agent: Fix issue with Anthropic thinking models (#33317)
cc @osyvokon We were seeing a bunch of errors in our backend when people were using Claude models with thinking enabled. In the logs we would see > an error occurred while interacting with the Anthropic API: invalid_request_error: messages.x.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 However, this issue did not occur frequently and was not easily reproducible. Turns out it was triggered by us not correctly handling [Redacted Thinking Blocks](https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#thinking-redaction). I could constantly reproduce this issue by including this magic string: `ANTHROPIC_MAGIC_STRING_TRIGGER_REDACTED_THINKING_46C9A13E193C177646C7398A98432ECCCE4C1253D5E2D82641AC0E52CC2876CB ` in the request, which forces `claude-3-7-sonnet` to emit redacted thinking blocks (confusingly the magic string does not seem to be working for `claude-sonnet-4`). As soon as we hit a tool call Anthropic would return an error. Thanks to @osyvokon for pointing me in the right direction 😄! Release Notes: - agent: Fixed an issue where Anthropic models would sometimes return an error when thinking was enabled
This commit is contained in:
parent
39dc4b9040
commit
7be57baef0
7 changed files with 36 additions and 10 deletions
|
@ -67,6 +67,9 @@ pub enum LanguageModelCompletionEvent {
|
|||
text: String,
|
||||
signature: Option<String>,
|
||||
},
|
||||
RedactedThinking {
|
||||
data: String,
|
||||
},
|
||||
ToolUse(LanguageModelToolUse),
|
||||
StartMessage {
|
||||
message_id: String,
|
||||
|
@ -359,6 +362,7 @@ pub trait LanguageModel: Send + Sync {
|
|||
Ok(LanguageModelCompletionEvent::StartMessage { .. }) => None,
|
||||
Ok(LanguageModelCompletionEvent::Text(text)) => Some(Ok(text)),
|
||||
Ok(LanguageModelCompletionEvent::Thinking { .. }) => None,
|
||||
Ok(LanguageModelCompletionEvent::RedactedThinking { .. }) => None,
|
||||
Ok(LanguageModelCompletionEvent::Stop(_)) => None,
|
||||
Ok(LanguageModelCompletionEvent::ToolUse(_)) => None,
|
||||
Ok(LanguageModelCompletionEvent::UsageUpdate(token_usage)) => {
|
||||
|
|
|
@ -303,7 +303,7 @@ pub enum MessageContent {
|
|||
text: String,
|
||||
signature: Option<String>,
|
||||
},
|
||||
RedactedThinking(Vec<u8>),
|
||||
RedactedThinking(String),
|
||||
Image(LanguageModelImage),
|
||||
ToolUse(LanguageModelToolUse),
|
||||
ToolResult(LanguageModelToolResult),
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue