Update installation tests to reference @kilocode/cli instead of
opencode-ai for npm/bun/pnpm version lookup assertions. Adjust
session schema decoding test to omit the patch field from
SummaryFileDiff, matching the kilo-specific schema shape.
Replace zod schema definitions with effect Schema equivalents in
BusEvent definitions, tool parameters, session network, suggestions,
and related modules. This aligns Kilo-specific code with the upstream
v1.14.23 migration from zod to effect Schema.
- Convert BusEvent property schemas from zod objects to Schema.Struct
- Migrate tool parameter definitions (recall, warpgrep, suggest) to
Schema.Struct with annotated descriptions
- Replace zod-based SessionNetwork.Wait with effect Schema and add
zod interop via withStatics helper
- Extract shared EditorContext schema in message-v2 and reuse in
prompt input
- Replace `fn()` wrappers in session.ts with explicit
Schema.decodeUnknownSync calls for type safety
- Use branded SessionID/QuestionID types in place of raw z.string()
- Update pending map in SessionNetwork from Record to Map<QuestionID>
- Update tests to use SessionID.make() for branded identifiers
Include `variant: undefined` in metadata objects to match the expected
shape returned by the provider, ensuring the assertion compares all
fields accurately.
Verify that when a subtask completes, the child session's assistant
cost is correctly propagated to the parent wrapper message. This
covers the cost aggregation path in handleSubtask for subagent
interactions.
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.
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.
Replace the `pwd -P` approach with an explicit positional argument (`$1`)
for zsh and bash login shell invocations. Login shells source profile
scripts (`/etc/profile`, `~/.profile`, `~/.bashrc`) before the `-c`
script executes, and those scripts may change the working directory
(e.g. nvm, direnv), making both `$PWD` and `pwd -P` unreliable at
script evaluation time. By passing `ctx.directory` as `$1` and falling
back to `$PWD` when unset, the shell script always receives the correct
session directory regardless of profile side effects.
Simplify the corresponding integration test by removing verbose CI
debug probes and replacing them with a straightforward `pwd` assertion.
Replace `$PWD` with `$(pwd -P)` when capturing the working directory
in zsh and bash login shell invocations. When the child shell inherits
a stale PWD environment variable — common in CI where the spawner's
cwd differs from the session directory — `$PWD` can point to the wrong
location, causing `cd "$__oc_cwd"` to silently escape the intended
directory. `pwd -P` queries the kernel via getcwd(), ensuring the
correct physical path is always used.
The corresponding test is updated with richer cwd diagnostics to
validate the fix and surface root-cause information on failure.
Skip "glob tool keeps instance context during prompt runs" and
"prompt submitted during an active run" tests tracked in #9958.
Replace "build" agent assertion with "code" to align with Kilo
agent naming conventions.
users can now see when transient failures occur during assistant responses,
such as rate limits or provider overloads, giving visibility into what
issues were encountered and automatically resolved before the final response
Marius