: Provider 'ollama-cloud' is set in config.yaml but no API key was found. Set the OLLAMA_API_KEY environment variable, or switch to a different provider with `hermes model`.
2026-04-22 11:38:21,506 INFO gateway.platforms.base: [Telegram] Sending response (267 chars) to 5192807992
2026-04-22 12:10:58,516 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (3 chars)
2026-04-22 12:10:58,517 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hey'
2026-04-22 12:10:59,339 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:10:59,382 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:10:59,399 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:10:59,482 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary flush_memories: using auto (google/gemini-3-flash-preview)
2026-04-22 12:11:02,029 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:11:02,055 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: using auto (minimax-m2.7) at http://localhost:11434/v1/
2026-04-22 12:11:03,393 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: connection error on auto (Connection error.), trying fallback
2026-04-22 12:11:03,451 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary compression: connection error on auto — falling back to openrouter (google/gemini-3-flash-preview)
2026-04-22 12:11:41,897 INFO [20260422_043657_026972d3] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 12:12:03,086 INFO [20260422_043657_026972d3] gateway.run: Session split detected: 20260422_043657_026972d3 → 20260422_121111_9c914d (compression)
2026-04-22 12:12:03,122 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=64.6s api_calls=1 response=518 chars
2026-04-22 12:12:03,158 INFO gateway.platforms.base: [Telegram] Sending response (518 chars) to 5192807992
2026-04-22 12:35:35,933 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (54 chars)
2026-04-22 12:35:35,936 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u running on to generate this response?'
2026-04-22 12:35:37,280 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:35:37,323 INFO [20260422_043657_026972d3] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 12:35:37,339 INFO [20260422_043657_026972d3] agent.model_metadata: Could not detect context length for model 'minimax-m2.7' at http://localhost:11434/v1/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-22 12:36:07,707 INFO [20260422_121111_9c914d] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 12:36:15,775 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=39.8s api_calls=1 response=203 chars
2026-04-22 12:36:15,809 INFO gateway.platforms.base: [Telegram] Sending response (203 chars) to 5192807992
2026-04-22 12:39:20,019 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:43:28,461 INFO gateway.run: Stopping gateway for restart...
2026-04-22 12:43:29,018 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 12:43:29,034 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 12:43:29,040 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 12:43:29,060 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 12:43:29,061 INFO gateway.run: ✓ telegram disconnected
2026-04-22 12:43:29,123 INFO slack_bolt.AsyncApp: The current session (s_8691271700633) has been abandoned by disconnect() method call
2026-04-22 12:43:29,137 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 12:43:29,137 INFO gateway.run: ✓ slack disconnected
2026-04-22 12:43:29,204 INFO gateway.run: Gateway stopped
2026-04-22 12:43:29,205 INFO gateway.run: Cron ticker stopped
2026-04-22 12:44:03,123 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 12:44:03,123 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 12:44:05,230 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 12:44:05,231 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 12:44:05,275 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 12:44:05,647 INFO gateway.run: Connecting to telegram...
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 12:44:05,865 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 12:44:06,444 INFO apscheduler.scheduler: Scheduler started
2026-04-22 12:44:06,444 INFO telegram.ext.Application: Application started
2026-04-22 12:44:08,734 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 12:44:08,735 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 12:44:08,736 INFO gateway.run: ✓ telegram connected
2026-04-22 12:44:08,995 INFO gateway.run: Connecting to slack...
2026-04-22 12:44:09,360 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 12:44:09,363 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 12:44:09,364 INFO gateway.run: ✓ slack connected
2026-04-22 12:44:09,364 INFO gateway.run: 1 hook(s) loaded
2026-04-22 12:44:09,365 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 12:44:09,386 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 12:44:09,387 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 12:44:09,471 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 12:44:09,747 INFO slack_bolt.AsyncApp: A new session (s_8135995012657) has been established
2026-04-22 12:44:09,748 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 12:44:49,951 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:45:39,798 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 12:53:07,584 INFO slack_bolt.AsyncApp: The old session (s_8135995012657) has been abandoned
2026-04-22 12:53:07,778 INFO slack_bolt.AsyncApp: A new session (s_8135995002745) has been established
2026-04-22 12:53:08,007 INFO slack_bolt.AsyncApp: The old session (s_8135995002745) has been abandoned
2026-04-22 12:53:08,133 INFO slack_bolt.AsyncApp: A new session (s_8135994407801) has been established
2026-04-22 12:53:08,303 INFO slack_bolt.AsyncApp: The old session (s_8135994407801) has been abandoned
2026-04-22 12:53:08,427 INFO slack_bolt.AsyncApp: A new session (s_8135994407217) has been established
2026-04-22 12:55:14,440 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 12:56:14,708 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (54 chars)
2026-04-22 12:56:14,717 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u running on to generate this response?'
2026-04-22 12:56:16,250 INFO agent.model_metadata: Cached context length gemma4:e4b@http://172.17.224.1:11434/v1 -> 131,072 tokens
2026-04-22 12:56:17,005 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 12:56:21,436 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (gemma4:e4b)
2026-04-22 12:56:21,830 INFO agent.model_metadata: Cached context length gemma4:e4b@http://172.17.224.1:11434/v1/ -> 131,072 tokens
2026-04-22 12:57:05,281 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=50.6s api_calls=1 response=47 chars
2026-04-22 12:57:05,335 INFO gateway.platforms.base: [Telegram] Sending response (47 chars) to 5192807992
2026-04-22 12:57:16,568 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (15 chars)
2026-04-22 12:57:16,570 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model name'
2026-04-22 12:57:44,957 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=28.4s api_calls=1 response=135 chars
2026-04-22 12:57:44,996 INFO gateway.platforms.base: [Telegram] Sending response (135 chars) to 5192807992
2026-04-22 12:57:58,474 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (46 chars)
2026-04-22 12:57:58,475 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='yes you do ... does the name gemma ring a bell'
2026-04-22 12:58:57,708 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=59.2s api_calls=2 response=158 chars
2026-04-22 12:58:57,765 INFO gateway.platforms.base: [Telegram] Sending response (158 chars) to 5192807992
2026-04-22 13:01:33,891 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:01:33,892 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='waht model are u using'
2026-04-22 13:01:36,251 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (openrouter/auto)
2026-04-22 13:01:49,715 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=15.8s api_calls=1 response=380 chars
2026-04-22 13:01:49,752 INFO gateway.platforms.base: [Telegram] Sending response (380 chars) to 5192807992
2026-04-22 13:02:16,475 INFO gateway.run: Stopping gateway for restart...
2026-04-22 13:02:19,884 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 13:02:19,885 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 13:02:19,895 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 13:02:19,902 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 13:02:19,902 INFO gateway.run: ✓ telegram disconnected
2026-04-22 13:02:19,944 INFO slack_bolt.AsyncApp: The current session (s_8135994407217) has been abandoned by disconnect() method call
2026-04-22 13:02:19,946 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 13:02:19,946 INFO gateway.run: ✓ slack disconnected
2026-04-22 13:02:19,962 INFO gateway.run: Gateway stopped
2026-04-22 13:02:19,962 INFO gateway.run: Cron ticker stopped
2026-04-22 13:02:51,459 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 13:02:51,459 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 13:02:53,473 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 13:02:53,473 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 13:02:53,521 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 13:02:53,919 INFO gateway.run: Connecting to telegram...
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 13:02:54,204 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 13:02:54,776 INFO apscheduler.scheduler: Scheduler started
2026-04-22 13:02:54,776 INFO telegram.ext.Application: Application started
2026-04-22 13:02:56,029 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 13:02:56,030 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 13:02:56,031 INFO gateway.run: ✓ telegram connected
2026-04-22 13:02:56,327 INFO gateway.run: Connecting to slack...
