Add missing 'variant' property to task tool metadata in prompt-effect test, required after upstream added model variant support to the task tool's ExecuteResult type.
* fix: allow ChatGPT login over OpenAI provider config
Let users with inherited or globally configured OpenAI API keys sign in with ChatGPT for Codex without first removing their existing provider setup.
* fix: satisfy provider login ci checks
Annotate Kilo-specific shared CLI changes and apply webview formatting so the existing ChatGPT login flow passes CI.
Strengthen the Kilo queue integration test to capture each LLM
request body and assert the second request ends with the queued
user message, not a prior-turn assistant tail. Update the skipped
upstream prompt-effect active-run test comment to reference #9492
and point at the Kilo-specific authoritative coverage.
The gateway wraps @openrouter/ai-sdk-provider internally, so the same
openrouter SDK-side reasoning handling applies. Without this, users
routing through api.kilo.ai still see DeepSeek 400 'reasoning_content
must be passed back' errors.
The task tool propagates each child session's total cost into the parent's tool-wrapper assistant message. Counting both root and child sessions in `kilo stats` would double-count that contribution. Filter `getAllSessions()` to root sessions (parent_id IS NULL), matching how the TUI session list and web sidebar already treat child sessions.
finish-step and cleanup previously re-wrote the parent assistant message with a stale in-memory cost, clobbering the subagent cost written by task.ts during tool execution. Refresh from DB before each write so the propagated cost is preserved across steps. Verified live via side-by-side `kilo serve` vs dev `bun serve` with 2 parallel subagents; parent now shows own LLM + children, matching real spend.
DeepSeek thinking mode may return empty reasoning_content on assistant
messages in a tool call chain, which must be sent back in subsequent
requests. The interleaved transform's truthy check was dropping it.
Always set providerOptions.openaiCompatible[field] for assistant
messages so the AI SDK's metadata spread carries it through.
Cherry-picked from anomalyco/opencode#24146 (931e6ed).
Add a check for UTF-16 byte order marks before the NUL/control-char
heuristic so that legitimate UTF-16 encoded files are not incorrectly
classified as binary. Also update Opus 4.7 transform test to expect
the `display: "summarized"` property in xhigh reasoning config.
Remove unused `open` from fs/promises and `readDirectoryFiles` from
kilocode read-directory module to clean up dead imports in the
compatibility layer.
Replace object spread (`{...props}`) with `mergeProps` when forwarding
props through the plugin Slot wrapper. Spreading props in SolidJS
evaluates each prop once at mount time, freezing reactive values like
`ref`, `visible`, `disabled`, and `on_submit`. This caused handlers to
bind against stale closures after overlay transitions, breaking Enter
submission on the session_prompt slot.
Add regression tests verifying the wrapper uses `mergeProps` (not
spread) and that reactive prop tracking is preserved at runtime.
Drop a debug short-circuit shipped upstream in #23037 that flipped `sync.ready` before sync actually finished, producing a 1-2s delay before home content (agents, news, tips) appeared in the TUI. Bisected from origin/main.
When a session spawned subagents via the task tool, the displayed cost reflected only the parent's own LLM steps. Propagate each subagent's total up to the invoking assistant message so every UI sums the full tree.
Alex Alecu