Extract buildFamilyCosts, buildFamilyLabels, and buildCostBreakdown
into session-utils.ts as pure functions with no store dependency.
Session.tsx memos now delegate to these functions.
20 new tests covering:
- buildFamilyCosts: empty family, multi-session summing, zero-cost
filtering, missing messages
- buildFamilyLabels: subagent_type preference, description fallback,
tool name fallback, label truncation, family boundary, dedup
- buildCostBreakdown: empty costs, root labeling, child labeling,
session ID fallback for unlabeled children
Decouple cost computation (reads store.messages) from label extraction
(reads store.parts) so they recompute independently. Cost updates
(new assistant messages) no longer trigger the parts walk, and part
mutations (tool state changes) no longer re-sum costs.
* feat(vscode): detect sessions in old extension
* feat(vscode): added session types
* feat(cli): add endpoints for inserting a session
* feat(vscode): use session types from sdk for parsing
* feat(kilo-vscode): parsing session project
* feat(vscode): parse legacy session details
* feat(kilo-vscode): refactoring
* feat(vscode): parse legacy session messages
* feat(vscode): parse legacy session parts
* feat(vscode): added testing files and id creation
* feat(vscode): merge tool parts on imported session
* feat(vscode): session message part refactoring
* feat(vscode): cover provider-specific reasoning parts on session migration
* feat(kilo-vscode): handle completion result parts
* feat: type hardening on session migration
* feat(kilo-vscode): create tool part correctly
* feat(kilo-vscode): adjust session part processing
* feat(vscode): persist migrated session in kilo.db
* feat(vscode): add error handling to session migration
* feat(vscode): add directory field to session migration
* feat(kilo-vscode): display completion check on session migration
* feat(vscode): prevent migrating sessions twice
* feat(cli): use correct project id when inserting migrated session
* feat(kilo-vscode): Use correct project id for session migration
* feat(kilo-vscode): load sessions on migration complete
* feat(kilo-vscode): ignore environment details user part when migrating sessions
* feat(cli): create project details following current backend logic
* feat(kilo-vscode): cleaner messages without environment_details parts
* feat(kilo-vscode): refactoring
* feat(kilo-vscode): refactoring and organization
* feat(kilo-vscode): method renaming to improve clarity
* feat(kilo-vscode): added session migration test strategy
* test(kilo-vscode): implement legacy migration unit tests for all migration modules
Replace todo stubs with full test implementations across messages,
parts, tools, reasoning, parser, migrate, project, and session test
files. Add new project.test.ts and session.test.ts covering project
construction, session metadata, and deterministic ID generation.
* style(kilo-vscode): apply prettier formatting across legacy migration source and test files
* fix(legacy-migration): filter out non-user/assistant entries before parsing messages
Exclude system and other non-conversational roles from the conversation
array prior to mapping, ensuring parentID references remain consistent
across imported messages when skipped entries exist.
* refactor(parts): skip part generation for non-conversational message roles
Entries with roles other than user or assistant should not produce
parts, keeping part output consistent with the messages that are
actually imported during legacy migration.
* fix(ids): use semantic kind strings to prevent part ID collisions for reasoning entries
Replace numeric indices with descriptive kind strings ("reasoning",
"provider-reasoning") in extra part ID generation to avoid collisions
between reasoning parts and regular content parts within the same
message.
Introduce `createExtraPartID` to distinguish reasoning-specific IDs
from standard sequential part IDs produced by `createPartID`.
* refactor(session-import): guard against empty worktree in legacy project import
Prevent silent misattribution of migrated sessions by rejecting empty
worktree paths before resolving the project directory. Without this
check, an empty string would fall back to the current process directory,
causing the imported session to be attached to the wrong project.
* perf(cli): cache MCP listTools results to avoid redundant RPCs per loop step (#7922)
MCP.tools() called client.listTools() for every connected server on
every agent loop iteration. With multiple servers this added hundreds
of milliseconds of overhead per step (measured ~300-750ms for remote
servers like Vercel).
