You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit b06bd16
Browse filesBrowse the repository at this point in the historyBrowse files
fix(session): retry a failed session title on later turns and report why it failed (#1688)
A session whose first title request failed kept its New session placeholder for life and logged only the generic No output generated. The title is now retried on each of the first five user messages with the first message as context, one request in flight per session, and a generated title only ever replaces the placeholder. Each failure is logged with the provider error (name, message, status) and reported as a title_generation_failed telemetry event with no message text; failures before the request, such as a small_model the provider does not list, are reported too. TestLLMServer.title() queues title answers for tests. Docs: telemetry catalogue row and the small_model paragraph on the models page.
Closes#1689
Co-Authored-By: Claude Fable 5.1 <[email protected]>
Copy file name to clipboardExpand all lines: docs/docs/configure/models.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,6 +18,8 @@ altimate supports models from all configured providers. Use the `model` and `sma
18
18
19
19
The model format is `provider/model-name`.
20
20
21
+
`small_model` handles the small background requests that are not part of the conversation, such as the session title and prompt enhancement. When it is not set, Altimate Code picks a cheap model from the same provider (Claude Haiku, Gemini Flash or GPT-5 nano when the provider lists one) and otherwise uses the chat model. A `small_model` the provider cannot serve, or does not list, fails only those requests: chat keeps working, while new sessions keep their `New session - <time>` placeholder title until a retry succeeds. Altimate Code retries the title on each of the first five messages of a session and reports every failure in telemetry.
Copy file name to clipboardExpand all lines: docs/docs/reference/telemetry.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -24,6 +24,7 @@ We collect the following categories of events:
24
24
|`auth_logout`| A user logs out (provider only) |
25
25
|`mcp_server_status`| An MCP server connects, disconnects, or errors (server name and transport) |
26
26
|`provider_error`| An AI provider returns an error (error type and HTTP status, but no request content) |
27
+
|`title_generation_failed`| A session-title request failed, so the session keeps its `New session - <time>` placeholder until a retry succeeds; retries stop after the fifth user message. Provider, model, `attempt` (1 to 5), error class and type, HTTP status when there was one. No message text. |
27
28
|`engine_started`| The native tool engine initializes (version and duration) |
28
29
|`engine_error`| The native tool engine fails to start (phase and truncated error) |
29
30
|`upgrade_attempted`| A CLI upgrade is attempted (version and method) |
@@ -251,6 +252,7 @@ Event type names use **snake_case** with a `domain_action` pattern:
251
252
-`mcp_server_status`, `mcp_server_census` for MCP server lifecycle
252
253
-`engine_started`, `engine_error` for native engine events
253
254
-`provider_error` for AI provider errors
255
+
-`title_generation_failed` for a session-title request the small model did not answer
254
256
-`session_forked` for session lifecycle
255
257
-`environment_census` for environment snapshot events
256
258
-`context_utilization`, `context_overflow_recovered` for context management events
0 commit comments