2026-04-22 13:02:56,670 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 13:02:56,672 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 13:02:56,673 INFO gateway.run: ✓ slack connected
2026-04-22 13:02:56,674 INFO gateway.run: 1 hook(s) loaded
2026-04-22 13:02:56,674 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 13:02:56,691 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 13:02:56,691 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 13:02:56,814 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 13:02:57,050 INFO slack_bolt.AsyncApp: A new session (s_8398139429125) has been established
2026-04-22 13:02:57,051 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 13:02:57,225 INFO slack_bolt.AsyncApp: The old session (s_8398139429125) has been abandoned
2026-04-22 13:02:57,353 INFO slack_bolt.AsyncApp: A new session (s_8398139510873) has been established
2026-04-22 13:02:57,537 INFO slack_bolt.AsyncApp: The old session (s_8398139510873) has been abandoned
2026-04-22 13:02:57,660 INFO slack_bolt.AsyncApp: A new session (s_8398135806557) has been established
2026-04-22 13:02:57,834 INFO slack_bolt.AsyncApp: The old session (s_8398135806557) has been abandoned
2026-04-22 13:02:57,957 INFO slack_bolt.AsyncApp: A new session (s_8398135196233) has been established
2026-04-22 13:02:58,128 INFO slack_bolt.AsyncApp: The old session (s_8398135196233) has been abandoned
2026-04-22 13:02:58,249 INFO slack_bolt.AsyncApp: A new session (s_8398135196529) has been established
2026-04-22 13:03:46,010 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:03:46,011 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='waht model are u using'
2026-04-22 13:03:47,637 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 13:03:49,901 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (openrouter/auto)
2026-04-22 13:03:59,633 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=13.6s api_calls=1 response=316 chars
2026-04-22 13:03:59,675 INFO gateway.platforms.base: [Telegram] Sending response (316 chars) to 5192807992
2026-04-22 13:04:13,254 WARNING gateway.run: Unrecognized slash command /models from telegram — replying with unknown-command notice
2026-04-22 13:04:13,255 INFO gateway.platforms.base: [Telegram] Sending response (132 chars) to 5192807992
2026-04-22 13:15:26,048 INFO hermes_cli.web_server: env/reveal: OPENROUTER_API_KEY
2026-04-22 13:15:45,569 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 13:16:10,564 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 13:17:42,533 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 13:17:42,535 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model are u using'
2026-04-22 13:17:43,446 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: marking OPENROUTER_API_KEY exhausted (status=401), rotating
2026-04-22 13:17:43,470 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:43,502 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:43,502 WARNING [20260422_121111_9c914d] agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:17:43,503 WARNING [20260422_121111_9c914d] root: Fallback to openrouter failed: provider not configured
2026-04-22 13:17:43,508 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:17:43,573 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=1.0s api_calls=1 response=75 chars
2026-04-22 13:17:43,597 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:17:43,608 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:17:52,835 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (1 chars)
2026-04-22 13:17:52,835 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='h'
2026-04-22 13:17:52,976 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,142 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,455 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:17:53,462 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:17:53,533 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=0.7s api_calls=1 response=75 chars
2026-04-22 13:17:53,558 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:17:53,572 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:19:45,170 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 13:19:45,172 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 13:19:45,425 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:45,645 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:46,099 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:46,105 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:19:46,170 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=1.0s api_calls=1 response=75 chars
2026-04-22 13:19:46,201 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:19:46,211 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:19:49,824 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 13:19:49,825 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 13:19:49,967 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,127 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,435 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:19:50,441 ERROR [20260422_121111_9c914d] root: Non-retryable client error: Error code: 401 - {'error': {'message': 'User not found.', 'code': 401}}
2026-04-22 13:19:50,518 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=0.7s api_calls=1 response=75 chars
2026-04-22 13:19:50,546 INFO gateway.run: Skipping transcript persistence for failed request in session 20260422_121111_9c914d to prevent session growth loop.
2026-04-22 13:19:50,556 INFO gateway.platforms.base: [Telegram] Sending response (75 chars) to 5192807992
2026-04-22 13:21:51,623 INFO hermes_cli.web_server: env/reveal: OPENROUTER_API_KEY
2026-04-22 13:28:33,001 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (3 chars)
2026-04-22 13:28:33,002 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hey'
2026-04-22 13:28:33,141 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,317 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,705 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,705 WARNING [20260422_121111_9c914d] agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:28:33,734 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:33,916 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using openai-codex (gpt-5.2-codex) — skipped: openrouter, nous, local/custom
2026-04-22 13:28:43,806 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=10.8s api_calls=1 response=271 chars
2026-04-22 13:28:43,841 INFO gateway.platforms.base: [Telegram] Sending response (271 chars) to 5192807992
2026-04-22 13:28:57,989 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (19 chars)
2026-04-22 13:28:57,990 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u on now'
2026-04-22 13:28:58,124 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:28:58,287 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:29:09,017 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=11.0s api_calls=1 response=287 chars
2026-04-22 13:29:09,052 INFO gateway.platforms.base: [Telegram] Sending response (287 chars) to 5192807992
2026-04-22 13:29:30,917 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (39 chars)
2026-04-22 13:29:30,917 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='youre supposed to be on openrouter/auto'
2026-04-22 13:29:31,059 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:29:31,216 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:30:20,503 INFO gateway.platforms.telegram: Telegram button resolved 1 approval(s) for session agent:main:telegram:dm:5192807992 (choice=always, user=DocA)
2026-04-22 13:30:38,843 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=67.9s api_calls=4 response=953 chars
2026-04-22 13:30:38,891 INFO gateway.platforms.base: [Telegram] Sending response (953 chars) to 5192807992
2026-04-22 13:31:25,508 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (48 chars)
2026-04-22 13:31:25,509 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg="what file is the 'default model' settings in ..?"
2026-04-22 13:31:25,650 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:31:25,934 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:31:35,725 WARNING gateway.platforms.telegram_network: [Telegram] Primary api.telegram.org connection failed (); trying fallback IPs 149.154.167.220
2026-04-22 13:31:36,381 WARNING gateway.platforms.telegram_network: [Telegram] Primary api.telegram.org path unreachable; using sticky fallback IP 149.154.167.220
2026-04-22 13:31:53,362 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=27.9s api_calls=1 response=1259 chars
2026-04-22 13:31:53,398 INFO gateway.platforms.base: [Telegram] Sending response (1259 chars) to 5192807992
2026-04-22 13:32:21,546 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (85 chars)
2026-04-22 13:32:21,547 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='why are you using openclaw gateway config file when you are hermes and have your'
2026-04-22 13:32:21,691 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:32:21,851 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:32:46,831 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=25.3s api_calls=1 response=1672 chars
2026-04-22 13:32:46,864 INFO gateway.platforms.base: [Telegram] Sending response (1672 chars) to 5192807992
2026-04-22 13:34:08,776 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (150 chars)
2026-04-22 13:34:08,777 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='but im lookin at the config.yaml in root/.hermes and default models and fall b'
2026-04-22 13:34:08,909 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:09,063 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:11,550 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (16 chars)
2026-04-22 13:34:12,516 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:34:39,616 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=30.8s api_calls=2 response=1262 chars
2026-04-22 13:34:39,650 INFO gateway.platforms.base: [Telegram] Sending response (1262 chars) to 5192807992
2026-04-22 13:36:05,585 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (153 chars)
2026-04-22 13:36:05,586 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='find out what seeting and wwhat file is causing hermes to try to use openclaws c'
2026-04-22 13:36:05,735 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:36:05,895 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:37:50,669 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=105.1s api_calls=9 response=2995 chars
2026-04-22 13:37:50,758 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:37:50,758 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 13:37:50,770 INFO gateway.platforms.base: [Telegram] Sending response (2995 chars) to 5192807992
2026-04-22 13:39:56,734 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (139 chars)
2026-04-22 13:39:56,735 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what i want to know is why The actual runtime routing in this environment is gov'
2026-04-22 13:39:56,883 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:39:57,036 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:40:22,682 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=25.9s api_calls=1 response=3701 chars
2026-04-22 13:40:22,714 INFO gateway.platforms.base: [Telegram] Sending response (3701 chars) to 5192807992
2026-04-22 13:49:39,191 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (23 chars)
2026-04-22 13:49:39,193 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u using now?'
2026-04-22 13:49:39,476 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:39,642 INFO [20260422_121111_9c914d] agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:47,341 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=8.1s api_calls=1 response=524 chars
2026-04-22 13:49:47,410 INFO gateway.platforms.base: [Telegram] Sending response (524 chars) to 5192807992
2026-04-22 13:49:47,421 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 13:49:47,422 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 14:00:59,033 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,168 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,168 WARNING agent.auxiliary_client: resolve_provider_client: openrouter requested but OPENROUTER_API_KEY not set
2026-04-22 14:01:05,196 INFO agent.credential_pool: credential pool: no available entries (all exhausted or empty)
2026-04-22 14:01:05,402 INFO agent.auxiliary_client: Auxiliary auto-detect: using openai-codex (gpt-5.2-codex) — skipped: openrouter, nous, local/custom
2026-04-22 14:26:26,982 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (18 chars)
2026-04-22 14:26:26,984 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model you on?'
2026-04-22 14:26:37,029 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=10.0s api_calls=1 response=200 chars
2026-04-22 14:26:37,088 INFO gateway.platforms.base: [Telegram] Sending response (200 chars) to 5192807992
2026-04-22 14:26:41,079 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (29 chars)
2026-04-22 14:26:41,080 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='i dont believe that accurate.'
2026-04-22 14:27:41,358 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=60.3s api_calls=4 response=1910 chars
2026-04-22 14:27:41,457 INFO gateway.platforms.base: [Telegram] Sending response (1910 chars) to 5192807992
2026-04-22 14:53:23,489 INFO hermes_cli.web_server: env/reveal: OLLAMA_BASE_URL
2026-04-22 14:53:26,349 INFO hermes_cli.web_server: env/reveal: OLLAMA_API_KEY
2026-04-22 14:53:55,467 INFO gateway.run: Stopping gateway for restart...
