342 commits

Author	SHA1	Message	Date
STAR-QUAKE	de0ba9d065	fix(agent-core): count validation-rejected tool calls toward the repeat breaker (#2313) ... * fix(agent-core): count validation-rejected tool calls toward the repeat breaker Args-rejected calls returned before prepareToolExecution, so the breaker never counted them and the model could re-issue the same invalid call until maxSteps. Register them in finalizeToolResult so reminders fire at 3/5/8 and the turn force-stops at 12. * fix(agent-core): key parse-failed repeats on raw argument text Malformed JSON arguments normalize to {} on parse failure, which keyed every malformed-but-different attempt identically and could force-stop a turn whose calls were evolving rather than identical. Register skipped calls on the raw arguments text when parsing failed. --------- Co-authored-by: fengchenchen <fengchenchen@moonshot.ai>	2026-07-28 18:39:26 +08:00
Petrichor	cdbd33c13c	fix(kosong): fail fast on quota-exhausted 429 instead of retrying (#1857) ... * fix(kosong): fail fast on quota-exhausted 429 instead of retrying A 429 caused by an exhausted account quota or insufficient balance (Moonshot error.type "exceeded_current_quota_error", OpenAI "insufficient_quota") can never succeed on retry, yet it was classified as APIProviderRateLimitError and silently retried for the whole budget (10 attempts, ~3 minutes of backoff) with no UI feedback — the session appeared frozen on every request. Introduce APIProviderQuotaExhaustedError, minted in normalizeAPIStatusError from the structured body error.type/error.code forwarded by convertOpenAIError, with billing-anchored message patterns as a fallback for gateways that flatten the body to text. The new class is excluded from isRetryableGenerateError (fail fast, even when a retry-after header is present) and from isProviderRateLimitError (no swarm requeue/suspend). toKimiErrorPayload and translateProviderError map it to provider.api_error (retryable: false) instead of provider.rate_limit, and classifyApiError reports it as quota_exhausted in telemetry. agent-core-v2 mirrors the same fix. Transient rate-limit 429s keep the existing retry, backoff, and Retry-After behavior (verified end-to-end against a mock provider: quota body fails after attempt 1/10; rate-limit body still walks the full 10-attempt ladder). Behavior changes to note: quota-failed swarm subagents now fail instead of suspending indefinitely as "Rate limited...", and quota errors cross the wire as provider.api_error rather than provider.rate_limit. * fix(kosong): classify quota exhaustion in OpenAI Responses stream errors Responses response.failed / error SSE events carry no HTTP status and were minted by errorFromOpenAIResponsesEvent as either a rate-limit error (rate_limit_exceeded / embedded status_code=429) or a base ChatProviderError — and the base class falls into the retryable unclassified-failure fallback, so an insufficient_quota event still burned the whole retry budget on the openai_responses path. Route the event code and message through the same quota-exhausted check before the rate-limit branch, in kosong and the agent-core-v2 mirror. Covers all three entry paths (error events, response.failed, nested gateway frames) since they share the single converter. * style(agent-core-v2): drop inline comments per AGENTS.md header-only rule agent-core-v2 comments live solely in the top-of-file block, never beside functions or statements; the kosong twins keep the full rationale. * refactor(kosong,agent-core-v2): move quota-429 checks to vendor hook Per review on #1857: the knowledge of how a backend signals quota exhaustion is vendor-specific and must not run for every OpenAI-compatible provider from the shared conversion layer. - Add a convertError hook: ProtocolTrait.convertError in agent-core-v2 (single-value, last-declarer-wins, bound by composeOpenAIChatHooks / composeAnthropicHooks / traitConvertError) and an equivalent optional hook parameter on convertOpenAIError / convertAnthropicError. Bases consult it with the raw failure (SDK error on HTTP paths, raw event on the Responses in-stream path) after the abort guard, before their own rules. - Declare Moonshot's quota signals (exceeded_current_quota_error, billing wordings) on the Kimi side: kimiOpenAITrait and kimiAnthropicTrait in v2, the KimiChatProvider and KimiFiles catch sites in kosong, all through the new classifyKimiQuotaError. - Drop the options parameter from normalizeAPIStatusError and the shared quota code/pattern tables: the contract layer keeps only the vendor-neutral APIProviderQuotaExhaustedError type and its retry / rate-limit / wire-mapping semantics. - The OpenAI bases keep recognizing only OpenAI's own documented insufficient_quota code (HTTP and Responses stream events) as protocol knowledge of that wire. Behavior: kimi and openai provider types classify exactly as before; an unregistered vendor speaking Moonshot billing wordings through a plain openai transport now stays a retryable rate limit by design. * fix(kosong,agent-core,agent-core-v2): wire kimi quota hook fully Follow-up to the second review round on #1857, all four findings: - Kimi-over-Anthropic (legacy engine): AnthropicOptions gains the same optional convertError hook as the OpenAI bases, threaded through AnthropicStreamedMessage and every catch site, and the provider manager's anthropic route now passes classifyKimiQuotaError for provider type kimi — a quota-exhausted 429 over this transport previously still burned the retry budget. classifyKimiQuotaError now also walks error -> .error -> .error.error for the code/type, since the Anthropic SDK keeps the full body on .error instead of hoisting. - v2 telemetry: ApiErrorKind gains 'quota_exhausted' and classifyApiError checks APIProviderQuotaExhaustedError before the generic 429 branch, matching the legacy engine's reporting. - Hook contract: converted ChatProviderErrors now pass through before the vendor hook is consulted in convertOpenAIError / convertAnthropicError (both engines), so the hook sees each raw failure exactly once even when a stream-minted error crosses an outer catch; tests assert the single consult. - protocolTrait: the convertError member doc shrinks to the concise style and the consult contract moves into the file header's composition rules. * test(kosong,agent-core,agent-core-v2): lock quota hook assembly paths Third review round on #1857: - Fix the v2 anthropic base header and AnthropicHooks doc still claiming withThinking is the only hook. - Drop the two remaining non-header JSDoc blocks in protocolTrait.ts per the AGENTS.md header-only rule; the consult contract already lives in the file header. - Update the ProtocolTrait contract test to the seventeen-hook shape (convertError included) and cover the traitConvertError binding. - Add real-assembly regression probes: the v2 registry composes a (kimi, anthropic) provider whose mocked SDK client throws a Moonshot quota 429 and generate rejects with the non-retryable APIProviderQuotaExhaustedError (a plain anthropic composition keeps the same 429 retryable); the legacy ProviderManager routing test asserts convertError is classifyKimiQuotaError on the kimi-anthropic route and absent for plain anthropic; the legacy provider threads options.convertError to its generate catch. * test(kosong,agent-core-v2): cover KimiFiles quota 429 and drop stale docs Fourth review round on #1857: - Drop the AnthropicHooks member JSDoc (its content already lives in the anthropic.ts and anthropicHooks.ts file headers) and fix the anthropic contrib header still calling the hook set single-hook. - Add the missing KimiFiles regression in both engines: a mocked files client rejecting with a Moonshot quota 429 makes uploadVideo reject with the non-retryable APIProviderQuotaExhaustedError, locking the classifyKimiQuotaError argument at the upload catch sites.	2026-07-28 14:35:12 +08:00
Luyu Cheng	0cef160c4b	fix(agent-core): continue goal pursuit when a goal turn hits the per-turn step limit (#2210) ... * fix(agent-core): continue goal pursuit when a goal turn hits the per-turn step limit * chore(agent-core-v2): regenerate state manifest * fix(agent-core): start goal pursuit when the goal-creating turn hits the step limit * refactor(agent-core-v2): drop step-cap narration from goal module and test	2026-07-27 00:30:33 +08:00
Luyu Cheng	c497af60e6	fix(tui): steer user messages into the running turn while a goal is active (#2153) ... * fix(tui): steer user messages into the running turn while a goal is active * fix(tui): reset request state when steering mid-goal input fails * fix(agent-core): update session prompt metadata on steer	2026-07-25 02:12:24 +08:00
Liu Zhongnuo	f06eb5c60e	feat(agent-core): defer registered user tools (#2119) ... * feat(agent-core): defer registered user tools Allow hosts to mark registered user tools as deferred so select_tools can discover and load their schemas on demand in both agent-core implementations. * fix(agent-core): hide unregistered deferred tools Filter loaded deferred user-tool schemas from provider history and loaded-state checks after unregister while preserving canonical history and disconnected MCP behavior. * fix(agent-core-v2): drop stale inline schemas Stop treating previously loaded user-tool schemas as active after the same tool is re-registered for inline disclosure.	2026-07-24 17:48:36 +08:00
Kai	66f611aae9	fix: echo thinking under the reasoning field the endpoint actually uses (#2104) ... OpenAI-compatible endpoints disagree on the wire field for reasoning content: `reasoning_content` (DeepSeek/Moonshot convention, older vLLM) vs `reasoning` (OpenAI GPT-OSS guidance, current vLLM — which also only accepts `reasoning` on the request side, vllm-project/vllm#38488). Reading only `reasoning_content` silently dropped thinking, and the lost thinking then never made it back into later requests. Add per-endpoint dialect detection: inbound responses are scanned in priority order (reasoning_content, reasoning_details, reasoning; first string value wins), the carrying key is remembered, and outbound messages echo thinking under the same key (default reasoning_content). An explicit `reasoningKey` / `reasoning_key` config still pins the dialect. - kosong: shared reasoning-key module; wire the kimi and openai-legacy providers; the dialect cell is shared across per-step provider clones. - agent-core-v2: same mechanism in the vendored openai-legacy base; the kimi trait no longer pins reasoning_content (the default already is), keeping Moonshot wire behavior byte-identical while adapting to vLLM. - agent-core: memoize the base provider behind ConfigState.provider so the detected dialect survives across turns instead of being rebuilt per access.	2026-07-23 21:15:00 +08:00
7Sageer	5fdbdb4a22	feat: configure web search/fetch services via KIMI_WEB_* env vars (#2096) ... * feat: configure web search/fetch services via KIMI_WEB_* env vars KIMI_WEB_SEARCH_BASE_URL / KIMI_WEB_SEARCH_API_KEY and KIMI_WEB_FETCH_BASE_URL / KIMI_WEB_FETCH_API_KEY overlay the [services] config section field by field in both engines (env wins over config.toml), so the WebSearch and FetchURL backends can be pointed at a Moonshot service without OAuth login. The v2 engine now also honors the explicit [services.moonshot_fetch] section (config > managed OAuth > local), which it previously parsed but never consumed. * fix(agent-core-v2): guard stripServicesEnv against clearing the services section config.replace(SERVICES_SECTION, undefined) — the logout deprovisioning path in authService — passes undefined straight into the section strip, and the composed stripServicesEnv dereferenced it (value[key]), throwing TypeError and aborting logout mid-cleanup. Add the same isPlainObject guard the other strip implementations (stripProvidersEnv, stripEnvBoundFields) already have, plus a regression test that also locks in the env overlay staying effective after the file value is cleared. * style(agent-core-v2): follow header-only comment convention * fix: isolate env web service credentials * Add env vars for web search and fetch services The new environment variables `KIMI_WEB_SEARCH_BASE_URL`, `KIMI_WEB_SEARCH_API_KEY`, `KIMI_WEB_FETCH_BASE_URL`, and `KIMI_WEB_FETCH_API_KEY` take priority over the corresponding fields in `config.toml`. The `kimi web` backend now honors the `[services.moonshot_fetch]` config section. Signed-off-by: 7Sageer <sag77r@hotmail.com> --------- Signed-off-by: 7Sageer <sag77r@hotmail.com>	2026-07-23 17:36:16 +08:00
7Sageer	527d485d92	feat: add global default MCP server timeout configs (#2065) ... * feat: add global default MCP server startup timeout config Add a `[mcp] startup_timeout_ms` config.toml section with a `KIMI_MCP_STARTUP_TIMEOUT_MS` env override as the global default MCP server connection (startup + tool discovery) timeout. Precedence: per-server `startupTimeoutMs` in mcp.json > env var > config.toml > built-in 30s default. * feat: add global default MCP tool call timeout config Extend the `[mcp]` section with `tool_timeout_ms` and the `KIMI_MCP_TOOL_TIMEOUT_MS` env override as the global default for single MCP tool calls, mirroring the startup timeout: a per-server `toolTimeoutMs` in mcp.json still wins, and unset entries fall back to the SDK built-in 60s default. * chore: shorten the mcp timeouts changeset * feat(agent-core): add global default MCP server timeout configs Port the `[mcp]` section (`startup_timeout_ms` / `tool_timeout_ms`) and the `KIMI_MCP_STARTUP_TIMEOUT_MS` / `KIMI_MCP_TOOL_TIMEOUT_MS` env overrides to agent-core (v1), mirroring the v2 semantics: per-server fields in mcp.json > env vars > config.toml > built-in defaults. The v1 TOML loader gains explicit `mcp` read/write mappings, and both connection-manager construction sites (Session, testGlobalMcpServer RPC) pass the resolved defaults through. * fix(agent-core): validate and apply MCP timeout defaults * fix: propagate MCP startup timeout to SDK requests * refactor(agent-core-v2): resolve MCP default timeouts at connect time Keep the session connection manager synchronously lazy instead of gating its existence on config readiness: resolveDefaultTimeouts is read from the mcp config section at each (re)connect, so AgentMcpService's eager construction stays unconditionally safe and reconnects pick up changed preferences. The initial connect still awaits config.ready for a deterministic snapshot. Also restore the ISessionMcpService method docs, bump the changeset to minor, and fix the v1 env-parse comment. * chore(agent-core-v2): regenerate config manifest for the mcp section * Add global default MCP server timeouts configuration Specify the new global default MCP server timeouts in both the config file and environment variables. Signed-off-by: 7Sageer <sag77r@hotmail.com> --------- Signed-off-by: 7Sageer <sag77r@hotmail.com>	2026-07-23 12:41:08 +08:00
