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

fix(llm): honor DeepSeek SSE keep-alives

Browse Source
This commit is contained in:
fz
2026-08-04 11:48:34 +08:00
parent 804b724202
commit cd6bd5c188
17 changed files with 134 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
packages/llm/llm-deepseek/README.md
View File

@@ -46,7 +46,7 @@ The same exact-model result exposes ordered `off`, `high`, and `max` efforts und
`thinking: disabled` is a deployment lock that publishes only `off` with `off` as its default. Omitting `reasoningEffort` or configuring it as `off` is valid; configuring `high` or `max` fails plugin loading, and a direct per-request attempt to enable thinking fails before network I/O. A request with `GenerateOptions.purpose: 'session-title'` also forces thinking disabled and omits the already-resolved effort, reserving its bounded output for visible title text without changing conversation or compaction defaults.
`streamIdleTimeoutMs` bounds each outstanding provider read, including the initial `fetch`, without counting time the consumer spends between chunks. One stable abort signal reaches the request and body reader for the whole call; expiry stops the transport and throws `LlmError('TIMEOUT')`, while an earlier caller abort throws `LlmError('ABORTED')`. The adapter makes exactly one provider request per `stream()` call; it registers the configured policy as provider metadata, and `dsh-llm-retry` separately executes it at durable agent-step boundaries.
`streamIdleTimeoutMs` bounds each outstanding provider read, including the initial `fetch`, without counting time the consumer spends between chunks. DeepSeek SSE comments rearm an outstanding read as transport activity but never become `StreamChunk` values or session-log events. One stable abort signal reaches the request and body reader for the whole call; expiry stops the transport and throws `LlmError('TIMEOUT')`, while an earlier caller abort throws `LlmError('ABORTED')`. The adapter makes exactly one provider request per `stream()` call; it registers the configured policy as provider metadata, and `dsh-llm-retry` separately executes it at durable agent-step boundaries.
## Dynamic configuration (settings + credentials)