[Bug]: Improved Integration for Microsoft Foundry

### Bug Description

The delegation for Microsoft Foundry (Anthropic) is not functioning as expected. The API mode `anthropic_messages` is being ignored, resulting in 404 errors.

    **Current Configuration:**
    - **Main Model:** claude-opus-4.6 via Microsoft Foundry (foundry.services.ai.azure.com)
    - **Delegation Configuration:**
      - API Mode set to `anthropic_messages`
      - API Key: (hidden for security)

    - **Smart Routing Configuration:**
      - Currently uses gpt-4o-mini via GitHub Copilot for simple queries.

 **Issue Details:**
    When trying to delegate tasks to Microsoft Foundry, the requests return a 404 error as the system defaults to an incorrect API path instead of the appropriate `anthropic_messages`. The integration seems to ignore the proper configuration settings.

    It would be helpful to revisit the integration process to enable seamless utilization of Azure Foundry as a delegation provider.

### Steps to Reproduce

1. Configure Hermes with the following delegation settings:
       - Set `provider: custom`
       - Set `base_url` to `https://foundry.services.ai.azure.com/anthropic`
       - Set `api_mode` to `anthropic_messages`
       - Include the appropriate API Key.
2. Attempt to delegate a task using the command:
       `delegate_task({"goal": "Test delegation.", "toolsets": ["terminal"]})`
3. Observe the error returned is a 404: "Resource not found".

### Expected Behavior

When delegating tasks to Microsoft Foundry, the system should:
    - Successfully identify and utilize the `anthropic_messages` API mode.
    - Return a proper response based on the task delegated, without resulting in a 404 error.

### Actual Behavior

The requests to delegate tasks return a 404 error, indicating that the API mode `anthropic_messages` is not recognized. The system defaults to an incorrect API path instead of utilizing the proper configuration settings, leading to failure in task delegation.

### Affected Component

CLI (interactive chat)

