github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13331] {"error":"json: cannot unmarshal object into Go struct field GenerateRequest.format of type string"} #70865

New Issue
Closed
opened 2026-05-04 23:16:36 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-04 23:16:36 -05:00
Owner
Copy Link

Originally created by @ijustlovemath on GitHub (Dec 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13331

What is the issue?

Describe the issue

Hi,

I'm trying to setup mini-swe-agent to help me write some Python code for a fun sideproject. I have 6GB of VRAM and would like to use "deepseek-r1:8b", which I have successfully tested (for speed and access). It's not fast, but it should be serviceable for some overnight testing tasks.

I've setup both .env and mini.yaml in the following ways:

.env

MSWEA_MODEL_NAME="ollama/deepseek-r1:8b"
MSWEA_MODEL_API_KEY=""
MSWEA_CONFIGURED="true"
OPENAI_API_KEY=""
MSWEA_COST_TRACKING="ignore_errors"
OLLAMA_API_BASE="http://localhost:11434"

mini.yaml (defaults not included)

model:
  model_name: "ollama/deepseek-r1:8b"
#  cost_tracking: "ignore_errors"
  model_kwargs:
    temperature: 0.0
    custom_llm_provider: "ollama"
    api_base: "http://localhost:11434"
#    drop_params: true

I then attempted to run a trajectory with the following prompt:

Generate a new C program in fib.c which calculates arbitrary Fibonacci numbers using tail recursion

It then hangs on "Waiting on the LM to respond..."

I tried sending this JSON to ollama directly:

