When a completion request fails with a retryable error (e.g. a 500 from
the upstream provider), the retry loop waits on a timer before trying
again. This timer did not race with the cancellation signal, so if the
user switched models and submitted a new message during the retry delay,
the old turn would continue retrying with the stale model for up to 15
seconds — making requests to the wrong provider and corrupting the
thread's message list with spurious Resume entries.
Now the retry delay races with the cancellation receiver, so the old
turn exits immediately when cancelled.
Release Notes:
- Fixed cancelled turns in a conversation that failed (e.g. 500 from the
LLM provider) bein retried even after cancellation
Removes unused `edit_agent_output` from `EditFileTool`. This makes it
easier to maintain compatibility between the `EditFileTool` and
`StreamingEditFileTool`.
Release Notes:
- N/A
Store the user's unsent message editor text in DbThread so it survives
quitting and reloading Zed. The draft flows through Thread → AcpThread →
AcpThreadView on load, and back via a debounced observer on the message
editor for saves.
Currently works for native Zed agents only; external ACP agents will
pick this up once general ACP history persistence lands.
## Changes
- **`DbThread`** / **`Thread`**: New `draft_prompt: Option<String>`
field, included in `to_db()`/`from_db()`
- **`AcpThread`**: Bridge field with getter/setter, populated during
`register_session()`
- **`NativeAgent::save_thread()`**: Copies draft from `AcpThread` →
`Thread` before persisting
- **`AcpThreadView`**: Restores draft into `MessageEditor` on load;
syncs editor text → `AcpThread` via observer; debounced (500ms) Thread
notify triggers DB save
Co-authored-by: Anthony Eid <anthony@zed.dev>
Co-authored-by: Mikayla Maki <mikayla@zed.dev>
Subagents now forward buffer reads/writes/edits to a parent action log,
allowing the parent's review experience to track all file changes made
by subagents alongside its own.
Release Notes:
- N/A
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
When the model, summarization model, thinking settings, speed, or
profile are updated on a thread, apply the same settings to any
currently running subagents.
Release Notes:
- N/A
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Release Notes:
- agent: Add new `spawn_agent` tool which allows the Zed Agent to
utilize subagents for doing tasks in parallel and better context
management.
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
We now stream the new text into the buffer as soon as we receive partial
chunks of `new_text`. This is pretty much a full re-write of the way
streaming worked, which is now much closer to how the edit agent works:
- `ToolEditParser` buffers chunks as they stream in, and emits relevant
events (`OldTextChunk`,`NewTextChunk`, ...) that we use to power the
`EditSession` pipeline.
- `EditSession::process_events` takes care of consuming these events and
applying the edits incrementally as chunks stream in. `EditPipeline`
maintains the underlying state machine for each edit.
- We handle whitespace mismatches similar to the edit agent, the code is
shared by moving that logic to `reindent.rs`
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
This is a staff only toggle for now, since the consequences of
activating it are not obvious and quite dire (tokens costs 6 times
more).
Also, persist thinking, thinking effort and fast mode in DbThread so the
thinking mode toggle and thinking effort are persisted.
Release Notes:
- Agent: The thinking mode toggle and thinking effort are now persisted
when selecting a thread from history.
This has lots of benefits, but mainly allows users to uninstall agents.
Release Notes:
- N/A
---------
Co-authored-by: Anthony Eid <hello@anthonyeid.me>
Co-authored-by: cameron <cameron.studdstreet@gmail.com>
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
---------
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
This code was part of a series of stacked diff PRs that became obsolete
because we changed the UI design, so none of this code is necessary
anymore.
Release Notes:
- N/A
This PR introduces a `ToolInput` struct which allows tools to receive
their inputs incrementally as they stream in. Right now no tool makes
use of the streaming APIs, will be used for the streaming edit file tool
in #50004
Release Notes:
- N/A
Release Notes:
- The agent edit tool no longer clears files until the first edit comes
in, preventing a buffer being empty for prolonged time if the agent is
slow in reporting the first text chunk
Fixes a regression introduced in #48545 (reasoning effort selector). We
saw edit file tool calls taking a long time (loading animation was
displayed, no diff) when using Opus 4.6. This was caused by Opus 4.6.
emitting thinking tokens even when the user explicitly disabled thinking
in the UI.
<img width="289" height="67" alt="image"
src="https://github.com/user-attachments/assets/090a99f8-9b07-4d25-9058-3706f9333396"
/>
In addition to the thinking tokens causing overhead, we were slowing
down file editing even more. because changing between
thinking/non-thinking between requests causes the cache to be
invalidated
([docs](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#what-invalidates-the-cache)).