github-actions[bot]	8bf5bacba9	ci: release packages (#1989) ... Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2026-07-22 17:24:39 +08:00
Haozhe	8250e590f3	docs(cron): drop references to the non-existent kimi resume command (#2050) ... * docs(cron): drop references to the non-existent `kimi resume` command - point user docs at the real resume command `kimi --session` - reword cron tool descriptions and code comments in agent-core and agent-core-v2 to describe session resume without naming a subcommand * chore: add changeset for cron docs wording fix	2026-07-22 16:59:08 +08:00
Kai	4c763f6763	feat: send prompt-attached videos directly with the prompt (#1999) ... * feat: send prompt-attached videos directly with the prompt Videos attached to a prompt (pasted in the TUI, uploaded in the web UI) previously reached the model only after it opened the file with ReadMediaFile — an extra tool round trip that could leave the video unseen when the model never made that call. They are now uploaded through the model provider's file channel and embedded directly in the user message as the provider-issued reference; ReadMediaFile stays as the fallback and as the model's own way to open video files. - agent-core: new uploadVideo agent RPC and Session.uploadVideo in the SDK; the TUI uploads pasted videos at submit time, falling back to the file-tag form on failure - kap-server: inline file-source video prompt parts at the REST edge and map provider file ids back to local uploads behind GET /files/llm/{llm_id} - kimi-web: play provider-referenced prompt videos after reload/resume * fix: fall back to inline video when the upload channel fails ReadMediaFile only used the provider's video upload channel when one was bound, and surfaced a hard tool error when the upload itself failed — on providers without a files endpoint (or a transient upload failure) the model was told the video could not be read at all. Now a missing or failing upload falls back to delivering the video inline (base64), the same shape providers without an upload channel already get. Both engines (agent-core and agent-core-v2) are fixed. * test: cover prompt video edge cases and failure paths Stress coverage for the prompt video pipeline: - agent-core uploadVideo RPC: extension/magic classification (.txt with video bytes accepted, extension trusted when magic is absent), exact 100MB boundary, directory and nonexistent paths - TUI: mixed per-video outcomes (one inlined, one tag fallback), submission order behind an in-flight upload, queued video messages carrying final uploaded parts - kap-server: per-video provider-id mappings, Range requests through the llm redirect, mapping persistence across a server restart * fix: surface auth rejections from the video upload channel The base64 fallback for a failing video upload must not mask auth rejections: a 401/403 (surfaced as provider.auth_error) drives the credential force-refresh and a clear auth error, while an inline payload would just be rejected again by the next request. Only a missing or broken upload channel (no files endpoint, network/server errors) falls back to inline delivery. * fix: keep the by-design no-hook video error from degrading to inline Main's contract for a provider with no video upload hook is an honest "does not support video upload" tool error — an inline payload would be dropped on that protocol's wire anyway. The base64 fallback now only applies to an upload channel that exists but failed at runtime. The no-hook throw gets a stable type (VideoUploadUnsupportedError) so the two cases are told apart without matching message text. * fix: constrain the llm video route param to a safe alphabet The provider file id is used as a blob-store key, and the node-fs backend joins scope and key into a storage path. An id containing an encoded path separator (%2F) could address a different storage path than the intended llm-video mapping; the route now only accepts the provider-id alphabet. * style(agent-core-v2): move added explanations into top-of-file comment blocks The package's comment convention keeps comments solely in the top-of-file block; relocate the new notes (url-source id pairing, video delivery fallback, VideoUploadUnsupportedError) from functions and schema fields into their module headers. * fix: reject prompt video uploads when the model lacks video input The uploadVideo RPC only checked the provider's upload channel, so an SDK caller on a text-only or unknown-capability model could obtain a valid-looking video_url part the current model is not supposed to accept. The TUI capability guard does not cover this public path, so the agent now gates on video_in itself. * fix: sniff uploaded video bytes before inlining them The inline branch trusted the upload-time content type; now the bytes are sniffed first, and anything magic-confirmed as a non-video kind (e.g. an image mislabeled as video/mp4) falls back to the file-tag form instead of being uploaded. Like the image gate, bytes are authoritative where the container format allows it — an MPEG-PS lookalike still rides the extension, matching ReadMediaFile. * test: keep the generation stub pending until the abort lands An immediately-answered 404 ends the turn (non-retryable) before the test's abort call, racing the cleanup into a 409; the stub now hangs generation until the abort cancels it. * fix: validate prompt file references before mutating session controls A stale file_id failed inside media resolution — after the model, thinking and permission overrides had already been applied — so a rejected prompt still changed the session's controls. File references are now checked up front, keeping failed submits side-effect free. * fix: serialize prompt submissions per session A slow provider video upload let a later text-only request reach the queue ahead of an earlier video one, silently reordering the conversation for REST clients and multiple tabs. Submissions to the same session now chain, matching the ordering the TUI already guarantees locally. * fix: play reloaded provider videos through the authenticated fetch path A video recovered from an ms:// reference carried only the bare redirect URL, which 401s under daemon auth when loaded natively. The attachment now keeps the provider file id (llmFileId) end to end, and AuthMedia fetches the bytes with the Bearer credential through the daemon's llm redirect — the same blob-URL path uploaded files already use. * fix: fence pending video submits against session and model switches A slow paste-upload left the TUI idle, so /new, the session picker or /model could fire mid-upload; the continuation then dispatched the old session's provider reference into the newly selected session or a model that cannot resolve it. The dispatch now re-checks that the session and model are unchanged and asks for a resend instead. * fix: preserve the caller's video path verbatim in uploadVideo Trimming the path changed the filesystem target before validation and upload, so a name that legitimately starts or ends with whitespace resolved to the wrong file; the trim is now only the emptiness check. * fix: forward provider-issued ids on image URL prompt parts too The shared url-source schema accepts id for image and video parts, but only the video path forwarded it, dropping provider-keyed image ids between prompt acceptance and the model request. * fix(web): reconcile inlined video echoes into the optimistic user message The loose user-message matcher counted media parts and <video path> tags but not the [video:ms://…] text shape, so a racing server echo of an inlined upload slipped through as a duplicate user bubble. * fix: queue bash submits behind a pending video upload A bash-mode submit could start while a pasted video was still uploading, recording shell context before the earlier prompt was dispatched and reordering user actions; it now chains behind the upload like normal submits. * test: cast the driver through unknown for the session-switch fence test * fix: validate prompt file references before resolving the prompt agent A stale file_id posted to a fresh or cold session materialized the main agent (registering it in session metadata and igniting agent-scoped services) before the request was rejected. The file check now runs first, so failed submits create nothing and mutate nothing. * fix: key the playback mapping by the id embedded in the reference URL Projections and clients read the provider id from the ms:// URL, not the id field, so an upload that returns an id-less or mismatched reference would inline fine but 404 on playback. The mapping now derives its key from the URL, falling back to the explicit id. * fix: sanitize provider video ids on the write side of the playback map The read route got the safe-alphabet guard, but recordLlmVideoRef still used the provider-returned id verbatim as a blob-store key; a crafted provider response could write the mapping outside the llm-video namespace. Out-of-alphabet ids are now dropped on both put and get. * fix(web): keep recovered provider videos resendable through the edit path The composer reload path only honored fileId and fell back to a bare fetch(url) without the Bearer token, so editing a reloaded provider-video turn dropped the chip after a 401. llmFileId is now threaded through and the bytes are re-uploaded via the authenticated llm redirect. * fix: fall back to inline video for no-hook providers whose wire carries it The by-design no-hook error is only the honest answer when the wire would drop an inline payload anyway (the OpenAI family). Protocols that convert video_url (kimi, anthropic, google-genai, vertex) now take the base64 fallback instead of failing every video read; the registrar computes the flag from the model's protocol. * test: satisfy the full IBlobStore shape in the playback-map stub The tsgo typecheck job rejects a structural stub missing _serviceBrand and list even though plain tsc accepted it. * fix: queue prompt-producing slash commands behind pending uploads Skill activations and plugin commands started their turn immediately while a pasted video was still uploading, so the earlier video prompt queued behind them and user actions ran out of order. Both paths now chain behind inputSubmitChain (and re-check session/model at dispatch) like normal and bash submits. * fix: validate media kinds in the prompt file-reference preflight The preflight only proved a referenced file exists; a real upload used with the wrong kind (e.g. a PDF submitted as video) still passed it and mutated session controls before assertMediaFile rejected the request. The kind assertion now runs up front with the existence check. * fix(web): play sent and recovered videos in the file preview The media preview returned early for every kind except image, so a user-turn video chip's play action was a no-op even with llmFileId threaded through. The preview now handles video: bytes come from the authenticated file/llm fetch into a blob URL and render in a native player. * fix(web): preview recovered videos with the authenticated blob URL The llm re-upload branch fetched bytes with auth but kept the protected redirect URL as the chip preview, which 401s as a native video src; the fetched blob now becomes the preview URL, mirroring the fileId branch. * style(agent-core-v2): move the inline-fallback note into the module header Same package comment convention as before: rationale lives in the top-of-file block, not beside the registration call. * fix: fence delayed bash submits to the originating session The chained bash callback ran runShellCommandFromInput against whatever session was active at dispatch time, so a command submitted in session A could execute in session B's workspace and be recorded there after a mid-upload switch. The originating session is now captured at submit and re-verified at dispatch, like the prompt and skill paths. * fix: emit prompt video telemetry from the agent scope video_upload is an agent-level event requiring ambient agent identity, but the uploader was built with the Core-scoped session view, leaving prompt-upload events unattributable. The route now resolves telemetry from the target agent for the uploader while image compression keeps the session-scoped view. * fix: preserve provider image ids through legacy projections and web mappers The url-source id accepted by the prompt schema was dropped again by the legacy message projection and the web wire mapper, so provider- keyed image references lost their id across messages, snapshots, and undo responses. It now flows through both directions. * fix(web): revoke recovered video blob URLs before dropping attachments A failed llm re-upload removed the attachment without revoking the freshly created preview blob URL, pinning the whole video in the browser blob store until page unload on every failed