last_mini_run.traj.json

{
      "model": {
        "model_name": "ollama/deepseek-r1:8b",
        "model_kwargs": {
          "temperature": 0.0,
          "custom_llm_provider": "ollama",
          "api_base": "http://localhost:11434"
        },
        "litellm_model_registry": null,
        "set_cache_control": null,
        "cost_tracking": "ignore_errors"
      },
  "info": {
    "exit_status": "EOFError",
    "submission": "",
    "model_stats": {
      "instance_cost": 0.0,
      "api_calls": 0
    },
    "mini_version": "1.17.1",
    "config": {
      "agent": {
        "system_template": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat your response as shown in <format_example>.\n\n<format_example>\nYour reasoning and analysis here. Explain why you want to perform the action.\n\n```bash\nyour_command_here\n```\n</format_example>\n\nFailure to follow these rules will cause your response to be rejected.\n",
        "instance_template": "Please solve this issue: {{task}}\n\nYou can execute bash commands and edit files to implement the necessary changes.\n\n## Recommended Workflow\n\nThis workflows should be done step-by-step so that you can iterate on your changes and any possible problems.\n\n1. Analyze the codebase by finding and reading relevant files\n2. Create a script to reproduce the issue\n3. Edit the source code to resolve the issue\n4. Verify your fix works by running your script again\n5. Test edge cases to ensure your fix is robust\n6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.\n   Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>\n\n## Important Rules\n\n1. Every response must contain exactly one action\n2. The action must be enclosed in triple backticks\n3. Directory or environment variable changes are not persistent. Every action is executed in a new subshell.\n   However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files\n\n<system_information>\n{{system}} {{release}} {{version}} {{machine}}\n</system_information>\n\n## Formatting your response\n\nHere is an example of a correct response:\n\n<example_response>\nTHOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.\n\n```bash\nls -la\n```\n</example_response>\n\n## Useful command examples\n\n### Create a new file:\n\n```bash\ncat <<'EOF' > newfile.py\nimport numpy as np\nhello = \"world\"\nprint(hello)\nEOF\n```\n\n### Edit files with sed:\n\n{%- if system == \"Darwin\" -%}\n<important>\nYou are on MacOS. For all the below examples, you need to use `sed -i ''` instead of `sed -i`.\n</important>\n{%- endif -%}\n\n```bash\n# Replace all occurrences\nsed -i 's/old_string/new_string/g' filename.py\n\n# Replace only first occurrence\nsed -i 's/old_string/new_string/' filename.py\n\n# Replace first occurrence on line 1\nsed -i '1s/old_string/new_string/' filename.py\n\n# Replace all occurrences in lines 1-10\nsed -i '1,10s/old_string/new_string/g' filename.py\n```\n\n### View file content:\n\n```bash\n# View specific lines with numbers\nnl -ba filename.py | sed -n '10,20p'\n```\n\n### Any other command you want to run\n\n```bash\nanything\n```\n",
        "timeout_template": "The last command <command>{{action['action']}}</command> timed out and has been killed.\nThe output of the command was:\n <output>\n{{output}}\n</output>\nPlease try another command and make sure to avoid those requiring interactive input.",
        "format_error_template": "Please always provide EXACTLY ONE action in triple backticks, found {{actions|length}} actions.\nIf you want to end the task, please issue the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`\nwithout any other command.\nElse, please format your response exactly as follows:\n\n<response_example>\nHere are some thoughts about why you want to perform the action.\n\n```bash\n<action>\n```\n</response_example>\n\nNote: In rare cases, if you need to reference a similar format in your command, you might have\nto proceed in two steps, first writing TRIPLEBACKTICKSBASH, then replacing them with ```bash.\n",
        "action_observation_template": "<returncode>{{output.returncode}}</returncode>\n{% if output.output | length < 10000 -%}\n<output>\n{{ output.output -}}\n</output>\n{%- else -%}\n<warning>\nThe output of your last command was too long.\nPlease try a different command that produces less output.\nIf you're looking at a file you can try use head, tail or sed to view a smaller number of lines selectively.\nIf you're using grep or find and it produced too much output, you can use a more selective search pattern.\nIf you really need to see something from the full command's output, you can redirect output to a file and then search in that file.\n</warning>\n{%- set elided_chars = output.output | length - 10000 -%}\n<output_head>\n{{ output.output[:5000] }}\n</output_head>\n<elided_chars>\n{{ elided_chars }} characters elided\n</elided_chars>\n<output_tail>\n{{ output.output[-5000:] }}\n</output_tail>\n{%- endif -%}\n",
        "action_regex": "```bash\\s*\\n(.*?)\\n```",
        "step_limit": 0.0,
        "cost_limit": 3.0,
        "mode": "confirm",
        "whitelist_actions": [],
        "confirm_exit": true
      },
      "model": {
        "model_name": "ollama/deepseek-r1:8b",
        "model_kwargs": {
          "temperature": 0.0,
          "custom_llm_provider": "ollama",
          "api_base": "http://localhost:11434"
        },
        "litellm_model_registry": null,
        "set_cache_control": null,
        "cost_tracking": "ignore_errors"
      },
      "environment": {
        "cwd": "",
        "env": {},
        "timeout": 30
      },
      "agent_type": "minisweagent.agents.interactive.InteractiveAgent",
      "model_type": "minisweagent.models.litellm_model.LitellmModel",
      "environment_type": "minisweagent.environments.local.LocalEnvironment"
    },
    "traceback": "Traceback (most recent call last):\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 81, in step\n    return super().step()\n           ^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/default.py\", line 91, in step\n    return self.get_observation(self.query())\n                                ^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 67, in query\n    return super().query()\n           ^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/default.py\", line 97, in query\n    response = self.model.query(self.messages)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/models/litellm_model.py\", line 71, in query\n    response = self._query(messages, **kwargs)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 338, in wrapped_f\n    return copy(f, *args, **kw)\n           ^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 477, in __call__\n    do = self.iter(retry_state=retry_state)\n         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 378, in iter\n    result = action(retry_state)\n             ^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 400, in <lambda>\n    self._add_action_func(lambda rs: rs.outcome.result())\n                                     ^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/concurrent/futures/_base.py\", line 449, in result\n    return self.__get_result()\n           ^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/concurrent/futures/_base.py\", line 401, in __get_result\n    raise self._exception\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 480, in __call__\n    result = fn(*args, **kwargs)\n             ^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/models/litellm_model.py\", line 61, in _query\n    return litellm.completion(\n           ^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/utils.py\", line 1251, in wrapper\n    result = original_function(*args, **kwargs)\n             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/main.py\", line 3444, in completion\n    response = base_llm_http_handler.completion(\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/llms/custom_httpx/llm_http_handler.py\", line 519, in completion\n    response = self._make_common_sync_call(\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/llms/custom_httpx/llm_http_handler.py\", line 216, in _make_common_sync_call\n    response = sync_httpx_client.post(\n               ^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/llms/custom_httpx/http_handler.py\", line 925, in post\n    response = self.client.send(req, stream=stream)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 914, in send\n    response = self._send_handling_auth(\n               ^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 942, in _send_handling_auth\n    response = self._send_handling_redirects(\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 979, in _send_handling_redirects\n    response = self._send_single_request(request)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 1014, in _send_single_request\n    response = transport.handle_request(request)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_transports/default.py\", line 250, in handle_request\n    resp = self._pool.handle_request(req)\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py\", line 256, in handle_request\n    raise exc from None\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py\", line 236, in handle_request\n    response = connection.handle_request(\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/connection.py\", line 103, in handle_request\n    return self._connection.handle_request(request)\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 136, in handle_request\n    raise exc\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 106, in handle_request\n    ) = self._receive_response_headers(**kwargs)\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 177, in _receive_response_headers\n    event = self._receive_event(timeout=timeout)\n            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 217, in _receive_event\n    data = self._network_stream.read(\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_backends/sync.py\", line 128, in read\n    return self._sock.recv(max_bytes)\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^\nKeyboardInterrupt\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/run/mini.py\", line 97, in main\n    exit_status, result = agent.run(task)  # type: ignore[arg-type]\n                          ^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/default.py\", line 82, in run\n    self.step()\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 84, in step\n    interruption_message = self._prompt_and_handle_special(\n                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 121, in _prompt_and_handle_special\n    user_input = prompt_session.prompt(\"\")\n                 ^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/shortcuts/prompt.py\", line 1055, in prompt\n    return self.app.run(\n           ^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/application/application.py\", line 1002, in run\n    return asyncio.run(coro)\n           ^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/asyncio/runners.py\", line 190, in run\n    return runner.run(main)\n           ^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/asyncio/runners.py\", line 118, in run\n    return self._loop.run_until_complete(task)\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/asyncio/base_events.py\", line 653, in run_until_complete\n    return future.result()\n           ^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/application/application.py\", line 886, in run_async\n    return await _run_async(f)\n           ^^^^^^^^^^^^^^^^^^^\n  File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/application/application.py\", line 746, in _run_async\n    result = await f\n             ^^^^^^^\nEOFError\n"
  },
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat your response as shown in <format_example>.\n\n<format_example>\nYour reasoning and analysis here. Explain why you want to perform the action.\n\n```bash\nyour_command_here\n```\n</format_example>\n\nFailure to follow these rules will cause your response to be rejected.",
      "timestamp": 1764868600.5859184
    },
    {
      "role": "user",
      "content": "Please solve this issue: Generate a new C program in fib.c which calculates arbitrary Fibonacci numbers using tail recursion\n\nYou can execute bash commands and edit files to implement the necessary changes.\n\n## Recommended Workflow\n\nThis workflows should be done step-by-step so that you can iterate on your changes and any possible problems.\n\n1. Analyze the codebase by finding and reading relevant files\n2. Create a script to reproduce the issue\n3. Edit the source code to resolve the issue\n4. Verify your fix works by running your script again\n5. Test edge cases to ensure your fix is robust\n6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.\n   Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>\n\n## Important Rules\n\n1. Every response must contain exactly one action\n2. The action must be enclosed in triple backticks\n3. Directory or environment variable changes are not persistent. Every action is executed in a new subshell.\n   However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files\n\n<system_information>\nLinux 6.6.87.2-microsoft-standard-WSL2 #1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025 x86_64\n</system_information>\n\n## Formatting your response\n\nHere is an example of a correct response:\n\n<example_response>\nTHOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.\n\n```bash\nls -la\n```\n</example_response>\n\n## Useful command examples\n\n### Create a new file:\n\n```bash\ncat <<'EOF' > newfile.py\nimport numpy as np\nhello = \"world\"\nprint(hello)\nEOF\n```\n\n### Edit files with sed:```bash\n# Replace all occurrences\nsed -i 's/old_string/new_string/g' filename.py\n\n# Replace only first occurrence\nsed -i 's/old_string/new_string/' filename.py\n\n# Replace first occurrence on line 1\nsed -i '1s/old_string/new_string/' filename.py\n\n# Replace all occurrences in lines 1-10\nsed -i '1,10s/old_string/new_string/g' filename.py\n```\n\n### View file content:\n\n```bash\n# View specific lines with numbers\nnl -ba filename.py | sed -n '10,20p'\n```\n\n### Any other command you want to run\n\n```bash\nanything\n```",
      "timestamp": 1764868600.5901904
    }
  ],
  "trajectory_format": "mini-swe-agent-1"
}