Cache listTools results in a module-level Map and return them on
subsequent calls. The cache is invalidated on:
- ToolListChangedNotification from the MCP server
- Server add/connect/disconnect
- Instance dispose (config change, project switch, shutdown)
* fix(agent-manager): add retries to worktree cleanup for macOS .app bundles (#7921)
* chore: hide non-English localization files in GitHub PR diffs
Mark all non-English i18n locale files as linguist-generated=true so
they are collapsed by default in GitHub PR diffs, reducing noise when
reviewing changes that touch translation files.
* feat(vscode): add Browse Marketplace button to MCP settings
Add a "Browse Marketplace" button to the MCP Servers subtab in Agent
Behaviour settings, guiding users to discover and install MCPs from the
marketplace rather than only configuring them manually.
- Add button above the MCP server list that opens the Marketplace panel
- Add openMarketplacePanel webview message type and handler
- Add translations for all 18 supported languages
* fix(vscode): preserve project directory when opening marketplace from settings
Pass the current panel's project directory through to the marketplace
panel so project-scoped MCP installs work correctly in multi-root
workspaces. Without this, the marketplace panel would fall back to
null project directory since there is no active text editor when
clicking from a webview.
* feat(vscode): add Browse Marketplace button to agents and skills tabs
Add the Browse Marketplace button to the Agents and Skills subtabs in
Agent Behaviour settings, matching the existing button in the MCP
Servers subtab. This lets users discover marketplace items from any
of the three configuration tabs.
- Agents tab: added as a ghost button in the header row alongside
Import and Create Mode buttons
- Skills tab: added as a secondary button at the top-right, matching
the MCP tab layout
- Extracted the browse handler to the component scope for reuse
* chore: update kilo-vscode visual regression baselines
* perf(agent-manager): extend slimPart to strip heavy tool metadata for faster session switching (#7927)
Extend slim-metadata.ts to handle apply_patch, multiedit, write, and bash
tools in addition to edit. Previously only edit tool parts had their heavy
metadata stripped before IPC serialization. apply_patch parts carried full
file before/after contents per file, write parts carried the entire written
file, and bash parts carried up to 30KB of output — all serialized on every
session switch.
This reduces session-switch time by ~2x for sessions with many tool calls.
* style(legacy-migration): reformat long reasoning push call for readability
* refactor(legacy-migration): filter non-user/assistant entries before indexing
Move the role filter from inside `parseParts` to `parsePartsFromConversation`
so that message indices are derived only from the filtered list. This ensures
part message IDs stay aligned with the imported messages and skipped entries
(e.g. system role) do not cause index gaps in the generated IDs.
* fix(legacy-migration): add `_migrated_` infix to generated IDs
Prefix all migrated entity IDs (sessions, messages, parts) with a
`_migrated_` segment so they are clearly distinguishable from IDs
produced by the regular runtime. Updates tests to assert the new
prefix format.
* refactor(legacy-migration): consolidate conversation parsing into `parseSession`
Remove the intermediate `createMessages` and `createParts` async
wrappers that each independently read and parsed the conversation
file. The file is now fetched and parsed once in `parseSession`,
with the resulting conversation passed directly to
`parseMessagesFromConversation` and `parsePartsFromConversation`,
eliminating redundant I/O.
* fix(parts-builder): remove `toTextWithinMessage` and use `toText` directly
`toTextWithinMessage` was a duplicate of `toText` with identical
behavior. Replace all call sites with `toText` and delete the
redundant function.
* fix(parts-builder): skip provider-specific reasoning when explicit reasoning entry exists
Guard `isProviderSpecificReasoning` with `!isReasoning` to prevent
duplicate reasoning parts when an entry carries both a `type:
"reasoning"` field and a provider-specific reasoning field (e.g.
`reasoning_content`). The explicit reasoning entry takes precedence.