edit attempt. * fix: serialize foreground slash commands behind pending uploads /compact and /init started their turn while a pasted video was still uploading, so the earlier message landed after them — and compaction summarized the context without it. Prompt-producing builtin commands now share the same queueBehindPendingUploads chain (with the session/model dispatch fence) as skill, plugin, and bash submits. * fix: defer session controls until media preparation succeeds Media resolution now runs before any profile/model/thinking/permission/ denylist mutation, with the uploader resolved transiently from the requested (or currently bound) model — a failed submission leaves the session's controls untouched. A concurrent model switch during preparation is rejected with session.busy instead of enqueueing a reference uploaded for the previous model. * chore: bump the new SDK video upload API as a minor release Session.uploadVideo is new public API surface, not a patch-level tweak. * fix: re-check busy state before draining upload-queued commands A slash command deferred behind a video upload ran the moment the video prompt dispatched, landing on an already-running turn: beginSessionRequest wiped the active turn's live pane, and /init or /compact started on top of it. The deferred callbacks for skills, plugin commands, /compact and /init now re-run the resolver's busy check at dispatch and show the same blocked message the user would get when typing while streaming. * fix: resolve profile-bound models before choosing the uploader A first prompt carrying "profile" without "model" resolved the upload model from the still-unbound alias, so no uploader was installed and every attached video fell back to a tool-read tag even when the configured default model supports provider upload. The transient resolution now mirrors AgentProfileService.bind: an explicit body model wins, a profile bind falls back to the configured default model, and only otherwise does the currently bound alias apply. * refactor: resolve prompt videos at request time inside the engine Move prompt-video delivery out of the submission edge: the TUI submits synchronously with a local file:// part the v1 turn resolves before the message enters history, and kap-server carries an internal kimi-file:// reference the v2 requester resolves against the effective model with an app-scoped upload cache. History keeps the durable local file id, the /messages projection emits structured video parts, and the web plays videos back through the authenticated /files channel - deleting the submit fences, per-session serialization, provider-id reverse mapping, redirect endpoint, and the unreleased SDK upload API. * fix: propagate abort through video upload delivery instead of degrading A turn cancelled mid-upload used to be treated as an ordinary upload failure: v1 fell back to an inline base64 part and appended the degraded message to history, and the v2 resolver memoized the tag fallback for the rest of the agent's lifetime. Both catch sites now check the delivery signal itself - abort rejections vary in shape by provider - and re-throw so cancellation ends the turn (v1, classified as cancelled via the abort reason) or the request (v2, not memoized, so the next turn uploads). * fix: keep the tag form for no-upload providers whose wire drops inline video An OpenAI-family model configured with video_in but no provider upload channel used to receive prompt videos as an inline base64 part - which chat completions rejects and the Responses adapter degrades to an omitted-video placeholder, persisting ~4/3x the file size in history for bytes the model never sees. The prompt path now mirrors the v2 resolver's protocol gate and degrades to the <video path> tag instead; ReadMediaFile's own delivery is unchanged. Also merges the prompt-video changesets into a single user-facing entry. * fix: escape the NUL separator in the video upload cache key The cache-key template literal contained a literal NUL byte instead of the \0 escape, which made Git classify the whole source file as binary - no inline diffs, unreliable text tooling. The escape produces the byte-identical runtime string, so hashed cache keys are unchanged. * fix: check the abort signal before the inline video fallback The no-uploader inline path (and the post-upload-failure fall-through) never consulted the delivery signal, so cancelling a turn while the video bytes were being read still base64-encoded the file and appended the degraded message to history. The inline branch now re-throws the abort reason first, matching the upload catch. * fix: retry transient prompt video upload failures on later steps A generic upload failure used to memoize its tag fallback for the rest of the agent's lifetime, freezing a transient files-endpoint error into a permanently degraded video. The resolver now marks failure-born fallbacks as non-memoizable: the current request keeps the lightweight tag form and the next step retries the upload. Structural outcomes (successful uploads, capability and sniff fallbacks, no-hook inline) stay memoized for step-retry stability.	2026-07-22 13:46:00 +08:00
Kai	ba921ca531	fix: gate always-thinking inference to OpenAI wires, plus catalog review follow-ups (#2036) ... * fix: gate always-thinking inference to OpenAI wires, plus review follow-ups - catalog: strip the inferred alwaysThinking marker on non-OpenAI wires so Claude/Gemini keep their native off; verified against live models.dev - v1 provider-manager: honor per-alias baseUrl on kimi/google-genai/vertexai - thinking: rewrite the PHASE-6 contract comment, drop three dead cannot-disable warning branches, normalize requested effort in v1 to match v2 - tests: input-cap compaction preference in both engines, kap-server WS status cap, v2 legacy status input cap - docs + changeset: new model fields, catalog-refresh behavior, kap-server * fix: strip always-thinking only where the wire encodes a true off The previous gate kept the marker only on the OpenAI wires, which wrongly stripped it from Gemini 3 on the Google wires: its floor is thinkingLevel MINIMAL with suppressed thoughts — still reasoning — so an Off option there would be a lie. The criterion is now the wire's encoding, not its family: strip only on anthropic and kimi, the two wires with a protocol-level `thinking: {type: 'disabled'}` that the catalog's effort list can never show. Verified against live models.dev data: google now marks exactly the gemini-3 family (10), anthropic and moonshotai stay 0. * docs(agent-core-v2): move the strict-validation contract into the thinking.ts file header The scoped guide keeps comments in the top-of-file block only; the function JSDoc shrinks to a short what-it-answers note matching its neighbors. No behavior change.	2026-07-22 13:43:10 +08:00
Kai	ec88d352e8	fix: five correctness follow-ups to the catalog metadata work (#2030) ... * fix: five correctness follow-ups to the catalog metadata work - Normalize a configured effort value (case/whitespace) before thinking resolution on both engines, so "OFF" is read as off instead of being sent upstream as an invalid effort. - Clamp a declared input cap to the effective context window in the effective model resolution, so an override lowering max_context_size cannot leave a stale larger cap behind. - Report context usage against the same effective cap (max_input_tokens ?? max_context_tokens) in the SDK getStatus and the v2 legacy status projections, matching the session-event and service surfaces. - Preserve concretely declared per-model endpoints when the override npm is unrecognized, via the same OpenAI-compatible fallback used for top-level entries. - Attribute resolved.maxInputSize and resolved.capabilities .max_input_tokens in the model inspector to their config, override, or clamp provenance. * fix: honor observed context caps and publish the effective cap in v2 status - The overflow-learned provider window is now written into both max_context_tokens and max_input_tokens of the effective compaction context, so the strategy cannot bypass it by re-selecting the raw catalog input cap during overflow recovery. - agent.status.updated publishes max_input_tokens ?? max_context_tokens, matching the other v1/v2 status surfaces. * fix: never mutate config on clamp, cap usage ratio, and refuse proprietary override SDKs - effectiveModelAlias / effectiveModelConfig now build a copy before clamping maxInputSize to the effective window instead of rewriting the caller's config record in place. - context_usage is clamped to 1 in the v2 legacy status, the v1 session service, and the SDK getStatus; the default-model status fallback also resolves the input cap. - Overrides naming known proprietary SDKs (Bedrock, Cohere) are refused before the OpenAI-compatible fallback, matching top-level import behavior. - The inspector attributes a clamped maxInputSize to the clamp even when the raw value came from models.*.overrides. * fix: normalize forced efforts, prefer input cap in WS status, keep raw event ratio - Whitespace-only configured efforts now read as absent, and the KIMI_MODEL_THINKING_EFFORT override is lowercased on both engines. - kap-server's WS legacy status publishes max_input_tokens ?? max_context_tokens like the other status surfaces. - SDK getStatus keeps the ratio unclamped on purpose (>100% is the documented overflow signal on that path); schema-bounded REST status stays clamped to 1. - Pin the provider-observed window beating a declared input cap with a v1 full-compaction regression test. * fix: attribute resolved.maxInputSize provenance and drop test-body comments in v2	2026-07-22 03:13:10 +08:00
Kai	b5efba7abc	fix: consume the model metadata declared by the models.dev catalog (#2015) ... * fix: stop advertising Claude thinking efforts for non-Claude models Models served over the Anthropic protocol whose names carry no Claude marker (e.g. a catalog-imported Kimi K3) no longer inherit the latest Opus effort list, so the model selector stops offering levels the model does not accept. The models.dev catalog import now also parses reasoning_options and records the declared effort levels on the model alias, so K3 offers its real levels (low / high / max). * fix: consume deprecated, override, and input-limit metadata from the models.dev catalog - Models declared status=deprecated in the catalog are no longer offered for import. - Per-model provider overrides on gateway providers (an npm package targeting an Anthropic SDK plus a usable endpoint) now land as alias protocol and base_url, so those models are served over the right protocol and endpoint; overrides without a usable URL are skipped. - A declared limit.input now sizes the context budget instead of the larger total context window (e.g. gpt-5: 272k instead of 400k). The model alias schema gains an optional base_url field (not accepted in overrides) that Anthropic wire resolution prefers over the provider-level base URL. * fix: honor thinking-disable semantics and the OpenAI-compatible fallback in catalog imports - reasoning_options 'none' is the model's off encoding: off_effort flows from the catalog through the model alias to the OpenAI wire providers, so turning thinking off sends 'none' instead of omitting the effort field; models with effort levels but no way to disable thinking are imported as always_thinking and no longer offer an Off option. - Bare Claude family aliases (e.g. sonnet-latest) recover the inferred Anthropic effort profile; v2 comment conventions restored. - Providers whose SDK the catalog does not type now fall back to the OpenAI-compatible wire (with a visible "guessed" note) instead of being refused; imports lacking a usable endpoint ask for one (--base-url on the CLI, a prompt in the TUI). Proprietary SDKs (Amazon Bedrock), unrecognized explicit types, and env-placeholder URLs are refused with a clear reason. * fix: align catalog imports with the reference models.dev consumer - A JSON null tier in declared effort values is now read as the 'none' off-encoding (previously such models were wrongly imported as always-thinking with no way to turn reasoning off). - Alpha-status models are filtered out alongside deprecated ones. - Models whose per-model provider override targets a wire that cannot be expressed per-model (e.g. Claude on google-vertex, whose wire here is Gemini-mode Vertex, or gpt entries on an Anthropic provider) are skipped instead of being imported under the silently wrong protocol. - interleaved: true no longer pins reasoning_content: the provider's default three-field scan is wider and the pinned key only narrowed reasoning parsing for gateways answering with another field name. * fix: require endpoints for Anthropic-compatible catalog imports and honor --base-url - catalogProviderNeedsBaseUrl now covers the Anthropic wire: a non-official Anthropic-compatible vendor without a concrete catalog endpoint (e.g. google-vertex-anthropic) must supply --base-url / the TUI prompt instead of silently falling back to the default Anthropic endpoint. - --base-url now takes precedence over the catalog-declared endpoint, and an empty --base-url is rejected instead of persisting a blank endpoint. * fix: enforce always-on thinking on every wire and refuse Cohere at import A model that declares always_thinking (e.g. a catalog-imported gpt-5) no longer resolves to a dishonest off state via thinking.enabled=false or an SDK/ACP off request: resolution clamps to the model's default effort on every wire instead of letting upstream keep reasoning while the UI reports Off. The Anthropic warn-and-send path for unlisted effort levels is unchanged. Cohere's proprietary SDK joins Amazon Bedrock on the import-refusal list instead of being guessed as OpenAI-compatible. * fix: harden catalog import edge cases - An explicit but unrecognized catalog type is now refused before