This PR ensures that we inherit the setting for enabling or disabling
thinking from the thread from which the edit tool was called.
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- Fixed an issue where editing files was taking a long time when using
Opus 4.6
---------
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
Allow the parent agent to handle cases where the subagent is running on
of context window. Also communicates if it has completely out of
context.
Release Notes:
- N/A
For the last few days, the model has never picked a good timeout value.
It seems they are better at choosing timeouts for bash commands but not
agents. Given there are some rate limits involved, I think it is hard to
estimate and we already have an upper bound of execution which is the
context window to keep it from going indefinitely.
Release Notes:
- N/A
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Release Notes:
- N/A
---------
Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>
After looking around a bit, I felt like subagent wasn't the right way to
introduce this tool to the model. And with some back and forth
verification + market research, we both agreed spawn_agent was a better
name for what this tool is doing.
It still calls the right tool if you ask for a subagent, but especially
if we move these to be running in the background, spawn will be a better
name anyway.
Release Notes:
- N/A
Previously we only had the ability to return anyhow errors, which
limited the amount of structured data we could send the model.
Now tools can also return structured data in the error cases, which is
super helpful for subagents in particular
Release Notes:
- N/A
Looking at this more, the map of tools is just for what is available and
all of the filtering happens at runtime. So we can just rely on the
current behavior for the list of tools (it was already a matching set)
and we can simplify all of the code paths again where we were adding
this filtered list.
Release Notes:
- N/A
There are some UI concerns, especially for permission requests, that get
extremely complicated for recurisve subagents.
We'll move this to 1 for now to reduce complexity, and revisit once we
have a better way for representing all current permission requests.
Release Notes:
- N/A
Removes tool filtering since this was throwing off certain models, and
also allows for more generic task prompts that don't always require
summaries. Since the models usually provide a wrap-up message, we don't
have to wait for another turn.
This also sets us up to allow the agent to re-interact with an existing
subagent thread.
Release Notes:
- N/A
---------
Co-authored-by: Jakub Konka <kubkon@jakubkonka.com>
Before you mark this PR as ready for review, make sure that you have:
- [x] Added a solid test coverage and/or screenshots from doing manual
testing
- [x] Done a self-review taking into account security and performance
aspects
- [x] Aligned any UI changes with the [UI
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
Requests will be rate-limited by our internal logic, but it will "just"
work.
Release Notes:
- N/A
Add `agent_worktree_directory` to `GitSettings` for configuring where
agent worktrees are stored (default: Zed data dir). Remove `Copy` derive
from `GitSettings`/`GitContentSettings` (incompatible with String field)
and fix downstream `.as_ref().unwrap()` call sites.
Define `AgentGitWorktreeInfo` (branch, worktree_path, base_ref) and add
it to `DbThread` + `DbThreadMetadata` for persistence and session list
display.
Closes AI-33
Release Notes:
- N/A
This PR adds a button in the `git: branch diff` view that allows to
quickly and easily send the entire diff to your last used agent for a
review. What this does is automatically submits a (pre-written and
generic) prompt to the last agents you were using in the agent panel
with the whole content of your diff.
<img width="750" height="1964" alt="Screenshot 2026-02-18 at 3 35@2x"
src="https://github.com/user-attachments/assets/493d8cf4-4815-4b01-91a0-6a39ad6219fe"
/>
Release Notes:
- Added a "Review Branch" button in the `git: branch diff` view so that
the whole diff can be quickly sent for review to an agent.
---------
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>
Redirects to `/dev/null` (e.g. `2>/dev/null`, `&>/dev/null`) are
known-safe I/O routing, not commands. Previously, `extract_commands`
emitted normalized redirect strings like `"2> /dev/null"` as separate
entries in the command list checked against auto-allow regexes. Since
`check_commands` requires **all** extracted entries to match an allow
pattern, the unmatched redirect caused false-negatives — e.g. `git log
--oneline -20 2>/dev/null || echo ...` would not be auto-allowed despite
matching `^git` and `^echo` patterns.
Rather than removing all redirects from extraction (which would hide
dangerous redirects like `> /etc/passwd` from deny/confirm pattern
checking), this fix surgically skips only `/dev/null` targets during
redirect normalization. Redirects to real files are still emitted and
still require a matching pattern for auto-allow, preserving the
defense-in-depth property.
Closes AI-41
Release Notes:
- Fixed terminal auto-allow patterns incorrectly prompting for
confirmation on commands containing `/dev/null` redirects (e.g.
`2>/dev/null`).
Bennet Bo Fenner