anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

LiteLLM error: Anthropic doesn't support tool calling without tools= param specified #1916

New Issue
Closed
opened 2026-02-16 17:33:13 -05:00 by yindo · 14 comments
yindo commented 2026-02-16 17:33:13 -05:00
Owner
Copy Link
Copy Source

Originally created by @jessevdp on GitHub (Oct 2, 2025).

Originally assigned to: @rekram1-node on GitHub.

I'm running into some issues related to my provider: LiteLLM proxy. I realize this is a somewhat niche case, sorry 😬. See my config below.

Is this somehow something I can resolve client side?

AI_APICallError: litellm.UnsupportedParamsError: Anthropic doesn't support tool calling without tools= param specified. Pass tools= param OR set litellm.modify_params = True // litellm_settings::modify_params: True to add dummy tool to the request.

Dummy session with the error (error not shown in web UI for some reason?): https://opencode.ai/s/SWAsOXyz

Image

My config

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "my-litellm-provider": {
      "name": "My LiteLLM Provider",
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://my-provider.com",
        "apiKey": "...",
        "includeUsage": true
      },
      "models": {
        "claude-4-5-sonnet": {
          "name": "Anthropic Claude 4.5 Sonnet",
          "release_date": "2025-09-29",
          "attachment": true,
          "reasoning": true,
          "temperature": true,
          "tool_call": true,
          "limit": {
            "context": 200000,
            "output": 64000
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budget_tokens": 16000,
            },
          }
        },
      }
    }
  }
}
Originally created by @jessevdp on GitHub (Oct 2, 2025). Originally assigned to: @rekram1-node on GitHub. I'm running into some issues related to my provider: LiteLLM proxy. I realize this is a somewhat niche case, sorry 😬. See my config below. Is this somehow something I can resolve client side? > AI_APICallError: litellm.UnsupportedParamsError: Anthropic doesn't support tool calling without `tools=` param specified. Pass `tools=` param OR set `litellm.modify_params = True` // `litellm_settings::modify_params: True` to add dummy tool to the request. **Dummy session with the error** (error not shown in web UI for some reason?): https://opencode.ai/s/SWAsOXyz <img width="1400" height="1008" alt="Image" src="https://github.com/user-attachments/assets/73bd0b1e-ef12-4c92-af1b-463c2a73c3e4" /> ### My config ```json { "$schema": "https://opencode.ai/config.json", "provider": { "my-litellm-provider": { "name": "My LiteLLM Provider", "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "https://my-provider.com", "apiKey": "...", "includeUsage": true }, "models": { "claude-4-5-sonnet": { "name": "Anthropic Claude 4.5 Sonnet", "release_date": "2025-09-29", "attachment": true, "reasoning": true, "temperature": true, "tool_call": true, "limit": { "context": 200000, "output": 64000 }, "options": { "thinking": { "type": "enabled", "budget_tokens": 16000, }, } }, } } } } ```
yindo closed this issue 2026-02-16 17:33:13 -05:00
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@jessevdp commented on GitHub (Oct 2, 2025):

It seems to only happen / error with the thinking options added.

@jessevdp commented on GitHub (Oct 2, 2025): It seems to only happen / error with the `thinking` options added.
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 2, 2025):

@jessevdp is your proxy dropping metadata? it seems like the issue is on your proxy rather than opencode.

If you turn on reasoning we need to keep the reasoning chunks otherwise anthropic with return error

@rekram1-node commented on GitHub (Oct 2, 2025): @jessevdp is your proxy dropping metadata? it seems like the issue is on your proxy rather than opencode. If you turn on reasoning we need to keep the reasoning chunks otherwise anthropic with return error
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@jessevdp commented on GitHub (Oct 3, 2025):

Thanks for getting back to me!

I might have been too quick to come to conclusions. I turned off thinking mode because this LiteLLM proxy distributes between Google Vertex and AWS Bedrock and it seems when forwarding to Vertex thinking mode was giving an error.

(I left a comment on a closed, seemingly sorta related issue https://github.com/sst/opencode/issues/2599#issuecomment-3359320262)

After turning thinking mode off I was back to not getting those tools related error messages and continued work. But later in the day the error messages returned.

What might have happened is that earlier in the day the issue was still there, but LiteLLM was falling back / retrying on Vertex (Bedrock is our main provider) and since thinking was now disabled those requests would succeed. We might have simply run out of Vertex capacity later that day.

What’s interesting is that whenever I get this error and I just type “go” the agent seems fine to just carry on. But that might again just be related to capacity on Google Vertex I suppose…

Anyway, I probably need to do some more digging to figure out what’s happening.

Is there some way to enable a nice HTTP log? That way I can inspect the request that resulted in this issue. I’ve tried log level DEBUG but that doesn’t seem to be it.