2026-04-22 14:53:55,997 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 14:53:56,001 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 14:53:56,012 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 14:53:56,022 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 14:53:56,022 INFO gateway.run: ✓ telegram disconnected
2026-04-22 14:53:56,060 INFO slack_bolt.AsyncApp: The current session (s_8398135196529) has been abandoned by disconnect() method call
2026-04-22 14:53:56,064 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 14:53:56,065 INFO gateway.run: ✓ slack disconnected
2026-04-22 14:53:56,080 INFO gateway.run: Gateway stopped
2026-04-22 14:53:56,080 INFO gateway.run: Cron ticker stopped
2026-04-22 14:54:30,726 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 14:54:30,726 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 14:54:32,952 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 14:54:32,952 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 14:54:32,993 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 14:54:33,330 INFO gateway.run: Connecting to telegram...
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 14:54:33,574 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 14:54:34,127 INFO apscheduler.scheduler: Scheduler started
2026-04-22 14:54:34,127 INFO telegram.ext.Application: Application started
2026-04-22 14:54:36,509 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 14:54:36,510 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 14:54:36,511 INFO gateway.run: ✓ telegram connected
2026-04-22 14:54:36,754 INFO gateway.run: Connecting to slack...
2026-04-22 14:54:37,142 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 14:54:37,145 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 14:54:37,146 INFO gateway.run: ✓ slack connected
2026-04-22 14:54:37,147 INFO gateway.run: 1 hook(s) loaded
2026-04-22 14:54:37,148 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 14:54:37,170 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 14:54:37,171 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 14:54:37,254 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 14:54:37,587 INFO slack_bolt.AsyncApp: A new session (s_8773147605217) has been established
2026-04-22 14:54:37,588 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 14:56:31,142 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (22 chars)
2026-04-22 14:56:31,144 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model you on now?'
2026-04-22 14:56:32,646 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 14:56:36,396 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 14:56:37,543 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 14:56:52,194 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=21.0s api_calls=1 response=915 chars
2026-04-22 14:56:52,231 INFO gateway.platforms.base: [Telegram] Sending response (915 chars) to 5192807992
2026-04-22 14:57:11,059 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (6 chars)
2026-04-22 14:57:11,060 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='wrong.'
2026-04-22 14:57:11,576 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 14:57:12,004 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 14:58:08,933 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=57.9s api_calls=3 response=2496 chars
2026-04-22 14:58:08,973 INFO gateway.platforms.base: [Telegram] Sending response (2496 chars) to 5192807992
2026-04-22 15:08:54,457 INFO gateway.run: Stopping gateway for restart...
2026-04-22 15:08:55,018 INFO telegram.ext.Application: Application is stopping. This might take a moment.
2026-04-22 15:08:55,019 INFO apscheduler.scheduler: Scheduler has been shut down
2026-04-22 15:08:55,029 INFO telegram.ext.Application: Application.stop() complete
2026-04-22 15:08:55,033 INFO gateway.platforms.telegram: [Telegram] Disconnected from Telegram
2026-04-22 15:08:55,033 INFO gateway.run: ✓ telegram disconnected
2026-04-22 15:08:55,070 INFO slack_bolt.AsyncApp: The current session (s_8773147605217) has been abandoned by disconnect() method call
2026-04-22 15:08:55,071 INFO gateway.platforms.slack: [Slack] Disconnected
2026-04-22 15:08:55,071 INFO gateway.run: ✓ slack disconnected
2026-04-22 15:08:55,075 INFO gateway.run: Gateway stopped
2026-04-22 15:08:55,076 INFO gateway.run: Cron ticker stopped
2026-04-22 15:09:27,183 INFO hermes_cli.plugins: Plugin 'openai' registered image_gen provider: openai
2026-04-22 15:09:27,183 INFO hermes_cli.plugins: Plugin discovery complete: 2 found, 1 enabled
2026-04-22 15:09:29,281 INFO gateway.run: Starting Hermes Gateway...
2026-04-22 15:09:29,281 INFO gateway.run: Session storage: /root/.hermes/sessions
2026-04-22 15:09:29,338 INFO gateway.run: Previous gateway exited cleanly — skipping session suspension
2026-04-22 15:09:29,666 INFO gateway.run: Connecting to telegram...
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram_network: DoH discovery yielded no new IPs (system DNS: 149.154.166.110); using seed fallback IPs 149.154.167.220
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram: [Telegram] Auto-discovered Telegram fallback IPs: 149.154.167.220
2026-04-22 15:09:29,890 INFO gateway.platforms.telegram: [Telegram] Telegram fallback IPs active: 149.154.167.220
2026-04-22 15:09:30,446 INFO apscheduler.scheduler: Scheduler started
2026-04-22 15:09:30,447 INFO telegram.ext.Application: Application started
2026-04-22 15:09:32,918 INFO gateway.platforms.telegram: [Telegram] Telegram menu: 100 commands registered, 680 hidden (over 100 limit). Use /commands for full list.
2026-04-22 15:09:32,919 INFO gateway.platforms.telegram: [Telegram] Connected to Telegram (polling mode)
2026-04-22 15:09:32,919 INFO gateway.run: ✓ telegram connected
2026-04-22 15:09:33,152 INFO gateway.run: Connecting to slack...
2026-04-22 15:09:33,503 INFO gateway.platforms.slack: [Slack] Authenticated as @unknown in workspace unknown (team: )
2026-04-22 15:09:33,504 INFO gateway.platforms.slack: [Slack] Socket Mode connected (1 workspace(s))
2026-04-22 15:09:33,505 INFO gateway.run: ✓ slack connected
2026-04-22 15:09:33,506 INFO gateway.run: 1 hook(s) loaded
2026-04-22 15:09:33,506 INFO gateway.run: Gateway running with 2 platform(s)
2026-04-22 15:09:33,522 INFO gateway.run: Channel directory built: 2 target(s)
2026-04-22 15:09:33,522 INFO gateway.run: Press Ctrl+C to stop
2026-04-22 15:09:33,593 INFO gateway.run: Cron ticker started (interval=60s)
2026-04-22 15:09:33,875 INFO slack_bolt.AsyncApp: A new session (s_7829486155165) has been established
2026-04-22 15:09:33,875 INFO slack_bolt.AsyncApp: ⚡️ Bolt app is running!
2026-04-22 15:13:06,715 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:13:06,717 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:13:08,303 INFO run_agent: Loaded environment variables from /root/.hermes/.env
2026-04-22 15:13:11,748 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:13:12,750 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:13:29,367 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=22.7s api_calls=1 response=878 chars
2026-04-22 15:13:29,408 INFO gateway.platforms.base: [Telegram] Sending response (878 chars) to 5192807992
2026-04-22 15:17:15,365 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (23 chars)
2026-04-22 15:17:15,367 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u running?hi'
2026-04-22 15:17:15,901 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:17:16,328 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:17:24,323 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.0s api_calls=1 response=738 chars
2026-04-22 15:17:24,359 INFO gateway.platforms.base: [Telegram] Sending response (738 chars) to 5192807992
2026-04-22 15:19:06,278 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:06,278 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:19:06,783 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:07,198 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:14,363 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:15,716 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:16,134 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:19,992 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:19:20,800 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (kimi-k2.6:cloud)
2026-04-22 15:19:21,240 INFO [20260422_121111_9c914d] root: Fallback activated: kimi-k2.6:cloud → openrouter/auto (openrouter)
2026-04-22 15:19:30,490 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=24.2s api_calls=1 response=777 chars
2026-04-22 15:19:30,526 INFO gateway.platforms.base: [Telegram] Sending response (777 chars) to 5192807992
2026-04-22 15:21:36,750 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:21:36,752 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:21:37,453 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider ollama-cloud (minimax-m2.7)
2026-04-22 15:21:37,876 INFO [20260422_121111_9c914d] root: Fallback activated: minimax-m2.7 → openrouter/auto (openrouter)
2026-04-22 15:21:46,540 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.8s api_calls=1 response=680 chars
2026-04-22 15:21:46,616 INFO gateway.platforms.base: [Telegram] Sending response (680 chars) to 5192807992
2026-04-22 15:23:50,124 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (2 chars)
2026-04-22 15:23:50,125 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='hi'
2026-04-22 15:23:50,790 INFO [20260422_121111_9c914d] agent.auxiliary_client: Auxiliary auto-detect: using main provider openrouter (xiaomi/mimo-v2-pro)
2026-04-22 15:24:02,666 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=12.5s api_calls=1 response=498 chars
2026-04-22 15:24:02,711 INFO gateway.platforms.base: [Telegram] Sending response (498 chars) to 5192807992
2026-04-22 15:24:15,505 INFO gateway.platforms.telegram: [Telegram] Flushing text batch agent:main:telegram:dm:5192807992 (15 chars)
2026-04-22 15:24:15,505 INFO gateway.run: inbound message: platform=telegram user=DocA chat=5192807992 msg='what model u on'
2026-04-22 15:24:25,097 INFO gateway.run: response ready: platform=telegram chat=5192807992 time=9.6s api_calls=1 response=502 chars
2026-04-22 15:24:25,133 INFO gateway.platforms.base: [Telegram] Sending response (502 chars) to 5192807992Operating System
ubunto 24.04
Python Version
No response
Hermes Version
No response
Additional Logs / Traceback (optional)
Root Cause Analysis (optional)
No response
Proposed Fix (optional)
No response
Are you willing to submit a PR for this?