npm/id inference, so a future catalog protocol is never silently miswired through the OpenAI fallback. - User-supplied --base-url values for Anthropic-wire providers get the same trailing-/v1 normalization as catalog endpoints, avoiding /v1/v1/messages requests. - The TUI import prompt rejects env-placeholder base URLs like the CLI does. * fix: await the floating assertion promise in the catalog add CLI test * refactor: unify catalog import resolution into a single decision function Wire-type inference, the OpenAI-compatible fallback, proprietary-SDK refusal, endpoint adaptation, and the base-URL requirement are now produced together by resolveCatalogImport, one pure resolver consumed by both the CLI and the TUI — replacing the cooperating predicates (inferWireType, isGuessedWireType, catalogProviderNeedsBaseUrl) whose permutations kept producing edge cases. No behavior change. * fix: close configured-off clamp hole, keep inferWireType compat, carry same-wire override endpoints - A configured thinking.effort = "off" no longer bypasses the always-on clamp: it is treated as absent and the model default applies, mirrored on both engines. - The previously public inferWireType stays as a deprecated compatibility wrapper over resolveCatalogImport so existing SDK consumers do not break on a patch release. - Catalog model overrides that stay on the provider's wire but declare their own endpoint now persist it on the alias (and the v1 OpenAI wire branches honor alias-level base URLs like the Anthropic branch). * fix: split total window from input cap and close override/endpoint gaps - max_context_tokens once again means the total context window (used by completion budgeting); a model's declared input limit is tracked as max_input_tokens, which compaction, context-splice and usage-ratio checks prefer — fixing the over-clamping introduced when the input cap was stored as the context budget. - A catalog endpoint declared only as an env placeholder now always produces needs-base-url (official SDK included), so credentials are never sent to the public vendor host by default. - api-only per-model overrides are honored as same-wire endpoint changes; overrides targeting another known but inexpressible wire (e.g. google-genai on an OpenAI gateway) are skipped; same-wire models whose declared endpoint is an unusable placeholder are skipped instead of silently rerouted. * style: drop a function-level comment from the v2 thinking resolver * chore: consolidate the PR's changesets into two user-facing entries	2026-07-22 01:23:31 +08:00
Kai	37eda4e59a	feat(config): add env overrides for loop control and background task limits (#1993) ... * feat(config): add env overrides for loop control and background task limits Add three operational environment overrides, resolved as env > config.toml > default in both engines (agent-core and agent-core-v2), matching the existing KIMI_IMAGE_MAX_EDGE_PX / KIMI_SUBAGENT_TIMEOUT_MS pattern: - KIMI_LOOP_MAX_STEPS_PER_TURN overrides loop_control.max_steps_per_turn - KIMI_LOOP_MAX_RETRIES_PER_STEP overrides loop_control.max_retries_per_step - KIMI_CODE_BACKGROUND_MAX_RUNNING_TASKS overrides background.max_running_tasks Invalid values are ignored and fall back to the config value. The v2 engine resolves them through config section env bindings (effective-only, never persisted); the v1 engine resolves them at the consumption point. * fix(config): strip env-bound fields before persisting config writes Environment overrides resolved into the effective config could be echoed back through IConfigService.set/replace (e.g. GET then POST /api/v1/config) and persisted into config.toml, outliving the env var. This affected the pre-existing image / subagent / keep-alive bindings as well as the new loop control and max-running-tasks bindings. Extend ConfigStripEnv with a getEnv parameter and add a shared stripEnvBoundFields helper: while a field's env var is set, writes restore the field's raw on-disk value (or drop it) instead of persisting an echoed env value; when unset, normal writes persist. Register it for the loopControl, task/background, image, and subagent sections. Also fix ConfigService.stripEnv looking up rawSnake by the camelCase domain key; on-disk sections are keyed snake_case. * fix(config): honor binding parsers when stripping env fields on persist An invalid env value (e.g. KIMI_LOOP_MAX_STEPS_PER_TURN=abc) is ignored on the read path but still marked the field env-owned on the write path, so a config write for that field was silently dropped. stripEnvBoundFields now derives the guard from the section's envBindings and skips fields whose env value fails the binding's parse, so invalid env values are ignored on both paths — and the duplicated field/env descriptor list is gone. Also drop function-level comments added beside helpers; agent-core-v2 keeps comments solely in the top-of-file block, so the strip semantics now live in the config.ts / configService.ts headers. * fix(config): re-apply env overlays from the env-free base on every read Two follow-ups from review: - ConfigService.get()/getAll() re-applied section env bindings on the already-overlaid effective cache (and get() mutated it in place), so a valid override degraded to invalid or unset kept serving the stale value until the next reload — and an echoed stale value could then be persisted by a config write. Reads now recompute from a cached env-free validated base, so degraded or removed env values fall back to the file immediately. - stripEnvBoundFields restored env-owned fields from the raw snake sub-object, missing values persisted under legacy keys (e.g. max_steps_per_run). Section stripEnv now receives the env-free, fromToml-normalized raw base, so legacy aliases are honored. * test(kap-server): retry temp-home cleanup in auth tests auth.test.ts removed its temp home with a plain recursive rm, which races late async writers in the server shutdown path and flakes with ENOTEMPTY (seen on main CI and locally on main). Harden the cleanup with the same maxRetries/retryDelay options sessions.test.ts already uses. * chore(changeset): consolidate the env-override changesets into two entries One feature entry (loop/background env overrides, both engines plus the CLI) and one fix entry (env values persisting on writes and sticking after degrade/unset, agent-core-v2 plus the CLI). * fix(config): clear fully-stripped sections and refresh overlay domains on get() Two follow-ups from review: - stripEnvBoundFields returned an empty object when every written field was env-owned, so a section with a non-empty default (e.g. subagent) stored raw = {} and the default stopped applying until the next reload. A fully stripped result now clears the raw section instead. - get(domain) only recomputed env overlays for sections with env bindings, so domains written solely by a ConfigEffectiveOverlay (models / defaultModel from KIMI_MODEL_NAME) kept serving stale cached values after the env changed. get() now derives every non-memory domain from the fresh env-free base, matching getAll(). * test(config): drive the get() overlay freshness test with an inline overlay The previous version imported the model env overlay to activate it, which the CI runners failed to resolve from this test file (both tsgo and vitest, while the same specifier resolves elsewhere — not reproducible locally). An inline ConfigEffectiveOverlay double exercises the same ConfigService contract with a tighter seam and no module dependency. * fix(config): preserve unknown fields on full strip and clone nested env targets Two follow-ups from review: - stripEnvBoundFields cleared the raw section whenever the stripped result was empty, so an env echo write could drop unknown forward-compatible fields from the TOML table. An emptied section now keeps its raw table while the env-free base still holds other fields, and is cleared only when nothing remains (defaults keep applying). - applyEnvBindings reused nested child objects in place, so a nested env binding on a persistable key would mutate the env-free validated base and serve stale values after the env var is removed. Children are now cloned before descending. * fix(config): keep the env-free base when a strip leaves nothing to persist Returning {} for a fully stripped write stored the empty object into the raw layer while the TOML table survived via rawSnake, so the bases diverged; a second echo write then saw an empty base, cleared the section, and deleted the table — dropping unknown forward-compatible fields. When nothing persistable remains, the write is now a no-op for the section (the env-free base is kept as-is), and the section is cleared only when the base is empty. * fix(config): revalidate stripped results so restored raw values never persist A strip may restore on-disk values from the unvalidated raw base (e.g. an env-masked invalid field), smuggling them past the merge-time validation into the stored config: the section would then fail the next buildValidated pass, dropping accompanying valid edits from the runtime while the invalid value stayed persisted. set() now revalidates the stripped result — discarding the parse output so unknown fields survive — and rejects the write instead, matching replace().	2026-07-21 19:49:00 +08:00
liruifengv	e45832398d	fix(tui): keep long sessions responsive and bound resumed history (#1976) ... * fix(pi-tui): reuse processed lines across frames in the renderer Each frame previously re-truncated, re-normalized, and re-compared every transcript line, so steady-state frames (spinner ticks, streaming flushes) cost O(total lines x chars) and pegged one core in long sessions. Keep the previous frame's raw lines, processed output, and per-line kitty image ids; a line whose raw string reference is unchanged reuses its processed output verbatim, and image-id consumers read the cache instead of re-scanning text. * fix(tui): stop tree-wide transcript invalidation on structural updates Grouping a second Read/Agent call, removing swarm progress, finalizing an MCP status row, replay tool-call removal, and /undo each invalidated the entire transcript tree, forcing every mounted message to re-render (markdown lexing + code highlighting) on the next frame. The container's render cache already validates per child by reference, so structural child-list changes are picked up without a tree-wide invalidate; reserve it for global style changes such as theme switches. * fix(tui): fold older assistant messages into the turn step summary Step merging only collapsed thinking/tool steps, so assistant text blocks accumulated without bound inside a turn (hundreds of markdown components in a single long turn, all re-processed every frame). A running turn now keeps its last 20 assistant messages (KIMI_CODE_TUI_KEEP_RECENT_ASSISTANT), and a finished turn folds down to its conclusion tail of 2 (KIMI_CODE_TUI_KEEP_RECENT_ASSISTANT_COMPLETED); older ones collapse into the step summary line with a message count. Entries are kept, so expand behavior is unchanged. * fix(session): bound resumed history to the most recent user turns Resume used to return every agent's full replay over the RPC boundary (a long session can reach ~100MB, serialized and parsed several times on an in-process call), while the TUI only renders the last 10 user turns. The resume payload now accepts an optional replayTurnLimit, the turn-boundary predicate moves into agent-core as the single source of truth (limitAgentReplayByTurns, re-exported through the SDK), and the CLI passes its existing 10-turn limit so resume transfers just the tail. * fix(session): count goal continuation rounds as replay turns Replay turn boundaries only matched real user input, so a 100-round goal (a handful of user prompts plus 100 system-trigger continuations) fell entirely inside the 10-turn replay window and resumed by rendering the whole run from the start. The goal driver already fires one synthetic prompt per goal turn and counts those as turns itself, so replay trimming now treats goal_continuation prompts as turn boundaries and keeps the most recent 10 rounds. The continuation prompt is model-facing and hidden live; replay no longer renders it as a user bubble either, while still advancing the replay turn so each round groups separately. * fix(tui): keep replay turn folding when goal continuations are hidden Suppressing goal continuation bubbles removed every turn-boundary component from goal-session replays, so mergeAllTurnSteps found no turn edges and skipped step/assistant folding entirely — a single oversized goal round still mounted all of its tool cards and assistant messages. Mount an invisible ReplayTurnBoundaryComponent for each hidden continuation: it renders zero lines but keeps the turn edges discoverable to folding and window trimming, matching replay trimming's per-round turn semantics. * chore: consolidate and simplify changesets	2026-07-21 15:20:12 +08:00
