26 commits

Author	SHA1	Message	Date
7Sageer	7b62ed5b2c	feat: support a configurable secondary model for subagents (#2064) ... * feat: support a configurable secondary model for subagents * refactor: move the subagent model config to a consumer-neutral [secondary_model] The secondary model becomes a model-domain concept next to default_model so future consumers beyond subagents can share it: [secondary_model] model / effort in config.toml, KIMI_SECONDARY_MODEL / KIMI_SECONDARY_EFFORT env overrides, and the Agent / AgentSwarm per-spawn choice renamed from "subagent" to "secondary". * docs: replace "v2 engine only" notes with the concrete effective surfaces State that [secondary_model], its env overrides, the Agent/AgentSwarm model parameter, and SYSTEM.md take effect only under kimi web and experimental kimi -p (the TUI ignores them), and that --agent / --agent-file are available only under experimental kimi -p. Also drop the SYSTEM.md claim of parity with --agent/--agent-file, which was inaccurate: SYSTEM.md is an agent-core-v2 app-domain feature and also applies under kimi web, while the flags are gated at the CLI. * fix: review follow-ups for the subagent secondary model - Drop the "cheaper" claim from the Agent/AgentSwarm model parameter descriptions and the advertised model list — the secondary model is not necessarily the cheaper one. - Downgrade the changeset to patch, note the kimi web / experimental kimi -p effective surface, and tighten the wording. - Remove the onWillRestore stub fields from two lifecycle stubs; they belong to upcoming lifecycle work, not to this change. * fix(agent-core-v2): prevent ghost agents from invalid model bindings * fix: narrow the secondary-model error hint to missing-alias failures The model catalog's not-configured throw now carries details.model, and wrapSubagentModelError only decorates errors whose details.model matches the bound model. Malformed [models.*] entries and unrelated config.invalid failures during agent creation pass through untouched instead of being misattributed to an invalid secondary-model alias. * fix: mark subagent resume semantics as breaking * chore(agent-core-v2): follow header-only comment convention * fix(agent-core-v2): await agent restore preparation * feat(agent-core-v2): support agent model preferences * Update subagent-secondary-model.md Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn> * fix: validate secondary models before agent creation * Delete .changeset/secondary-model-startup-warning.md Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn> * Add secondary_model config section for subagents Individual agents can override this via the new `model_preference` field in their agent file. Signed-off-by: 7Sageer <sag77r@hotmail.com> * feat(agent-core-v2): support override patches in [secondary_model] The recipe is now `model` plus the flattened ModelOverride field set. With any patch field set, a config overlay synthesizes a derived registry entry (base copy, patch merged into overrides, aliases dropped) so subagent spawning rides the standard effectiveModelConfig merge; with none, subagents bind the pointed entry directly. `default_effort` replaces `effort` (KIMI_SECONDARY_EFFORT rebinds) and doubles as the explicit subagent thinking; unset, thinking resolves naturally instead of inheriting the caller. The overlay strips the derived entry (and any defaultModel pointer to it) from writes, and the kap-server GET /models route hides it from pickers. * fix(agent-core-v2): fire section events for overlay-rewritten domains rebuildEffective only committed the caller-named domains, so a ConfigEffectiveOverlay or section env binding that rewrote a sibling domain (setting [secondary_model] synthesizes a derived models entry; removing the recipe retracts it) left consumers of the models section stale. Widen the commit candidates with every domain the recompute actually changed; commit() deepEqual-guards each candidate, so the widening costs nothing. * feat(agent-core-v2): gate secondary model behind experimental flag * Update subagent-secondary-model.md Signed-off-by: 7Sageer <sag77r@hotmail.com> --------- Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn> Signed-off-by: 7Sageer <sag77r@hotmail.com>	2026-07-24 12:16:53 +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	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
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
Haozhe	ad8cc85251	feat(cli): foreground-only web servers, deprecated kimi server kill (#1967) ... - the /web slash command now always starts a new server instead of offering to reuse a running one - remove the kimi web kill and kimi web ps subcommands; foreground servers stop with Ctrl+C - keep kimi server kill as a deprecated fallback that only stops servers started by a version before 0.28.0 (recorded in the legacy server lock)	2026-07-20 21:50:09 +08:00
liruifengv	e8f2a077d3	docs(changelog): sync 0.28.0 from apps/kimi-code/CHANGELOG.md (#1944) ... * docs(changelog): sync 0.28.0 from apps/kimi-code/CHANGELOG.md * docs: tighten the 0.28.0 changelog and fix web command references --------- Co-authored-by: qer <wbxl2000@outlook.com>	2026-07-20 17:28:48 +08:00
Haozhe	a41a09c33c	feat(cli): replace the kimi server command tree with kimi web and share one home across servers (#1826) ... * feat(kap-server): enable multi-server shared home by default - always register kap-server instances under server/instances and drop the legacy single-instance lock (acquireLock/getLiveLock/ServerLockedError) - remove the multi_server experimental flag and its KIMI_CODE_EXPERIMENTAL_MULTI_SERVER env var from agent-core-v2 - discover running servers via the instance registry in server ps/kill/rotate-token, kimi web daemon reuse, and the desktop app - remove the pending minidb changesets * feat(cli): add per-instance targeting to server kill and ps - `kimi server kill [serverId]` stops only the matching instance; without an id it still stops the longest-running one, and an unknown id errors with the live server ids listed - `kimi server ps` lists connections grouped per server id (`--json` nests them under a per-server object); an unreachable instance degrades to a per-server note instead of failing the whole listing - update the zh/en command reference and the multi-server changeset * feat(cli): replace kimi server with the kimi web command tree - `kimi web` now runs the local server in the foreground and opens the browser; the background daemon (ensureDaemon / spawn / idle-exit) is removed, so repeated runs simply start another instance on the next free port - drop the OS-service lifecycle (install/uninstall/start/stop/restart/ status) together with kap-server's svc layer - `kimi web kill [serverId]`, `kimi web