Commit graph

10 commits

Author SHA1 Message Date
Piotr Osiewicz
9e0e233319
Fix clippy::needless_borrow lint violations (#36444)
Release Notes:

- N/A
2025-08-18 21:54:35 +00:00
Michael Sloan
86957a5614
Use the same prompt as agent thread summary for text threads (#35669)
This was causing text thread summarization to be counted as a usage of 1
prompt

Release Notes:

- Fixed bug with agent text threads (not chat threads) counting
summarization as a usage of 1 prompt.

Co-authored-by: Oleksiy <oleksiy@zed.dev>
2025-08-05 21:47:17 +00:00
Michael Sloan
42699411f6
Fix update of prompt usage count when using text threads (#35671)
Release Notes:

- Fixed update of prompt usage count when using agent text threads.

Co-authored-by: Oleksiy <oleksiy@zed.dev>
2025-08-05 21:39:34 +00:00
Marshall Bowers
7be1f2418d
Replace zed_llm_client with cloud_llm_client (#35309)
This PR replaces the usage of the `zed_llm_client` with the
`cloud_llm_client`.

It was ported into this repo in #35307.

Release Notes:

- N/A
2025-07-30 00:09:14 +00:00
Bennet Bo Fenner
41fe2a2ab4
agent: Disable thinking when using inline assistant/edit file tool (#34141)
This introduces a new field `thinking_allowed` on `LanguageModelRequest`
which lets us control whether thinking should be enabled if the model
supports it.
We permit thinking in the Inline Assistant, Edit File tool and the Git
Commit message generator, this should make generation faster when using
a thinking model, e.g. `claude-sonnet-4-thinking`

Release Notes:

- N/A
2025-07-09 18:05:39 +00:00
Michael Sloan
d497f52e17
agent: Improve error handling and retry for zed-provided models (#33565)
* Updates to `zed_llm_client-0.8.5` which adds support for `retry_after`
when anthropic provides it.

* Distinguishes upstream provider errors and rate limits from errors
that originate from zed's servers

* Moves `LanguageModelCompletionError::BadInputJson` to
`LanguageModelCompletionEvent::ToolUseJsonParseError`. While arguably
this is an error case, the logic in thread is cleaner with this move.
There is also precedent for inclusion of errors in the event type -
`CompletionRequestStatus::Failed` is how cloud errors arrive.

* Updates `PROVIDER_ID` / `PROVIDER_NAME` constants to use proper types
instead of `&str`, since they can be constructed in a const fashion.

* Removes use of `CLIENT_SUPPORTS_EXA_WEB_SEARCH_PROVIDER_HEADER_NAME`
as the server no longer reads this header and just defaults to that
behavior.

Release notes for this is covered by #33275

Release Notes:

- N/A

---------

Co-authored-by: Richard Feldman <oss@rtfeldman.com>
Co-authored-by: Richard <richard@zed.dev>
2025-06-30 21:01:32 -06:00
Ben Brandt
6c46e1129d
Cleanup remaining references to max mode (#33509)
Release Notes:

- N/A
2025-06-27 08:32:13 +00:00
Peter Tripp
2a5a1814cd
text_thread: Improve roles after assistant::Split (shift-enter) (#33215)
Default to `You` when triggering `assistant::Split` at the end of a thread

Release Notes:

- agent_thread: Improved roles when triggering `assistant::Split`
(`shift-enter`)
2025-06-25 13:26:24 -04:00
Bennet Bo Fenner
7be57baef0
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
2025-06-24 16:23:59 +00:00
Max Brunsfeld
4cd4d28531
Move UI code from assistant_context_editor -> agent_ui (#33289)
This breaks a transitive dependency of `agent` on UI crates. I've also
found and eliminated some dead code in assistant_context_editor.

Release Notes:

- N/A
2025-06-23 22:22:01 -07:00
Renamed from crates/assistant_context_editor/src/context.rs (Browse further)