OpenAI-compatible providers can now send vLLM's top-level 'priority'
request field (lower value = earlier handling, server default 0),
which matters when vLLM runs with --scheduling-policy priority and a
box serves both interactive and background/batch work: setting
vllmPriority on a background model defers its long prefills behind
interactive sessions.
- types.ts: OpenAICompletionsCompat.vllmPriority?: number (off by default)
- openai-completions.ts: resolved through getCompat, injected in buildParams
- model-config.ts: models.json schema accepts compat.vllmPriority
- test: priority sent when set, omitted otherwise
Co-authored-by: Daniel-Clegg <daniel.clegg@civica.co.uk>
Some OpenAI Responses-compatible gateways (e.g. Codex-protocol proxies)
reject the max_output_tokens parameter with a 400 BadRequest. The
openai-responses API always sent it when maxTokens was set, with no way
to opt out.
Add a supportsMaxOutputTokens compat flag (default: true) to
OpenAIResponsesCompat. When false, buildParams omits max_output_tokens
from the request body. Also register the flag in the coding-agent
model-config schema so custom providers can set it.
- follow up of missed commits for feat(coding-agent): adjust TUI selections in thinking-mode, models and scoped models #8900
* fix(coding-agent): keep fixed theme marker visible
- distinguish the saved theme from the preview cursor
- align the automatic option and update coverage
* fix(coding-agent): keep automatic theme marker visible
- mark configured light and dark themes during preview
- reuse shared theme formatting and update coverage
When tools are registered by an extension (e.g. Kimchi) the execute callback
receives an ExtensionContext with the real session cwd. Use ctx.cwd || cwd so
tools resolve paths against the current session cwd instead of the cwd captured
at tool creation time.
Applies to read, write, edit, grep, find, ls, bash, and powershell.
Co-authored-by: Kimchi <noreply@kimchi.dev>
* fix(coding-agent): keep selector status markers visible
- place status markers before labels
- strike unavailable scoped models and update tests
* fix(coding-agent): align scoped model toggle behavior
- show checks for the all-enabled state
- toggle individual models consistently and add coverage
* docs(coding-agent): add changelog entry
* fix(coding-agent): keep trust marker visible while browsing
- move the saved marker before the trust option
- update tests and changelog
* fix(coding-agent): mark per-model thinking overrides
- add the leading level marker
- update tests and changelog
Run next-turn preparation only when the agent loop continues, allowing threshold compaction before the next provider request. Restore interactive progress when the same run resumes.
Closes#6879
Important to notice:
this changes when prepareNextTurn & prepareNextTurnWithContext are invoked:
the now run only when a next turn actually happens, and after shouldStopAfterTurn.
Extension messages sent with triggerTurn: false while the agent was
running were pushed into agent state and the session tree immediately,
landing between an assistant tool call and its result. Providers that
validate message order reject the replayed history. Queue them during
the run and append at turn_end, mirroring recordBashResult.
closes#8537