- I'd like to fix this myself and submit a PR
extent analysis
TL;DR
The issue can be fixed by adding model.pop("api_key", None) in the _model_flow_api_key_provider() function to clear the API key when switching providers.
Guidance
- Locate the
_model_flow_api_key_provider()function: Find this function inhermes_cli/main.pyand navigate to line 3736. - Add API key clearing code: Insert
model.pop("api_key", None)after updating the provider and base URL to clear the API key when switching providers. - Verify the fix: After making the change, restart the Hermes Gateway and test switching between providers to ensure the API key is correctly updated.
- Check for similar issues: Review other parts of the codebase for similar logic that may also require API key clearing when switching providers.
Example
# In hermes_cli/main.py, around line 3736
def _model_flow_api_key_provider():
# ...
model["provider"] = provider_id
model["base_url"] = effective_base
model.pop("api_mode", None)
model.pop("api_key", None) # Add this line to clear the API key
save_config(cfg)
# ...Notes
This fix assumes that the issue is solely due to the missing model.pop("api_key", None) line. If the problem persists after applying this fix, further investigation into the code and logs may be necessary.
Recommendation
Apply the workaround by adding model.pop("api_key", None) to the _model_flow_api_key_provider() function, as this directly addresses the identified issue.
Vote matrix · Quick signals
Still need to ship something?
×6Another batch ranked right after the header list — different links, same matching logic.
TRENDING
- Feature Request: Configurable per-minute rate limiting (RPM) for models to prevent 429 errors
- Android: Hermes App + Termux install share ~/.hermes and cause silent permission loops
- hermes update emits unicode-animations ANSI demo in non-interactive logs
- hermes update downgrades aiohttp from 3.13.4 to 3.13.3
- npm install warns about deprecated @babel/plugin-proposal-private-methods
- DingTalk inbound media URLs are skipped as unreadable native image paths
- fix(dashboard): ChatPage clears header action buttons on ALL pages, not just Sessions
- [Bug]: check_web_api_key() hardcodes built-in backends — third-party web search plugins silently disabled
- Hermes Web UI 修复经验:GatewayManager 补丁、进程 D 状态、数据库升级问题
- Telegram gateway can silently drop turn after /stop with response=0 chars while internal work continues
- Bug Report: v0.14.0 上下文污染 — 历史回复碎片回注到新请求
- Bug: hermes skills search table truncates Identifier column — install fails with copied value
- [skills-index-watchdog] Skills index is stale or degraded (degraded)
- Discord approval embed not rendering on web/mobile — embed data present in API but invisible
- Idea: Discord voice-channel participation / opt-in auto-join mode
- [Feature]: Claude Code--ultrawork
- build-arm64 job deterministically fails on cold cache (Azure SAS token expires mid-build)
- [Enhancement] computer_use: action=type should fall back to key events for terminal emulators (Ghostty/Terminal.app/iTerm2)
- Feature Request: Session Recovery on Temporary Provider Outage
- [Bug]: Hermes dashboard not working on NixOS (container)
- [Feature]: Add option to ignore @all/@everyone mentions in Feishu group chats
- QQ Bot WebSocket 频繁断开:长时间工具执行阻塞 asyncio 事件循环导致心跳超时
- patch tool: new_string escape sequences (\t) get written literally
- Feature Request: i18n / 多语言支持(国际化)
- Bug: web_crawl schema lets models auto-guess "instructions" instead of asking the user via clarify
- feat: `!command` prefix for direct shell execution (like Claude Code)
- Expose currently-running cron jobs via /api/jobs (or new endpoint)
- [Bug]: Kanban parent-child handoff: scratch workspace GC destroys artifacts before child can read them
- [Bug, Windows] hermes gateway restart loses session context — planned_stop_marker not written before SIGTERM
- [Bug]: Codex→DeepSeek fallback sends assistant turns without reasoning_content → HTTP 400 (require-side cross-provider failover)
- [Bug]: Update got stuck half way, reboot it, then ModuleNotFoundError: No module named 'hermes_cli'
- Kanban dispatcher corrupt-board handling and multi-profile gateway ownership ambiguity
- Gateway can resend a short fallback message when the real final Telegram response was already delivered
- [BUG] Bedrock: Fix 'Invalid API Key format' for presigned URL tokens
- Secret redaction corrupts code syntax in tool output (write_file, execute_code, terminal)
- Unable to connect Ollama Cloud with Pro Subscription to Hermes
- feat: fuzzy substring matching for /skill autocomplete
- PRD: Autonomous market-impact prediction briefing system
- Kanban dashboard should support task/card deep links
- [Feature] Native Feishu CardKit Streaming: consolidate best-in-class implementations
- [Feature]: Inject mental model into context when using Hindsight
- Interactive CLI hides tool output despite display.tool_progress=all, and hermes chat -v does not restore it
- fix(api_server): _handle_responses drops text.format JSON schema — structured output constraints silently ignored
- state.db FTS corruption goes undetected — no integrity check, no repair path
- bug: fallback routing can select text-only models for image requests and hide the primary failure
- feat(kanban): persist worker session_id per run and pass --resume on respawn after unblock
- feat(kanban): support GitHub/OMO lifecycle bridge for Xiyou-style automation
- Expose update-safe TUI/composer hooks for voice transcript and composer events
- Hide or configure voice transcript status rows in editable dictation mode
- [Feature]: Per-Tool / Per-Toolset Approval Policies
- Context compression creates orphan sessions missing from state.db
- messaging platform
- feat: Add read-only / silent monitoring mode for WhatsApp adapter
- double-.hermes path mismatch, the HOME env var leak, and the fallback-notification UX problem
- Bug: Plattform-Bundle name `hermes-yuanbao` in `agent.disabled_toolsets` silently kills ALL tools in gateway path (Telegram + cron), CLI unaffected
- CLI /yolo (in-chat) does not bypass dangerous command approvals — env var freeze + missing enable_session_yolo call
- OpenAI Codex provider crashes with "'NoneType' object is not iterable" (HTTP None)
- DEEPSEEK_API_KEY blocked by env blocklist in gateway process — cron jobs fail with deepseek provider
- fix(feishu): Card action callback routing issues - invalid message_id and unrecognized /card command
- Discord plugin: profiles without explicit `discord:` block silently get `require_mention=true` + `auto_thread=true` (regression in cc8e5ec2a)
- [Bug]: DISCORD_ALLOWED_ROLES ignored by gateway _is_user_authorized — role-authorized users get 'Unauthorized user' rejection
- [Bug]: /new, /clear, and /reset commands freeze the terminal session
- openai-codex subscription backend returns HTTP 200 with response.output=None, causing Slack/cron failures
- RFC: Centralized Model/Provider Registry
- bug: openai-codex provider — TypeError: 'NoneType' object is not iterable on every request (gpt-5.5)
- [Feature]: Source-aware instruction gate — architectural mitigation for indirect prompt injection
- Named custom provider stale_timeout_seconds ignored because runtime provider is normalized to `custom`
- guard test (ignore)
- [Feature]: per-platform LLM request_overrides (extra_body / reasoning_effort / service_tier)
- One-shot smoke: add Flue-backed orchestration fixture
- Gateway should not treat stale Codex app-server progress as final response after post-tool silence
- `docker_run_as_host_user: true` breaks bundled skills: Hermes home is mounted into `/root/.hermes` but the container runs as a non-root user (`HOME=/home/pn`)
- [Bug]: gateway api_server streaming bypasses server-side tool-call loop when chat_template_kwargs.enable_thinking=false (model emits tool name as plain text)
- [Feature]: Pre-install python-telegram-bot in Umbrel Hermes Docker image
- YouTube Shorts filter not working in youtube-content skill
- v0.15.0 PyPI release breaks ALL platforms — plugin.yaml manifests missing from package
- RFC: On-demand tool/skill/MCP discovery — decouple schema registration from process lifecycle
- Pixshelf: local-first stock photo workflow command center
- [Bug]: baoyu infographic skill should not silently bypass image_generate
- Pixshelf v1.5: manual submission tracking for stock agencies
- `hermes config set` silently accepts unknown keys, writing them where the runtime never reads
- Honcho memory prefetch hang on fresh CLI subprocess in v0.15.0 (regression from #27190)
- [Bug] v0.15.0 Docker image: stage2-hook.sh, main-wrapper.sh missing; container_boot module removed
- Feature: Reduce cache-read token overhead for DeepSeek providers — configurable cache_ttl, skills snapshot trimming, memory compaction
- Windows: three bugs from daily use (plugin discovery, gateway exit code, Unicode decode
- holographic memory: HRR silently degrades to FTS5 when numpy is missing
- Make max_tokens configurable for aux vision calls
- Conversation compression desynchronizes session ID between agent context and gateway routing, causing silent message loss
- [Bug]: v0.15.0 Docker image:The TUI cannot be used in the dashboard.
