The startup-timeout integration tests in `chatloop` used a 5ms real-time
budget and relied on wall-clock scheduling to fire the startup guard
timer before the first stream part arrived. On loaded CI runners the
timer sometimes lost the race, producing `attempts == 2` instead of
`attempts == 1` and flaking `TestRun_FirstPartDisarmsStartupTimeout`.
Replace the real `time.Timer` in `startupGuard` with a `quartz.Timer` so
tests can control time deterministically. Production behavior is
unchanged: `RunOptions.Clock` defaults to `quartz.NewReal()` when nil,
and the startup timeout still covers both opening the provider stream
and waiting for the first stream part.
- Add `RunOptions.Clock quartz.Clock` with nil-safe default.
- Tag the startup guard timer as `"startupGuard"` for quartz trap
targeting.
- Rewrite the four startup-timeout integration tests to use
`quartz.NewMock(t)` with trap/advance/release sequences instead of
wall-clock sleeps.
- Add `awaitRunResult` helper so tests fail with a clear message instead
of hanging when `Run` does not complete.
Closes https://github.com/coder/internal/issues/1460
Adds an optional `CreatedAt` timestamp to `tool-call` and `tool-result`
`ChatMessagePart` variants so the frontend can compute tool execution
duration (`result.created_at - call.created_at`).
Timestamps are recorded at the correct moments in the chatloop:
- **Tool-call**: when the model stream emits the tool call
- **Tool-result**: when tool execution completes (or is interrupted)
These are passed through `PersistedStep.PartCreatedAt` so the
persistence layer can apply accurate timestamps to stored parts.
SSE-published parts also carry `CreatedAt` for real-time display.
Old persisted messages without `created_at` deserialize to `nil` — fully
backward compatible.
<details><summary>Implementation notes (Coder Agents
generated)</summary>
### Why not stamp in `PartFromContent`?
`PartFromContent` is called both for SSE publishing (correct timing) and
during persistence (wrong timing — both tool-call and tool-result would
get the same "persistence time" timestamp, yielding ~0 duration).
Instead, timestamps are captured in the chatloop at the right moments
and carried through `PersistedStep.PartCreatedAt` as a
`map[string]time.Time` keyed by `"call:<id>"` / `"result:<id>"`.
### Interrupted tool calls
`persistInterruptedStep` also stamps `CreatedAt` on synthetic error
results for cancelled/interrupted tool calls, so partial duration is
available.
### Files changed
| File | Change |
|------|--------|
| `codersdk/chats.go` | Add `CreatedAt *time.Time` field |
| `codersdk/chats_test.go` | JSON round-trip test |
| `coderd/database/dbtime/dbtime.go` | Add `TimePtr` helper |
| `coderd/x/chatd/chatloop/chatloop.go` | Track timestamps, pass through
`PersistedStep` |
| `coderd/x/chatd/chatd.go` | Apply timestamps during persistence |
| `coderd/x/chatd/chatprompt/chatprompt_test.go` | Verify
`PartFromContent` does NOT stamp |
| `site/src/api/typesGenerated.ts` | Auto-generated |
</details>
---------
Co-authored-by: Ethan <39577870+ethanndickson@users.noreply.github.com>
Adds client-executed dynamic tools to the chat API. Dynamic tools are
declared by the client at chat creation time, presented to the LLM
alongside built-in tools, but executed by the client rather than chatd.
This enables external systems (Slack bots, IDE extensions, Discord bots,
CI/CD integrations) to plug custom tools into the LLM chat loop without
modifying chatd's built-in tool set.
Modeled after OpenAI's Assistants API: the chat pauses with
`requires_action` status when the LLM calls a dynamic tool, the client
POSTs results back via `POST /chats/{id}/tool-results`, and the chat
resumes.
See [this example](https://github.com/coder/coder-slackbot-poc) as a
reference for how this is used. It's highly-configurable, which would
enable creating chats from webhooks, periodically polling, or running as
a Slackbot.