ps`, and `kimi web rotate-token` manage instances from the registry - the TUI /web command now connects to an already-running instance instead of spawning a background daemon - update the zh/en command reference, dev scripts, and tests * feat(cli): route kimi server invocations to a deprecation notice Any `kimi server …` call — bare or with any legacy subcommand/flags — now prints a deprecation notice pointing at `kimi web` and exits 1, instead of failing with an opaque "unknown command". The shim is scheduled for removal in the next major version. * feat(cli): add the `all` keyword to kimi web kill `kimi web kill all` stops every live instance in the registry (ULIDs can never collide with the keyword). Each instance still gets the API shutdown + SIGTERM/SIGKILL treatment; a failure on one instance does not stop the sweep and is reported at the end. * docs(changeset): drop the web-foreground-default changeset The kimi web command tree replaces the foreground-default behavior this entry describes: --background, daemon reuse, and the version-mismatch hint no longer exist, so the pending entry would contradict the actual release notes. * docs(changeset): tighten the multi-server entry wording * feat(cli): let /web pick a running server or start a new one The /web picker now lists the live instances from the registry with their versions (flagging a CLI mismatch) instead of only connecting to the longest-running one, and offers starting a new server: that one runs in the foreground attached to the terminal after the TUI exits, via the restored exit-takeover wiring. formatReadyBanner is exported and adapts its Stop hint to Ctrl+C for the attached case. * feat(cli): skip the /web picker and start a new server when none is running	2026-07-19 11:43:46 +08:00
qer	4f3c7240c4	feat(cli): run kimi web and the TUI /web command in the foreground by default (#1853) ... * feat(cli): run kimi web and the TUI /web command in the foreground by default kimi web and /web now start the server attached to the terminal (Ctrl+C stops it) instead of backgrounding a daemon; --background opts back into the daemon behavior. kimi server run is unchanged. A foreground kimi web reuses an already-running server instead of failing to bind, the /web handoff prints the same ready banner as kimi web (plus the session deep link), and the banner Stop hint adapts to the hosting mode. * fix(cli): resolve the server token after the server is up in /web The token lookup had moved ahead of ensureDaemon()/startServerForeground() during the foreground-default refactor, so a first-time start (no server.token on disk yet) opened the browser without the #token= fragment and left the user at the auth gate. Resolve the token after the daemon is healthy, and inside the foreground ready hook. * docs(changeset): flag the web foreground default as breaking in the changelog The bump stays minor, but the entry now calls out the behavior break and the --background mitigation for scripts that expect kimi web to return immediately. * feat(cli): flag a version mismatch when reusing a server from an older CLI After an upgrade, an older still-running server is reused as-is. The lock's host_version is now surfaced: kimi web / server run print a version-mismatch line next to the reuse notice, /web shows the same as a status warning, and the docs plus changeset tell users a single kimi server kill switches them onto the new version.	2026-07-18 23:32:41 +08:00
Haozhe	e715b1648c	docs(server): document --dangerous-bypass-auth and --keep-alive flags (#1373) ... Add the two kimi server run flags introduced in #1368 to the CLI reference (en + zh), including a danger callout for the auth-bypass flag, and add the changeset so the next release notes the feature.	2026-07-04 18:33:22 +08:00
Kai	e9a3b7c83a	feat(cli): add update alias for upgrade command (#1125) ... Register a `kimi update` alias for the existing `kimi upgrade` command via commander's .alias(), so both forms run the same upgrade flow. Document the alias in the command reference and add a routing test.	2026-06-26 16:48:45 +08:00
liruifengv	6b68aa85e2	feat(cli): add -c as shorthand for --continue (#999) ... The lowercase -c now maps to --continue, shown in help as the primary short flag. The uppercase -C still works as a hidden alias since commander does not allow two short flags on a single option.	2026-06-23 13:53:31 +08:00
liruifengv	c0eeca2469	feat: add workspace add-dir support (#812) ... * feat: add workspace add-dir support Add multi-directory /add-dir management with session-only or project-remembered persistence, directory completion, confirmation UI, and runtime workspace/permission wiring. * fix: honor --add-dir for resumed sessions Pass CLI additional directories through shell and prompt resume paths, resolve caller-relative dirs against workDir, and add regression coverage. * fix: keep additional dirs AGENTS.md out of default context Load only user-level and cwd AGENTS.md by default, while preserving additional directory listings in the prompt context. * feat: append /add-dir result as user message Add a session appendUserMessage RPC and use it after /add-dir so the command result is recorded as a normal user message and surfaced in the transcript. * docs: add add-dir research and follow-up todos Document the add-dir / local-command-stdout research findings and the follow-up tasks for stdout wrapping, slash file completion, and hints. * feat: wrap /add-dir output as local-command-stdout Insert the /add-dir result as a user-role <local-command-stdout> record with an injection origin directly inside Session.addAdditionalDir. It enters the model context on the next turn but does not start a turn, and stays out of the live and resumed transcript; the transient status toast is kept for immediate feedback. --add-dir is unaffected since it bypasses addAdditionalDir. Remove the now-unused appendUserMessage RPC and SDK method. * feat: reopen /add-dir completion after accepting a directory Generalize the slash-argument completion reopen so it fires whenever the text before the cursor ends with '/', not only when the literal '/' key is typed. After Tab-accepting a directory (or auto-applying a single-child dir), the next level's completion list reappears automatically, so repeated Tab keeps drilling down into subdirectories. '@' file mention is unaffected. * feat: reopen file mention completion after accepting a directory Extend the path completion reopen so it also fires for '@' file mentions. After Tab-accepting a directory in an '@' mention, the next level's completion list reappears automatically, matching the '/add-dir' continuous-Tab behavior. * feat: show inline argument hints for slash commands Render a dim ghost-text argument hint inside