% cat ~/.config/mini-swe-agent/last_mini_run.traj.json | curl -H "Content-Type: application/json" -X POST --data-binary @- http://localhost:11434/api/generate
{"error":"model '' not found"}%

And when I copy the "model" dict into the root object:

% cat ~/.config/mini-swe-agent/last_mini_run.traj.json | curl -H "Content-Type: application/json" -X POST --data-binary @- http://localhost:11434/api/generate
{"error":"json: cannot unmarshal object into Go struct field GenerateRequest.model of type string"}%

It's at this point I think I must be doing something wrong, and I'm not sure what the next steps are. Any advice is welcome!

Relevant log output

OS

WSL2

GPU

Nvidia

CPU

Intel

Ollama version

0.13.1

Originally created by @ijustlovemath on GitHub (Dec 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13331 ### What is the issue? ### Describe the issue Hi, I'm trying to setup mini-swe-agent to help me write some Python code for a fun sideproject. I have 6GB of VRAM and would like to use "deepseek-r1:8b", which I have successfully tested (for speed and access). It's not fast, but it should be serviceable for some overnight testing tasks. I've setup both .env and mini.yaml in the following ways: ## .env ``` MSWEA_MODEL_NAME="ollama/deepseek-r1:8b" MSWEA_MODEL_API_KEY="" MSWEA_CONFIGURED="true" OPENAI_API_KEY="" MSWEA_COST_TRACKING="ignore_errors" OLLAMA_API_BASE="http://localhost:11434" ``` ## mini.yaml (defaults not included) ``` model: model_name: "ollama/deepseek-r1:8b" # cost_tracking: "ignore_errors" model_kwargs: temperature: 0.0 custom_llm_provider: "ollama" api_base: "http://localhost:11434" # drop_params: true ``` I then attempted to run a trajectory with the following prompt: ``` Generate a new C program in fib.c which calculates arbitrary Fibonacci numbers using tail recursion ``` It then hangs on "`Waiting on the LM to respond...`" I tried sending this JSON to ollama directly: ## last_mini_run.traj.json ``` { "model": { "model_name": "ollama/deepseek-r1:8b", "model_kwargs": { "temperature": 0.0, "custom_llm_provider": "ollama", "api_base": "http://localhost:11434" }, "litellm_model_registry": null, "set_cache_control": null, "cost_tracking": "ignore_errors" }, "info": { "exit_status": "EOFError", "submission": "", "model_stats": { "instance_cost": 0.0, "api_calls": 0 }, "mini_version": "1.17.1", "config": { "agent": { "system_template": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat your response as shown in <format_example>.\n\n<format_example>\nYour reasoning and analysis here. Explain why you want to perform the action.\n\n```bash\nyour_command_here\n```\n</format_example>\n\nFailure to follow these rules will cause your response to be rejected.\n", "instance_template": "Please solve this issue: {{task}}\n\nYou can execute bash commands and edit files to implement the necessary changes.\n\n## Recommended Workflow\n\nThis workflows should be done step-by-step so that you can iterate on your changes and any possible problems.\n\n1. Analyze the codebase by finding and reading relevant files\n2. Create a script to reproduce the issue\n3. Edit the source code to resolve the issue\n4. Verify your fix works by running your script again\n5. Test edge cases to ensure your fix is robust\n6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.\n Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>\n\n## Important Rules\n\n1. Every response must contain exactly one action\n2. The action must be enclosed in triple backticks\n3. Directory or environment variable changes are not persistent. Every action is executed in a new subshell.\n However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files\n\n<system_information>\n{{system}} {{release}} {{version}} {{machine}}\n</system_information>\n\n## Formatting your response\n\nHere is an example of a correct response:\n\n<example_response>\nTHOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.\n\n```bash\nls -la\n```\n</example_response>\n\n## Useful command examples\n\n### Create a new file:\n\n```bash\ncat <<'EOF' > newfile.py\nimport numpy as np\nhello = \"world\"\nprint(hello)\nEOF\n```\n\n### Edit files with sed:\n\n{%- if system == \"Darwin\" -%}\n<important>\nYou are on MacOS. For all the below examples, you need to use `sed -i ''` instead of `sed -i`.\n</important>\n{%- endif -%}\n\n```bash\n# Replace all occurrences\nsed -i 's/old_string/new_string/g' filename.py\n\n# Replace only first occurrence\nsed -i 's/old_string/new_string/' filename.py\n\n# Replace first occurrence on line 1\nsed -i '1s/old_string/new_string/' filename.py\n\n# Replace all occurrences in lines 1-10\nsed -i '1,10s/old_string/new_string/g' filename.py\n```\n\n### View file content:\n\n```bash\n# View specific lines with numbers\nnl -ba filename.py | sed -n '10,20p'\n```\n\n### Any other command you want to run\n\n```bash\nanything\n```\n", "timeout_template": "The last command <command>{{action['action']}}</command> timed out and has been killed.\nThe output of the command was:\n <output>\n{{output}}\n</output>\nPlease try another command and make sure to avoid those requiring interactive input.", "format_error_template": "Please always provide EXACTLY ONE action in triple backticks, found {{actions|length}} actions.\nIf you want to end the task, please issue the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`\nwithout any other command.\nElse, please format your response exactly as follows:\n\n<response_example>\nHere are some thoughts about why you want to perform the action.\n\n```bash\n<action>\n```\n</response_example>\n\nNote: In rare cases, if you need to reference a similar format in your command, you might have\nto proceed in two steps, first writing TRIPLEBACKTICKSBASH, then replacing them with ```bash.\n", "action_observation_template": "<returncode>{{output.returncode}}</returncode>\n{% if output.output | length < 10000 -%}\n<output>\n{{ output.output -}}\n</output>\n{%- else -%}\n<warning>\nThe output of your last command was too long.\nPlease try a different command that produces less output.\nIf you're looking at a file you can try use head, tail or sed to view a smaller number of lines selectively.\nIf you're using grep or find and it produced too much output, you can use a more selective search pattern.\nIf you really need to see something from the full command's output, you can redirect output to a file and then search in that file.\n</warning>\n{%- set elided_chars = output.output | length - 10000 -%}\n<output_head>\n{{ output.output[:5000] }}\n</output_head>\n<elided_chars>\n{{ elided_chars }} characters elided\n</elided_chars>\n<output_tail>\n{{ output.output[-5000:] }}\n</output_tail>\n{%- endif -%}\n", "action_regex": "```bash\\s*\\n(.*?)\\n```", "step_limit": 0.0, "cost_limit": 3.0, "mode": "confirm", "whitelist_actions": [], "confirm_exit": true }, "model": { "model_name": "ollama/deepseek-r1:8b", "model_kwargs": { "temperature": 0.0, "custom_llm_provider": "ollama", "api_base": "http://localhost:11434" }, "litellm_model_registry": null, "set_cache_control": null, "cost_tracking": "ignore_errors" }, "environment": { "cwd": "", "env": {}, "timeout": 30 }, "agent_type": "minisweagent.agents.interactive.InteractiveAgent", "model_type": "minisweagent.models.litellm_model.LitellmModel", "environment_type": "minisweagent.environments.local.LocalEnvironment" }, "traceback": "Traceback (most recent call last):\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 81, in step\n return super().step()\n ^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/default.py\", line 91, in step\n return self.get_observation(self.query())\n ^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 67, in query\n return super().query()\n ^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/default.py\", line 97, in query\n response = self.model.query(self.messages)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/models/litellm_model.py\", line 71, in query\n response = self._query(messages, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 338, in wrapped_f\n return copy(f, *args, **kw)\n ^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 477, in __call__\n do = self.iter(retry_state=retry_state)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 378, in iter\n result = action(retry_state)\n ^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 400, in <lambda>\n self._add_action_func(lambda rs: rs.outcome.result())\n ^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/concurrent/futures/_base.py\", line 449, in result\n return self.