* test(legacy-migration): add coverage for edge cases in parts and tools parsing
Add unit tests for two previously uncovered scenarios:
- Task block extraction: verify only the content inside `<task>` tags
is kept when text exists outside the legacy task wrapper
- Empty tool result: verify the tool name is used as fallback output
when `tool_result` carries no readable text content
Also replace the dynamic `FileType.Directory` workaround with the
direct `vscode.FileType.Directory` enum reference, and harden
`parseFile` to throw on non-array JSON instead of silently returning
an empty array.
* fix(migration): require all items to succeed before marking migration complete
Tighten the completion condition so migration is only marked "completed"
when every item succeeds, not just when at least one does. Introduce a
dedicated "error" phase in the wizard UI so partial failures are surfaced
clearly rather than silently collapsed into the "done" state.
- `handleStartLegacyMigration`: gate `setMigrationStatus("completed")` on
`!failed && success` instead of `success` alone
- `migrate`: propagate the actual `Error.message` from a failed session
migration instead of a generic fallback string
- `MigrationWizard`: add `"error"` phase, show per-group error messages
inline, add a "Continue" button to proceed past the error screen, and
trigger `loadSessions` on completion
- `migration.css`: add `.migration-wizard__error-text` style using
`--vscode-errorForeground`
* fix(migration): defer disposeGlobal and loadSessions until after error check
Move `disposeGlobal` call inside the success-only branch so the
extension is not torn down when migration partially fails. Similarly,
defer the `loadSessions` webview message to the "Continue" button on
the error screen so sessions are only reloaded after the user
acknowledges the failure.
- `handleStartLegacyMigration`: move `disposeGlobal` inside the
`!failed && success` guard to avoid disposing on partial failure
- `MigrationWizard`: skip `loadSessions` post-message when errors are
present; send it from the "Continue" button instead
* refactor(migration): extract MigrationError component and error selector utilities
Replace inline error text rendering in MigrationWizard with a dedicated
MigrationError component that displays a structured error box with a
copy-to-clipboard action. Extract error parsing logic into reusable
selector functions in a separate module.
- Add `MigrationError` component with header, detail text, and
preformatted error code block; copy button writes error to clipboard
and shows a success toast
- Add `error-selectors.ts` with `getMigrationError` (strips error type
prefix), `getSessionMigrationError`, and `getSessionMigrationErrorDetail`
- Replace `<Show>` + raw `error-text` div in MigrationWizard sessions
row with `<MigrationError>` using the new selector-derived signals
* feat(migration): introduce view-model module for migration state derivations
Extract `ProgressEntry` type and inline derived-state functions from
`MigrationWizard` into a dedicated `migration-view-model.ts` module,
and update call sites to use the new public API.
- Add `migration-view-model.ts` exporting `ProgressEntry`, `getGroupStatus`,
`getGroupMessage`, `getSuccessCount`, `getTotalCount`,
`getCurrentSessionError`, and `getCurrentSessionErrorDetail`
- Remove duplicated logic from `MigrationWizard` and delegate to the
new module, keeping the component focused on rendering concerns
- Consolidate the `getGroupMessage` resolver used by error selectors so
it is derived from a single source of truth
* refactor(legacy-migration): split shared types into dedicated modules
Move `MigrationResultItem` out of `legacy-types.ts` into a new
`migration-types.ts` module, and introduce a `MigrationFailure`
typed error structure in `errors/migration-failure.ts`.
- Add `migration-types.ts` exporting `MigrationResultItem` to separate
runtime migration result types from legacy configuration types
- Add `errors/migration-failure.ts` defining `MigrationFailure` and
`MigrationFailureKind` for structured error classification
- Remove `MigrationResultItem` from `legacy-types.ts` to eliminate
the coupling between legacy config shapes and migration output types
- Update `migration-service.ts` import to reference the new module
* feat(errors): add migration error normalization utilities
Introduce `migration-error.ts` with `normalizeMigrationError` and
`getMigrationErrorMessage` to convert arbitrary thrown values into
typed `MigrationFailure` objects.