the input box after a slash command that takes arguments, replacing the popup-only hint that was easy to miss. The hint appears once the command is typed and disappears as soon as an argument is entered, and is truncated to fit the box width. Add argument hints for /compact, /swarm, /goal and /title; /add-dir already had one. * test: remove stale additional-dirs AGENTS.md assertion The subagent-host test still asserted that an additional directory's AGENTS.md content appears in the agent system prompt, but additional-dirs AGENTS.md has been intentionally excluded from the default context since an earlier commit (covered by context.test.ts). Drop the stale assertion. * fix: resolve /add-dir paths against workdir and persist via kaos Resolve user-supplied /add-dir paths against the current workdir instead of the project root, so launching from a subdirectory behaves like the CLI --add-dir flag. Also route the local.toml read/write through the kaos abstraction instead of host fs, so the remember path works for non-local sessions. * fix: expand ~ in /add-dir paths before resolving The /add-dir completer emits ~/... values, but the core treated ~/foo as a relative path because pathe isAbsolute('~/foo') is false, producing <workDir>/~/foo. Expand ~ and ~/ to the home directory (via kaos.gethome()) before resolving. * chore: remove add-dir dev docs from the branch These were working notes (research and follow-up todos) that don't belong in the PR. * chore: clarify add-dir changeset for users * docs: document /add-dir, --add-dir, and local.toml * test: flush records before reading wire in add-dir runtime tests FileSystemAgentRecordPersistence.append buffers records and flushes asynchronously, so readMainWire can read the wire before the local-command-stdout record lands. Flush the main agent's records explicitly in the two add-dir runtime tests to make them deterministic.	2026-06-22 19:42:13 +08:00
wenhua020201-arch	90745abc29	docs(reference): fix kimi web to document background-daemon behavior (#871) ... * docs(reference): 修正 kimi web 为后台守护进程运行 kimi web 实际复用 server run 的后台守护进程流程（web-alias.ts 中 defaultOpen 置为 true），原文档误写为前台运行。改为后台启动、命令返回， 并补充 --foreground 示例。 * docs(reference): 与文档站参考手册版本对齐 kimi web 说明	2026-06-18 11:16:48 +08:00
Haozhe	9a8fea5c85	feat(web): introduce Kimi web app and daemon gateway (#625) ... * docs(reports): collapse P3 plan into a single final-solution doc Drop the per-step TDD/commit scaffolding; keep the substance as one final approach per area (what it does, files to touch, key types/events/projection, component responsibilities, verification, risks, sequencing). * fix(kimi-web): normalize chat block spacing Group consecutive tool cards structurally so chat block spacing is applied consistently without leaking card borders or shadows. * feat(web): land P3 — goal / swarm / subagent + terminal + view split Implements the locked P3 design end-to-end: - subagent lifecycle projection (spawned→started→suspended→completed/failed) + inline Agent / AgentGroup cards; swarm progress card (multi-column) derived from swarmIndex; goal dock strip (expandable) from goal.updated; plan/goal/ swarm activation badges in the composer status line. - terminal as a view (xterm + WS terminal_* frames with since_seq replay) and a tab/view-dimension split (usePaneLayout tree + ViewGroup + SplitLayout, VSCode editor-group style), persisted to localStorage. Adds swarm-groups / subagent-goal / agent-group-turns unit tests and stub-daemon seeds. 98 tests pass; vue-tsc + oxlint clean; production build OK. Accepted by review (see reports/web-p3-acceptance.md); no blocking issues. * docs(reports): P3 landing acceptance review Comprehensive acceptance of the P3 landing (f5a7f21c): per-area verdicts, the terminal 'map' crash explained as a stale-stub test artifact, non-blocking recommendations, and verification record (98 tests, vue-tsc/oxlint clean, prod build, in-browser smoke). No serious issues found; no code changed per the 'only fix serious issues' instruction. * fix(terminal): make node-pty load and spawn in packaged + pnpm-dev builds Two distinct PTY failures: - 'Failed to load native module: pty.node' (npx/published daemon): node-pty was transitively bundled via @moonshot-ai/services (alwaysBundle), inlining its JS while its native binary can't be bundled and wasn't shipped. Mark node-pty external in tsdown (neverBundle) and declare it as a runtime dependency of @moonshot-ai/kimi-code so npm/npx installs it with its prebuilt pty.node. - 'posix_spawnp failed' (local pnpm dev): node-pty's prebuilds/*/spawn-helper loses its +x bit through pnpm's store extraction. Add a root postinstall (scripts/fix-node-pty-perms.mjs) that restores the executable bit; verified it fixes a reproducible spawn failure. Also harden defaultShell() to fall back on an empty (not just unset) $SHELL. Note: the SEA standalone binary still needs node-pty's pty.node + spawn-helper wired into scripts/native/native-deps.mjs (not addressed here; npx path covers the reported case). * fix(web): use a real monospace font + tighter line height in the terminal xterm's fontFamily takes a literal font string, so 'var(--mono)' never resolved and the terminal fell back to courier with loose metrics — the wrong-looking font and spacing. Pass the actual JetBrains Mono stack, await document.fonts before xterm measures the cell (so the variable font isn't mismeasured), tighten lineHeight 1.25 → 1.1, and pin letterSpacing 0. * style(web): drop the staggered line-in animation on expanded tool-call output Remove the per-line kimi-line-in stagger on `.box.open .bb > div` (modern/kimi themes) and its keyframes — expanding a tool card no longer animates each output line in. * feat(web): move the tool-call summary into the card when expanded Previously the command/summary always sat on the header. Now it shows on the header only while collapsed; expanding hides it from the header and renders it at the top of the card body (above the output) — so it appears exactly once and the expanded header stays clean. Re-adds the .bb-summary style and a mount test. * feat(web): show the full, un-truncated summary in the expanded tool card The expanded body has room to wrap, so it shouldn't keep the header's '…' clip. Add a `full` flag to toolSummary that skips the length clip and use it for the .bb-summary; the collapsed header keeps the clipped form (CSS ellipsis still guards overflow). Extends the mount test to cover full-vs-clipped. * revert(web): keep the sending moon until the turn ends Reverts 980ff9d4: dropping the moon the instant the first token streamed wasn't wanted. Remove the assistantDelta/messageUpdated clear so sendingBySession is again cleared only on turn end (onSessionIdle), restoring the prior behavior, and delete the now-moot sending-moon test. * style(web): bump composer textarea font-size to 14px The composer input (.ph) under the modern/kimi themes was 13px while the terminal-theme baseline is 14px. Unify on 14px so the textarea text matches the rest of the composer. * fix(web): dedupe the daemon echo of an image steer (no double user bubble) Steering an image while a turn was running rendered TWO user bubbles and the steer text looked like it never landed. Two causes: 1. The reducer matched the daemon's user-message echo to our optimistic copy by exact content equality. Image content serializes differently on each side (our {source:{kind:'file',fileId}} vs the daemon's resolved URL/base64), so the echo never matched and appended a duplicate. Match by prompt_id first (stamped on the optimistic message at submit), falling back to content. 