__get_result()\n ^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/concurrent/futures/_base.py\", line 401, in __get_result\n raise self._exception\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/tenacity/__init__.py\", line 480, in __call__\n result = fn(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/models/litellm_model.py\", line 61, in _query\n return litellm.completion(\n ^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/utils.py\", line 1251, in wrapper\n result = original_function(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/main.py\", line 3444, in completion\n response = base_llm_http_handler.completion(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/llms/custom_httpx/llm_http_handler.py\", line 519, in completion\n response = self._make_common_sync_call(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/llms/custom_httpx/llm_http_handler.py\", line 216, in _make_common_sync_call\n response = sync_httpx_client.post(\n ^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/litellm/llms/custom_httpx/http_handler.py\", line 925, in post\n response = self.client.send(req, stream=stream)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_client.py\", line 1014, in _send_single_request\n response = transport.handle_request(request)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpx/_transports/default.py\", line 250, in handle_request\n resp = self._pool.handle_request(req)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py\", line 256, in handle_request\n raise exc from None\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py\", line 236, in handle_request\n response = connection.handle_request(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/connection.py\", line 103, in handle_request\n return self._connection.handle_request(request)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 136, in handle_request\n raise exc\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 106, in handle_request\n ) = self._receive_response_headers(**kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 177, in _receive_response_headers\n event = self._receive_event(timeout=timeout)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_sync/http11.py\", line 217, in _receive_event\n data = self._network_stream.read(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/httpcore/_backends/sync.py\", line 128, in read\n return self._sock.recv(max_bytes)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^\nKeyboardInterrupt\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/run/mini.py\", line 97, in main\n exit_status, result = agent.run(task) # type: ignore[arg-type]\n ^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/default.py\", line 82, in run\n self.step()\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 84, in step\n interruption_message = self._prompt_and_handle_special(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/minisweagent/agents/interactive.py\", line 121, in _prompt_and_handle_special\n user_input = prompt_session.prompt(\"\")\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/shortcuts/prompt.py\", line 1055, in prompt\n return self.app.run(\n ^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/application/application.py\", line 1002, in run\n return asyncio.run(coro)\n ^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/asyncio/runners.py\", line 190, in run\n return runner.run(main)\n ^^^^^^^^^^^^^^^^\n File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/asyncio/runners.py\", line 118, in run\n return self._loop.run_until_complete(task)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.pyenv/versions/3.11.3/lib/python3.11/asyncio/base_events.py\", line 653, in run_until_complete\n return future.result()\n ^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/application/application.py\", line 886, in run_async\n return await _run_async(f)\n ^^^^^^^^^^^^^^^^^^^\n File \"/home/someuser/.local/share/uv/tools/mini-swe-agent/lib/python3.11/site-packages/prompt_toolkit/application/application.py\", line 746, in _run_async\n result = await f\n ^^^^^^^\nEOFError\n" }, "messages": [ { "role": "system", "content": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat your response as shown in <format_example>.\n\n<format_example>\nYour reasoning and analysis here. Explain why you want to perform the action.\n\n```bash\nyour_command_here\n```\n</format_example>\n\nFailure to follow these rules will cause your response to be rejected.", "timestamp": 1764868600.5859184 }, { "role": "user", "content": "Please solve this issue: Generate a new C program in fib.c which calculates arbitrary Fibonacci numbers using tail recursion\n\nYou can execute bash commands and edit files to implement the necessary changes.\n\n## Recommended Workflow\n\nThis workflows should be done step-by-step so that you can iterate on your changes and any possible problems.\n\n1. Analyze the codebase by finding and reading relevant files\n2. Create a script to reproduce the issue\n3. Edit the source code to resolve the issue\n4. Verify your fix works by running your script again\n5. Test edge cases to ensure your fix is robust\n6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.\n Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>\n\n## Important Rules\n\n1. Every response must contain exactly one action\n2. The action must be enclosed in triple backticks\n3. Directory or environment variable changes are not persistent. Every action is executed in a new subshell.\n However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files\n\n<system_information>\nLinux 6.6.87.2-microsoft-standard-WSL2 #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025 x86_64\n</system_information>\n\n## Formatting your response\n\nHere is an example of a correct response:\n\n<example_response>\nTHOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.\n\n```bash\nls -la\n```\n</example_response>\n\n## Useful command examples\n\n### Create a new file:\n\n```bash\ncat <<'EOF' > newfile.py\nimport numpy as np\nhello = \"world\"\nprint(hello)\nEOF\n```\n\n### Edit files with sed:```bash\n# Replace all occurrences\nsed -i 's/old_string/new_string/g' filename.py\n\n# Replace only first occurrence\nsed -i 's/old_string/new_string/' filename.py\n\n# Replace first occurrence on line 1\nsed -i '1s/old_string/new_string/' filename.py\n\n# Replace all occurrences in lines 1-10\nsed -i '1,10s/old_string/new_string/g' filename.py\n```\n\n### View file content:\n\n```bash\n# View specific lines with numbers\nnl -ba filename.py | sed -n '10,20p'\n```\n\n### Any other command you want to run\n\n```bash\nanything\n```", "timestamp": 1764868600.5901904 } ], "trajectory_format": "mini-swe-agent-1" } ``` ``` % cat ~/.config/mini-swe-agent/last_mini_run.traj.json | curl -H "Content-Type: application/json" -X POST --data-binary @- http://localhost:11434/api/generate {"error":"model '' not found"}% ``` And when I copy the "model" dict into the root object: ``` % cat ~/.config/mini-swe-agent/last_mini_run.traj.json | curl -H "Content-Type: application/json" -X POST --data-binary @- http://localhost:11434/api/generate {"error":"json: cannot unmarshal object into Go struct field GenerateRequest.model of type string"}% ``` It's at this point I think I must be doing something wrong, and I'm not sure what the next steps are. Any advice is welcome! ### Relevant log output ```shell ``` ### OS WSL2 ### GPU Nvidia ### CPU Intel ### Ollama version 0.13.1
GiteaMirror added the bug label 2026-05-04 23:16:36 -05:00
GiteaMirror commented 2026-05-04 23:16:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 4, 2025):

Most of the stuff in last_mini_run.traj.json is not relevant to the Ollama API.

$ curl -s localhost:11434/api/chat -d '{
  "model":"deepseek-r1:8b",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat your response as shown in <format_example>.\n\n<format_example>\nYour reasoning and analysis here. Explain why you want to perform the action.\n\n```bash\nyour_command_here\n```\n</format_example>\n\nFailure to follow these rules will cause your response to be rejected."
    },
    {
      "role": "user",
      "content": "Please solve this issue: Generate a new C program in fib.c which calculates arbitrary Fibonacci numbers using tail recursion\n\nYou can execute bash commands and edit files to implement the necessary changes.\n\n## Recommended Workflow\n\nThis workflows should be done step-by-step so that you can iterate on your changes and any possible problems.\n\n1. Analyze the codebase by finding and reading relevant files\n2. Create a script to reproduce the issue\n3. Edit the source code to resolve the issue\n4. Verify your fix works by running your script again\n5. Test edge cases to ensure your fix is robust\n6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.\n   Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>\n\n## Important Rules\n\n1. Every response must contain exactly one action\n2. The action must be enclosed in triple backticks\n3. Directory or environment variable changes are not persistent. Every action is executed in a new subshell.\n   However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files\n\n<system_information>\nLinux 6.6.87.2-microsoft-standard-WSL2 #1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025 x86_64\n</system_information>\n\n## Formatting your response\n\nHere is an example of a correct response:\n\n<example_response>\nTHOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.\n\n```bash\nls -la\n```\n</example_response>\n\n## Useful command examples\n\n### Create a new file:\n\n```bash\ncat <<'EOF' > newfile.py\nimport numpy as np\nhello = \"world\"\nprint(hello)\nEOF\n```\n\n### Edit files with sed:```bash\n# Replace all occurrences\nsed -i 's/old_string/new_string/g' filename.py\n\n# Replace only first occurrence\nsed -i 's/old_string/new_string/' filename.py\n\n# Replace first occurrence on line 1\nsed -i '1s/old_string/new_string/' filename.py\n\n# Replace all occurrences in lines 1-10\nsed -i '1,10s/old_string/new_string/g' filename.py\n```\n\n### View file content:\n\n```bash\n# View specific lines with numbers\nnl -ba filename.py | sed -n '10,20p'\n```\n\n### Any other command you want to run\n\n```bash\nanything\n```"
    }
  ],
  "stream":false
}'  | jq -r .message.content
THOUGHT: I need to create a C program that calculates Fibonacci numbers using tail recursion. ...

