Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(web): surface max-tokens turn ends as a localized truncation notice

Browse Source 
A turn the provider ends at its per-request output cap previously produced
no visible sign in the Web chat flow: only error-kind turn/end events built
a conversation node, so the truncated answer read as a normal completion.

Add a turn-max-tokens conversation node Definition over the durable
turn/end event, a warning-styled localized notice row distinct from
turn-error, a fixture max-tokens sample turn, and an assembled keyless
snapshot pinning the dot state, title, and hint.

Closes #1522
This commit is contained in:
creatixchu
2026-08-12 15:36:27 +08:00
parent 3784607f3d
commit e4ca03cb85
22 changed files with 356 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
packages/client/runtime/README.md
View File

@@ -68,6 +68,8 @@ Every `ToolCallBlock` recursively owns its children through `subCalls`, in start
The Host-owned LLM retry invariant validates provider-routed `llm/retry` and `llm/retry-started` records at the durable append boundary, including their identity, ordering, timer, integer, status, provider-delay, and non-empty diagnostic contracts. In the client, the Retry, Assistant, and Turn Error Definitions fold those records with Assistant and Turn/Step events: a failed step's streaming partial is removed and a durable retry notice appears at the retry event's sequence position. The notice is `scheduled` until the matching started record arrives; closing its owning Step or Turn first marks it `cancelled`, while the started record marks it `started`. Normal-mode notices carry their finite maximum; always-mode notices remain explicitly unbounded. A terminal `turn/end` error without a retry projects one `turn-error` node from its durable message and optional code; AUTH projections replace provider copy that may echo credential fragments with `API key is invalid`, while the raw diagnostic remains in the session log. A retried failure keeps only the retry notice for that attempt. Window rebuild and history replay use the same Definitions, so refresh neither resurrects discarded chunks nor loses terminal failure feedback. Visible unfinalized output is frozen as an interrupted Assistant node beside the terminal error.
A `turn/end` whose reason is `max-tokens` projects one `turn-max-tokens` node at the turn position: a warning-styled localized notice that the reply stopped at the per-request output cap, with the truncated output kept in the flow and guidance that sending "continue" resumes in a new turn. The notice carries no token counts because the event reports none. The same Definition rebuilds it on window rebuild and history replay, so the reason survives refresh, restore, and history replay.
## Session forking
`ISessions.fork({sessionId, atSeq?, increaseTitle?})` resolves only after the child summary is locally addressable, carrying source lineage and cwd with `blank: false`; callers choose whether to open it. With `increaseTitle: true`, the client renames the child from the source session's persisted title: a trailing `(N)` or `（N）` is incremented without changing bracket style, while any other title gets ` (1)` appended; the rename is skipped when the source has no persisted title, and a rename failure rejects the promise but leaves the created child in place. This option is not sent in the Host fork request. A `workspace-attach-failed` response still identifies a child already published by the Host, so `SessionManager` reconciles that partial success before `SessionForkError` reaches the caller instead of making a retry create a duplicate child.