2. Optimistic message ids were msg_opt_<Date.now()>. A queued send + a steer in the same millisecond collided on one id, so the prompt_id stamp landed on the wrong message. Use a monotonic counter for a unique id per optimistic message. steerPrompt now also stamps the real prompt_id onto its optimistic echo, like submitPromptInternal already did. * fix(web): don't flash the chat pane when opening an empty session Selecting a never-opened session set sessionLoading=true until its snapshot arrived, so the chat pane (loading spinner) rendered for a beat before the empty-composer. A session the daemon reports as empty (messageCount 0) has nothing to load — keep sessionLoading false for it so the empty-composer shows immediately. Non-empty sessions still show the loading state. * fix(web): auto-scroll to the latest content after a mid-stream refresh Refreshing while a turn was streaming left two things parked above the live output: - The thinking block's inner 5-line window stayed at its TOP. Its scroll watcher only re-pins when already at the bottom, but a refresh delivers the whole thinking text at once with scrollTop 0. Pin a streaming block to its latest line on mount. - The transcript could stop short of the bottom: the first scroll runs before markdown highlighting/images lay out and grow the content. Re-pin on the next couple of frames (only while still following) so a refresh ends at the latest content. * fix(web): stop subagent turns from fragmenting the parent transcript A subagent runs under the parent session id and streams its own turn / step / delta / tool frames over the SAME session channel, each tagged with the subagent's agentId. The web projector folded them into the parent transcript, which produced the reported bug: empty 'skeleton' assistant bubbles (a subagent turn.step.started opened a parent assistant message the main agent never filled) and fragmented snippets (subagent deltas appended to the parent). Skip transcript-building frames whose agentId is a non-main subagent, mirroring the server's InFlightTurnTracker (which already tracks only main-agent activity). Subagent progress is unaffected — it flows through the subagent.* -> task -> AgentCard path, which is intentionally not gated. * feat(web): remove the floating todo/background-task overlay The wide-screen float-stack pinned a todo card + running-tasks card to the top-right of the chat. Drop the overlay entirely (and the now-unused TasksCard.vue) — todos and background tasks live in their own ~/todo and ~/tasks tabs, so the overlay was a redundant, transcript-covering duplicate. * feat(web): show all background tasks in the tasks tab, scroll on overflow The tasks tab capped the list at 5 rows and showed '… +N more', hiding the rest even with plenty of room. Render every task and let the list scroll internally once it overflows the pane, so nothing is silently dropped. * feat(web): running spinner + unread blue dot left of the session title The gutter slot left of each session title (which kept the title aligned under the workspace name) now carries a status indicator instead of being an empty spacer: - a small SVG spinner (Kimi-blue arc) while the session is running, replacing the old absolutely-positioned pulse dot; - an unread blue dot when a BACKGROUND session finished a turn the user hasn't opened yet. Tracked via unreadBySession (set on idle for a non-active session, cleared when the session is selected). * feat(web): unify archive/remove wording + keep the confirm within the title - Clarify the two list-removal actions: a session is 'Archive' (归档), a workspace is 'Remove workspace' (移除工作区) — the workspace menu used the bare 'Delete', which read as the same action as the session archive. - Keep the session row's archive-confirm strip aligned under the title: the leading gutter slot now persists in the confirm state, so the confirm row starts at the title's left boundary instead of spilling to the row edge. * feat(web): new-conversation button + workspace picker on the empty composer - Add a compose button in the sidebar header (top-left) that starts a new conversation in the active workspace. It wires up the previously-dead 'create' emit (handleCreateSession → openWorkspaceDraft). - On the empty composer, add a workspace picker below the hint so a new conversation can be started in any workspace without leaving the screen (switching enters that workspace's draft via openWorkspaceDraft). * feat(web): add a Fork entry to the session row menu Forking already worked via the /fork command and the daemon's :fork route, but had no discoverable affordance. Add a 'Fork session' item to each session row's kebab menu; forkSession() now takes an optional session id so any row (not just the active one) can be forked. * feat(web): recall sent messages with ArrowUp/ArrowDown in the composer Shell-style history: ArrowUp on the first line of the composer walks back through previously sent messages; ArrowDown on the last line walks forward and finally restores the live draft. Editing the text leaves history-browsing, and the edge-line guards keep multi-line cursor movement intact. Submitting (or steering) a message appends it to the history (consecutive duplicates skipped). * feat(web): capture console.log/info/debug + reusable log export The client trace only captured console.error/warn. Capture every console level (log/info/debug too) when tracing is enabled, so the exported troubleshooting log reflects the full front-end console. Extract the JSONL download into a reusable downloadTraceLog() (the debug panel now calls it; a settings 'Export log' action can reuse it). * feat(web): extract settings into a dedicated Settings page Settings used to live in the sidebar account popover (a cramped fixed dropdown that mixed appearance, language, account and the daemon endpoint). Move them into a dedicated SettingsDialog modal opened