- cron: skip_memory=True blocks fact_store/memory tools from all cron jobs
- TUI: Node.js OOM crash when agent uses browser tools repeatedly
- feat: model_profiles — per-model toolset and memory config
- Automatic background skill patching disrupts active sessions (severe impact on local models)
- ensure_hermes_home() creates root-owned dirs in profile subdirectories when kanban workers are dispatched
- Feature: opt-in webhook bypass for DISCORD_ALLOW_BOTS — allow operator-initiated probes without weakening bot-loop guard
- v0.15.0: Codex requests fail HTTP 400 when participant display_name contains non-ASCII (emoji breaks input[].name pattern)
- Architecture: State Persistence Precedence (Memory vs Skills vs Hooks)
- [Bug]: cronjob tool: create action always fails with "schedule is required for create" even when parameters are provided
- codex-oauth: 'NoneType' object is not iterable in _run_codex_stream (gpt-5.5) — every turn fails non-retryably
- Docs/Config: Plugin local scope enablement ambiguity
- [Bug]: CLI freezes after using /new command (WSL)
- Profile Codex auth can ignore global credential pool when local state is stale
- [workflow-engine] CRITICAL: variable substitution crashes on regex metachars in user input
- [workflow-engine] HIGH: loop and bash nodes leak subprocesses on timeout
- [workflow-engine] HIGH: README documents config env vars the engine never reads
- [workflow-engine] MEDIUM: workflow_run rate limit bypassable via concurrent calls (TOCTOU)
- [workflow-engine] chore: manifest gaps, side-effectful register(), dead code, unauth kanban dispatch
- [mcp_lazy] HIGH: synthetic mcp_server_<name> stub collides with a real MCP server named 'server'
- [mcp_lazy] HIGH: promote_server eager flag documented but never persisted
- [mcp_lazy] MEDIUM: _prev_mode dict leaks and goes stale; not cleared on session evict
- [mcp_lazy] MEDIUM: get_pool has unlocked check-then-set race on pool creation
- [mcp_lazy] MEDIUM: pre_tool_call gives no guidance for unpromoted server-stub calls
- [mcp_lazy] chore: undeclared pre_tool_call hook, nonexistent 'mcp_load_tools' name in docs, missing tests
- [a2a_fleet] CRITICAL: server never auto-starts — register() runs outside an event loop
- [a2a_fleet] CRITICAL: auth_required defaults to false on a cross-machine surface
- [a2a_fleet] HIGH: remove invented disable() hook — loader never calls it, port leaks on reload
- [a2a_fleet] HIGH: plugin.yaml missing kind / provides_tools / requires_env (token env undeclared)
- [a2a_fleet] MEDIUM: tighten wide-open CORS, anonymous /health peer leak, and peer-URL SSRF
- [a2a_fleet] MEDIUM: relocate tests to tests/plugins/ and cover sync-register + auth-default paths
- xai-oauth auxiliary client incorrectly uses Responses API (CodexAuxiliaryClient), causing 403 on compression/vision/web_extract
- [Bug]: Direct Copilot gpt-5.5 large resumes are killed by 12s Codex TTFB watchdog
- [Bug]: `hermes uninstall` does not work on Windows
- TUI: Thinking block leaks raw JSON and Σ character
- Hostinger VPS: migration Hermes Agent → Hermes WebUI impossible (tini + UID mismatch + sessions)
- /goal judge over-continues exploratory goals unless the assistant explicitly says the goal is complete
- /goal auto-continuation can be amplified by preflight compression/session split and resurrect stale task state
- Dashboard infinite reload loop in loopback mode — GET /api/auth/me returns 401 on every page load
- [Bug]: Provider/LLM switch leaves stale encrypted_content causing 400 errors on Telegram sessions
- [Bug]: Infinite reload loop / React state loop on Sessions tab (Firefox + Chrome) — repeated 401 on /api/auth/me (v0.15.0)
- show_reasoning should work independently of streaming in CLI mode
- Feature Request: Strip reasoning/<think> blocks from TTS preprocessing
- mcp add / mcp test raise NameError when mcp package not installed
- v0.14.0 dashboard breaks behind reverse proxies — two regressions
- Skills hub creates empty category directories when no skills installed
- [Bug]: Custom endpoint: ChatCompletions returns content, but Hermes treats response as empty (v0.14.0)
- fix: atomic_replace() fails with EXDEV when HERMES_HOME is a cross-filesystem symlink
- fix(gateway): Feishu session cancellation orphans session guard, permanently blocking messages
- Custom endpoint pricing can overestimate Crof qwen3.5-9b cost by 1,000,000x
- MCP OAuth callback: module-level port global causes port collisions and structural weaknesses vs upstream
- Bug: send_message tool bypasses validate_media_delivery_path security check
- Proposal: Add Mnemosyne to official memory provider documentation
- feat(swarm): support custom verifier/synthesizer body + skills
- Template conversion failed
- Error occurred in the operation of the agent node in the workflow.
- PubSub client overrides Sentinel client when REDIS_USE_SENTINEL is enabled
- Frontend description of the Retrieval node output does not match the actual output
- JSON type input var raise Intenal server error
- cannot extract elements from a scalar
- 负载均衡 为模型配置多组凭据,并自动调用,此功能无法选择
- add models is error
- panic: could not create filter
- Persist partially generated messages when /chat-messages/:task_id/stop is called
- MCP server connection fails with 403 — request never leaves Dify (SSRF proxy suspected)
- Support durable async execution backends for long-running workflow steps
- [Xiaomi MiMo] Credentials validation fails with 400 "Not supported model mimo-v2-flash" when using Token Plan endpoint (v0.0.7)
- After clicking preview on a parent-child segmented knowledge base, it shows 0 chunks
- Retrieval score differs between UI upload (.docx) and API upload (.txt) despite identical chunk content and embedding model
- gemini cli crash again
- Xbox gift card code damage
- Damage caused by the gemini cli crash
- ioctl(2) failed, EBADF (Bad File Descriptor)
- Feat: Support Bun as an alternative runtime/package manager for updates and extensions
- fatal error again!!!!
- ioctl error
- Critical Crash: ioctl(2) failed, EBADF in ShellExecutionService.resizePty
- ioctl(2) failed, EBADF
- v0.44.0 Regression: Critical crash with ioctl(2) failed, EBADF during PTY resize
- Crash on startup: ioctl(2) failed, EBADF in UnixTerminal.resize
- Crash: `ioctl(2) failed, EBADF` in `node-pty` during PTY resize on macOS
- Gemini CLI crashes with `ioctl(2) failed, EBADF` in `node-pty` during `resizePty`
- Remote Role
- ERROR ioctl(2) failed, EBADF /home/mich
- RangeError: Maximum call stack size exceeded
- EBADF Error during folder creationg broke session and terminal glitches
- MAIP / Gargoub Project - Mediterania - North Coast
- Gemini cli crash again in this morning
- ERROR ioctl(2) failed, EBADF
- Verified node install fails — Checksum verification failed (Cloud)
- The extended debugging key did not arrive during registration.