### Messaging Platform (if gateway-related)

_No response_

### Debug Report

```shell
--- hermes dump ---
version:          0.9.0 (2026.4.13) [e69526be]
os:               Linux 6.6.87.2-microsoft-standard-WSL2 x86_64
python:           3.11.15
openai_sdk:       2.31.0
profile:          default
hermes_home:      ~/.hermes
model:            claude-opus-4-6
provider:         custom
terminal:         local

api_keys:
  openrouter           not set
  openai               not set
  anthropic            set
  anthropic_token      not set
  nous                 not set
  glm/zai              not set
  zai                  not set
  kimi                 not set
  minimax              not set
  deepseek             not set
  dashscope            not set
  huggingface          not set
  ai_gateway           not set
  opencode_zen         not set
  opencode_go          not set
  kilocode             not set
  firecrawl            not set
  tavily               not set
  browserbase          not set
  fal                  not set
  elevenlabs           not set
  github               not set

features:
  toolsets:           hermes-cli
  mcp_servers:        0
  memory_provider:    built-in
  gateway:            stopped
  platforms:          none
  cron_jobs:          0
  skills:             79

config_overrides:
  display.streaming: True
  smart_model_routing.enabled: True
--- end dump ---


--- agent.log (last 200 lines) ---
2026-04-15 10:09:21,757 ERROR [20260415_100918_151563] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:10:01,722 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:10:01,766 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 10:10:55,220 INFO run_agent: Loaded environment variables from /home/user/.hermes/.env
2026-04-15 10:10:56,718 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:10:56,927 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:10:57,238 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:11:05,146 INFO agent.model_metadata: Could not detect context length for model 'gpt-5.4-mini' at https://stumm-foundry.openai.azure.com/openai/v1 — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:11:09,314 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:11:09,369 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (gpt-5.4-mini)
2026-04-15 10:11:13,160 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 10:11:13,161 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:11:21,054 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:11:21,100 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-haiku-4-5)
2026-04-15 10:11:25,520 INFO [20260415_095319_fad3a7] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (gpt-5.4-mini)
2026-04-15 10:11:26,010 ERROR [20260415_101125_155807] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:12:34,800 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:12:34,843 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (gpt-5.4-mini)
2026-04-15 10:13:50,043 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:13:50,089 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-haiku-4-5)
2026-04-15 10:16:01,038 INFO agent.model_metadata: Could not detect context length for model 'claude-opus-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:16:01,038 INFO root: Model switched in-place: claude-haiku-4-5 (custom) -> claude-opus-4-6 (custom:stumm-foundry.services.ai.azure.com)
2026-04-15 10:16:01,039 INFO agent.model_metadata: Could not detect context length for model 'claude-opus-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:16:13,001 INFO root: Model switched in-place: claude-opus-4-6 (custom:stumm-foundry.services.ai.azure.com) -> claude-opus-4-6 (anthropic)
2026-04-15 10:17:06,368 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:17:06,847 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider anthropic (claude-opus-4-6)
2026-04-15 10:17:08,494 INFO [20260415_095319_fad3a7] agent.model_metadata: Could not detect context length for model 'claude-sonnet-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:17:08,495 INFO [20260415_095319_fad3a7] root: Fallback activated: claude-opus-4-6 → claude-sonnet-4-6 (custom)
2026-04-15 10:17:15,105 INFO [20260415_095319_fad3a7] agent.auxiliary_client: Auxiliary flush_memories: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:17:15,470 INFO [20260415_095319_fad3a7] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-sonnet-4-6)
2026-04-15 10:17:15,483 INFO [20260415_095319_fad3a7] agent.auxiliary_client: Auxiliary compression: using auto (claude-sonnet-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:17:15,843 WARNING [20260415_095319_fad3a7] root: Failed to generate context summary: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}. Further summary attempts paused for 60 seconds.
2026-04-15 10:17:22,973 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:17:51,322 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:17:51,366 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-haiku-4-5)
2026-04-15 10:18:17,812 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:18:17,864 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-haiku-4-5)
2026-04-15 10:21:22,348 INFO anthropic._base_client: Retrying request to /v1/messages in 60.000000 seconds
2026-04-15 10:23:54,634 INFO anthropic._base_client: Retrying request to /v1/messages in 41.000000 seconds