The server log may provide insight.

<!-- gh-comment-id:3613594276 --> @rick-github commented on GitHub (Dec 4, 2025): Most of the stuff in `last_mini_run.traj.json` is not relevant to the [Ollama API](https://github.com/ollama/ollama/blob/main/docs/api.md). ```console $ curl -s localhost:11434/api/chat -d '{ "model":"deepseek-r1:8b", "messages": [ { "role": "system", "content": "You are a helpful assistant that can interact with a computer.\n\nYour response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).\nInclude a THOUGHT section before your command where you explain your reasoning process.\nFormat your response as shown in <format_example>.\n\n<format_example>\nYour reasoning and analysis here. Explain why you want to perform the action.\n\n```bash\nyour_command_here\n```\n</format_example>\n\nFailure to follow these rules will cause your response to be rejected." }, { "role": "user", "content": "Please solve this issue: Generate a new C program in fib.c which calculates arbitrary Fibonacci numbers using tail recursion\n\nYou can execute bash commands and edit files to implement the necessary changes.\n\n## Recommended Workflow\n\nThis workflows should be done step-by-step so that you can iterate on your changes and any possible problems.\n\n1. Analyze the codebase by finding and reading relevant files\n2. Create a script to reproduce the issue\n3. Edit the source code to resolve the issue\n4. Verify your fix works by running your script again\n5. Test edge cases to ensure your fix is robust\n6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.\n Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>\n\n## Important Rules\n\n1. Every response must contain exactly one action\n2. The action must be enclosed in triple backticks\n3. Directory or environment variable changes are not persistent. Every action is executed in a new subshell.\n However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files\n\n<system_information>\nLinux 6.6.87.2-microsoft-standard-WSL2 #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025 x86_64\n</system_information>\n\n## Formatting your response\n\nHere is an example of a correct response:\n\n<example_response>\nTHOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.\n\n```bash\nls -la\n```\n</example_response>\n\n## Useful command examples\n\n### Create a new file:\n\n```bash\ncat <<'EOF' > newfile.py\nimport numpy as np\nhello = \"world\"\nprint(hello)\nEOF\n```\n\n### Edit files with sed:```bash\n# Replace all occurrences\nsed -i 's/old_string/new_string/g' filename.py\n\n# Replace only first occurrence\nsed -i 's/old_string/new_string/' filename.py\n\n# Replace first occurrence on line 1\nsed -i '1s/old_string/new_string/' filename.py\n\n# Replace all occurrences in lines 1-10\nsed -i '1,10s/old_string/new_string/g' filename.py\n```\n\n### View file content:\n\n```bash\n# View specific lines with numbers\nnl -ba filename.py | sed -n '10,20p'\n```\n\n### Any other command you want to run\n\n```bash\nanything\n```" } ], "stream":false }' | jq -r .message.content THOUGHT: I need to create a C program that calculates Fibonacci numbers using tail recursion. ... ``` The [server log](https://docs.ollama.com/troubleshooting) may provide insight.
GiteaMirror commented 2026-05-04 23:16:41 -05:00
Author
Owner
Copy Link

@ijustlovemath commented on GitHub (Dec 4, 2025):

Here's a test file I made from another project's suggestion:

topost.json

{
    "model": "deepseek-coder:1.3b",
    "messages": [
        {
            "role": "system",
            "content": "You are a d20 dice roller. Do not output any numbers outside the range 1-20. Use a uniform distribution to choose numbers."
        },
        {
            "role": "user",
            "content": "roll a d20."
        }
    ]
}

I then ran it with CURL, and got an interesting response (which was not rolling a d20, nor does it seem like an error):

% cat topost.json | curl -H "Content-Type: application/json" -X POST -d @- http://localhost:11434/api/generate
{"model":"deepseek-coder:1.3b","created_at":"2025-12-04T22:01:19.574329926Z","response":"","done":true,"done_reason":"load"}%

Here's some of the output from journalctl -u ollama after running that:

Dec 04 10:26:17 P53 ollama[102372]: [GIN] 2025/12/04 - 10:26:17 | 200 |        91.7µs |       127.0.0.1 | HEAD     "/"
Dec 04 10:26:17 P53 ollama[102372]: [GIN] 2025/12/04 - 10:26:17 | 404 |     733.799µs |       127.0.0.1 | POST     "/api/show"
Dec 04 10:26:18 P53 ollama[102372]: [GIN] 2025/12/04 - 10:26:18 | 200 |  328.610131ms |       127.0.0.1 | POST     "/api/pull"
Dec 04 10:29:09 P53 ollama[102372]: [GIN] 2025/12/04 - 10:29:09 | 200 |        65.8µs |       127.0.0.1 | HEAD     "/"
Dec 04 10:29:09 P53 ollama[102372]: [GIN] 2025/12/04 - 10:29:09 | 404 |       292.8µs |       127.0.0.1 | POST     "/api/show"
Dec 04 10:29:09 P53 ollama[102372]: time=2025-12-04T10:29:09.980-05:00 level=INFO source=download.go:177 msg="downloading 59bb50d8116b in 16 239 MB part(s)"
Dec 04 10:30:17 P53 ollama[102372]: time=2025-12-04T10:30:17.128-05:00 level=INFO source=download.go:177 msg="downloading a3a0e9449cb6 in 1 13 KB part(s)"
Dec 04 10:30:18 P53 ollama[102372]: time=2025-12-04T10:30:18.267-05:00 level=INFO source=download.go:177 msg="downloading 8893e08fa9f9 in 1 59 B part(s)"
Dec 04 10:30:19 P53 ollama[102372]: time=2025-12-04T10:30:19.402-05:00 level=INFO source=download.go:177 msg="downloading 8972a96b8ff1 in 1 297 B part(s)"
Dec 04 10:30:20 P53 ollama[102372]: time=2025-12-04T10:30:20.708-05:00 level=INFO source=download.go:177 msg="downloading 772f510b9558 in 1 483 B part(s)"
Dec 04 10:30:36 P53 ollama[102372]: [GIN] 2025/12/04 - 10:30:36 | 200 |         1m26s |       127.0.0.1 | POST     "/api/pull"
Dec 04 10:30:36 P53 ollama[102372]: [GIN] 2025/12/04 - 10:30:36 | 200 |     19.2764ms |       127.0.0.1 | POST     "/api/show"
Dec 04 10:30:36 P53 ollama[102372]: [GIN] 2025/12/04 - 10:30:36 | 200 |     22.3223ms |       127.0.0.1 | POST     "/api/show"
Dec 04 10:30:36 P53 ollama[102372]: time=2025-12-04T10:30:36.605-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45163"
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: loaded meta data with 26 key-value pairs and 291 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-59bb50d8116b6a1f9bfbb940d6bb946a05554e591e30c8c2429ed6c854867ecb>
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   0:                       general.architecture str              = llama
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   1:                               general.name str              = deepseek-ai
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   2:                       llama.context_length u32              = 16384
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   4:                          llama.block_count u32              = 32
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 11008
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 32
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000001
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 100000.000000
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  11:                    llama.rope.scaling.type str              = linear
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  12:                  llama.rope.scaling.factor f32              = 4.000000
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  13:                          general.file_type u32              = 2
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = gpt2
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,32256]   = ["!", "\"", "#", "$", "%", "&", "'", ...
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  16:                      tokenizer.ggml.scores arr[f32,32256]   = [0.000000, 0.000000, 0.000000, 0.0000...
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,32256]   = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,31757]   = ["Ġ Ġ", "Ġ t", "Ġ a", "i n", "h e...
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 32013
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 32021
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 32014
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv  25:               general.quantization_version u32              = 2
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - type  f32:   65 tensors
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - type q4_0:  225 tensors
Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - type q6_K:    1 tensors
Dec 04 10:30:37 P53 ollama[102372]: print_info: file format = GGUF V3 (latest)
Dec 04 10:30:37 P53 ollama[102372]: print_info: file type   = Q4_0
Dec 04 10:30:37 P53 ollama[102372]: print_info: file size   = 3.56 GiB (4.54 BPW)
Dec 04 10:30:37 P53 ollama[102372]: load: missing or unrecognized pre-tokenizer type, using: 'default'
Dec 04 10:30:37 P53 ollama[102372]: load: control-looking token:  32015 '<｜fim▁hole｜>' was not control-type; this is probably a bug in the model. its type will be overridden

This last line says "this is probably a bug in the model". I'll try another model, it's possible I just don't have enough VRAM for this. Though I figured if that was the case, it would not have let me run the model in the first place.