- CollaborationPane unmounts collaboration store on single-user instances, causing permanent "No network connection" state
- Workflow cannot be saved when the name contains "->" (Potentially malicious string)
- automation does not work and does not show an error
- Raj Ai Automation
- Default Data Loader: DOMMatrix is not defined error
- Feature: Per-node execution timestamp overlay on canvas during workflow run
- AI Agent + Vertex `gemini-3.5-flash`: 400 "missing thought_signature" on sequential multi-turn tool calls (post-#24982)
- PDF Loader in Pinecone Vector Store fails due to pdf-parse version conflict (v2 not supported)
- emailReadImap: add UID deduplication, batch size cap, and numeric uid enforcement
- Manual node execution fails with "Could not find a node" when autosave is disabled (N8N_WORKFLOWS_AUTOSAVE_DISABLED)
- Schedule Trigger stopped firing — workflow Published & active, manual executions succeed, no automated fires for 2+ hours
- [MCP SDK] create_workflow_from_code intermittently returns HTTP 500, often as a false negative (workflow persists anyway, causing duplicates on retry)
- Credential-load wedge: workflows using googleApi/jwtAuth credentials silently fail to execute after key rotation
- Google Sheets Trigger every minute is not working manual Execute is working sent email
- [BUG] Plugin marketplace MCP connector remains stuck "still connecting" when mcp-remote requires OAuth
- [redacted at user request]
- Opus 4.7 behavioral regression: loaded instruction-following discipline degraded in recent Claude Code/Cowork updates
- [BUG] Tailscale via Homebrew CLI + Mac App Store GUI, both Macs on macOS, Cowork blocked by VPN detector despite Tailscale being a mesh VPN with no traffic interception
- stopShellPty on tab switch kills active sessions (exit 143) — regression in May 27 build
- [BUG] Long URLs are broken into multiple lines and become unclickable in terminal output
- [BUG] claude rm/stop/reap SIGKILLs background session tree without SIGTERM grace, orphaning git index.lock and similar
- [BUG] Default git workflow in the system prompt was pushed without context or consent
- [MODEL] Inconsistent output quality / Ignoring instructions (overfitting and inappropriate repetition of Korean vocabulary)
- You've hit your weekly limit · resets May 31 at 5pm (Asia/Shanghai)
- Paid yearly subscription silently downgraded to Free with no user action
- [Regression v2.1.153] Plugin bash hooks fail with "echo: write error: Permission denied" on Windows (claude-mem, shell: "bash")
- [BUG] Connector toggles in conversation are not clickable — must click text label instead
- [remote-control] Input from mobile app/browser not reaching host session — output works fine
- Model fails to read/reference CLAUDE.md contents despite being loaded in context
- [BUG] Claude Desktop reinstall destroys Code chat history (transcripts + Recents) while regular Chat history, project files, and memory all survive
- Bypass mode clamps to Accept Edits even with the toggle ON (Claude Code Desktop 1.9255.2 / CC 2.1.149)
- [BUG] TUI input freezes randomly mid-typing — entire prompt becomes unresponsive for minutes
- [BUG] Cowork downloads Linux ELF binary instead of macOS binary on macOS Sonoma 14.8.7 — exit code 132 (SIGILL) on every session
- [Feature Request] Persistent project memory — sessions forget everything on close, forcing users to keep many sessions open
- [Bug] Thread context stale after sleep/resume, returns outdated date and calendar data
- [FEATURE] Add context window usage indicator and warning before auto-compaction
- [BUG] Dictation error: Invalid character in header content ["x-config-keyterms"] on Windows
- [Bug] Anthropic API Error: Server rate limiting despite normal usage
- Does delegating work to `claude -p` subprocesses reduce context accumulation in the parent session?
- [BUG] Claude Code hangs on M1 Mac when terminal says "opening browser to sign in" and browser opens
- [BUG] Claude_Preview MCP preview_start spawns dev server with main-repo cwd instead of session's worktree cwd
- [Bug] Anthropic API Error: Server rate limiting during request execution
- [Bug] Anthropic API Error: Server rate limiting on concurrent requests
- [Bug] Ultraplan ready notification fires before cloud agent completes execution
- [BUG] API 500 ERROR ALL THROUGHOUT THE DAY
- [BUG] Cowork: Live Artifacts folder path changed in 1.9255.2, no automatic migration from Documents\Claude\Artifacts
- [Bug] Auto-compact never triggers despite statusline reporting "100% context used" (v2.1.153, Max sub, 200K mode)
- [BUG] [Desktop / macOS] 'Open in → New Window' detached session: font renders smaller than main, no per-window controls, Cmd+/Cmd- keystrokes routed to main window instead
- Feature request: option to switch between classic and new minimal UI
- [Feature Request] Show timestamps for each message
- [BUG] Terminal corruption when permission prompt appears while navigating Agent Teams agent selection menu
- [FEATURE] Allow users to customize the background color of the Claude desktop app beyond the current light/dark theme presets.
- [BUG] Statusline not displaying on Windows [fixed]
- Background agent UI Stop button is a no-op for stuck agents — process keeps consuming tokens
- Background agents silently die on session pause/resume — no completion notification, no work recovery
- Add option to hide email address from welcome banner
- [BUG] SSH Remote: `projects` field in remote ~/.claude.json becomes null after desktop restart — jsonl files intact, UI shows 'No messages yet' for every session
- [Bug] Claude Code not applying fixes despite claiming to complete tasks
- billing is unfair and poorly documented
- [BUG] Claude Code on the web: declared plugins inactive on first session, require restart to fully load
- [BUG] Restore from archive deleted sessions instead of restoring them
- [BUG] M365 connector fails with AADSTS50011 in Cowork — localhost vs 127.0.0.1 redirect URI mismatch
- claude agents: workflow slash-commands missing from dispatch-input completion (regression-adjacent to #61424)
- Claude Desktop's Info.plist missing TCC usage strings, blocks all EventKit-based MCP servers
- False-positive safety blocks on self-administered governance amendments — request for owner-authority mode for verified professional users
- [BUG] Stop pushing "AUTO"-mode
- [DOCS] Plugin marketplace guide omits `skipLfs` option for git-based sources
- [DOCS] MCP docs omit combined startup notification for MCP server and connector authentication
- [DOCS] Agent view docs omit macOS Privacy & Security identity for background agents
- [DOCS] Npm update docs do not explain release-channel behavior for `claude update`
- [DOCS] Agent SDK docs omit `subagent_type: "claude"` worktree and output persistence behavior
- [DOCS] Background session docs omit `$CLAUDE_JOB_DIR` temp-file behavior
- [FR] mask env-var values in 'claude mcp get <server>' output
- [FR] subagent worktrees should not inherit stale local 'user.email' from prior dispatches
- [BUG] Windows: Grep tool leaks rg.exe + conhost.exe processes (~2000 zombies / 14 GB RAM in long sessions)
- [BUG] Stats dashboard "Peak hour" appears off by one hour
- [BUG] Diff highlight (teal SGR background) bleeds past changed text in 2.1.150–2.1.153
- [FEATURE] confirm before deleting session
- Plugin PostToolUse hooks still silently skip in Claude Desktop / Cowork (re-filing closed #51904)
- /code-review skill: silent fallback to main...HEAD reviews other people's commits, and JSON-only output is hard to read
- Monitor tool doesn't source the shell snapshot like Bash does; PATH-dependent tools (jq, sleep, etc.) fail in Monitor commands on macOS/Nix
- [Bug] Long input lines truncated with ellipsis while typing instead of wrapping in terminal UI
- [FEATURE] VS Code extension: Render submitted user messages as Markdown in chat
- OSC 52 copy from Claude TUI doesn't reach clipboard inside tmux (regression in 2.1.146–2.1.153)
- [BUG] RemoteTrigger create/update returns HTTP 400 with circular error: "event_type is required" / "unknown field event_type"
- [BUG] Option to hide or minimize the built-in "status footer" (multi-line debug/cost panel) [re-raise of #31475]
- [Bug] Feedback submissions being closed without review or action
- [FEATURE] Word-jump cursor navigation in Chat input (option+arrow / bindable actions)
- [FEATURE] ! shell mode: filesystem tab completion
- [BUG] API Error: Usage credits required for 1M context
- claude agents: OSC 52 clipboard emission broken in tmux (regression in 2.1.146–2.1.153)
- CLI crashes on macOS 15 M3 - exit code 1
- [FEATURE] Support Cmd+V image paste from clipboard
- [FEATURE] Enhance claude.ai M365 connector to support MS Planner
- [BUG] Slash command autocomplete hijacks pasted absolute file paths starting with /
- PreToolUse hook `if` filter false-positives on complex Bash commands
- [BUG] Diff panel hangs/whites out
- Feature Request: Support drag-and-drop for binary documents (.wps, .doc, .docx, .xlsx, .pdf) in VS Code extension
- [BUG] activation of 1M context in VSCode
- [FEATURE] Support i18n / language localization for built-in slash command outputs
- Ctrl+V para colar imagens deixou de funcionar no CLI (Windows, PowerShell)
- [FEATURE] Please add Norwegian (Bokmål/Nynorsk) language support to the Claude Code interface
- [BUG] OTel log events (claude_code.user_prompt, api_request_body, tool_decision, hook_execution_complete) emitted with empty trace_id/span_id while sibling spans correlate correctly
- [BUG] Cowork crashes on every message, no VM logs generated, missing AppData\Roaming\Claude
- [FEATURE] first-class session handoff + per-session token budgets for unattended runs
- [FEATURE] Smart paste: convert clipboard code to file reference chips (like Cursor)
- [Feature Request] Restore chat pin functionality to title chat submenu
- [BUG] SIGILL issues with version 2.1.153
- [BUG] Cowork plugin upload fails with generic "Plugin validation failed" when a `description` field in any SKILL.md frontmatter contains angle brackets (`<…>`)
- [BUG] Desktop App 2.1.144+: startup scanner deletes cliSessionId from claude-code-sessions local files on every launch — session not found on disk
- [Feature Request] Add keyboard shortcut to copy last message with proper formatting
- [MODEL] Opus 4.7 not 1M
- Allow naming/renaming background agents in `claude agents` view
- Stale worktrees in .claude/worktrees/ are never cleaned up, consuming massive disk space
- Agent worktrees are never cleaned up, silently consuming disk space
- Subagent worktrees not auto-cleaned when reviewer writes scratch files
- [Bug] Skill initialization hangs for extended duration in Plan Mode
- Claude Desktop writes malformed registry Run entry (nested escaped quotes) - crashes Windows Task Manager and other Run-key parsers
- IME candidate window shows at bottom-right corner instead of caret position (Windows CMD)
- [BUG] Pressing 'Escape' doesn't close the /BTW conversation when the main conversation is asking for approval
- [BUG] Opus 4.7 (1M) intermittently emits empty-string values for tool_use.input fields, killing the session
- FleetView agent UI shows "running" with incrementing elapsed time after agent has returned
- /doctor flags context-scoped cmd+c binding as macOS conflict (false positive)
- [BUG] Text Rendering in Elvish
- Desktop app: Bypass Permissions mode flips to Accept Edits on first prompt (M5 / macOS 26.5)
- [Workaround] Date-Weekday Verification Hook — Prevents Claude from writing wrong weekdays
- [BUG] Claude Code create c:/memfs directory without asking me.