- Classify errors by kind (`http`, `sdk`, `generic`, `unknown`) based
on the presence of `status`, `data`, `body`, or `Error` instance
- Extract human-readable message from `message`, `body`, `data`, or
raw string fallback, defaulting to "Unknown migration error"
- Compose a `detail` string from status code, body, and data fields
when they differ from the primary message
- Propagate nested `cause` text for additional diagnostic context
* refactor(migrate): wrap migrate return in typed Result and normalize errors
* chore(migration): inline view-model helpers and remove extracted modules
Remove the separately extracted `migration-view-model.ts`, `error-selectors.ts`,
`MigrationError.tsx`, and `MigrationFailure` type in favour of inlined logic
directly in `MigrationWizard` and a simplified `getMigrationErrorMessage`
utility.
- Delete `MigrationFailure` type and `normalizeMigrationError`; replace with
a flat `getMigrationErrorMessage` function
- Inline `ProgressEntry` interface, group-status logic, and count helpers
into `MigrationWizard`
- Replace `MigrationError` component with inline clipboard copy handler
using `showToast`
- Simplify session migrate result shape: drop structured `error` field,
surface plain `message` string instead
* feat(i18n): add migration error copy-to-clipboard translations across all locales
* style(migration): add error box and copy button styles for migration wizard
Add CSS for the error display box and copy-to-clipboard button in the
migration wizard, including layout, typography, theming via VSCode CSS
variables, hover/active/focus-visible states, and high-contrast border
overrides. Also align wizard items to flex-start for multi-line content.
* fix: merge conflict issues resolved
* fix: formatting
* i18n(migration): add localized strings for session migration progress and errors
* fix:formatting
* feat(session-import): remove temporary test error from project import
* fix(vscode): remove unused migration progress translations
* fix: formatting
* fix(migration): track individual session progress instead of grouping all sessions
Replace the single "Chat sessions" progress item with per-session
tracking, passing the session ID directly to onProgress calls and
mapping each session to its own pending item in the wizard's progress
list.
* fix: formatting
---------
Co-authored-by: Marius <marius@kilocode.ai>
Co-authored-by: kiloconnect[bot] <240665456+kiloconnect[bot]@users.noreply.github.com>
Co-authored-by: Mark IJbema <mark@kilocode.ai>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
The family.size <= 1 early-return caused costBreakdown to return []
for sessions without subagents, making TaskHeader sum to 0 and hide
the cost badge entirely. Remove the guard so single-session cost is
still reported.
totalCost was a redundant memo that duplicated the same sessionFamily
walk already done by costBreakdown. TaskHeader now sums the breakdown
entries directly, eliminating the extra accessor from the context.
* fix(agent-manager): prevent model comparison popover from dismissing on interaction
Harden Popover dismiss logic against SolidJS DOM detachment during
reactive updates that caused the multi-model selector to close on every
click (Windows). Disable Kobalte built-in interact/focus-outside
dismissal in favor of custom window-level handlers with isConnected and
relatedTarget guards. Change compare popover placement to top-start with
flip disabled.
Closes#7990
* fix(ui): drop relatedTarget guard that blocked keyboard focus-outside dismiss
The isConnected check already handles SolidJS DOM detachment. The
relatedTarget guard prevented closing when tabbing out because the
element losing focus was still inside the popover.
Tab KiloProvider instances (Open in Tab and TabPanel deserializer) were
missing setContinueInWorktreeHandler, causing "Continue in Worktree" to
silently no-op and leave the spinner stuck on "Capturing changes..." forever.
Wire the handler for both openKiloInNewTab and the tab deserializer, and
add a defensive error fallback in KiloProvider when the handler is null.
- Use <div> per entry instead of newline-joined string (Tooltip value
prop accepts JSX, not plain text with newlines)
- Prefer subagent_type over description for shorter labels
- Truncate labels longer than 24 chars
- Add white-space: nowrap to prevent wrapping within entries
When a session has subagent costs, the cost tooltip in the task header
now shows a line-by-line breakdown (e.g. 'Parent session: $0.12',
'Code review: $0.08'). Labels come from the task tool's input
description or subagent_type. When there's only one session (no
subagents), falls back to the simple 'Session cost' tooltip.