@jessevdp commented on GitHub (Oct 3, 2025): Thanks for getting back to me! I might have been too quick to come to conclusions. I turned off thinking mode because this LiteLLM proxy distributes between Google Vertex and AWS Bedrock and it seems when forwarding to Vertex thinking mode was giving an error. (I left a comment on a closed, seemingly sorta related issue https://github.com/sst/opencode/issues/2599#issuecomment-3359320262) After turning thinking mode off I was back to not getting those `tools` related error messages and continued work. But later in the day the error messages returned. What might have happened is that earlier in the day the issue was still there, but LiteLLM was falling back / retrying on Vertex (Bedrock is our main provider) and since thinking was now disabled those requests would succeed. We might have simply run out of Vertex capacity later that day. What’s interesting is that whenever I get this error and I just type “go” the agent seems fine to just carry on. But that might again just be related to capacity on Google Vertex I suppose… --- Anyway, I probably need to do some more digging to figure out what’s happening. Is there some way to enable a nice HTTP log? That way I can inspect the request that resulted in this issue. I’ve tried log level DEBUG but that doesn’t seem to be it.
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 3, 2025):

hm dont think we do any http logs now? I feel like we used to do it may still be possible id have to check

@rekram1-node commented on GitHub (Oct 3, 2025): hm dont think we do any http logs now? I feel like we used to do it may still be possible id have to check
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@mschenk42 commented on GitHub (Oct 25, 2025):

I am also encountering this issue. This appears to occur consistently when the session is compressed either manually or automatically upon reaching the context limit. Otherwise, the system functions flawlessly. Given that it appears to be triggered by compression, it does not appear to be related to using the Lite LLM Proxy.

I wanted to give you a heads up about the configuration. This is the main agent that uses subagents. I'm wondering if there's anything to do with the subagent sessions?

When running without subagents manual compaction works fine.

Image
@mschenk42 commented on GitHub (Oct 25, 2025): I am also encountering this issue. This appears to occur consistently when the session is compressed either manually or automatically upon reaching the context limit. Otherwise, the system functions flawlessly. Given that it appears to be triggered by compression, it does not appear to be related to using the Lite LLM Proxy. I wanted to give you a heads up about the configuration. This is the main agent that uses subagents. I'm wondering if there's anything to do with the subagent sessions? When running without subagents manual compaction works fine. <img width="1701" height="446" alt="Image" src="https://github.com/user-attachments/assets/a8c2af0c-cfcd-4fa8-9c6f-920bd08a8ecf" />
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 25, 2025):

would it be fixed if we just passed an empty tools array when we compact?

@rekram1-node commented on GitHub (Oct 25, 2025): would it be fixed if we just passed an empty tools array when we compact?
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@mschenk42 commented on GitHub (Oct 27, 2025):

Yeah, based on the error message that seems like it would resolve the problem.

@mschenk42 commented on GitHub (Oct 27, 2025): Yeah, based on the error message that seems like it would resolve the problem.
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 27, 2025):

ill try that

@rekram1-node commented on GitHub (Oct 27, 2025): ill try that
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 27, 2025):

Should be fixed by: https://github.com/sst/opencode/commit/0af450575647fc906f017b0065fe3aca227c369f

Will release soon

@rekram1-node commented on GitHub (Oct 27, 2025): Should be fixed by: https://github.com/sst/opencode/commit/0af450575647fc906f017b0065fe3aca227c369f Will release soon
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@mschenk42 commented on GitHub (Oct 28, 2025):

Unfortunately that didn't work. I'm going to reach out to our team that manages our Lite LLM Proxy. Thanks for trying to resolve. I'll share here if I find a way to resolve this.

@mschenk42 commented on GitHub (Oct 28, 2025): Unfortunately that didn't work. I'm going to reach out to our team that manages our Lite LLM Proxy. Thanks for trying to resolve. I'll share here if I find a way to resolve this.
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 28, 2025):

thank you for heads up

@rekram1-node commented on GitHub (Oct 28, 2025): thank you for heads up
yindo commented 2026-02-16 17:33:13 -05:00
Author
Owner
Copy Link
Copy Source

@hewliyang commented on GitHub (Nov 5, 2025):

A long time ago, Anthropic models would throw an error if you submitted a completions request w/ a message history containing tool calls & results - but don't pass in any tools. This is what happens during compaction, where we send the existing conversation history + a summary prompt, but disable all tools, i.e. completion([...existing_history_with_tools, summarize_prompt])

https://github.com/BerriAI/litellm/blob/c45fad3855847715afaebba71926f8e84eb7b355/litellm/llms/anthropic/chat/transformation.py#L672-L686

        if (
            "tools" not in optional_params
            and messages is not None
            and has_tool_call_blocks(messages)
        ):
            if litellm.modify_params:
                optional_params["tools"], _ = self._map_tools(
                    add_dummy_tool(custom_llm_provider="anthropic")
                )
            else:
                raise litellm.UnsupportedParamsError(
                    message="Anthropic doesn't support tool calling without `tools=` param specified. Pass `tools=` param OR set `litellm.modify_params = True` // `litellm_settings::modify_params: True` to add dummy tool to the request.",
                    model="",
                    llm_provider="anthropic",
                )

This is no longer the case (evidenced by the fact that compaction works fine via AI SDK). In the short term you can fix this on the LiteLLM side by running the proxy with modify_params=True, as the error message implies. This will add a dummy tool to the request in this case

https://github.com/BerriAI/litellm/blob/c45fad3855847715afaebba71926f8e84eb7b355/litellm/utils.py#L6809-L6827

def add_dummy_tool(custom_llm_provider: str) -> List[ChatCompletionToolParam]:
    """
    Prevent Anthropic from raising error when tool_use block exists but no tools are provided.