- [BUG] Claude Code's Bash execution waits forever with no processes running
- [BUG] usage stays stuck waiting for 5 hr limit after upgrading to premium seat in team plan
- [Workflow tool] resume cache is unreachable for nontrivial workflows because LLM dispatchers can't transcribe args byte-exactly
- Code review (Preview): "Add a repository" shows no results for private GitHub org repos
- [BUG] /context commands blows up context
- [Feature Request] Add precache expiry hook to enable proactive compaction before token eviction
- [BUG] Context indicator shows 0% at session start despite ~20K+ tokens already loaded
- [Feature Request] Add semantic search for --resume session history
- [Feature Request] Add session search, tagging, and filtering capabilities
- [BUG] Cowork Dispatch reports "desktop not available" on Windows 11 while standard Cowork works normally
- [Bug] Claude Code provides incorrect suggestions with high confidence despite errors
- defaultMode: acceptEdits silently overrides per-path permissions.ask rules for Write/Edit
- [FEATUR configurable tip interval (e.g. tipIntervalSeconds: 30 in settings)E]
- Plugin marketplace fails to load: schema rejects 'displayName' key (v2.1.153)
- claude agents: in-session copy uses broken OSC 52 path while overview correctly uses tmux buffer
- [BUG] Plugin agent descriptions (and custom agents) load unconditionally into context — no parity with disable-model-invocation for skills
- Crashed ultrareview consumed a free credit despite producing zero findings
- [Bug] Character rendering issue - invisible or missing text display
- [BUG] Cowork: processo Claude Code encerra com código 3 — .claude.json não contém token de autenticação (Windows 11 25H2)
- [BUG] 2.1.153 silently discards tools/list response from rmcp 0.12.0 HTTP MCP server (works in 2.1.152, wire-identical handshake)
- VS Code extension: option to auto-resume last session when reopening a workspace folder
- [Bug] Conversation continuation failure
- [BUG] Cowork crashes every time I start a new chat or attempt to continue an existing one in any project. The error displayed is: "Claude Code è andato in crash
- [Bug] Unannounced quota changes
- Native update/install fails with 'socket connection was closed unexpectedly' behind proxy — undici TLS incompatibility
- [BUG] Session name reverting after manual change
- [BUG] 非正常思考,上下文过长时,一直显示思考,点击interrupt按钮失效
- Honor `tools:` frontmatter when an agent is invoked via `@mention` — strip `Task` only when the agent did not declare it
- macOS TCC popup still recurring on v2.1.153 — "2.1.153" would like to access data from other apps
- Claude Code leaks pty handles — exhausts pseudo-terminals on macOS after long session
- [Bug] Agent fails to execute or respond to user input
- [BUG] Persistent "Expecting value: line 1 column 1 (char 0)" JSON parse error after tool execution
- [Feature Request] Implement proactive unit test coverage recommendations for recurring bugs
- VS Code panel lacks status line + terminal lacks image paste in Codespaces, forcing a tradeoff
- `/powerup` only shows ~10 lessons — allow viewing the full catalog
- [Bug] Context contamination after auto-compact with unrelated email draft of Tejo/Sado Basin
- [Bug] VSCode terminal output displays corrupted text with garbled symbols
- [Feature Request] Add LaTeX/KaTeX math rendering to TUI
- [Bug] Sub-agent PR review results not validated by orchestrating agent
- Subagents on Pro 1M tier: trivial probes pass, real workloads fail at first tool call (probe-vs-workload divergence)
- Path-scoped rules and subdirectory CLAUDE.md not loaded when creating new files matching the pattern
- AskUserQuestion: cancelling during extended thinking poisons the whole session with 400 'thinking blocks cannot be modified' (2.1.153); concurrent prompts overwrite each other
- Ideas Missing from Claude Cowork Menu (Windows)
- [BUG_BOUNTY_SAFE_POC_2026] Prompt Injection RCE Test - Command Execution Proof
- [BUG] Cowork scheduled task: execution history row not showing after successful run
- Resuming an extended-thinking session fails permanently with 400 "thinking blocks cannot be modified" (transcript stores thinking text as empty but keeps signature)
- [Bug] Plugin-registered CwdChanged and FileChanged hooks don't fire (settings.json works) — v2.1.153
- Auto-archive on PR merge / branch delete — clarify autoArchiveSessions semantics or add dedicated opt-out
- `claude mcp add` echoes Authorization header value verbatim to stdout, leaks bearer tokens to terminal and session transcripts
- [BUG] Bug report — /insights skill, Claude Code The /insights skill outputs a malformed file path.
- Plugin slash commands render with '*'-inline format instead of two-column, despite matching official plugin shape
- [Bug] Unexpected long text generation without user input or goal
- [Bug] Thinking blocks causing task progression blocked without user modification
- [BUG] (Critical!) contamination by an unknown session simirlar to the report => [Bug] Context contamination after auto-compact with unrelated email draft of Tejo/Sado Basin #63137
- [Critical] Opus 4.7 Korean output degeneration — Korean grammar itself collapses in long contexts
- [BUG] Title: Autocompact buffer persists across /clear — wastes tokens for irrelevant old context
- [Bug] Auto-Compact loses user input before processing in conversation history
- Feature: per-invocation effort parameter + runtime session-config introspection for skills
- Auto-mode classifier mislabels Azure DevOps vote -5 as "Reject" when denying PR vote actions
- [BUG] Claude Desktop and Claude Code CLI never re-register MCP tools after OAuth 2.1 handshake on a remote HTTP server
- [BUG] Workspace file tags leak across sessions
- [BUG] Ink renderer crashes on Windows 11 build 26200 (Canary) duplicate banners, terminal mode leaks, mid-operation aborts
- [BUG] Claude Code Desktop issue
- PTY master fd leak in Claude desktop app exhausts macOS kern.tty.ptmx_max after ~2-3 days
- [BUG] Claude Code — Session Management after Unexpected Interruption
- [Windows] Cowork OpenTelemetry exporter does not initialize - zero events emitted to any destination, including loopback
- [Bug] Opus 4.7: 400 `thinking blocks ... cannot be modified` on long extended-thinking sessions, triggered by history-altering events (scheduled prompts / parallel tool-call cancellation)
- [BUG] API Error: Server is temporarily limiting requests (not your usage limit) · Rate limited
- Multi-plugin custom marketplace: only first plugin registered in installed_plugins.json, skills don't load
- [BUG] Git push through the SDK's git proxy fan-outs into ~500 GitHub REST API calls, exhausting the 5,000/hour budget after a handful of pushes
- [BUG] Claude took liberties it really shouldn't with my global config
- [BUG] Agent window focus lost after navigating with arrow keys, causing scroll deadlock
- [BUG] `--model` flag silently ignored in interactive sessions (works in `--print` only)
- [BUG] Dispatch permanently shows "desktop appears offline" on Windows 11 - never worked on first use
- feat: support per-command enableWeakerNetworkIsolation as safer alternative to dangerouslyDisableSandbox
- /code-review outputs a raw JSON array instead of readable findings
- [BUG] Cowork — Additional allowed domains ignored on Team plan; same domain works on Pro plan
- Haiku
- [Bug] False positive blocking beneficial outcomes in tool execution
- 3P Bedrock SSO: credentials silently expire without triggering re-auth on day 2+
- CLAUDE_AUTOCOMPACT_PCT_OVERRIDE in settings.json env block silently ignored by autocompact logic
- Auto-compaction deletes main session JSONL before verifying summary completion, causing data loss
- [Bug] Claude Code not executing stated actions or producing expected results
- [FEATURE] Deferred Messages — Queue Input for End of Turn
- [BUG] Up/Down arrows in input box navigate history instead of moving cursor — regression in 2.1.149+
- Cancelling a parallel tool-call batch corrupts thinking blocks -> 400 "thinking blocks cannot be modified" permanently wedges the session
- Claude Code caused data loss, then contradicted itself about recovery (two incidents, one session)
- [Bug] Unclear error messages from Claude Code CLI
- [Bug] Agent tool rejecting due to context size limit exceeded
- claude agents: daemon and bg-spare processes spin at ~100% CPU when idle
- [BUG] Compaction fails with "context window limit" error even when context usage is low (e.g., 20%) — regression in v2.1.153
- Remote Control entitlement lost after May 27-28 incident — `Error: Remote Control is not yet enabled for your account` on active Max subscription
- PreToolUse hook exit code 2 does not block Write tool