The previous approach searched store.sessions by parentID, but child
sessions are not reliably present in store.sessions (they arrive via
SSE and syncSession, not the initial sessions list). This caused the
totalCost to miss subagent costs entirely—or even show a lower total
than a single subagent's cost.
Switch to sessionFamily() which does a BFS walk through tool parts to
discover all descendant session IDs, then sum costs from their messages
in the store. This is the same proven mechanism used for scoped
permissions, questions, and familyData.
* feat(vscode): detect sessions in old extension
* feat(vscode): added session types
* feat(cli): add endpoints for inserting a session
* feat(vscode): use session types from sdk for parsing
* feat(kilo-vscode): parsing session project
* feat(vscode): parse legacy session details
* feat(kilo-vscode): refactoring
* feat(vscode): parse legacy session messages
* feat(vscode): parse legacy session parts
* feat(vscode): added testing files and id creation
* feat(vscode): merge tool parts on imported session
* feat(vscode): session message part refactoring
* feat(vscode): cover provider-specific reasoning parts on session migration
* feat(kilo-vscode): handle completion result parts
* feat: type hardening on session migration
* feat(kilo-vscode): create tool part correctly
* feat(kilo-vscode): adjust session part processing
* feat(vscode): persist migrated session in kilo.db
* feat(vscode): add error handling to session migration
* feat(vscode): add directory field to session migration
* feat(kilo-vscode): display completion check on session migration
* feat(vscode): prevent migrating sessions twice
* feat(cli): use correct project id when inserting migrated session
* feat(kilo-vscode): Use correct project id for session migration
* feat(kilo-vscode): load sessions on migration complete
* feat(kilo-vscode): ignore environment details user part when migrating sessions
* feat(cli): create project details following current backend logic
* feat(kilo-vscode): cleaner messages without environment_details parts
* feat(kilo-vscode): refactoring
* feat(kilo-vscode): refactoring and organization
* feat(kilo-vscode): method renaming to improve clarity
* feat(kilo-vscode): added session migration test strategy
* test(kilo-vscode): implement legacy migration unit tests for all migration modules
Replace todo stubs with full test implementations across messages,
parts, tools, reasoning, parser, migrate, project, and session test
files. Add new project.test.ts and session.test.ts covering project
construction, session metadata, and deterministic ID generation.
* style(kilo-vscode): apply prettier formatting across legacy migration source and test files
* fix(legacy-migration): filter out non-user/assistant entries before parsing messages
Exclude system and other non-conversational roles from the conversation
array prior to mapping, ensuring parentID references remain consistent
across imported messages when skipped entries exist.
* refactor(parts): skip part generation for non-conversational message roles
Entries with roles other than user or assistant should not produce
parts, keeping part output consistent with the messages that are
actually imported during legacy migration.
* fix(ids): use semantic kind strings to prevent part ID collisions for reasoning entries
Replace numeric indices with descriptive kind strings ("reasoning",
"provider-reasoning") in extra part ID generation to avoid collisions
between reasoning parts and regular content parts within the same
message.
Introduce `createExtraPartID` to distinguish reasoning-specific IDs
from standard sequential part IDs produced by `createPartID`.
* refactor(session-import): guard against empty worktree in legacy project import
Prevent silent misattribution of migrated sessions by rejecting empty
worktree paths before resolving the project directory. Without this
check, an empty string would fall back to the current process directory,
causing the imported session to be attached to the wrong project.
* perf(cli): cache MCP listTools results to avoid redundant RPCs per loop step (#7922)
MCP.tools() called client.listTools() for every connected server on
every agent loop iteration. With multiple servers this added hundreds
of milliseconds of overhead per step (measured ~300-750ms for remote
servers like Vercel).