    Relevent Issues: https://github.com/BerriAI/litellm/issues/5388, https://github.com/BerriAI/litellm/issues/5747
    """
    return [
        ChatCompletionToolParam(
            type="function",
            function=ChatCompletionToolParamFunctionChunk(
                name="dummy_tool",
                description="This is a dummy tool call",  # provided to satisfy bedrock constraint.
                parameters={
                    "type": "object",
                    "properties": {},
                },
            ),
        )
    ]

But obviously this is suboptimal because now your arguments can be massaged in unknown ways.

tldr: not an opencode problem, litellm has a lot of footguns

@hewliyang commented on GitHub (Nov 5, 2025): A long time ago, Anthropic models would throw an error if you submitted a completions request w/ a message history containing tool calls & results - but don't pass in any tools. This is what happens during compaction, where we send the existing conversation history + a summary prompt, but disable all tools, i.e. `completion([...existing_history_with_tools, summarize_prompt])` https://github.com/BerriAI/litellm/blob/c45fad3855847715afaebba71926f8e84eb7b355/litellm/llms/anthropic/chat/transformation.py#L672-L686 ```py if ( "tools" not in optional_params and messages is not None and has_tool_call_blocks(messages) ): if litellm.modify_params: optional_params["tools"], _ = self._map_tools( add_dummy_tool(custom_llm_provider="anthropic") ) else: raise litellm.UnsupportedParamsError( message="Anthropic doesn't support tool calling without `tools=` param specified. Pass `tools=` param OR set `litellm.modify_params = True` // `litellm_settings::modify_params: True` to add dummy tool to the request.", model="", llm_provider="anthropic", ) ``` This is no longer the case (evidenced by the fact that compaction works fine via AI SDK). In the short term you can fix this on the LiteLLM side by running the proxy with `modify_params=True`, as the error message implies. This will add a dummy tool to the request in this case https://github.com/BerriAI/litellm/blob/c45fad3855847715afaebba71926f8e84eb7b355/litellm/utils.py#L6809-L6827 ```py def add_dummy_tool(custom_llm_provider: str) -> List[ChatCompletionToolParam]: """ Prevent Anthropic from raising error when tool_use block exists but no tools are provided. Relevent Issues: https://github.com/BerriAI/litellm/issues/5388, https://github.com/BerriAI/litellm/issues/5747 """ return [ ChatCompletionToolParam( type="function", function=ChatCompletionToolParamFunctionChunk( name="dummy_tool", description="This is a dummy tool call", # provided to satisfy bedrock constraint. parameters={ "type": "object", "properties": {}, }, ), ) ] ``` But obviously this is suboptimal because now your arguments can be massaged in unknown ways. tldr: not an opencode problem, litellm has a lot of footguns
yindo commented 2026-02-16 17:33:14 -05:00
Author
Owner
Copy Link
Copy Source

@geoHeil commented on GitHub (Dec 29, 2025):

For me, the native pass-through works much better

  "provider": {
    "my-litellm": {
    "my-anthropic": {
      "npm": "@ai-sdk/anthropic",
      "name": "my LiteLLM (Anthropic native)",
      "options": {
        "baseURL": "https://llm.my.corp.com/anthropic/v1",
        "apiKey": "{env:MY_KEY}"
      },
@geoHeil commented on GitHub (Dec 29, 2025): For me, the native pass-through works much better ``` "provider": { "my-litellm": { "my-anthropic": { "npm": "@ai-sdk/anthropic", "name": "my LiteLLM (Anthropic native)", "options": { "baseURL": "https://llm.my.corp.com/anthropic/v1", "apiKey": "{env:MY_KEY}" }, ```
yindo commented 2026-02-16 17:33:14 -05:00
Author
Owner
Copy Link
Copy Source

@danielfrg commented on GitHub (Jan 13, 2026):

I understand this is not an opencode problem directly but its hard to make changes on existing deployments in large companies. This is not the end of the world since a new session is usually fine to continue existing work but a workaround in the config would be nice, maybe a way to set a dummy tool in all calls so compaction works?

@danielfrg commented on GitHub (Jan 13, 2026): I understand this is not an opencode problem directly but its hard to make changes on existing deployments in large companies. This is not the end of the world since a new session is usually fine to continue existing work but a workaround in the config would be nice, maybe a way to set a dummy tool in all calls so compaction works?
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#1916
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?