2026-04-15 10:24:33,604 INFO run_agent: Loaded environment variables from /home/user/.hermes/.env
2026-04-15 10:24:35,048 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:24:35,266 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:24:35,589 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:25:15,021 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:25:15,070 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-haiku-4-5)
2026-04-15 10:25:33,679 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 10:25:33,679 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:25:38,605 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:25:38,717 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:25:38,766 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-haiku-4-5)
2026-04-15 10:25:39,190 ERROR [20260415_102538_adfb42] root: Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:25:58,878 INFO agent.model_metadata: Could not detect context length for model 'claude-opus-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:25:58,878 INFO root: Model switched in-place: claude-haiku-4-5 (custom) -> claude-opus-4-6 (custom)
2026-04-15 10:25:58,879 INFO agent.model_metadata: Could not detect context length for model 'claude-opus-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:26:59,875 INFO [20260415_102434_923956] agent.model_metadata: Could not detect context length for model 'claude-sonnet-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:26:59,875 INFO [20260415_102434_923956] root: Fallback activated: claude-opus-4-6 → claude-sonnet-4-6 (custom)
2026-04-15 10:27:04,695 WARNING [20260415_102434_923956] root: Invalid API response (retry 1/3): response.content is empty | Provider: model=claude-sonnet-4-6
2026-04-15 10:27:13,627 WARNING [20260415_102434_923956] root: Invalid API response (retry 2/3): response.content is empty | Provider: model=claude-sonnet-4-6
2026-04-15 10:27:27,760 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:27:28,047 INFO [20260415_102434_923956] root: Primary runtime restored for new turn: claude-opus-4-6 (custom)
2026-04-15 10:28:06,707 INFO anthropic._base_client: Retrying request to /v1/messages in 24.000000 seconds
2026-04-15 10:28:31,215 INFO anthropic._base_client: Retrying request to /v1/messages in 0.988707 seconds
2026-04-15 10:29:31,230 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:29:31,273 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 10:29:38,875 INFO anthropic._base_client: Retrying request to /v1/messages in 0.442634 seconds
2026-04-15 10:29:39,319 INFO anthropic._base_client: Retrying request to /v1/messages in 0.857219 seconds
2026-04-15 10:29:44,507 INFO [20260415_102434_923956] agent.model_metadata: Could not detect context length for model 'gpt-5.4-mini' at https://stumm-foundry.openai.azure.com/openai/v1 — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:29:44,525 INFO [20260415_102434_923956] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (gpt-5.4-mini)
2026-04-15 10:29:45,001 ERROR [20260415_102942_87d4ee] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:31:10,099 INFO run_agent: Loaded environment variables from /home/user/.hermes/.env
2026-04-15 10:31:11,585 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:31:11,792 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:31:12,097 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:31:40,809 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:31:40,853 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 10:31:46,312 INFO [20260415_102434_923956] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 10:31:46,815 ERROR [20260415_103146_9a0be1] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:35:03,715 ERROR asyncio: Task exception was never retrieved
future: <Task finished name='Task-441' coro=<Application._handle_exception.<locals>.in_term() done, defined at /home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py:1018> exception=OSError(5, 'Input/output error')>
Traceback (most recent call last):
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 649, in sleep
    return await future
           ^^^^^^^^^^^^
asyncio.exceptions.CancelledError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 190, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 641, in run_until_complete
    self.run_forever()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 608, in run_forever
    self._run_once()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 1936, in _run_once
    handle._run()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/events.py", line 84, in _run
    self._context.run(self._callback, *self._args)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 1226, in _poll_output_size
    await asyncio.sleep(interval)
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 651, in sleep
    h.cancel()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/events.py", line 151, in cancel
    def cancel(self):

  File "/home/user/.hermes/hermes-agent/cli.py", line 9682, in _signal_handler
    raise KeyboardInterrupt()
KeyboardInterrupt

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 1026, in in_term
    await _do_wait_for_enter("Press ENTER to continue...")
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 1545, in _do_wait_for_enter
    await session.app.run_async()
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 886, in run_async