7Sageer	ce0e3ceb04	feat: support custom agent files (#1735) ... * feat: support custom agent files Discover Markdown+frontmatter agent definitions from user, project, and configured directories; merge them into a session-level profile catalog (priority: builtin < user < extra < project < explicit). Custom agents work as subagents via the Agent tool and as the main agent. - agent-core-v2: new agentFileCatalog domain (discovery/parsing/profile factory, mirroring skillRoots/parseFrontmatter) and sessionAgentProfileCatalog merged view; AgentProfile.tools becomes optional (undefined = all tools) and gains disallowedTools deny list, evaluated in profileService.isToolActive and persisted in session wire records so resume keeps the gate even if the file is gone - CLI: restore --agent/--agent-file for the v2 print runner (KIMI_CODE_EXPERIMENTAL_FLAG); the v1 TUI rejects them with a clear v2-only error - kap-server/protocol: optional profile field on prompt submission with first-bind semantics (same-name no-op, different name rejected) - docs: custom agents section (en/zh) + config/CLI references + changeset * chore: shorten custom agents changeset * fix(agent-core-v2): stringify caught errors in agent catalog log calls * docs: drop v2 engine notes from custom agents docs * fix: align custom agent binding semantics across engine and edges - agent-core-v2: bind now owns the first-bind invariant — switching profiles after bind throws profile.already_bound (checked again in the synchronous segment before the first wire dispatch, so concurrent binds cannot both pass); unknown names throw profile.unknown; same-name rebinds keep the persisted thinking effort. - kap-server / CLI: edges degrade to error mapping / same-name no-op instead of their own divergent guards. - agent files: reject non-string mode values, honor disallowedTools in the append-mode Skill probe, pass --agent-file through unresolved so the engine can expand ~, reject empty --agent-file values. - session catalog: ready is recoverable via reload() after a fatal source failure, and agent-file discovery is kicked at session materialize so resumed sessions see file agents from the first turn. - docs: first-bind semantics, name: agent override, tools: [] meaning, --agent-file last-wins. * fix: tighten custom agent behavior * fix: address custom agent review findings * fix(agent-core,agent-core-v2): keep active-tool wire records replayable by v1 Binding a profile without a tool allowlist (the default for file-defined custom agents) persisted a tools.set_active_tools record with no `names` key. v1 clients discover v2 sessions through the shared session index and replay newer wire versions without migration, so the record crashed v1 resume with a TypeError and wedged the session permanently. The v2 engine no longer writes the record when the base set is already "every tool active" (its absence encodes the same state), and v1 replay now skips records that lack `names` as defense in depth for wires already written by preview builds. A same-name rebind that resets an allowlist to "all tools" has no v1-safe encoding and is left as a documented gap (no production caller today); a future tools.reset_active_tools Op is safe because v1 silently no-ops unknown record types. * fix(agent-core-v2): tolerate unreadable directories in agent-file discovery A single unreadable subdirectory (EACCES anywhere in the scanned tree) previously aborted the whole discovery pass, zeroing every agent of that source on every session start with one path-less warning. The walker now skips-and-warns per directory below the root (mirroring the skill discovery it parallels), root-level failures are isolated per root so one bad root no longer takes its siblings down, and only a genuinely transient whole-fs outage (os.fs.unavailable) still propagates so the session catalog keeps its previous contribution. Source-level warnings now name the offending path, and repeated skip warnings are capped with a summary that samples the suppressed paths. Also consolidates the path primitives (~ expansion, base-relative resolution, realpath type probes) shared by the root resolvers, the walker, and the explicit-file source into agentFileCatalog/paths.ts, and tightens parser diagnostics: frontmatter null is treated as absent, and a present-but-wrong-typed name/description reports a type error instead of "missing". * fix(agent-core-v2): warn when a same-name builtin suppresses a file profile A directory-discovered agent file colliding with a builtin profile without override: true was silently dropped at merge time. The suppression now logs a warning naming the profile and the opt-in. * refactor(agent-core-v2): pass skillActive explicitly to renderSystemPrompt The third parameter was a full tool list used only for includes('Skill'), which forced the agent-file profile factory to answer a boolean question with sentinel lists. The template now takes an explicit skillActive flag; a skillActiveFor helper keeps builtin call sites derived from their tool arrays. * refactor(agent-core-v2): fall back to the configured default model in bind BindAgentInput.model is now optional: the engine resolves a missing model against the configured defaultModel and throws model.not_configured when neither is set, so edges no longer each re-implement the fallback. * fix(agent-core-v2,kap-server): reject unsupported thinking atomically at first bind A REST prompt carrying profile + an unsupported thinking effort bound the session first and failed setThinking after, wedging the session on an identity the user never successfully used. The effort is now validated up front when the caller marks it as an explicit request (strictThinking): the bind rejects before any await or state mutation, and the requested effort rides along in the bind instead of a separate setThinking. Internal spawn/fork paths pass inherited thinking without the flag and keep the previous clamp behavior — a persisted effort that drifted out of the model's support list must not break subagent spawning. The route's now-redundant model fallback is dropped in favor of the engine-side default. * fix(agent-core-v2): await the agent profile catalog at session materialize The catalog's ready promise was only kicked, so a resumed session's first turn could render the Agent tool description without the file-defined agent types. Discovery is local-fs and cheap, so materialize now awaits it; ready only rejects for a fatal explicit-source error, which is exactly the case that should fail fast. A failure there now also removes and disposes the half-materialized handle instead of leaving it registered in the session cache. * test: cover the --agent-file fatal path and tidy profile registration hygiene The v2 print CLI now has a test asserting an invalid --agent-file fails before any turn. The denylist profiles in binding.test.ts register in a beforeAll (idempotent, scoped to the describe's run window) instead of at module scope during collection. * docs: align custom agent docs with v2-engine gating --agent/--agent-file are rejected without the v2 engine, so restore the requirement in the Agents and Command Reference pages (and use KIMI_CODE_EXPERIMENTAL_FLAG=1 in the examples), note that tool lists only shape model-visible disclosure (permission rules are the enforcement layer), and remind authors of delegation-bound agents to state the handoff contract in the prompt body. * test(agent-core-v2): revert unrelated style churn in fs/workspace tests Keep these files' diff limited to the realpath fakes the feature needs; the lint-preference rewrites belong to a separate cleanup. * feat(agent-core-v2): add permanent system prompt override via SYSTEM.md Read $KIMI_CODE_HOME/SYSTEM.md on every startup and inject it as the default main-agent profile (name "agent", override: true), replacing the builtin default system prompt while inheriting builtin tools and description. Missing or empty files are ignored; unreadable files warn and fall back to the builtin profile. The body supports variable substitution (${skills}, ${agents_md}, ${cwd}, ${cwd_listing}, ${os}, ${shell}, ${now}); unknown variables pass through verbatim. Priority: --agent-file / --agent / project override > SYSTEM.md > same-name user-scope scan files. * feat(agent-core-v2): gate tools globally and accept session disabledTools Add a [tools] config section: "enabled" acts as a global allowlist (empty = unconstrained), "disabled" as a denylist applied on top, both intersected with the active profile's policy in isToolActive (mcp glob supported). Plumb a session-persistent disabledTools parameter through the stack: v2 RPC PromptPayload, REST "disabled_tools" (protocol and kap-server parallel schemas), klient contract/facade, and node-sdk. The server applies it via profileService.setSessionDisabledTools, which replaces the client-owned denylist, keeps the profile's own deny, persists across resume, and rejects calls before a profile is bound with profile.not_bound (mapped to 40001). v1 core-api gains a type-only field and ignores it. * fix: enforce session tool policy across agents * fix(agent-core-v2): enforce tool policy at execution * fix(agent-core-v2): align subagent tool descriptions with policy * fix(agent-core-v2): harden custom agent policy state * fix(agent-core-v2): harden custom agent lifecycle * refactor(agent-core-v2): persist profile binding in a single profile.bind record * fix(agent-core-v2): skip unreadable paths during agent file discovery * fix(agent-core-v2): exempt select_tools from the executor policy guard - share one composed profile/global/session tool-policy evaluation between the executor gate and prompt rendering instead of two verbatim copies - tolerate context-build failure in system prompt refresh instead of rejecting callers (config watcher void-fire, session policy fan-out) * test(agent-core-v2): resolve profile and tool-policy SUTs by interface - drop the Object.assign patching of tool-policy methods onto the shared profile service; rename describes so the SUT ownership is accurate - classify profile.bind as v2-only with the accepted v1-replay tradeoff documented, un-red the wire vocabulary guard test - cover the select_tools guard exemption with an executor-level test * fix(agent-core-v2): enforce explicit select_tools policy * feat(agent-core-v2): accept Claude-style tool lists and rename agent-file mode to promptMode * feat(agent-core-v2): unify prompt templating on ${var} - Replace the nunjucks renderer with a single ${var} regex renderer (unknown placeholders pass through verbatim) and drop nunjucks from agent-core-v2. - Merge the variable tables into one catalog shared by the builtin system.md, SYSTEM.md, and agent file bodies; adds additional_dirs_info plus code-composed blocks (windows_notes, additional_dirs_section, skills_section). - Replace the agent-file promptMode field with ${base_prompt}: bodies are always rendered as templates, and ${base_prompt} expands to the effective default profile prompt (honoring the SYSTEM.md override). - Migrate the builtin system.md, goal reminders, compaction instruction, and tool description templates to the same syntax. * docs: complete agent priority chain and link SYSTEM.md precedence * test: fix invalid custom agent fixture * fix(cli): reject multiple agent selectors * feat(agent-core-v2): add subagents allowlist to agent files * fix(agent-core-v2): persist the subagent allowlist in the profile binding The delegation allowlist now rides the profile.bind record like the tool denylist, so a resumed session keeps enforcing it even when the source agent file was deleted or changed. Agent/AgentSwarm resolve the caller's allowlist from the persisted binding data instead of looking the profile up in the live catalog. * feat(agent-core-v2): warn on tool patterns that never match Profile bind/apply and [tools] config changes now statically flag entries that can never activate anything — wildcards without the mcp__ prefix (a bare * in an allowlist disables everything, in a denylist nothing), incomplete mcp__ literals, and names no registered or builtin-profile tool has — via a tool-pattern-no-match warning event, once per pattern, instead of letting the tool set silently shrink. The known-name vocabulary is the live registry plus literal names from the builtin profiles, so flag-gated tools stay known and a typo in one agent file cannot legitimize the same typo in another. * docs: align --agent-file docs with the single-selector CLI The flag accepts exactly one file and conflicts with --agent, but the docs still described the earlier repeatable, composable design. * docs: note the agent-file trust model and never-matching tool patterns Spell out that project-scoped agent files can replace the default main agent's whole system prompt (unlike AGENTS.md reference injection), and list the three tool-pattern shapes that never match and now raise a warning. * chore: slim changeset wording to user-facing language Drop wire record names, enforcement mechanics, and template syntax from the entries; split the v1 resume fix into its own patch changeset; add a patch entry for the tool-pattern warnings. * chore: shorten changeset entries to one-line summaries * Delete .changeset/v1-resume-v2-sessions.md Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn> * test: drop class-instance spread in sessionLifecycle test stub * chore: clear the comments --------- Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>	2026-07-21 15:01:43 +08:00