<details>
<summary>Design context</summary>
### Architecture
The chatloop **exits** when it encounters dynamic tools and
**re-enters** when results arrive. No blocking channels, no pubsub for
tool results, no in-memory registry. The DB is the only coordination
mechanism.
```
Phase 1 (chatloop):
LLM response → execute built-in tools only →
Persist(assistant + built-in results) →
status = requires_action → chatloop exits
Phase 2 (POST /tool-results):
Persist(dynamic tool results) →
status = pending → wakeCh → chatloop re-enters
```
### Validation (POST /tool-results)
1. Chat status must be `requires_action` (409 if not)
2. Read chat's `dynamic_tools` → set of dynamic tool names
3. Read last assistant message → extract tool-call parts matching
dynamic tool names
4. Submitted tool_call_ids must match exactly (400 for missing/extra)
5. Persist tool-result message parts, set status to `pending`, signal
wake
### Idempotency
Tool call IDs scoped per LLM step. State machine (`requires_action` →
`pending`) is the guard. First POST wins, subsequent get 409.
### Mixed tool calls
When the LLM calls both built-in and dynamic tools in one step, built-in
tools execute immediately. Their results are persisted in phase 1.
Dynamic tool results arrive via POST in phase 2. The LLM sees all
results when the chatloop resumes.
</details>
> 🤖 Generated by Coder Agents
Fixes https://github.com/coder/internal/issues/1418
The `TestRun_ActiveToolsPrepareBehavior` test asserts
`persistedStep.Runtime > 0`, but on Windows the timer resolution (~15ms)
means the in-memory mock model can complete within the same clock tick,
producing a measured duration of `0s`.
Change the assertion from `require.Greater` to `require.GreaterOrEqual`
so that a legitimately measured zero duration on low-resolution clocks
does not cause a flake.
> Generated by Coder Agents
`isContextLimitKey` had a fallback heuristic that matched any key starting with `"max"` containing `"context"`, causing false positives on keys like `"max_context_version"`. A provider returning such metadata would have the value parsed as a context limit.
Replace substring matching on the separator-stripped key with word-level matching. A new `metadataKeyWords` function tokenizes keys by splitting on separators and camelCase boundaries, then the fallback requires
`"context"` paired with a limit-related word (`"limit"`, `"window"` + qualifier, `"length"` + qualifier, or `"tokens"` + qualifier). Known exact forms like `"context_window"` remain in the fast-path switch.
Closes https://github.com/coder/coder/issues/23332
Follow-up to #23282. The retry and terminal error callouts had a few UX
oddities:
- Auto-retrying states reused backend error text that said "Please try
again" even while the UI was already retrying on behalf of the user.
- Terminal error states also said "Please try again" with no action the
user could take.
- `startup_timeout` had no specific title or retry copy — it fell
through to the generic "Retrying request" heading.
- The kind pill showed raw enum values like `startup_timeout` and
`rate_limit`.
- Terminal error metadata showed a "Retryable" / "Not retryable" label
that does not help users.
- A separate "Provider anthropic" metadata row duplicated information
already present in the message body.
- The `usage-limit` error kind used a hyphen while every backend kind
uses underscores.
Changes:
**Backend (`chaterror/message.go`)**
- Split message generation into `terminalMessage()` and
`retryMessage()`, replacing the old `userFacingMessage()`.
- Terminal messages include HTTP status codes and actionable guidance
(e.g. "Check the API key, permissions, and billing settings.").
- Retry messages are clean factual statements without status codes or
remediation, suitable for the retry countdown UI (e.g. "Anthropic is
temporarily overloaded.").
- Removed "Please try again" / "Please try again later" from all paths.
- `StreamRetryPayload` calls `retryMessage()` instead of forwarding
`classified.Message`.
**Frontend**
- Removed the parallel frontend message-generation system:
`getRetryMessage()`, `getProviderDisplayName()`,
`getRetryProviderSubject()`, and the `PROVIDER_DISPLAY_NAMES` map are
all deleted from `chatStatusHelpers.ts`.