- [Bug] Thinking blocks in latest assistant message are immutable
- GUI: dispatch file:// and custom-scheme clicks to OS shell handler
- Show current model in statusLine by default
- [Bug] Agent console becomes unresponsive to keyboard input after multiple agents initialized
- [FEATURE] PreToolUse hooks should have a way of updating the environment
- [Bug] Unable to start or use Claude Code CLI
- [BUG] Repository not visible in Claude Code web repo picker
- Session permanently wedged on 400 "thinking blocks cannot be modified" after parallel tool_results
- [Bug] @ autocomplete loses sibling repos after a file edit in multi-repo workspace
- Unclear error message when creating sub-agent without authentication
- [Bug] Anthropic API errors causing frequent failures and high token usage
- [BUG] @ mention file picker only shows packages, not individual files (desktop app - Code tab)
- [Bug] TUI panel footer remains sticky and consumes excessive terminal space
- PR-status polling exhausts GitHub GraphQL rate limit on repos with many open PRs
- [BUG] Windows: welcome panel not shown in some project folders (2.1.153)
- [Bug] Anthropic API Error: thinking blocks corrupted during context compaction with extended thinking enabled
- API 400 "thinking blocks cannot be modified" permanently bricks session during agent activation (interleaved thinking + tool use)
- Right-click Copy copies the whole message instead of the selection; pasted text retains dark background
- Mid-session model switch corrupts conversation when extended thinking is enabled (API 400: 'thinking blocks cannot be modified')
- [BUG] Markdown file links in chat output do not open files when clicked (VS Code extension)
- Stuck retry loop: `400 thinking blocks cannot be modified` on large interleaved-thinking turns using AskUserQuestion
- [FEATURE] Prompt user for approval before auto-compaction proceeds
- Custom MCP connectors not attachable to scheduled routines — no UUID discovery path
- [BUG] Claude in Chrome — Navigation blocked for teams.cloud.microsoft and outlook.cloud.microsoft after Microsoft domain migration**
- [BUG] Claude Desktop — Personal plugins panel renders list but is entirely non-interactive (macOS, v1.9255.2)
- [Bug] error when using Workflows
- [BUG] Persistent "update available" notification despite being on latest version
- [BUG] Sweep Agent from /code-review never completes
- [Bug] Tool calls not executing or returning results
- [FEATURE] Cloud-synced memory and settings across machines
- [Bug] Terminal UI freezes when Ctrl+O view exits during interactive prompt in plan mode
- Continuous api errors when using claude code with Opus 4.7 with thinking on low
- [Feature Request] Add support for installing and using previous Claude Code versions
- [Bug] Extended Thinking: Summarized thinking blocks fail signature validation when resent to API
- [Bug] Anthropic API Error: 'thinking' blocks cannot be modified
- [Bug] Anthropic API Error: Thinking blocks cannot be modified with extended thinking mode
- Feature request: Lazy/on-demand MCP server connections
- [Bug] Tool Arguments Parsed as String Instead of Object
- [Bug] Anthropic API Error: Insufficient context provided
- [Bug] Claude Opus occasionally uses moskovian(russian) orthography instead of Ukrainian in system-prompted responses
- Opus 4.8: backgrounded task completions (subagents AND Bash) crash with 400 "thinking blocks cannot be modified"
- [Bug] Opus 4.7 fabricates stable preferences ("my default") to rationalize arbitrary choices when challenged
- [Bug] Unable to update Claude Code CLI
- [BUG] Desktop app: /remote-control mints link + connects bridge (main.log) but in-chat link/QR panel never renders
- Feature: sessionColor and sessionName in .claude/settings.json
- [BUG] Anthropic API error: thinking blocks
- [FEATURE] Support Remote MCPs in Cowork as in Claude Code
- [Bug] Anthropic API Error: 400 Bad Request with Redacted Thinking - 0 4.7 & 4.8
- [Bug] Anthropic API Error: Cannot modify thinking blocks from different model versions
- Interleaved thinking + multi-tool turn corrupts thinking block (text blanked, signature kept) → permanent 400 'blocks must remain as they were'
- [BUG] Mode/permission changes mid-tool-loop (effortLevel: xhigh) poisons entire session
- Session failure log: Opus 4.6 ignores its own rules for an entire session
- [BUG] "400 Guardrail was enabled" error when using Claude Opus 4.8 with AWS Bedrock
- [Feature Request] Add subagent approach selection option to avoid accidental feedback
- Persistent 400 'thinking blocks in the latest assistant message cannot be modified' — interleaved thinking persisted with empty text + signature bricks sessions
- [BUG] DesktopvsApp
- [BUG] Opus 4.7 cache hit rate collapse after May 27 incident — Messages 1.1k→88.9k in 9 minutes, $630/session
- [Bug] Anthropic API Error: Invalid thinking block format
- [BUG] FUCK CLAUDE
- Opus 4.8 extended thinking: Stop hook block re-entry corrupts thinking blocks → 400
- [Bug] 4.8 Fails when accessing previous model history
- [Bug] Unintended File Modifications During Execution
- [DOCS] Model configuration docs omit lean system prompt default scope and model exceptions
- Add "Always allow globally" option to permission prompts
- Server-side model upgrade (Opus 4.7→4.8) wedges in-flight sessions with `thinking blocks cannot be modified` 400
- [DOCS] AskUserQuestion docs missing multiple-choice prompt decision threshold
- [DOCS] Agent view docs omit shell-command background session launch syntax
- [DOCS] Agent view dispatch input docs incorrectly imply `/logout` dispatches as a prompt
- [DOCS] Claude in Chrome docs omit connected-browser selection behavior
- [DOCS] Plugin docs omit `defaultEnabled: false` for opt-in plugins
- Feature Request: Customizable chat text colors for user and assistant messages
- [DOCS] `/plugin` Discover tab docs omit directory-based suggested plugin pins
- VSCode Chrome integration silently fails: 3 distinct bugs
- [DOCS] MCP stdio docs omit session environment variables
- [Bug] Anthropic API error on second request within session with Claude Opus 4.8
- Cowork emits a blank session "index" handoff on focus when a CLI session is paused awaiting input
- [DOCS] MCP docs omit `claude mcp list/get` pending-approval output for unapproved project servers
- [BUG] /compact fails with 400 error when last assistant turn contains thinking blocks
- [DOCS] `/claude-api` docs omit Opus 4.8 migration guidance
- [DOCS] Fast mode docs still recommend deprecated Opus 4.6 override variable
- [DOCS] Bash tool docs omit `$TMPDIR` consistency across sandboxed and unsandboxed commands
- [Bug] Anthropic API Error: 400 Bad Request on Extended Thinking
- [DOCS] Background session docs omit worktree-isolation behavior for spawned subagents
- Built-in mechanistic self-verification of verifiable claims (symmetric to the auto permission gate)
- [DOCS] Worktree docs do not clarify `worktree.baseRef: "head"` inside linked worktrees
- [BUG] Excessive RAM usage with multiple parallel chats (~10 sessions → 30 GB memory pressure, macOS OOM)
- [DOCS] Managed MCP policy docs omit invalid `allowedMcpServers`/`deniedMcpServers` entry behavior
- [DOCS] Effort docs omit `CLAUDE_CODE_ALWAYS_ENABLE_EFFORT` unsupported-model behavior
- Regression (2.1.147–2.1.150?): resuming an extended-thinking session after a CC update/model-switch → unrecoverable 400, session bricked
- [DOCS] Windows updater docs omit `claude.exe` in-use recovery guidance
- [DOCS] VS Code auto mode docs still tie mode-picker visibility to bypass-permissions setting
- [DOCS] MCP docs omit `/mcp` tool list and detail rendering behavior
- [DOCS] Fine-grained tool streaming docs still describe provider opt-in behavior
- bypassPermissions: session startup reads flat pref, GUI toggle writes per-account pref — they never sync
- [BUG] Claude Desktop Code tab causes disk write limit violation — 8.5GB in 11 min, macOS kills app (M5, v1.9659.1)
- Ultrareview v2.1.96: docs describe /tasks command + claude ultrareview --json subcommand that don't exist; findings hard to read after completion
- I'd be happy to help create a GitHub issue title, but I don't see the error message in your message. Could you please share the specific error you're encountering? That way I can generate an accurate and descriptive issue title for you.
- [BUG] Claude in Chrome `file_upload` rejects all scheduled-task sessions with misleading error (real cause: INVALID_SESSION)
- Extended thinking: signed thinking block 'cannot be modified' (400) permanently wedges session
- RTL text support for Hebrew (and Arabic) in Claude Code
- [Bug] Random errors occurring across multiple operations