feat(chatd): add LLM stream retry with exponential backoff (#22418)

## Summary

Adds automatic retry with exponential backoff for transient LLM errors
during chat streaming and title generation. Inspired by
[coder/mux](https://github.com/coder/mux)'s retry mechanism.

## Key Behaviors

- **Infinite retries** with exponential backoff: 1s → 2s → 4s → ... →
60s cap
- **Deterministic delays** (no jitter)
- **Error classification**: retryable (429, 5xx, overloaded, rate limit,
network errors) vs non-retryable (auth, quota, context exceeded, model
not found, canceled)
- **Retry status published to SSE stream** so frontend can show
"Retrying in Xs..." UI
- **Title generation** retries silently (best-effort, nil onRetry
callback)

## New Package: `coderd/chatd/chatretry/`

| File | Purpose |
|------|---------|
| `classify.go` | `IsRetryable(err)` and `StatusCodeRetryable(code)` |
| `backoff.go` | `Delay(attempt)` — exponential doubling with 60s cap |
| `retry.go` | `Retry(ctx, fn, onRetry)` — infinite loop with
context-aware timer |

## Test Helpers: `coderd/chatd/chattest/errors.go`

Anthropic and OpenAI error response builders for use in chattest
providers:
- `AnthropicErrorResponse()`, `AnthropicOverloadedResponse()`,
`AnthropicRateLimitResponse()`
- `OpenAIErrorResponse()`, `OpenAIRateLimitResponse()`,
`OpenAIServerErrorResponse()`

## SDK Changes: `codersdk/chats.go`

- New `ChatStreamEventType: "retry"`
- New `ChatStreamRetry` struct with `Attempt`, `DelayMs`, `Error`,
`RetryingAt` fields
- TypeScript types auto-generated

## Changed Files

- `coderd/chatd/chatloop/chatloop.go` — wraps `agent.Stream()` in
`chatretry.Retry()`
- `coderd/chatd/chatd.go` — publishes retry events to SSE stream with
logging
- `coderd/chatd/title.go` — wraps `model.Generate()` in silent retry
- `coderd/chatd/chattest/anthropic.go` / `openai.go` — error injection
support

## Tests

42 tests covering classification (33), backoff (9), and retry scenarios
(8).

codersdk/chats.go

@@ -444,6 +444,7 @@ const (
 	ChatStreamEventTypeStatus      ChatStreamEventType = "status"
 	ChatStreamEventTypeError       ChatStreamEventType = "error"
 	ChatStreamEventTypeQueueUpdate ChatStreamEventType = "queue_update"
+	ChatStreamEventTypeRetry       ChatStreamEventType = "retry"
 )
 
 // ChatQueuedMessage represents a queued message waiting to be processed.
@@ -470,6 +471,19 @@ type ChatStreamError struct {
 	Message string `json:"message"`
 }
 
+// ChatStreamRetry represents an auto-retry status event in the stream.
+// Published when the server automatically retries a failed LLM call.
+type ChatStreamRetry struct {
+	// Attempt is the 1-indexed retry attempt number.
+	Attempt int `json:"attempt"`
+	// DelayMs is the backoff delay in milliseconds before the retry.
+	DelayMs int64 `json:"delay_ms"`
+	// Error is the error message from the failed attempt.
+	Error string `json:"error"`
+	// RetryingAt is the timestamp when the retry will be attempted.
+	RetryingAt time.Time `json:"retrying_at" format:"date-time"`
+}
+
 // ChatStreamEvent represents a real-time update for chat streaming.
 type ChatStreamEvent struct {
 	Type           ChatStreamEventType    `json:"type"`
@@ -478,6 +492,7 @@ type ChatStreamEvent struct {
 	MessagePart    *ChatStreamMessagePart `json:"message_part,omitempty"`
 	Status         *ChatStreamStatus      `json:"status,omitempty"`
 	Error          *ChatStreamError       `json:"error,omitempty"`
+	Retry          *ChatStreamRetry       `json:"retry,omitempty"`
 	QueuedMessages []ChatQueuedMessage    `json:"queued_messages,omitempty"`
 }