    return await _run_async(f)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 739, in _run_async
    self._redraw()
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 543, in _redraw
    self.context.copy().run(run_in_context)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 526, in run_in_context
    self.renderer.render(self, self.layout)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/renderer.py", line 726, in render
    output.flush()
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/output/vt100.py", line 706, in flush
    flush_stdout(self.stdout, data)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/output/flush_stdout.py", line 37, in flush_stdout
    stdout.flush()
OSError: [Errno 5] Input/output error
2026-04-15 10:40:49,647 INFO agent.model_metadata: Could not detect context length for model 'claude-opus-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:40:49,647 INFO root: Model switched in-place: claude-haiku-4-5 (custom) -> claude-opus-4-6 (custom:stumm-foundry.services.ai.azure.com)
2026-04-15 10:40:49,647 INFO agent.model_metadata: Could not detect context length for model 'claude-opus-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:41:04,246 INFO root: Model switched in-place: claude-opus-4-6 (custom:stumm-foundry.services.ai.azure.com) -> claude-opus-4-6 (anthropic)
2026-04-15 10:41:21,417 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 10:41:21,839 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider anthropic (claude-opus-4-6)
2026-04-15 10:41:22,395 INFO [20260415_095052_95f7b6] agent.model_metadata: Could not detect context length for model 'claude-sonnet-4-6' at https://stumm-foundry.services.ai.azure.com/anthropic/ — defaulting to 128,000 tokens (probe-down). Set model.context_length in config.yaml to override.
2026-04-15 10:41:22,395 INFO [20260415_095052_95f7b6] root: Fallback activated: claude-opus-4-6 → claude-sonnet-4-6 (custom)
2026-04-15 10:41:31,299 INFO [20260415_095052_95f7b6] agent.auxiliary_client: Auxiliary flush_memories: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:41:31,702 INFO [20260415_095052_95f7b6] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-sonnet-4-6)
2026-04-15 10:41:31,714 INFO [20260415_095052_95f7b6] agent.auxiliary_client: Auxiliary compression: using auto (claude-sonnet-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 10:41:32,105 WARNING [20260415_095052_95f7b6] root: Failed to generate context summary: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}. Further summary attempts paused for 600 seconds.
2026-04-15 10:43:19,949 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/
2026-04-15 11:16:18,250 INFO run_agent: Loaded environment variables from /home/user/.hermes/.env
2026-04-15 11:16:20,176 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:16:20,390 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:16:20,726 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:19:19,584 INFO run_agent: Loaded environment variables from /home/user/.hermes/.env
2026-04-15 11:19:21,000 INFO agent.auxiliary_client: Vision auto-detect: using active provider copilot (claude-opus-4.6)
2026-04-15 11:19:21,058 INFO agent.auxiliary_client: Vision auto-detect: using active provider copilot (claude-opus-4.6)
2026-04-15 11:19:21,327 INFO agent.auxiliary_client: Vision auto-detect: using active provider copilot (claude-opus-4.6)
2026-04-15 11:20:00,571 INFO agent.auxiliary_client: Vision auto-detect: using active provider copilot (claude-opus-4.6)
2026-04-15 11:20:00,626 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider copilot (claude-opus-4.6)
2026-04-15 11:20:16,094 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider copilot (claude-opus-4.6)
2026-04-15 11:20:16,094 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (claude-opus-4.6) at https://api.githubcopilot.com
2026-04-15 11:24:49,179 INFO run_agent: Loaded environment variables from /home/user/.hermes/.env
2026-04-15 11:24:50,785 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:24:50,991 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:24:51,304 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:25:13,064 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:25:14,095 WARNING root: Failed to fetch model metadata from OpenRouter: HTTPSConnectionPool(host='openrouter.ai', port=443): Max retries exceeded with url: /api/v1/models (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))
2026-04-15 11:25:14,114 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider copilot (gpt-4o-mini)
2026-04-15 11:25:52,861 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:25:52,902 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 11:26:09,834 INFO [20260415_111920_6f0944] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 11:26:10,184 ERROR [20260415_112609_e35c88] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:26:23,296 INFO [20260415_112609_e35c88] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 11:26:23,847 ERROR [20260415_112623_c4c0ea] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:26:38,473 INFO [20260415_112623_c4c0ea] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 11:26:38,897 ERROR [20260415_112638_e324c4] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:26:58,112 INFO [20260415_112638_e324c4] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 11:26:58,534 ERROR [20260415_112658_29af91] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:27:08,720 INFO run_agent: Loaded environment variables from /home/user/.hermes/.env