- `liveStatusModel.ts` passes `retryState.error` through directly — the
backend owns the copy.
- Added specific title and retry copy for `startup_timeout`, and
extended the title mapping to cover `auth` and `config`.
- Kind pills now show humanized labels ("Startup timeout", "Rate limit",
etc.) instead of raw enum strings.
- Removed the redundant "Provider anthropic" metadata row.
- Removed the terminal "Retryable" / "Not retryable" badge.
- Normalized `"usage-limit"` → `"usage_limit"` and added it to
`ChatProviderFailureKind` so all error kinds follow the same underscore
convention and live in one enum.
Refs #23282.
We had a bug where computer use base64-encoded screenshots would not be
interpreted as screenshots anymore once saved to the db, loaded back
into memory, and sent to Anthropic. Instead, they would be interpreted
as regular text. Once a computer use agent made enough screenshots and
stopped, and you tried sending it another message, you'd get an out of
context error:
<img width="808" height="367" alt="Screenshot 2026-03-23 at 12 02 54"
src="https://github.com/user-attachments/assets/f0bf6be2-4863-47ca-a7a9-9e6d9dfceeed"
/>
This PR fixes that.
> **PR Stack**
> 1. #23351 ← `#23282`
> 2. #23282 ← `#23275`
> 3. **#23275** ← `#23349` *(you are here)*
> 4. #23349 ← `main`
---
## Summary
Extracts a structured error classification subsystem for agent chat
(`chatd`) so that retry and error payloads carry machine-readable
metadata — error kind, provider name, HTTP status code, and retryability
— instead of raw error strings.
This is the **backend half** of the error-handling work. The frontend
counterpart is in #23282.
## Changes
### New package: `coderd/chatd/chaterror/`
Canonical error classification — extracts error kind, provider, status
code, and user-facing message from raw provider errors. One source of
truth that drives both retry policy and stream payloads.
- **`kind.go`**: Error kind enum (`rate_limit`, `timeout`, `auth`,
`config`, `overloaded`, `unknown`).
- **`signals.go`**: Signal extraction — parses provider name, HTTP
status code, and retryability from error strings and wrapped types.
- **`classify.go`**: Classification logic — maps extracted signals to an
error kind.
- **`message.go`**: User-facing message templates keyed by kind +
signals.
- **`payload.go`**: Projectors that build `ChatStreamError` and
`ChatStreamRetry` payloads from a classified error.
### Modified
- **`codersdk/chats.go`**: Added `Kind`, `Provider`, `Retryable`,
`StatusCode` fields to `ChatStreamError` and `ChatStreamRetry`.
- **`coderd/chatd/chatretry/`**: Thinned to retry-policy only;
classification logic moved to `chaterror`.
- **`coderd/chatd/chatloop/`**: Added per-attempt first-chunk timeout
(60 s) via `guardedStream` wrapper — produces retryable
`startup_timeout` errors instead of hanging forever.
- **`coderd/chatd/chatd.go`**: Publishes normalized retry/error payloads
via `chaterror` projectors.
OpenAI Responses follow-up turns were replaying full assistant/tool
history even when `store=true`, which breaks after reasoning +
provider-executed `web_search` output.
This change persists the OpenAI response ID on assistant messages, then
in `coderd/x/chatd` switches `store=true` follow-ups to
`previous_response_id` chaining with a system + new-user-only prompt.
`store=false` and missing-ID cases still fall back to manual replay.
It also updates the fake OpenAI server and integration coverage for the
chaining contract, and carries the rebased path move to `coderd/x/chatd`
plus the migration renumber needed after rebasing onto `main`.
- Moves `coderd/chatd/`, `coderd/gitsync/`, `enterprise/coderd/chatd/`
under `x/` parent directories to signal instability
- Adds `Experimental:` glue code comments in `coderd/coderd.go`
> 🤖 This PR was created with the help of Coder Agents, and was
reviewed by my human. 🧑💻
Ethan