<!-- gh-comment-id:3614493109 --> @ijustlovemath commented on GitHub (Dec 4, 2025): Here's a test file I made from another project's suggestion: ## topost.json ``` { "model": "deepseek-coder:1.3b", "messages": [ { "role": "system", "content": "You are a d20 dice roller. Do not output any numbers outside the range 1-20. Use a uniform distribution to choose numbers." }, { "role": "user", "content": "roll a d20." } ] } ``` I then ran it with CURL, and got an interesting response (which was not rolling a d20, nor does it seem like an error): ``` % cat topost.json | curl -H "Content-Type: application/json" -X POST -d @- http://localhost:11434/api/generate {"model":"deepseek-coder:1.3b","created_at":"2025-12-04T22:01:19.574329926Z","response":"","done":true,"done_reason":"load"}% ``` Here's some of the output from `journalctl -u ollama` after running that: ``` Dec 04 10:26:17 P53 ollama[102372]: [GIN] 2025/12/04 - 10:26:17 | 200 | 91.7µs | 127.0.0.1 | HEAD "/" Dec 04 10:26:17 P53 ollama[102372]: [GIN] 2025/12/04 - 10:26:17 | 404 | 733.799µs | 127.0.0.1 | POST "/api/show" Dec 04 10:26:18 P53 ollama[102372]: [GIN] 2025/12/04 - 10:26:18 | 200 | 328.610131ms | 127.0.0.1 | POST "/api/pull" Dec 04 10:29:09 P53 ollama[102372]: [GIN] 2025/12/04 - 10:29:09 | 200 | 65.8µs | 127.0.0.1 | HEAD "/" Dec 04 10:29:09 P53 ollama[102372]: [GIN] 2025/12/04 - 10:29:09 | 404 | 292.8µs | 127.0.0.1 | POST "/api/show" Dec 04 10:29:09 P53 ollama[102372]: time=2025-12-04T10:29:09.980-05:00 level=INFO source=download.go:177 msg="downloading 59bb50d8116b in 16 239 MB part(s)" Dec 04 10:30:17 P53 ollama[102372]: time=2025-12-04T10:30:17.128-05:00 level=INFO source=download.go:177 msg="downloading a3a0e9449cb6 in 1 13 KB part(s)" Dec 04 10:30:18 P53 ollama[102372]: time=2025-12-04T10:30:18.267-05:00 level=INFO source=download.go:177 msg="downloading 8893e08fa9f9 in 1 59 B part(s)" Dec 04 10:30:19 P53 ollama[102372]: time=2025-12-04T10:30:19.402-05:00 level=INFO source=download.go:177 msg="downloading 8972a96b8ff1 in 1 297 B part(s)" Dec 04 10:30:20 P53 ollama[102372]: time=2025-12-04T10:30:20.708-05:00 level=INFO source=download.go:177 msg="downloading 772f510b9558 in 1 483 B part(s)" Dec 04 10:30:36 P53 ollama[102372]: [GIN] 2025/12/04 - 10:30:36 | 200 | 1m26s | 127.0.0.1 | POST "/api/pull" Dec 04 10:30:36 P53 ollama[102372]: [GIN] 2025/12/04 - 10:30:36 | 200 | 19.2764ms | 127.0.0.1 | POST "/api/show" Dec 04 10:30:36 P53 ollama[102372]: [GIN] 2025/12/04 - 10:30:36 | 200 | 22.3223ms | 127.0.0.1 | POST "/api/show" Dec 04 10:30:36 P53 ollama[102372]: time=2025-12-04T10:30:36.605-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45163" Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: loaded meta data with 26 key-value pairs and 291 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-59bb50d8116b6a1f9bfbb940d6bb946a05554e591e30c8c2429ed6c854867ecb> Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 0: general.architecture str = llama Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 1: general.name str = deepseek-ai Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 2: llama.context_length u32 = 16384 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 4: llama.block_count u32 = 32 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 32 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000001 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 10: llama.rope.freq_base f32 = 100000.000000 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 11: llama.rope.scaling.type str = linear Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 12: llama.rope.scaling.factor f32 = 4.000000 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 13: general.file_type u32 = 2 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32256] = ["!", "\"", "#", "$", "%", "&", "'", ... Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32256] = [0.000000, 0.000000, 0.000000, 0.0000... Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,31757] = ["Ġ Ġ", "Ġ t", "Ġ a", "i n", "h e... Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 32013 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 32021 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 32014 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de... Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - kv 25: general.quantization_version u32 = 2 Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - type f32: 65 tensors Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - type q4_0: 225 tensors Dec 04 10:30:37 P53 ollama[102372]: llama_model_loader: - type q6_K: 1 tensors Dec 04 10:30:37 P53 ollama[102372]: print_info: file format = GGUF V3 (latest) Dec 04 10:30:37 P53 ollama[102372]: print_info: file type = Q4_0 Dec 04 10:30:37 P53 ollama[102372]: print_info: file size = 3.56 GiB (4.54 BPW) Dec 04 10:30:37 P53 ollama[102372]: load: missing or unrecognized pre-tokenizer type, using: 'default' Dec 04 10:30:37 P53 ollama[102372]: load: control-looking token: 32015 '<｜fim▁hole｜>' was not control-type; this is probably a bug in the model. its type will be overridden ``` This last line says "this is probably a bug in the model". I'll try another model, it's possible I just don't have enough VRAM for this. Though I figured if that was the case, it would not have let me run the model in the first place.
GiteaMirror commented 2026-05-04 23:16:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 4, 2025):

The /api/generate endpoint does not use "messages", it uses "prompt".

$ curl -s localhost:11434/api/generate -d '{
    "model": "deepseek-coder:1.3b",
    "system": "You are a d20 dice roller. Do not output any numbers outside the range 1-20. Use a uniform distribution to choose numbers.",
    "prompt": "roll a d20.",
    "stream": false
}' | jq -r .response
As an AI, I can't physically perform actions like rolling or simulating physical events such as playing
with dice in real life but you could say that by following these steps using any random number generator
on your computer (using Python for example): 1 to 20 is the range of possible outcomes. Then choose
a single outcome randomly, and then use this method multiple times if needed until it gives all unique
numbers between 1-20 repetitively like in dice rolling simulator games or any simulation you'd want
with such random number generator would be called that out there but I can provide the steps for
anyone who wants to do so.
<!-- gh-comment-id:3614551754 --> @rick-github commented on GitHub (Dec 4, 2025): The `/api/generate` [endpoint](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-completion) does not use `"messages"`, it uses `"prompt"`. ```console $ curl -s localhost:11434/api/generate -d '{ "model": "deepseek-coder:1.3b", "system": "You are a d20 dice roller. Do not output any numbers outside the range 1-20. Use a uniform distribution to choose numbers.", "prompt": "roll a d20.", "stream": false }' | jq -r .response As an AI, I can't physically perform actions like rolling or simulating physical events such as playing with dice in real life but you could say that by following these steps using any random number generator on your computer (using Python for example): 1 to 20 is the range of possible outcomes. Then choose a single outcome randomly, and then use this method multiple times if needed until it gives all unique numbers between 1-20 repetitively like in dice rolling simulator games or any simulation you'd want with such random number generator would be called that out there but I can provide the steps for anyone who wants to do so. ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#70865
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?