from the header gear: - Appearance (theme / colour scheme / accent), Language - Account (provider, add workspace, reopen onboarding, sign in/out) - Advanced (daemon endpoint, Export log — reuses downloadTraceLog) The sidebar popover and its anchoring/positioning code are removed; the gear now just emits openSettings. A Notifications section is added next (T14). * feat(web): browser notification when a turn completes (with a settings toggle) When a session finishes a turn and the user isn't already watching it (page hidden, or a different session is active), fire a browser system notification titled with the session, clicking it focuses the window and opens the session. Opt-in via a new Notifications toggle in the Settings page; enabling it requests OS permission and the preference is persisted (stays off if the user blocks it). * feat(web): modes selector (plan/goal/swarm) + fix swarm double-render - The plan pill at the composer's bottom-left becomes a 'Modes' popover that groups Plan (a working client toggle) with Goal and Swarm. Each shows its activated state (plan on / goal active / swarm n/m), and goal/swarm focus their card in the chat when active. The menu is position:fixed so the composer input row can't paint over it. - Fix the swarm 'two blocks' bug: a multi-member swarm rendered BOTH inline as an AgentGroup AND as its SwarmCard. messagesToTurns now skips the inline block for swarm members (same membership test as buildSwarmGroups), so the swarm shows once — its special card in the chat flow. Note: starting a goal/swarm from the web needs a daemon REST endpoint (the goal RPC isn't exposed over REST and the daemon doesn't interpret slash commands in prompts); display + activation state are wired here. * feat(web): add a chat context header (workspace/session, git, open, copy, PR) A thin bar above the chat shows the workspace / session breadcrumb, the git branch with ahead/behind + changed-file count, an 'open in editor' action (daemon fs:open on the workspace root), and a 'copy all conversation' action (reuses ChatPane.copyConversation). It also has a GitHub PR slot that renders when PR data is available — the daemon doesn't expose PR status yet, so it's wired but currently passed null. Hidden on mobile and for the empty composer. * feat(web): default path + fuzzy recursive search in the add-workspace browser - Open the folder browser at the path kimi-web is working in (the active workspace root, falling back to $HOME) instead of always at $HOME. - The filter becomes an fzf-style search: typing runs a bounded, debounced RECURSIVE subsequence-fuzzy walk under the current folder (capped depth/dirs/ results, cancellable) and lists matching directories by relative path. The result list keeps a fixed height, so the dialog never resizes while searching. - Collapse the paste-an-absolute-path field behind a secondary 'enter a path' toggle (auto-expanded when the daemon can't browse). * chore(web): remove the non-functional /undo slash command /undo had no daemon endpoint — it only pushed an 'undo not implemented' warning, so it was a dead menu entry. Remove it from the slash list, the command router, and the client. The full slash-command review with deletion suggestions for the remaining commands is in reports/web-goal2-fixes.md (T17). * docs(reports): results report for the second web TODO sweep (19 items) * test(web): provide browser storage in vitest under node 24 * docs(reports): add web goal2 acceptance notes * feat: show shortPath over branch in sidebar workspace header * feat(kimi-code-web): use rounded chat bubble icon for new session button * feat(kimi-code-web): add workspace creation in empty composer and tidy settings dialog * feat: add manual swarm and goal activation to web ui - Extend protocol schemas with swarm_mode, goal_objective, goal_control - Add stub diff-dispatch in PromptService for new runtime controls - Wire swarm/goal state through useKimiWebClient and daemon events - Add Swarm toggle and Goal create/pause/resume/cancel in Composer modes menu - Update StatusPanel and MobileSettingsSheet with swarm indicator/toggle - Add bilingual i18n strings and update fixtures/tests * feat: remove copy-conversation button from view-tabs - Drop showCopyConversation / copyConversationCopied props from TabBar and ViewGroup - Remove the share-conversation button markup and styles from TabBar - Clean up related i18n strings in en/zh sidebar locales - Keep the existing ChatHeader copy-all button and internal copy state unchanged * feat: reorder chat-header layout and simplify git status styling - Move Copy all button next to the workspace/session title on the left - Move git branch/status and Open-in-editor to the right - Shorten editor button label via new openInEditorShort i18n key - Render ahead/behind/changes as plain colored text without pills - Update en/zh header locale files * style: make chat-header action buttons borderless icon + text - Remove border, background, border-radius, and padding from .ch-act - Keep label collapse on narrow widths, drop obsolete padding override * feat: move copy-all to kebab menu and add session actions in chat-header * feat: redesign chat-header open button with open-in menu * feat: align chat-header diff stats with git ++/-- red/green style * style(web): thinner, fainter scrollbars across all components * fix(web): re-pin chat to bottom when a turn finishes streaming * fix(web): keep the working moon spinning after a refresh mid-stream * fix(web): subagent card margins in bubble layout + expandable task/result detail * feat(web): rebuild subagent cards from the transcript so they survive a refresh * fix(web): stop code blocks getting stuck on the loading skeleton markstream's CodeBlock shows a skeleton while !stream && loading, and its loading prop defaults to true. We never set it, so every settled code block waited on shiki to highlight before showing anything; a screenful of code (long session / fast burst) overwhelms shiki and the skeletons get stuck, leaving the whole page blank. Pin loading:false so blocks render their plain-text fallback immediately and upgrade to highlighted when ready. * fix(web): tick running task timers + make task rows expandable to view output * fix(web): dedupe image-steer echo via a loose (text+image-count) match The daemon's messageCreated echo can land before submitPrompt stamps the prompt_id onto the optimistic copy, and an image serializes differently (file ref vs resolved URL), so neither the prompt_id nor exact-content match fired and the echo rendered as a SECOND user bubble. Add a loose fallback matching on text + image-count so the echo reconciles regardless of order. * fix(web): let ↑/↓ walk all the way through input history once browsing Recalling