2026-04-15 11:27:10,263 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:27:10,470 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:27:10,793 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:27:18,988 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:27:19,811 WARNING root: Failed to fetch model metadata from OpenRouter: HTTPSConnectionPool(host='openrouter.ai', port=443): Max retries exceeded with url: /api/v1/models (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))
2026-04-15 11:27:19,829 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider copilot (gpt-4o-mini)
2026-04-15 11:27:23,713 INFO [20260415_111920_6f0944] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4.6)
2026-04-15 11:27:24,271 ERROR [20260415_112723_10b964] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted
2026-04-15 11:27:45,297 INFO [20260415_112723_10b964] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4.6)
2026-04-15 11:27:45,816 ERROR [20260415_112745_0ff584] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted
2026-04-15 11:28:20,145 INFO [20260415_112745_0ff584] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4.6)
2026-04-15 11:28:20,687 ERROR [20260415_112820_e99965] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted
2026-04-15 11:29:03,194 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:29:03,244 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 11:30:11,805 INFO agent.auxiliary_client: Vision auto-detect: using active provider custom (claude-opus-4-6)
2026-04-15 11:30:12,517 WARNING root: Failed to fetch model metadata from OpenRouter: HTTPSConnectionPool(host='openrouter.ai', port=443): Max retries exceeded with url: /api/v1/models (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))
2026-04-15 11:30:12,539 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider copilot (gpt-4o-mini)
2026-04-15 11:30:16,108 INFO [20260415_111920_6f0944] agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4.6)
2026-04-15 11:30:16,638 ERROR [20260415_113016_834aeb] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted
2026-04-15 11:37:35,088 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider custom (claude-opus-4-6)
2026-04-15 11:37:35,101 INFO agent.auxiliary_client: Auxiliary flush_memories: using auto (claude-opus-4-6) at https://stumm-foundry.services.ai.azure.com/anthropic/

--- errors.log (last 100 lines) ---
2026-04-14 13:52:53,723 ERROR [20260414_135247_c190d2] root: Non-retryable client error: Error code: 404 - {'error': {'code': 'api_not_supported', 'message': 'Requested API is currently not supported', 'details': 'Requested API is currently not supported'}}
2026-04-14 13:55:36,472 ERROR [20260414_135533_f93a0b] root: Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-14 13:57:47,373 ERROR [20260414_135744_8943a2] root: Non-retryable client error: Error code: 404 - {'error': {'code': 'api_not_supported', 'message': 'Requested API is currently not supported', 'details': 'Requested API is currently not supported'}}
2026-04-14 14:38:00,292 ERROR [20260414_143759_0d2033] root: Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-14 14:44:15,995 ERROR [20260414_144415_f48275] root: [subagent-1] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-14 14:44:15,996 ERROR [20260414_144415_adfe39] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-14 14:44:16,019 ERROR [20260414_144415_26d692] root: [subagent-2] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-14 15:14:32,617 ERROR [20260414_151432_b6ec31] root: Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 09:52:13,175 ERROR [20260415_095210_93c03c] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 09:56:46,581 ERROR [20260415_095646_c524d6] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 09:58:20,037 ERROR [20260415_095819_c3dda2] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:02:11,344 ERROR [20260415_100210_a715e7] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:05:33,012 ERROR [20260415_100529_d23d6f] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:09:21,757 ERROR [20260415_100918_151563] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:11:26,010 ERROR [20260415_101125_155807] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:17:15,843 WARNING [20260415_095319_fad3a7] root: Failed to generate context summary: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}. Further summary attempts paused for 60 seconds.
2026-04-15 10:25:39,190 ERROR [20260415_102538_adfb42] root: Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:27:04,695 WARNING [20260415_102434_923956] root: Invalid API response (retry 1/3): response.content is empty | Provider: model=claude-sonnet-4-6
2026-04-15 10:27:13,627 WARNING [20260415_102434_923956] root: Invalid API response (retry 2/3): response.content is empty | Provider: model=claude-sonnet-4-6
2026-04-15 10:29:45,001 ERROR [20260415_102942_87d4ee] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:31:46,815 ERROR [20260415_103146_9a0be1] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 10:35:03,715 ERROR asyncio: Task exception was never retrieved
future: <Task finished name='Task-441' coro=<Application._handle_exception.<locals>.in_term() done, defined at /home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py:1018> exception=OSError(5, 'Input/output error')>
