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

[bug] v0.8.0 Introduced thinking block bug with Claude Sonnet 4: "AI_APICallError: messages.3.content.0.type: Expected thinking or redacted_thinking, but found text." #1718

New Issue
Closed
opened 2026-02-16 17:32:19 -05:00 by yindo · 7 comments
yindo commented 2026-02-16 17:32:19 -05:00
Owner
Copy Link
Copy Source

Originally created by @grantjayy on GitHub (Sep 14, 2025).

Originally assigned to: @thdxr on GitHub.

When using Claude Sonnet 4 with thinking enabled on Opencode v0.8.0, an Anthropic api error happens after tool invocation. Only happens after tool call (specifically read).

This bug is not present in Opencode v0.7.9.

Here is a share URL of the chat context: https://opencode.ai/s/6z4bcRrU

Here is the full API error (not listed in chat context):

AI_APICallError: messages.3.content.0.type: Expected `thinking` or
`redacted_thinking`, but found `text`. When `thinking` is enabled, a final `assistant`
message must start with a thinking block (preceeding the lastmost set of `tool_use`
and `tool_result` blocks). We recommend you include thinking blocks from previous
turns. To avoid this requirement, disable `thinking`. Please consult our documentation
at https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking

Here is my .opencode.json config:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "anthropic": {
      "options": {
        "headers": {
          "anthropic-beta": "context-1m-2025-08-07"
        }
      },
      "models": {
        "claude-opus-4-1-20250805": {
          "limit": {
            "context": 200000,
            "output": 12288
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 1024
            }
          }
        },
        "claude-sonnet-4-20250514": {
          "limit": {
            "context": 1000000,
            "output": 59904
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 4096
            }
          }
        }
      }
    }
  },
  "agent": {
    "CSS Tailwind (Build)": {
      "mode": "primary",
      "model": "claude-opus-4-1-20250805",
      "description": "Agent for handling HTML with Tailwind CSS",
      "prompt": "{file:<txt-file>}"
    }
  }
}
Originally created by @grantjayy on GitHub (Sep 14, 2025). Originally assigned to: @thdxr on GitHub. When using Claude Sonnet 4 with thinking enabled on Opencode v0.8.0, an Anthropic api error happens after tool invocation. Only happens after tool call (specifically `read`). This bug is not present in Opencode v0.7.9. Here is a share URL of the chat context: https://opencode.ai/s/6z4bcRrU Here is the full API error (not listed in chat context): ``` AI_APICallError: messages.3.content.0.type: Expected `thinking` or `redacted_thinking`, but found `text`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking ``` Here is my .opencode.json config: ``` { "$schema": "https://opencode.ai/config.json", "provider": { "anthropic": { "options": { "headers": { "anthropic-beta": "context-1m-2025-08-07" } }, "models": { "claude-opus-4-1-20250805": { "limit": { "context": 200000, "output": 12288 }, "options": { "thinking": { "type": "enabled", "budgetTokens": 1024 } } }, "claude-sonnet-4-20250514": { "limit": { "context": 1000000, "output": 59904 }, "options": { "thinking": { "type": "enabled", "budgetTokens": 4096 } } } } } }, "agent": { "CSS Tailwind (Build)": { "mode": "primary", "model": "claude-opus-4-1-20250805", "description": "Agent for handling HTML with Tailwind CSS", "prompt": "{file:<txt-file>}" } } } ```
yindo closed this issue 2026-02-16 17:32:19 -05:00
yindo commented 2026-02-16 17:32:20 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 14, 2025):

thanks for raising, looks like it was due to these changes: https://github.com/sst/opencode/pull/2577

@rekram1-node commented on GitHub (Sep 14, 2025): thanks for raising, looks like it was due to these changes: https://github.com/sst/opencode/pull/2577
yindo commented 2026-02-16 17:32:20 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 14, 2025):

I think the issue is that "providerOptions": {
"anthropic": {
"signature": "...."
}
}

Isn't being saved to the reasoning messages

shouldn't be hard to fix just need to find where

@rekram1-node commented on GitHub (Sep 14, 2025): I think the issue is that "providerOptions": { "anthropic": { "signature": "...." } } Isn't being saved to the reasoning messages shouldn't be hard to fix just need to find where
yindo commented 2026-02-16 17:32:20 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 14, 2025):

should be fixed in next release I tested with quite a few models

@rekram1-node commented on GitHub (Sep 14, 2025): should be fixed in next release I tested with quite a few models
yindo commented 2026-02-16 17:32:20 -05:00
Author
Owner
Copy Link
Copy Source

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

I'm running into a similar issue with Claude 4.5 Sonnet hosted on Google Vertex (through openai-compatible proxy: LiteLLM...)

messages.3.content.0.type: Expected `thinking` or `redacted_thinking`, but found `tool_use`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at https://docs.claude.com/en/docs/build-with-claude/extended-thinking

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "messages.3.content.0.type: Expected `thinking` or `redacted_thinking`, but found `tool_use`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at https://docs.claude.com/en/docs/build-with-claude/extended-thinking"
  },
  "request_id": "..."
}

Should I open a separate issue?

@jessevdp commented on GitHub (Oct 2, 2025): I'm running into a similar issue with Claude 4.5 Sonnet hosted on Google Vertex (through openai-compatible proxy: LiteLLM...) ``` messages.3.content.0.type: Expected `thinking` or `redacted_thinking`, but found `tool_use`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at https://docs.claude.com/en/docs/build-with-claude/extended-thinking ``` ```json { "type": "error", "error": { "type": "invalid_request_error", "message": "messages.3.content.0.type: Expected `thinking` or `redacted_thinking`, but found `tool_use`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at https://docs.claude.com/en/docs/build-with-claude/extended-thinking" }, "request_id": "..." } ``` Should I open a separate issue?
yindo commented 2026-02-16 17:32:20 -05:00
Author
Owner
Copy Link
Copy Source

@VisionaryOS commented on GitHub (Dec 27, 2025):

still running into this frequently "messages.101: The final block in an assistant message cannot be thinking" every few tasks with claude opus in opencode

@VisionaryOS commented on GitHub (Dec 27, 2025): still running into this frequently "messages.101: The final block in an assistant message cannot be `thinking`" every few tasks with claude opus in opencode
yindo commented 2026-02-16 17:32:20 -05:00
Author
Owner
Copy Link
Copy Source

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

@VisionaryOS can u share a session?

opencode export > session.json

@rekram1-node commented on GitHub (Dec 27, 2025): @VisionaryOS can u share a session? opencode export > session.json
yindo commented 2026-02-16 17:32:20 -05:00
Author
Owner
Copy Link
Copy Source

@Alumniminium commented on GitHub (Jan 7, 2026):

messages.581.content.0: When thinking is disabled, an assistantmessage in the final position cannot containthinking. To use thinking blocks, enable thinking in your request.

getting this constantly with claude opus with thinking mode on, usually after it calls MCPs, the next message has <thinking> tags visible and then when it stops generating, the error pops

I think this is somehow related to plugins and noReply/ignore messages.

@Alumniminium commented on GitHub (Jan 7, 2026): `messages.581.content.0: When thinking is disabled, an `assistant` message in the final position cannot contain `thinking`. To use thinking blocks, enable `thinking` in your request.` getting this constantly with claude opus with thinking mode on, usually after it calls MCPs, the next message has `<thinking>` tags visible and then when it stops generating, the error pops I think this is somehow related to plugins and noReply/ignore messages.
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#1718
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?