a multi-line entry left the caret on its last line, and the 'ArrowUp only on the first line' gate then refused to recall further, so history only ever went one step back. Once browsing (historyIndex set), walk history directly regardless of caret line; typing still exits browsing. * feat(web): minimize button on question/approval cards + stack option label/desc - Add a minimize toggle so a blocking question/approval can collapse to a thin header bar instead of covering the chat; number-key shortcuts are gated while collapsed so an unseen option can't be picked. - Stack each option's label above its description (was squeezed side-by-side into many thin lines when the description was long). Note: there is no question/approval timeout in the codebase (ask-user waits indefinitely), so the '10 minute' request is a no-op. * feat(web): archive-confirm text matches title size; workspace remove always hides - Bump the 'archive session?' confirm label to the session-title size (14px) so it lines up with the title instead of reading as a smaller note. - 'Remove workspace' now always hides the sidebar entry, even when it still has sessions: record the root in a persisted hidden set so mergedWorkspaces stops re-deriving it from session cwds. History/sessions are untouched; re-adding the same path un-hides it. * feat(web): persist unsent composer drafts per session in localStorage The composer text is saved under a per-session key as you type and restored when you switch back to that session or reload the page; sending/steering clears it. New-session drafts use a '__new__' key. * feat(web): implement undo + edit-and-resend the last user message - Wire the daemon POST /sessions/{id}:undo endpoint: client.undo(count) reverts the last turn(s) and re-syncs the snapshot. Restore the /undo slash command. - Add an 'edit & resend' button on the latest user message: it undoes the last exchange and refills the composer with that message's text for editing. * fix(web): reflect the agent's plan mode in the composer toggle The agent reports plan mode via agent.status.updated (e.g. it auto-entered plan mode for a 'make a plan' prompt), but the projector only forwarded swarmMode, so the composer's plan toggle never lit up. Carry planMode on sessionUsageUpdated, sync it into state, and also read it from GET /status — mirroring swarmMode. * fix(web): hide an empty {} argument from the tool-call title (kept in details) An empty tool argument was rendered as a noisy '{}' in the collapsed tool-card header. toolSummary now returns '' for empty args in header (non-full) mode while the expanded body still shows it. * feat(web): show file/media preview as a split pane (peer of chat/files) On desktop, opening a preview from a chat link/media now splits the layout and shows it as a 'preview' view at the chat/files level (a transient tab in that group, closeable via the group's close button) instead of a separate right-side panel — matching the split buttons. Mobile keeps the full-screen side panel; the preview view isn't persisted across reloads. * docs(reports): results report for the third web TODO sweep (16 items) * chore(kimi-web): temporarily hide open-in-app header menu * docs: design doc for temporarily disabling swarm and goal modes in web composer * feat(web): gray out swarm and goal modes with not-supported label * docs: design doc for composer queue bubble + expanded panel * feat(kimi-web): move undo button out of bubble with new icon and confirm step * fix: inherit split layout attributes * fix(kimi-web): smooth moon spinner speed * feat(web): wire swarm and goal controls to agent-core - enable swarm toggle and goal input/pause/resume/cancel controls in Composer\n- add goal error codes and agent-core-to-protocol route mappings\n- wire enterSwarm/exitSwarm and create/pause/resume/cancelGoal RPCs in PromptService\n- bootstrap swarmMode from agent-core state and track it in the shadow\n- update tests for swarm/goal dispatch and session status serialization * fix(tui): only show provider refresh status for added models Skip removed / metadata-only provider updates when reporting model list changes.\n\n add: test to enforce the behavior. * feat(tasks): add background task command and output polling to web - include command field on protocol/server tasks\n- support withOutput/outputBytes on task get endpoint\n- poll running task output and fetch final output in web client\n- show bash command and terminal output in TasksPane with copy buttons * feat(web,server): wire open-in app menu to daemon endpoint - add /fs:open-in endpoint and command builders for vscode, cursor, finder, iterm, terminal\n- expose installed open_in_apps via meta response\n- filter OpenInMenu by available apps and remove antigravity target\n- support optional line number when opening files in apps\n- add unit tests for open-in launch commands * feat(kimi-web): expose git diff line stats in chat header - add additions/deletions to fs:git_status protocol and daemon response\n- compute aggregate diff stats with git diff --numstat HEAD\n- render +N/-N counter and detached HEAD label in chat header\n- update tests and stub daemon fixtures * fix(kimi-web): hide terminal tab temporarily * feat(kimi-web): add UI font size setting * fix(kimi-web): repin chat after tail layout settles * feat(kimi-web): show live subagent progress * fix(kimi-web): align plaintext colors in dark mode * feat(kimi-web): stream running bash output * fix(kimi-web): avoid shiki overload on large messages * feat(kimi-web): preselect recommended questions * feat(kimi-web): add conversation outline nav * fix(kimi-web): tighten mobile layouts * feat(kimi-web): animate undo removal * feat(kimi-web): reorganize bottom dock * fix(web): lengthen session row running spinner arc * feat(kimi-web): turn goal mode into a toolbar toggle Turn the Modes menu's 'Goal' row from a dedicated input form into a switch that arms the main composer. When goal mode is on, the composer placeholder prompts for an objective and the next submitted prompt is sent as a goal via updateSession({ goalObjective }). The armed state is surfaced in the composer toolbar the same way as Plan and Swarm: the Modes pill shows a 'Goal' tag and the menu switch is highlighted. An active (agent-driven) goal continues to expose Pause / Resume controls in the menu. Also includes minor bottom-dock spacing alignment changes to keep goal chips, workbar, and composer visually consistent. * feat(config): add config API endpoint with redaction support add GET/POST /api/v1/config routes\nadd ConfigService and config protocol schemas\nredact api_key in config response\nadd web client bindings and config event handling\nadd e2e tests for config routes and ws-broadcast * fix: keep web tool