Traceback (most recent call last):
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 649, in sleep
    return await future
           ^^^^^^^^^^^^
asyncio.exceptions.CancelledError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 190, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 641, in run_until_complete
    self.run_forever()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 608, in run_forever
    self._run_once()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 1936, in _run_once
    handle._run()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/events.py", line 84, in _run
    self._context.run(self._callback, *self._args)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 1226, in _poll_output_size
    await asyncio.sleep(interval)
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 651, in sleep
    h.cancel()
  File "/home/user/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/events.py", line 151, in cancel
    def cancel(self):

  File "/home/user/.hermes/hermes-agent/cli.py", line 9682, in _signal_handler
    raise KeyboardInterrupt()
KeyboardInterrupt

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 1026, in in_term
    await _do_wait_for_enter("Press ENTER to continue...")
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 1545, in _do_wait_for_enter
    await session.app.run_async()
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 886, in run_async
    return await _run_async(f)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 739, in _run_async
    self._redraw()
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 543, in _redraw
    self.context.copy().run(run_in_context)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/application/application.py", line 526, in run_in_context
    self.renderer.render(self, self.layout)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/renderer.py", line 726, in render
    output.flush()
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/output/vt100.py", line 706, in flush
    flush_stdout(self.stdout, data)
  File "/home/user/.hermes/hermes-agent/venv/lib/python3.11/site-packages/prompt_toolkit/output/flush_stdout.py", line 37, in flush_stdout
    stdout.flush()
OSError: [Errno 5] Input/output error
2026-04-15 10:41:32,105 WARNING [20260415_095052_95f7b6] root: Failed to generate context summary: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}. Further summary attempts paused for 600 seconds.
2026-04-15 11:25:14,095 WARNING root: Failed to fetch model metadata from OpenRouter: HTTPSConnectionPool(host='openrouter.ai', port=443): Max retries exceeded with url: /api/v1/models (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))
2026-04-15 11:26:10,184 ERROR [20260415_112609_e35c88] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:26:23,847 ERROR [20260415_112623_c4c0ea] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:26:38,897 ERROR [20260415_112638_e324c4] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:26:58,534 ERROR [20260415_112658_29af91] root: [subagent-0] Non-retryable client error: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2026-04-15 11:27:19,811 WARNING root: Failed to fetch model metadata from OpenRouter: HTTPSConnectionPool(host='openrouter.ai', port=443): Max retries exceeded with url: /api/v1/models (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))
2026-04-15 11:27:24,271 ERROR [20260415_112723_10b964] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted
2026-04-15 11:27:45,816 ERROR [20260415_112745_0ff584] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted
2026-04-15 11:28:20,687 ERROR [20260415_112820_e99965] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted
2026-04-15 11:30:12,517 WARNING root: Failed to fetch model metadata from OpenRouter: HTTPSConnectionPool(host='openrouter.ai', port=443): Max retries exceeded with url: /api/v1/models (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))
2026-04-15 11:30:16,638 ERROR [20260415_113016_834aeb] root: [subagent-0] Non-retryable client error: bad request: Authorization header is badly formatted

--- gateway.log (last 100 lines) ---
```

### Operating System

WSL2 Debian 13

### Python Version

3.13.5

### Hermes Version

v0.9.0 (2026.4.13)

### Additional Logs / Traceback (optional)

```shell

```

### 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

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Bug]: Improved Integration for Microsoft Foundry #10213

Bug Description

Steps to Reproduce

Expected Behavior

Actual Behavior

Affected Component

Messaging Platform (if gateway-related)

Debug Report

Operating System

Python Version

Hermes Version

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

Proposed Fix (optional)

Are you willing to submit a PR for this?

Metadata

Assignees

Labels

Type

Fields

Projects

Milestone

Relationships

Development

[Bug]: Improved Integration for Microsoft Foundry #10213

Description

Bug Description

Steps to Reproduce

Expected Behavior

Actual Behavior

Affected Component

Messaging Platform (if gateway-related)

Debug Report

Operating System

Python Version

Hermes Version

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

Proposed Fix (optional)

Are you willing to submit a PR for this?

Metadata

Metadata

Assignees

Labels

Type

Fields

Projects

Milestone

Relationships

Development

Issue actions