7Sageer	e070a580f0	feat(telemetry): emit turn_id and agent_id on turn and tool events (#1675) ... * fix: emit turn_id on turn_started/ended/interrupted telemetry The turn lifecycle telemetry events (turn_started, turn_ended, turn_interrupted) never carried the turn id, while tool_call and tool_call_dedup_detected did. Any analysis correlating a turn's start, end, or interruption back to its tool calls had nothing to join on. Add turn_id (already in scope) to all three track() calls, matching the existing key/value convention used by tool_call_dedup_detected. Update the strict turn_started/turn_interrupted assertion to cover it. * fix(agent-core-v2): emit turn_id on turn_started/ended/interrupted telemetry Port the v1 fix to agent-core-v2: turn lifecycle telemetry events (turn_started, turn_ended, turn_interrupted) carried no turn id while tool_call did, leaving nothing to correlate a turn's start, end, or interruption back to its tool calls. Add turn_id to the three event interfaces, the telemetry registry property docs, and the three track2() calls in AgentLoopService, matching the existing ToolCallEvent key convention. Extend the turn telemetry assertions in loop.test.ts to cover it. * fix: emit turn_id on tool_call telemetry * docs(agent-core-v2): clarify turn_id is a per-agent index in the telemetry registry * feat(telemetry): add agent_id to turn and tool events turn_id is a per-agent counter, so it collides across the main agent and subagents within a session. Emit each agent's scope id as agent_id on turn_*, tool_call, tool_call_dedup_detected, api_error and subagent_created (plus parent_agent_id) so events become attributable via (session_id, agent_id, turn_id). * docs(changeset): cover turn_id emission alongside agent_id * feat(telemetry): add agent_id to agent-level settings events * feat(telemetry): link v2 events across agents, turns, and tool calls - subagent_created: parent_tool_call_id, so a child run joins to the tool call that launched it - permission_policy_decision / permission_approval_result: agent_id, turn_id, tool_call_id - plan_submitted / plan_resolved / plan_enter_resolved, context_projection_repaired: agent_id - compaction_finished / compaction_failed: agent_id + optional turn_id - cron_scheduled / cron_deleted: optional agent_id of the scheduling agent - api_error: turn_id + request_kind, so compaction request failures are distinguishable from turn requests - tool_call_repeat: agent_id + optional turn_id; tool_call_dedup_detected stops fabricating turn_id: 0 outside a turn - background_task_created/completed: task_id on both, unified kind vocabulary ('process' replaces the legacy 'bash' alias on created) - agent lifecycle: auto-assigned agent-N ids now skip ids persisted by previous runs, so a resumed session cannot reissue agent-0 and collide with earlier telemetry * fix(agent-core-v2): preserve telemetry turn attribution * chore: split telemetry changeset into two logical changes * refactor(agent-core-v2): bind agent telemetry context at scope * test(agent-core-v2): fix telemetry assertions for scope-bound agent_id - undoHistory/goal: include the injected agent_id in exact property assertions - rpc-events: assert on the shared records array instead of a track2 spy, which the scoped telemetry view bypasses * refactor(agent-core-v2): bind agent identity ambiently in telemetry - TelemetryService.withContext now returns a lightweight forwarding view: transport state (appenders, enabled flag) stays with the App-scoped root, so views created before an appender attaches no longer silently drop events, and enablement changes apply to every live view. - Agent-scope events register with defineAgentTelemetryEvent and compose the centrally declared AgentTelemetryEventContext (agent_id) into their wire schema; business payloads and call sites stay free of agent_id, enforced at compile time and by the registry convention test. - image_compress/image_crop stay plain events: the kap-server prompt routes emit them through a session-scoped view without agent identity. - v1 subagent_created gains parent_tool_call_id for parity with v2. - Add a lifecycle test asserting each agent scope's telemetry view binds its own agent id. * Delete .changeset/subagent-id-reuse.md Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn> --------- Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>	2026-07-21 14:48:09 +08:00
Haozhe	6dd4fd3368	refactor(agent-core-v2): rebuild the model wire layer on the kosong architecture (#1970) ... * refactor(v2): land kosong contract layer (L0 wire contract) * refactor(v2): land kosong protocol layer (L1 traits and base registry) * refactor(v2): land kosong provider layer (bases, trait composers, kimi definition) * refactor(v2): land kosong model and catalog layers * refactor(v2): migrate engine callers to kosong, drop old llmProtocol layer * test(v2): migrate agent-core-v2 tests and harness to kosong * refactor: sync peripheral packages to kosong architecture * refactor(v2): replace provider dialects with per-protocol definitions * refactor(v2): merge the vertexai protocol into google-genai via providerOptions * refactor(v2): remove vendor-name gates outside the kosong layer * feat(v2): add model resolution inspection and connectivity ping * refactor(v2): remove the unused platform config layer * test(klient): pin invalid-input behavior across providers in e2e * refactor(agent-core-v2): merge kimi traits, split bases by protocol - merge the seven kimi trait modules into kimi.contrib.ts as two trait objects: kimiOpenAITrait (all native-transport hooks) and kimiAnthropicTrait (thinking only) - move bases/* implementations into per-protocol directories (openai/, anthropic/, google-genai/) and rename openai.contrib.ts to openai-legacy.contrib.ts - add per-directory index.ts registration barrels (import = registration) and exempt them in check-domain-layers.mjs alongside *.contrib.ts * refactor(agent-core-v2): reorganize model and request-layer types - consolidate shared model types (ModelOverrides, CompletionBudgetConfig/Params, ResolvedModelAuthMaterial, ThinkingDefaults/ModelThinkingMetadata) into kosong/model/model.types.ts and drop modelOverrides.ts - rename L2 request types to the ModelRequest* prefix: LLMEvent -> ModelRequestEvent, LLMRequestInput -> ModelRequestInput, LLMCallParams -> ModelRequestParams - extract ModelRequestTiming to replace three duplicated copies of the stream-timing shape - rename L3 llmRequester types with the Agent prefix to match IAgentLLMRequesterService (AgentLLMRequestOverrides/Finish/Task/Source/ PartHandler/LogFields) - delete the unused LLMRequestParams type * refactor(agent-core-v2): fold kosong/catalog into kosong/model - merge IModelCatalogService's enumeration surface (listModels / listProviders / getProvider / setDefaultModel and the wire shapes) into IModelCatalog; delete kosong/catalog/modelCatalog.ts - move the remote refresh path to the new IProviderDiscoveryService (discovery.ts + discoveryService.ts, renamed from catalog/modelCatalogService.ts) - relocate configSection / errors to discoveryConfigSection.ts / errors.ts; DEFAULT_MODEL_SECTION now lives in kosong/model/model.ts - drop the L3 catalog layer from check-domain-layers.mjs - kap-server routes / refresh scheduler / channelRegistry follow the split; klient renames the contract modelCatalogService to modelResolver and adds providerDiscovery; kimi-inspect reads via IModelCatalog - modelRequesterImpl: drop the streamedAnyPart backfill, onMessagePart already delivers every part - tests: remove the app/modelCatalog and kosong/catalog suites, add the kosong/model catalog and discovery suites * feat(klient): trim trailing undefined args and add boundary smoke probes - add trimTrailingUndefined helper so optional trailing args no longer cross the wire as null in http/ipc transports, which defeated server-side default parameters - add model-requester-boundary smoke probe for ChatProvider error wrapping behavior against real config and a local stub - add kimi-select-tools smoke probe verifying the kimi-only wire encoding of dynamic tool declarations - extend smoke.ts with a models set/get/delete round-trip, catalog list assertions, and update AGENTS.md with the new scripts * fix(agent-core-v2): declare openai chat hooks as function properties Method-shorthand members on OpenAIChatCompletionsHooks tripped typescript-eslint(unbound-method) at every extraction site (`const hook = this._hooks?.convertMessage` and friends), failing the repo-wide lint job. Every implementation is a plain closure composed by openaiHooks.ts, so declare the members as function-typed properties, which matches the actual semantics and clears the four errors. * fix: repair stale references surfaced by the origin/main rebase - agent-core-v2: point vacuousContent's ContentPart import at kosong/contract - kap-server: rewrite the transcript test seed as IModelCatalog (IModelResolver is gone) - klient: inline onceEvent/waitFor after the http transport helpers were dropped - kimi-inspect: remove useLiveEvent from ModelCatalogView; catalog polls on a slow interval * chore: downgrade the kosong architecture changeset to patch	2026-07-21 13:03:54 +08:00
Kai	71bcfba54a	fix(agent-core): drop vacuous assistant messages that permanently wedge sessions (#1968) ... * fix(agent-core): drop vacuous assistant messages that permanently wedge sessions A provider-filtered response can seal an assistant message holding only an empty thinking part into the recorded history. The projection's empty-message guard only counted parts, so it survived, and was serialized as an assistant message with no content and no tool calls — which the provider rejects with "the message at position N with role 'assistant' must not be empty" on every resend, permanently wedging the session. The projection now drops any message whose parts all serialize to nothing (empty/whitespace text, or empty unsigned thinking). Content-bearing messages keep every part verbatim, including empty thinking blocks that preserved-thinking providers require back. Drops surface through a new vacuous_message_dropped projection anomaly with log/telemetry counters, and the structural-error recovery now recognizes this provider rejection so the strict resend self-heals any residual path. Mirrored in agent-core-v2. * docs(agent-core-v2): move vacuous-message rationale into the file header The v2 comment convention keeps comments solely in the top-of-file block. Move the vacuous-message drop rationale there and drop the inline/JSDoc comments added beside statements in the projector service, the llmProtocol error patterns, and the projector tests. No behavior change. * fix(agent-core-v2): drop output-free steps at fold settle time The loop-event fold already dropped a settled assistant message when it was structurally empty (no content, no tool calls), but a step that recorded only an empty thinking part — e.g. a provider-filtered response carrying an empty reasoning field — survived into history, relying on the projection to keep it off the wire. Widen the settle condition to drop the step whenever nothing sendable was recorded (no tool calls; every content part vacuous), using a predicate now shared with the context projector. This heals stored v2 histories at restore time instead of only at request time. * fix(agent-core): drop duplicate-stripped assistants left with only vacuous content The strict resend's dedupe pass could re-create the exact empty-assistant shape the projection now guards against: when every tool call a message carried was removed as a later duplicate, a remainder holding only an empty thinking part was kept (its content was non-empty), serialized as an assistant message with no content and no tool calls, and rejected again with "the message at position N with role 'assistant' must not be empty" — the same failure the strict resend was recovering from. The keep condition now requires sendable content, so such a message is dropped wholesale with a vacuous_message_dropped anomaly alongside the duplicate-tool-call one. Mirrored in agent-core-v2. * fix(agent-core-v2): mirror output-free step drops in the transcript reducer The live loop-event fold drops a settled assistant step when nothing sendable was recorded (no tool calls; every content part vacuous), but the cold transcript reducer still pushed an assistant on every step.begin and never dropped it. Cold readers (snapshot / messages) therefore kept showing output-free phantom assistants — including one per failed retry attempt, which predates the vacuous-step case — and foldedLength overcounted the live folded history, which can misplace the unflushed-tail splice in the messages view while a turn is in flight. The reducer now settles steps the same way the fold does: at a step's end or at the next begin, an assistant with no tool calls and only vacuous content is removed and foldedLength is decremented. Steps carrying any sendable output — real text, real thinking, signed thinking, or tool calls — are kept verbatim. * fix(agent-core-v2): update vacuous-content predicate documentation for clarity * docs(changeset): simplify the vacuous-assistant fix changelog entry	2026-07-21 11:04:55 +08:00