calls collapsed by default * feat(kimi-web): split dock work panel into bash, subagent, and todos tabs - Replace the single Background tasks tab with separate Bash and Subagent tabs in the bottom dock work panel. - Add i18n labels for the new dock tabs in both en and zh. - Filter task lists by kind and reuse TasksPane for each tab. - Align left edges of Bash/Subagent/Todos tab bodies and match the dock panel width/background to the Goal card style. - Hide TasksPane header title when rendered inside the dock to avoid duplicate headings. - Make the dock tab header show only the current tab name instead of clickable buttons. - Hide Goal card title summary on expand while keeping layout alignment for status/progress/chevron. - Update unit tests for the three-chip dock behavior. - Add changesets for the dock split and alignment fixes. * feat(kimi-web): beta proportional conversation outline with viewport indicator and hover tooltip * fix(kimi-web): avoid streaming markdown placeholders * fix(kimi-web): hide legacy conversation outline when beta TOC is off * chore(kimi-web): rename beta settings section to Experimental / 实验性 * fix(web): scale UI font size consistently Apply the web font size preference across readable text using the shared UI font scale, keep fixed icon glyph sizes pinned, and raise the default font size to 15px. * fix(web): remove task tabs from tab bar * feat(web): refresh OAuth model metadata for always-thinking models * fix(kimi-web): use 'Sub Agent' and 'Mode' in English labels * fix(kimi-web): keep swarm subagents across background-task refreshes REST /tasks lists only the main agent's background-task store and never returns foreground swarm subagents (kind 'subagent'), which arrive purely through the WS event stream. Both the 1s output poll and the session-load task fetch rebuilt tasksBySession from that REST list, so a plain replace dropped the subagents on every refresh and the next event re-added them — flickering the swarm/subagent cards, their live "currently doing" line, and the dock "running" count about once per second. Add keepLiveSubagents() to carry WS-owned subagent tasks across the REST refresh (REST stays authoritative for the background tasks it does return) and use it at both rebuild sites. * fix(kimi-web): hide completed swarm cards from conversation bottom stack - Filter out swarm groups whose members are all completed/failed. - Preserve markstream-vue .table-node styles without overriding its layout. - Add unit tests for swarm stack visibility. * feat(session): add session-level abort and expose current_prompt_id in snapshot - add POST /sessions/{sid}:abort to cancel running turns without prompt_id\n- expose current_prompt_id in in-flight turn snapshot\n- wire session-level abort fallback in kimi-web stop button\n- add IPromptService.abortBySession and getCurrentPromptId\n- update protocol, server, services, and web tests * fix(server): allow aborting queued prompts and add server-e2e send/cancel coverage add server-e2e scenario (12-send-and-cancel) and vitest cases for send prompt / cancel prompt flows, including repeated ESC idempotency\nsupport aborting queued prompts in PromptService.abort and add abortSession helper to DaemonClient/HttpClient\nhandle SSE transport case in MCP server mapping and fix related typecheck issues\nadd changeset for @moonshot-ai/services and @moonshot-ai/kimi-code * fix(kimi-web): prevent file preview scroll jump when opening a file at a line * fix(kimi-web): show just now for sessions created less than a minute ago * fix(kimi-web): keep sidebar logo intact and hide product name on narrow sidebars * fix(kimi-web): preserve markdown code gutter * feat(web): carry message createdAt into ChatTurn * feat(web): add formatMessageTime utility * feat(i18n): localize yesterday label for message timestamps * feat(web): render timestamp below user query bubble * fix(web): move user query timestamp outside the bubble * fix(web): place timestamp on same line as undo action * fix(web): swap timestamp and undo positions, reveal undo text on hover * feat(web): make timestamp a button that toggles full date time * feat(web): update sidebar branding and enlarge session tags; clean up changesets - Replace "Kimi Code Web" + "BETA" with "Kimi Code" + version pill - Enlarge session pending tags to match the title font size - Ignore internal private packages in changeset config - Remove stale changesets that only affected ignored packages - Document web release flow in README * style(web): equalize timestamp and undo button heights and alignment * feat(web): make workspace names bolder to distinguish from session titles * feat(kimi-web): rename themes to Explore/Native and remove accent selector * style(web): nudge undo icon up by 1px * style(web): align both meta actions to the right * style(web): remove gap between undo and timestamp buttons * style(web): nudge undo icon up by another 0.5px * feat(web): tune workspace name font-weight to 500 * fix(kimi-web): center tag/question text and limit shell-cmd height in approval card * style(kimi-web): remove icons from session pending tags * feat(kimi-web): limit recent workspaces in empty-composer picker * feat(kimi-web): rename sidebar new-workspace button to new-chat and adjust empty conversation title * style(kimi-web): refine sidebar typography, spacing and font settings * style(kimi-web): unify Composer typography with sidebar - Use --ui-font-size for queue text and --ui-font-size-xs for queue labels/bubbles. - Remove mono font-family from composer queue/bubble elements. - Normalize perm/mode/model pill text color to --text. - Set placeholder color to --muted. * style(kimi-web): keep model pill color dimmed Revert the model selector pill text color from --text back to --dim so it stays visually secondary, matching the original design intent. * style(kimi-web): adjust ChatHeader git status spacing and badge layout * style(kimi-web): polish composer dock chip styles * feat(kimi-web): refresh session list relative times on a 30s clock * fix(kimi-web): decode base64 file content in the preview pane * feat(kimi-web): show per-session answer/approve tags in the sidebar * feat(kimi-web): pop the KAP debug panel out into a separate window * feat(kimi-web): open subagent detail in the side panel; inline agent-live * style(kimi-web): align DiffView focus outline with KMBlue * feat(kimi-web): surface goal protocol errors; ignore global config-changed events * feat(kimi-web): support video attachments in user messages end-to-end * feat(kimi-web): add /swarm and /goal slash commands * feat(kimi-web): add /btw side chat backed by child sessions * style(kimi-web): pin user message bubble font size to 15px * style(kimi-web): use Lucide PR icon and text-only