Move the IndexingStatus Effect schema out of the KiloIndexing namespace into
a dedicated `indexing-event.ts` module so it can be shared between the bus
event system and the HttpApi layer without circular imports.
Additionally fix several OpenAPI spec inconsistencies:
- Inline PermissionReplyBody into the endpoint payload schema
- Make `organizationId` nullable in the organization set endpoint
- Replace opaque string response for `/kilo/fim` with a structured
streaming completion schema
- Register `indexing.status` as a typed SSE event in the global event union
- Add `matchLegacyKiloOpenApi` post-processor for backward-compatible
nullable fields and FIM response shape
- Relocate Kilo-specific bridge tests to `test/kilocode/server/` and trim
duplicated assertions from the core bridge test file
Replace direct `Instance.provide` usage with `WithInstance.provide` across
source modules and test files to decouple runtime context provisioning
from the core Instance singleton.
- Update kilo-sessions, remote-sender, roll-call, and plan-followup source
- Remove unused `Instance` imports where only `WithInstance` is needed
- Drop unnecessary `init` param from indexing-worktree test calls
- Add missing `WithInstance` import in fixture-dependent test files
Move inline cloud-sessions fetch logic from Hono route handler into a
reusable getCloudSessions function in handlers.ts, and introduce new
Effect HttpApi endpoints for fetching and importing individual cloud
sessions.
- Extract getCloudSessions handler from routes.ts inline implementation
- Export fetchCloudSession, fetchCloudSessionForImport, importSessionToDb
from kilo-gateway package
- Add cloudSession (GET /kilo/cloud/session/:id) endpoint for previewing
remote session data
- Add cloudSessionImport (POST /kilo/cloud/session/import) endpoint to
download and persist cloud sessions locally
- Define CloudSession, CloudSessionData, CloudMessage schemas in the
kilo-gateway API group
- Change claw status error response from 500 InternalServerError to
503 ServiceUnavailable
- Register new cloud routes in instance router
- Add test coverage for route disambiguation between import and :id paths
- Regenerate SDK types and OpenAPI spec
Reformat code with consistent line breaks, trailing commas, semicolons,
and line-length compliance. No logic changes — purely whitespace,
indentation, and punctuation adjustments driven by the project formatter.
- Break long function signatures and conditionals across multiple lines
- Remove trailing blank lines and stray leading newlines
- Replace string-expression JSX whitespace with literal spaces
- Convert quoted object keys to unquoted where valid
- Remove erroneous shell command prefix from openapi.json
- Deduplicate SessionNetworkWait1 schema and simplify Finite unions to
plain number type in OpenAPI spec
Introduce a structured Effect HttpApi surface for all Kilo-specific
endpoints, replacing inline Hono handler logic with declarative group
definitions, typed schemas, and composable handler layers.
Key changes:
- Add HttpApi group and handler modules for commit-message, enhance-prompt,
indexing, kilocode, network, remote, session-import, suggestion, and
telemetry
- Extract allow-everything permission logic into a reusable Effect function
- Register all Kilo HttpApi groups in InstanceHttpApi and wire route
forwarding in the Hono instance router
- Export Suggestion.RequestSchema and annotate schemas with identifiers
- Use NonNegativeInt for indexing status fields and Schema.Finite for
network wait timestamps
- Add httpapi-bridge test asserting parity between Hono and Effect specs
for all 22 Kilo overlay routes
- Regenerate SDK types and openapi.json to reflect the new endpoints
Add optional `escapeJson` parameter to `ConfigPaths.substitute` to control
whether file content should be JSON-escaped. When `false`, multiline content
and special characters are preserved as-is, which is required for agent
markdown prompts that need raw file content rather than escaped strings.
Update agent config processing to pass `escapeJson: false` when substituting
file content into markdown prompts, ensuring proper handling of multiline
files without unwanted escape sequences.
Add comprehensive test coverage for the new parameter and existing
substitution functionality.
Enable file content substitution in agent configuration prompts using the
existing `ConfigPaths.substitute` utility. This allows agent markdown files
to reference external file contents via `{file:path}` syntax, with missing
files resolving to empty strings.
Export `substitute` function from ConfigPaths to support agent config
processing.
* fix: catch EEXIST from recursive mkdir on Windows
fs.mkdir with { recursive: true } can still throw EEXIST on Windows
when the target directory is backed by an NTFS reparse point (OneDrive),
a directory junction, or a WSL-served path. libuv's recursive walk
doesn't treat these as regular directories, so mkdir with recursive:true
attempts to create an already-existing path segment and fails.
This adds a defensive EEXIST catch at both directory-creation origins:
- AppFileSystem.ensureDir / writeWithDirs (snapshots, config, plans)
- Encoding.write (all tool writes and edits)
No functional change on Linux/macOS where EEXIST is never thrown from
recursive mkdir.
Fixes#9618, #9755
* fix: remove extra arg from mkdirSafe call, add unit tests
* docs(kilo-docs): update auto-generated source links
Add 2 new GitHub issue references (9618, 9755) from encoding.ts
and update URL count from 84 to 86.
---------
Co-authored-by: nimgrim <nimgrim@users.noreply.github.com>
Co-authored-by: Imanol Maiztegui <imanol.mzd@gmail.com>
\S+ was greedily consuming trailing punctuation (. ! , ;) into the URL
match, causing new URL() to mutate clean ASCII URLs — e.g.
"see https://example.com." became "see https://example.com./".
Fix: strip trailing sentence punctuation before parsing, extract and
replace only the hostname (not href) to avoid adding trailing slashes to
bare origins, and restore the stripped tail afterward.
* fix(tool): clarify semantic_search returns snippets not file paths
The first description bullet read "Find files most relevant to the
search query using semantic search.", which led an AI agent to tell a
user that the tool returns file paths only. The tool actually returns
matching content with file paths, line ranges, and relevance scores.
Updates the first two description bullets to name the output shape
directly. No runtime change.
Closes#9767.
* test(cli): cover semantic_search description
---------
Co-authored-by: marius-kilocode <marius@kilocode.ai>
The existing apply_patch encoding test only checked final file bytes,
which were correct because Patch.deriveNewContentsFromChunks does its
own encoding-aware read. The diff and additions/deletions counts
returned to the user (and shown in the permission prompt) were
nonetheless garbled because the surrounding tool reused a hard-coded
UTF-8 decoder. Pin the diff metadata to catch that regression.
Kilo isn't always BYOK; what matters here is that Kilo doesn't charge a
per-request fee on top of the upstream inference cost. So for the Kilo
provider, the gateway/marketplace `cost` would understate the user's true
spend — always prefer the upstream/market cost when present.
* feat: support Kilo-hosted indexing embeddings
* fix: format indexing settings
* fix: serialize local model persistence
* fix: annotate local model persistence
* fix: stabilize MCP OAuth browser test
* fix: annotate MCP OAuth test wait
* fix: keep KiloProvider under line cap
* fix: align Kilo indexing auth defaults
* fix(vscode): add missing indexing translations
* feat(indexing): fetch Kilo embedding model catalog
* fix(indexing): align Kilo embedding metadata fallback
* fix(gateway): remove unused indexing dependency
* fix(indexing): keep fallback catalog webview safe
* fix(agent-manager): include embedding model provider
* fix(vscode): provide embedding models in stories
* refactor(indexing): rely on Cloud embedding catalog
* fix(indexing): hydrate Kilo model metadata from Cloud
* fix(indexing): clear model when switching provider
Imanol Maiztegui