liruifengv	11c1683a1c	feat: scope thinking effort to the current session (#1933) ... * feat: scope thinking effort to the current session Selecting a model or thinking mode in the TUI or web UI no longer persists the concrete effort to the config; only the boolean thinking toggle is saved. The web UI now restores and submits each session's own daemon-reported level instead of a browser-wide per-model pick, whose localStorage store is removed. * feat: persist bounded thinking efforts and migrate persisted max once Only low/medium/high/xhigh are written to the config on a pick; max and unrecognized levels stay session-only with just the boolean toggle saved. A one-shot migration rewrites a previously persisted thinking.effort max to high (recorded in migrations.json, never re-run). The web UI brings back the per-model localStorage pick as the seed for new sessions, while a session's own daemon-reported level keeps winning for existing ones. * feat: gate effort persistence on the model top declared level The session-only tier is now the last entry of the model's own support_efforts (ordered by strength) instead of a fixed name list, so custom provider-declared levels get the same treatment; anything below the top persists as before, and unknown model metadata keeps the concrete effort. * docs: align changeset wording with the top-tier persistence rule * refactor: rename the config migration marker file to migrations-effort.json * feat: drop the legacy global thinking pick fallback in the web UI A raw single-level string left in localStorage by older versions was migrated into a '*' fallback entry applied to every model; stale values (typically max) could silently steer any session. Non-map content is now discarded instead of inherited. * feat: drop the web per-model thinking pick store entirely Thinking in the web UI is now sourced only from the daemon: a session's own reported level wins when the model declares it, and everything else falls back to the model's catalog default. The stale localStorage key is cleaned up on startup. * feat: skip the effort write when the picker confirms its initial value Re-confirming the effort shown when the model/effort picker opened is not an explicit choice: the TUI persists only the model (no effort key, or no write at all when nothing changed), and the web skips the global config write the same way it already did for model switches. * revert: keep the web global thinking write on re-confirm for now Only the TUI skips the effort write when the picker confirms its initial value; the web behavior stays unchanged until the interaction is reconsidered. * fix: carry the draft thinking pick into a newly created session A level picked on the empty composer lived only in rawState.thinking, so selectSession's watcher overwrote it with the catalog default and the first prompt/skill submitted that instead of the pick. createDraftSession now captures the draft level and seeds the new session's own entry. * docs: simplify the changeset wording * fix: close the remaining top-tier persistence and draft-capture gaps The provider-add default-model flow now resolves support_efforts through effectiveModelForHost (overrides + protocol-profile inference), so a top-tier pick on catalog models without declared efforts no longer persists. The draft thinking level is captured before the session creation awaits, so a concurrent session switch can no longer seed the new session with another session's effort. * fix: wait for the session status fold before resolving prompt thinking In the cold window right after a reload or session switch, the session's own level has not landed from /status yet; resolving straight to the catalog default would carry the wrong level to the daemon, which writes it into the session profile. Send, steer, side-chat and skill-activation paths now await the fold when the session entry is missing.	2026-07-20 12:57:22 +08:00
7Sageer	df68995539	feat: add thinking_effort to turn telemetry events (#1916) ... * feat: add thinking_effort to turn telemetry events turn_started / turn_ended / turn_interrupted now carry the resolved effective thinking effort in both engines, so per-turn and per-session effort usage distribution becomes measurable. In agent-core-v2 the profile domain mirrors the effective effort (including the KIMI_MODEL_THINKING_EFFORT override) into the ambient telemetry context on model / thinking changes and after restore; the loop snapshots it at turn start. In agent-core the turn flow reads config.thinkingEffort at each emission point. * fix(agent-core-v2): align turn telemetry with request config * fix(agent-core-v2): preserve model-less turn startup	2026-07-19 21:41:21 +08:00
Kai	3086e47039	fix: unify YOLO and Auto permission mode descriptions across surfaces (#1867) ... * fix(tui): correct YOLO and Auto permission mode descriptions * fix: unify YOLO and Auto permission mode descriptions across CLI, ACP, web, and docs * docs: correct YOLO and Auto mode descriptions in the interaction guide * fix: correct YOLO mode notices in session replay and vscode extension * feat(vscode): rename /afk command to /auto, keeping afk as hidden alias Also correct the stale 'afk' mode reference in the built-in MCP config skill guidance of both agent engines. * fix(vscode): forward engine approval requests instead of blanket-approving them The extension-level approval handler auto-approved every request when legacy yolo/afk was on, silently swallowing the sensitive-file, plan-review, and ask-rule prompts the engine yolo mode still sends. Forward every request to the user and let the engine permission mode do the auto-approving, matching TUI and web behavior.	2026-07-18 02:09:31 +08:00
Haozhe	56a321d4d1	fix(workspace): dedupe workspaces across Windows path spelling variants (#1809) ... * fix(workspace): dedupe workspaces across Windows path spelling variants The same directory reached the workspace registry as distinct strings on Windows (drive-letter casing, typed vs on-disk casing, slash style), and every identity check compared exact strings, so one folder could appear as multiple workspaces with sessions split across hash-keyed buckets. - add workspaceRootKey (slash-normalize + case-fold Windows-shaped paths) in agent-core, agent-core-v2, and the web app, and compare roots by identity key everywhere instead of exact strings - registry createOrTouch folds alias spellings onto the existing entry instead of minting a new workspace id; session buckets reuse the registered id via a resolver in the v1 session store - list endpoints expand alias buckets (resolveAliasIds / resolveAliasWorkDirs, including session-index-only spellings) so previously split workspaces list all sessions and counts under one merged group; session_index entries use the registry-resolved id * fix(workspace): fold the runtime touch path and drive-root identity keys Two gaps in the Windows path-spelling folding, both reachable in the v1 session-create flow: - touchWorkspaceRegistry minted the alias spelling's id outright; the freshly persisted alias entry then became the resolver's preferred id on the next create, splitting sessions into a duplicate bucket again. It now folds onto the identity-matching existing entry, mirroring the registry service. - workspaceRootKey stripped trailing separators before testing the Windows shape, so a drive root (C:\) collapsed to C: and escaped the case-fold. The shape test now runs before the strip in all three copies (agent-core, agent-core-v2, web). * fix(workspace): unfold symmetric operations that escaped the identity key Two asymmetric spots left the folded comparison one-sided: - the web app matched hidden roots by folded key but cleared them on re-add by exact string, so hiding C:\Foo and re-adding c:\foo kept the workspace hidden forever; clearing now folds too - registry delete (both engines) removed and tombstoned only the exact id, so a legacy split sibling resurfaced as the directory's representative on the next list; delete now removes every registered spelling sharing the root's identity key and tombstones the full alias set (registered ids plus session-index spelling mints), so the session-index merge cannot resurrect the directory either	2026-07-17 14:56:06 +08:00
Haozhe	31449728b7	fix(security): close FetchURL SSRF bypasses and DNS-rebinding window (#1791) ... * fix(security): close FetchURL SSRF bypasses and DNS-rebinding window - resolve hostnames via DNS and reject any target resolving to loopback / RFC1918 / link-local / CGNAT / ULA ranges, including IPv4-mapped IPv6 forms (e.g. localtest.me, [::ffff:7f00:1]) — the static host denylist only matched literals and could be bypassed by crafted domains - follow redirects manually with full per-hop revalidation (10-hop cap) instead of auto-following, so a public URL cannot 302 the fetcher at internal services or cloud metadata endpoints - pin each connection to the DNS answers the check validated (per-hop undici Agent with a pinned lookup), closing the TOCTOU / DNS-rebinding window between the check and the connect; skipped when a proxy is configured or allowPrivateAddresses is set - apply to both agent-core and agent-core-v2 providers, with SSRF / redirect / pinning test coverage * chore: add changeset for FetchURL SSRF hardening * test: bridge undici type declarations in fetch pinning tests * fix(security): keep dispatcher option lib-agnostic for DOM typecheck consumers * fix(security): address review — pin NO_PROXY bypasses, drain oversized bodies, header-only comments	2026-07-17 11:21:05 +08:00
Kai	373abb02f0	fix(agent-core): record and close tool calls interrupted mid-stream (#1790) ... When the provider stream breaks off mid-tool-call (pause_turn, engine overload, token limit), the step ended with the partial tool call dropped silently: never executed, never recorded. If the response carried no other usable content, the persisted assistant message was effectively empty and every subsequent request — including compaction — was rejected with "assistant must not be empty" (HTTP 400), wedging the session. Record each unexecuted call instead (arguments sanitized to {} when the truncated JSON is unparseable) and immediately close it with a synthetic interrupted error result. The exchange stays wire-valid, the history stays truthful, and the model learns the calls never ran so it can re-issue them.	2026-07-16 21:12:00 +08:00
Haozhe	319001ae5c	refactor: remove git detection from workspace wire and folder browse (#1787)	2026-07-16 21:05:19 +08:00
Kai	365ba0001d	fix: use timestamped default filename for session debug exports (#1788) ... Both engine implementations defaulted the export ZIP path to <sessionId>.zip, so running /export-debug-zip or kimi export twice for the same session silently overwrote the first archive. The default filename is now kimi-debug-<shortId>-<timestamp>.zip (UTC, second precision), matching the /export-md naming convention. Explicit -o/outputPath behavior is unchanged.	2026-07-16 19:32:06 +08:00
github-actions[bot]	36b05820cb	ci: release packages (#1767) ... Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2026-07-16 18:54:29 +08:00
Kai	d531398d01	fix: scope Anthropic effort fallback profile to non-Kimi providers (#1765) ... * fix: scope Anthropic effort fallback profile to non-Kimi providers Managed Kimi models routed through the Anthropic protocol (protocol = "anthropic", no catalog-declared think_efforts) inherited the inferred latest-Opus effort profile, so the UI showed reasoning effort choices the server never declared. The fallback now applies only when the provider type is known, non-kimi, and the effective wire protocol is Anthropic; Kimi providers keep catalog-declared efforts only, and callers without provider context fall back to name matching. * fix: align v2 catalog with resolver for providerless Anthropic models Flat models (inline base_url, no named provider) and providers without a declared type now fall back to the model's own protocol when deciding the Anthropic fallback effort profile, so the model catalog stays consistent with runtime resolution. * fix: keep flat Anthropic model effort metadata in TUI and ACP catalogs Flat models without a named provider (inline base_url, protocol: "anthropic") have no provider entry to look up; fall back to the model's own protocol as the provider identity so the effort picker and ACP catalog stay consistent with runtime resolution. * style: move v2 anthropic fallback rationale into the modelAuth header The v2 comment convention keeps comments in the top-of-file block only; drop the inline explanations added beside functions and statements.	2026-07-16 17:30:20 +08:00
qer	d1ca65e1de	feat(vscode): migrate extension to Node SDK (#1769) ... * feat(vscode): migrate extension to Node SDK * fix(vscode): address CI failures * fix(vis): handle token count records * fix(vscode): keep chat toolbar and header readable at narrow widths * fix(vscode): map yolo to core yolo permission and honor the global yolo setting * docs(vscode): record Node SDK migration design * docs(vscode): split breaking changes out of the 0.6.0 changelog * fix(vscode): keep a resumed session's thinking effort instead of reapplying the default * fix(vscode): announce session status when a view attaches so the display matches it * fix(vscode): align webview thinking effort handling with the TUI	2026-07-16 17:27:21 +08:00
Haozhe	ffaf0b98ca	feat(agent-core): align coder subagent tools with v2 and drain background tasks (#1776) ... * feat(agent-core): align coder subagent tools with v2 and drain background tasks - align the bundled coder subagent profile tools with agent-core-v2 CODER_TOOLS (Skill, Agent, AgentSwarm, Task* trio, plan-mode tools, TodoList); cron tools stay declared-but-undelivered on sub agents, matching v2 - rebuild builtin tools in setActiveTools: profile-gated capabilities (Bash/Agent allowBackground via the Task* trio) were baked at construction with an empty enabled set, so profiles applied later (every subagent) silently lost them - hold subagent completion until the child agent's background tasks settle (print-mode drain semantics) and suppress their terminal notifications, so no unobserved follow-up turn runs on a finished subagent; the run's timeout/cancel signal bounds the drain - cover with real-Session e2e (tool execution, nested Agent/AgentSwarm, drain blocking and cancel) and update profile/subagent-host tests * chore: add changeset for coder subagent tool alignment * docs(agents): sync sub-agent capabilities with expanded coder tool set - coder sub-agents can now dispatch nested sub-agents and use background tasks, todo lists, Plan mode, and skills; drop the stale claim that sub-agents cannot schedule nested sub-agents - note that a sub-agent run reports completion only after its background tasks settle * fix(agent-core): close drain race for tasks settled before completion A background task that terminated before the drain's suppression pass was excluded from the active-only list, so its terminal notification escaped suppression and could still steer an orphan turn onto the finished subagent. Suppress every child task (including settled ones whose notification may still be in flight) and run the pass both before and after the settle wait; notification delivery re-checks suppression after its async output snapshot, which makes the block deterministic. Cover the mid-turn delivery path with an e2e case.	2026-07-16 17:14:53 +08:00