Cache listTools results in a module-level Map and return them on
subsequent calls. The cache is invalidated on:
- ToolListChangedNotification from the MCP server
- Server add/connect/disconnect
- Instance dispose (config change, project switch, shutdown)
* fix(agent-manager): add retries to worktree cleanup for macOS .app bundles (#7921)
* chore: hide non-English localization files in GitHub PR diffs
Mark all non-English i18n locale files as linguist-generated=true so
they are collapsed by default in GitHub PR diffs, reducing noise when
reviewing changes that touch translation files.
* feat(vscode): add Browse Marketplace button to MCP settings
Add a "Browse Marketplace" button to the MCP Servers subtab in Agent
Behaviour settings, guiding users to discover and install MCPs from the
marketplace rather than only configuring them manually.
- Add button above the MCP server list that opens the Marketplace panel
- Add openMarketplacePanel webview message type and handler
- Add translations for all 18 supported languages
* fix(vscode): preserve project directory when opening marketplace from settings
Pass the current panel's project directory through to the marketplace
panel so project-scoped MCP installs work correctly in multi-root
workspaces. Without this, the marketplace panel would fall back to
null project directory since there is no active text editor when
clicking from a webview.
* feat(vscode): add Browse Marketplace button to agents and skills tabs
Add the Browse Marketplace button to the Agents and Skills subtabs in
Agent Behaviour settings, matching the existing button in the MCP
Servers subtab. This lets users discover marketplace items from any
of the three configuration tabs.
- Agents tab: added as a ghost button in the header row alongside
Import and Create Mode buttons
- Skills tab: added as a secondary button at the top-right, matching
the MCP tab layout
- Extracted the browse handler to the component scope for reuse
* chore: update kilo-vscode visual regression baselines
* perf(agent-manager): extend slimPart to strip heavy tool metadata for faster session switching (#7927)
Extend slim-metadata.ts to handle apply_patch, multiedit, write, and bash
tools in addition to edit. Previously only edit tool parts had their heavy
metadata stripped before IPC serialization. apply_patch parts carried full
file before/after contents per file, write parts carried the entire written
file, and bash parts carried up to 30KB of output — all serialized on every
session switch.
This reduces session-switch time by ~2x for sessions with many tool calls.
* style(legacy-migration): reformat long reasoning push call for readability
* refactor(legacy-migration): filter non-user/assistant entries before indexing
Move the role filter from inside `parseParts` to `parsePartsFromConversation`
so that message indices are derived only from the filtered list. This ensures
part message IDs stay aligned with the imported messages and skipped entries
(e.g. system role) do not cause index gaps in the generated IDs.
* fix(legacy-migration): add `_migrated_` infix to generated IDs
Prefix all migrated entity IDs (sessions, messages, parts) with a
`_migrated_` segment so they are clearly distinguishable from IDs
produced by the regular runtime. Updates tests to assert the new
prefix format.
* refactor(legacy-migration): consolidate conversation parsing into `parseSession`
Remove the intermediate `createMessages` and `createParts` async
wrappers that each independently read and parsed the conversation
file. The file is now fetched and parsed once in `parseSession`,
with the resulting conversation passed directly to
`parseMessagesFromConversation` and `parsePartsFromConversation`,
eliminating redundant I/O.
* fix(parts-builder): remove `toTextWithinMessage` and use `toText` directly
`toTextWithinMessage` was a duplicate of `toText` with identical
behavior. Replace all call sites with `toText` and delete the
redundant function.
* fix(parts-builder): skip provider-specific reasoning when explicit reasoning entry exists
Guard `isProviderSpecificReasoning` with `!isReasoning` to prevent
duplicate reasoning parts when an entry carries both a `type:
"reasoning"` field and a provider-specific reasoning field (e.g.
`reasoning_content`). The explicit reasoning entry takes precedence.