7Sageer	70211a727f	feat: attach trace_id to telemetry events (#1724) ... * feat: attach KFC trace_id to telemetry events Capture the x-trace-id response header in both kimi providers (kosong and agent-core-v2 llmProtocol) via the openai SDK withResponse(), and thread it through the request result chain into telemetry so events can be joined with server-side request logs by trace id instead of session_id + time window. - kosong / llmProtocol: StreamedMessage/GenerateResult.traceId, GenerateOptions.onTraceId early capture (available mid-stream), APIStatusError.traceId on the error path - v1 (agent-core): per-turn traceIdByTurn on TurnFlow; attach trace_id to turn_ended/turn_interrupted/api_error/cancel/tool_call(+dedup, repeat)/permission_approval_result/question_*/compaction_* - v2 (agent-core-v2): AgentTelemetryContext carries turn_id/trace_id updated by llmRequester; registry gains trace_id on 13 events plus turn_id on turn_* and turn_id/step_no on api_error * fix: attribute trace_id to the failed request on error paths Review follow-ups for trace_id attribution on failure paths: - v1: chatWithRetry feeds a failed attempt's APIStatusError trace id into the turn's traceIdByTurn before the loop dispatches turn.interrupted, so turn_ended/turn_interrupted on error turns attribute to the failed request instead of the previous successful step. - v2: llmRequester keeps the onTraceId-captured trace in per-request state and trackApiError prefers it over error extraction, so failures after response headers arrived (empty response, mid-stream decode errors) no longer clear the ambient trace_id. - v2: compaction_failed falls back to the ambient trace_id once a summarizer request actually hit the wire, covering mid-stream failures whose error carries no trace. - kosong: parseTraceId filters empty x-trace-id headers and both kimi providers read the header through it. - v2 test harness forwards onTraceId to GenerateFn so tests can simulate the early header capture. * fix: attribute v1 api_error to the in-flight request on post-headers failures - v1: a failure after response headers arrived (mid-stream decode error, empty response) carries no trace on the error itself, so api_error lost the trace the client had already captured via onTraceId. Add a per-step in-flight capture (written by onTraceId, cleared at step begin/end) and fall back to it when the error carries no trace, aligning with v2's per-request requestTraceId. Failures before any response headers (network errors, local aborts) still report no trace rather than leaking a previous request's. - v2: document that ambient trace_id distribution assumes serialized LLM requests per agent, naming the two supported paths that break it (after-step compaction below the block ratio; inject-path turns during a manual compaction). * fix: isolate telemetry trace attribution * fix: isolate telemetry trace by request * fix: declare @moonshot-ai/protocol dependency of agent-core-v2 The trace-by-request refactor imports types from @moonshot-ai/protocol in toolContract and toolExecutorService, but the package was not declared, failing clean CI installs (TS2307). Also drop three type imports that are unused after the merge with main.	2026-07-16 09:14:12 +08:00
Kai	918c1354d9	fix: align Anthropic-compatible model capabilities (#1746) ... * fix: align Anthropic-compatible model capabilities * fix: warn on Anthropic effort mismatches * fix: harden Anthropic model resolution * fix: align Anthropic replay and ACP thinking state * fix: normalize Anthropic thinking stream payloads * fix: backfill non-empty preserved thinking * fix: resolve session thinking effort with provider context * fix: honor adaptive thinking opt-out in effort resolution	2026-07-16 01:31:38 +08:00
Kai	f0c8a103c6	fix: preserve the crash error in diagnostic logs on unexpected exit (#1757) ... The TUI crash path (uncaughtException / unhandledRejection) logged the error into an asynchronously-drained sink and then called process.exit() on the same tick, so the one line explaining the crash was never written to disk. Flush the diagnostic logs synchronously before exiting.	2026-07-16 01:26:27 +08:00
_Kerman	df75a0f5c2	refactor(agent-core-v2): derive session busy from agent activity (#1751)	2026-07-15 23:33:58 +08:00
Haozhe	a74ab44ac7	feat: raise default per-step LLM retry budget to 10 attempts (#1740) ... * feat: raise default per-step LLM retry budget to 10 attempts The default of 3 attempts only produced ~1.5s of backoff (0.5s/1s), so sustained provider overload (429) surfaced to the user almost immediately. With 10 attempts the exponential ramp (500ms base, x2, 32s cap, 25% jitter) waits out multi-minute overload windows before failing the turn. Applies to both agent-core (chatWithRetry) and agent-core-v2 (stepRetry service); loop_control.max_retries_per_step still overrides. * test(agent-core): pin retry-dependent tests to the new default budget - error-paths: the warn-log attempt field now reads 1/10 with the default 10-attempt budget - goal-session pause tests: every LLM call throws a retryable error, so the default 10-attempt backoff (~2min) blew the 5s test timeout; pin maxRetriesPerStep=1 since the pause behavior does not depend on the retry count	2026-07-15 15:24:17 +08:00
Haozhe	5d6ff022b1	feat(agent-core): drop default timeouts for print-mode background tasks (#1737) ... * feat(agent-core): drop default timeouts for print-mode background tasks - add `bash_task_timeout_s` config under [background] (0 = no timeout), covering the background Bash default and the re-arm after a foreground command is moved to the background on timeout - allow `[subagent] timeout_ms = 0` (no timeout) and thread it through Agent/AgentSwarm task registration and the swarm batch timer - fill both with 0 in print-mode config defaults so `kimi -p` never kills background work by wall-clock and only the model stops a task; interactive defaults are unchanged - sync the Bash tool description/parameter text with the effective default and update user docs (en/zh) plus changeset * test(agent-core): satisfy KimiConfig providers requirement in print-defaults tests * fix(agent-core): clear the foreground deadline on detach when the background timeout is disabled `detach()` only re-arms when `detachTimeoutMs` is defined, so passing `undefined` with `bash_task_timeout_s = 0` kept the armed foreground deadline and a manually detached command was still killed at its foreground timeout. Pass `0` instead so the reset clears the timer. Caught by Codex review on #1737.	2026-07-15 14:35:32 +08:00
liruifengv	286d3e7aca	feat: add check-kimi-code-docs builtin skill (#1727) ... * feat(agent-core): add check-kimi-code-docs builtin skill * feat(agent-core-v2): add check-kimi-code-docs builtin skill * docs: list check-kimi-code-docs in builtin skill commands * chore: add changeset for check-kimi-code-docs skill	2026-07-15 11:42:47 +08:00
Haozhe	3703d0346e	feat(agent-core): default print mode to steer with unbounded limits (#1722) ... - change the default print background mode from 'exit' to 'steer' so `kimi -p` stays alive while background tasks are pending and each completion steers a new main turn - add print-mode config defaults (applyPrintModeConfigDefaults): effectively unbounded wait ceiling and turn cap, 72h subagent timeout; explicit user config always wins - thread the new `uiMode` option from SDKRpcClient through KimiCore into session create/resume - clamp setTimeout delays to 0x7fffffff so huge timeouts are not clamped to 1ms by Node	2026-07-15 11:11:00 +08:00
_Kerman	26d499bca7	refactor(agent-core-v2): consolidate wire services (#1680)	2026-07-14 19:51:29 +08:00
7Sageer	ac216163b9	fix: emit turn_id on turn_started/ended/interrupted telemetry (#1668) ... * fix: emit turn_id on turn_started/ended/interrupted telemetry The turn lifecycle telemetry events (turn_started, turn_ended, turn_interrupted) never carried the turn id, while tool_call and tool_call_dedup_detected did. Any analysis correlating a turn's start, end, or interruption back to its tool calls had nothing to join on. Add turn_id (already in scope) to all three track() calls, matching the existing key/value convention used by tool_call_dedup_detected. Update the strict turn_started/turn_interrupted assertion to cover it. * fix(agent-core-v2): emit turn_id on turn_started/ended/interrupted telemetry Port the v1 fix to agent-core-v2: turn lifecycle telemetry events (turn_started, turn_ended, turn_interrupted) carried no turn id while tool_call did, leaving nothing to correlate a turn's start, end, or interruption back to its tool calls. Add turn_id to the three event interfaces, the telemetry registry property docs, and the three track2() calls in AgentLoopService, matching the existing ToolCallEvent key convention. Extend the turn telemetry assertions in loop.test.ts to cover it. * fix: emit turn_id on tool_call telemetry * docs(agent-core-v2): clarify turn_id is a per-agent index in the telemetry registry	2026-07-14 18:31:43 +08:00
Haozhe	9e6d53b025	fix(workspace): re-read the catalog on every v2 registry operation (#1706) ... - drop the in-memory write cache in the v2 registry: every list/get/ mutation is a fresh read-modify-write of workspaces.json under the op mutex, so v1 writers (touchWorkspaceRegistry) are never clobbered by a stale snapshot; the session-index merge stays once per process behind a flag (Codex P1) - move the shared workspaces.json helper from services/workspace (the upper facade) to session/store, so the rpc runtime no longer imports back into services/ (Codex P2)	2026-07-14 17:52:03 +08:00
Haozhe	07c3632415	fix(workspace): sync workspace catalog across v1/v2 and soft-delete (#1701) ... - register the cwd in workspaces.json when a v1 (TUI/SDK) session is created, via a shared workspaceRegistryFile read/write/touch module - merge session_index.jsonl into the catalog once at v2 startup (awaited during kap-server boot), adding only paths absent from workspaces.json - make v2 workspace delete a soft delete through the v1-compatible deleted_workspace_ids field: the session-index merge never resurrects tombstoned ids, while an explicit createOrTouch clears the tombstone	2026-07-14 17:34:35 +08:00
Haozhe	94c0ef89d2	fix(agent-core): re-register builtin tools when provider resolves late (#1688) ... When the model provider becomes resolvable only after the agent starts (async OAuth / managed free-tokens registration), the builtin tool table stayed empty: initializeBuiltinTools was gated on hasProvider at fixed checkpoints and none fired. loopTools now self-heals on read once a provider resolves, so tool calls no longer fail with "Tool not found".	2026-07-14 16:37:17 +08:00
Kai	d158e0a7ac	fix: resolve and synchronize thinking effort (#1625) ... * fix: preserve provider thinking effort values * fix: resolve Kimi thinking effort fallbacks * fix: use resolved Kimi effort in v2 requests * fix: align Kimi effort resolution paths * fix: synchronize forced Kimi effort state * fix: synchronize forced Kimi effort in v2 state * fix: tolerate unresolved models in v2 status	2026-07-14 16:37:03 +08:00
github-actions[bot]	2383137f3e	ci: release packages (#1583) ... Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2026-07-14 15:01:30 +08:00
Kai	32a89c3643	fix(agent-core): prevent oversized media from poisoning sessions (#1657)	2026-07-14 12:46:45 +08:00
Kai	7c889f3a96	fix(agent-core): mark auto-approved plan exits as not user-reviewed (#1638) ... * fix(agent-core): mark auto-approved plan exits as not user-reviewed In auto permission mode ExitPlanMode is approved without user involvement, but its result read "## Approved Plan:" exactly like a genuine user approval and the transcript showed a green "Approved" chip. The model treated that as a signal to start executing, even when the user had asked it to stop after planning. - Emit an "auto-approved, not user-reviewed" result with a note that execution follows the user's original instructions (v1 + v2). - Extend the auto-mode reminder: plan approvals are automatic and are not a user signal to proceed (v1 + v2). - Render an "Auto-approved" warning-toned chip in the TUI, keeping backward compatibility with the old result marker. - Document the Auto mode plan-exit behavior in interaction guides. * fix(agent-core): only mark plan exits as auto-approved in auto permission mode Address review feedback on the auto-approved plan exit change: - Branch the direct-execution output on the permission mode in both engines: only auto mode yields the "auto-approved, not user-reviewed" result and telemetry outcome. In manual / yolo modes the direct path means a configured or session allow/ask rule let the call through — an explicit user decision that keeps the user-approved output, the Approved transcript chip, and the approved outcome. - Move the v2 rationale out of the method body into the file header, per the agent-core-v2 comment convention. - Drop the absolute "only Auto mode" wording from the interaction guides (en/zh).	2026-07-14 11:30:47 +08:00
Haozhe	4ec2e7fab1	feat(server): default to kap-server and remove the v1 server package (#1617) ... * feat(server): default to kap-server and remove the v1 server package - kimi server run / kimi web now boot kap-server (agent-core-v2 engine) unconditionally; the KIMI_CODE_EXPERIMENTAL_FLAG gate on the server path is gone (the kimi -p print-mode gate stays) - move the OS service manager (svc: launchd/systemd/schtasks) from packages/server into packages/kap-server and export it there - repoint the CLI server subcommands, tests, and dev scripts at kap-server; relabel the web dev backend presets default/multi - delete packages/server and update workspace bookkeeping (flake.nix, pnpm-lock.yaml, changeset ignore docs, AGENTS.md, agent-core-dev skill) * test(server-e2e): remove scenarios that depend on v1 debug endpoints Scenarios 04-stateless-controls, 10-prompt-queue-steer and 12-send-and-cancel assert through the /api/v1/debug/prompts/* introspection routes, which only the deleted v1 server mounted — kap-server's --debug-endpoints is a documented no-op, so these scenarios can only 404 now. The vitest e2e files using the same surface already skip when it is absent.	2026-07-13 21:43:45 +08:00