* test(legacy-migration): add coverage for edge cases in parts and tools parsing
Add unit tests for two previously uncovered scenarios:
- Task block extraction: verify only the content inside `<task>` tags
is kept when text exists outside the legacy task wrapper
- Empty tool result: verify the tool name is used as fallback output
when `tool_result` carries no readable text content
Also replace the dynamic `FileType.Directory` workaround with the
direct `vscode.FileType.Directory` enum reference, and harden
`parseFile` to throw on non-array JSON instead of silently returning
an empty array.
* feat(legacy-migration): remove session migration tracking from global state
Drop the `readSessionsToMigrate` filter and the post-migration
`globalState` flag that tracked which sessions had already been
migrated. Detection now returns all sessions found in global storage
without filtering by prior migration status.
* fix(session-import): skip duplicate session imports and child data
Check for an existing session row before inserting and return a
`skipped: true` flag when the session already exists. The migration
client honours this flag to bypass message and part imports, avoiding
redundant work when migration is re-run.
Replace `onConflictDoUpdate` with `onConflictDoNothing` on the session
insert path to align with the new pre-check behaviour. Propagate the
optional `skipped` field through the result types and generated SDK
types for project, session, message, and part responses.
* refactor(parts-builder): mark legacy system error text parts as ignored
Tag text parts whose content begins with `[ERROR]` with `ignored: true`
and a `legacy-system-error` metadata source. Introduces a new
`isLegacySystemErrorText` utility in `parts-util` to encapsulate the
detection logic.
* feat(parts-util): extract feedback text from tool_result content into visible parts
Parse `<feedback>` tags embedded in `tool_result` content and emit a
dedicated text part so user feedback is surfaced as a visible message
rather than buried inside tool result data.
Introduces `getFeedbackText` utility to extract and trim the inner
content of `<feedback>` blocks from arbitrary input.
* fix: formatting
---------
Co-authored-by: Marius <marius@kilocode.ai>
Co-authored-by: kiloconnect[bot] <240665456+kiloconnect[bot]@users.noreply.github.com>
Co-authored-by: Mark IJbema <mark@kilocode.ai>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Swap order in KilocodePaths.skillDirectories() so global dirs (~/.kilo,
~/.kilocode, VSCode storage) are pushed first, followed by project-level
dirs. Since addSkill uses last-write-wins, project-level skills now
correctly take precedence over global skills.
Fixes#7886
When a provider emits tool-call without a preceding tool-input-start
event, the tool call was silently dropped causing conversation history
corruption and 400 errors on subsequent API requests.
This change creates a fallback tool part in the tool-call handler when
tool-input-start was never emitted, ensuring the tool call is persisted
and included in conversation history.
* fix(sdk): pass duplex in fetch init to survive VS Code proxy-agent wrapper
VS Code's vscode-proxy-agent wraps globalThis.fetch and, when proxy or
certificate support is active, calls originalFetch(request, { ...init,
dispatcher }). The previous fix set duplex on the config which propagated
to new Request() construction, but the custom fetch wrapper called
fetch(request) with no init arg. The proxy wrapper then created a new
init without duplex, causing undici to throw on Windows machines with
corporate proxy/cert settings.
Pass { duplex: 'half' } as the explicit init argument in the custom
fetch wrapper so it survives the proxy-agent spread.
Fixes#7847, #7872
* fix(sdk): include timeout in fetch init to preserve Bun timeout override
Address bot review: passing an init arg to fetch() causes Bun to clone
the Request, dropping the req.timeout = false property. Move timeout
into the init object so it survives the clone.
On Windows, VS Code's uri.fsPath returns lowercase drive letters (e.g. c:\...)
while Filesystem.resolve() canonicalises them to uppercase (C:\...) via
realpathSync.native. Sessions are stored with the resolved path but queried
with the raw fsPath, so SQLite's binary equality check never matches and no
sessions are shown after restart.
Apply Filesystem.resolve() to the directory filter in Session.list and
Session.listGlobal so both sides use the same canonical form.
Replace static "Try model" text with "Try <model name>" using the
model catalog display name. The i18n template now uses {{model}}
interpolation across all 18 locales.
Alex Gold