git status in header * fix(kimi-web): update undo tooltip copy and reduce hover delay * fix(kimi-web): auto-scroll to bottom on send, session switch, and tab switch - Scroll side-chat panel to bottom after sending and while streaming - Reset scroll baseline on session switch to avoid stale lastScrollTop - Reset scroll baseline when returning from files tab to chat - Reset scroll baseline after user sends a message - Include @moonshot-ai/kimi-code so CLI rebuilds bundle the updated web app * fix(kimi-web): drop duplicate config-changed case shadowing the real handler A stopgap no-op `case 'event.config.changed'` (added before the config feature landed) ended up earlier in the switch than the real configChanged mapper after merging origin/feat/web, silently swallowing config events. Remove the no-op so the proper handler runs. * style(kimi-web): unify PR badge with git status pills and drop changes count * style(kimi-web): remove unused changes computed in ChatHeader * fix: keep packaged web build in sync Build kimi-web before copying packaged web assets and surface the build version plus short commit in the settings dialog. * fix(web): support slash command input tails * fix(web): scope composer dock to chat tab * fix(web): route btw through side-channel agents * feat(web): open changed files from git status * feat(web): copy final assistant summary * feat(web): add tabbed model picker * fix(web): keep composer input height fixed * fix(web): preview composer attachments * feat(web): open workspace links in files tab * fix(web): stabilize subagent progress * docs(web): design tab split workflow * feat(web): connect daemon config settings * fix: resolve CI failures on feat/web - add missing 'event.config.changed' case in exhaustive switch test\n- fix oxlint errors (unused import, string spread, unsafe stringification)\n- update protocol test fixtures for additions/deletions, open_in_apps, swarm_mode\n- fix services mcp transport switch exhaustiveness for sse\n- update nix pnpm deps hash * fix(server): suppress debug logs by default - route BridgeClientAPI and PromptService debug logs through ILogService instead of console.error\n- lower SessionClientsService debug logs from info to debug\n- add changeset for @moonshot-ai/services, @moonshot-ai/server and @moonshot-ai/kimi-code * fix(kimi-web): remove model picker top blue bar and widen dialog - Remove the inset blue box-shadow from the model picker header. - Increase the default dialog width from 620px to 760px. * fix(kimi-web): replace model picker checkmark with icon - Swap the textual checkmark for a proper SVG check icon in ModelPicker, matching the icon used in the composer model dropdown. * fix(kimi-web): hide the Open in app menu - Remove OpenInMenu usage from ChatHeader and the prop/event plumbing through ConversationPane and App. - Remove the now-obsolete test case in files-tab-no-git.test.ts. * feat(kimi-web): scope composer dock to chat tab and polish BTW side chat - Move the composer dock into the chat tab only so it no longer appears in split file, task, preview, or BTW panes. - Render the BTW side chat as a split side pane scoped to the active session, and keep its messages out of the main conversation transcript. - Remove the side-chat panel header, relabel the tab to Side chat / 侧边聊天, and use the shared moon spinner while waiting for the first token. - Suppress the generic Started a step progress text for side-channel agents. * feat(server): expose live session status via HTTP and WebSocket - add status field to session status response schema and event.session.status_changed\n- compute session lifecycle status in SessionService from approvals, questions, prompts, and turns\n- broadcast event.session.status_changed globally to all WebSocket connections\n- re-export new event types from agent-core\n- add e2e and unit tests for status computation and broadcasting * fix(kimi-web): label sidebar session removal as Archive * feat(kimi-web): make tab/split chrome accessible TabBar is now a real ARIA tablist: role=tab buttons with aria-selected, roving tabindex, Left/Right/Home/End keyboard nav, focus-visible styling, and aria-controls wired to each ViewGroup's tabpanel (role=tabpanel + aria-labelledby). ViewGroup split-right/split-down/close buttons get localized aria-labels (no longer English title-only) and a 28x28 hit area. * fix(kimi-web): move auth banner into layout flow The onboarding/auth banner was position:fixed over the top of the conversation column, covering the desktop ChatHeader and the mobile top bar. Wrap the app grid in a flex-column shell and render the banner as the shell's first in-flow child so it reserves its own height above both the sidebar/header and the mobile top bar instead of overlapping navigation. * fix(kimi-web): enlarge and label header/sidebar icon buttons Unify icon-button hit areas and keyboard affordances: - ChatHeader kebab: 28x28 target, aria-label + aria-expanded/haspopup, focus-visible ring. - Sidebar workspace kebab (.gh-more): 24x24 target, aria-label, stays visible on keyboard focus (it was hover-only), focus ring. - Sidebar per-workspace add (.gh-add): aria-label + larger tap target. - Focus rings on the settings button and new-chat/new-workspace buttons. * feat(kimi-web): give overlay dialogs modal focus management Add useDialogFocus(): records the opener, moves focus into the dialog on open, and restores focus to the opener on close. Wire it plus aria-modal="true" / tabindex="-1" into ModelPicker, LoginDialog and ProviderManager (Escape-to-close was already present). ModelPicker keeps focusing its search box on open. Covered by a model-picker focus test. SettingsDialog is intentionally left for a follow-up to avoid colliding with in-flight settings work. * feat(kimi-web): consistent rules for the right-side detail layer The transient detail panels (thinking, compaction summary, subagent detail, mobile file/media preview) now share one set of rules: - the aside is a labelled role=complementary region (aria-hidden when collapsed), - Escape closes whichever panel is open — handled in App on the capture phase so it takes precedence over the conversation's "Esc interrupts a run" handler instead of firing both, - every close button has an aria-label (not just a title) and a focus-visible ring; thinking/subagent close targets bumped to 28x28, - FilePreview toolbar buttons get focus-visible rings too. * fix(kimi-web): calm the diff line colors Added/removed diff lines washed the entire row in green/red (12% tint + fully coloured text), which competed with reading the code. Drop the background to a faint 7% tint plus a left accent bar, color only the +/- sign, and let the code text keep the normal ink color so the content — not the color wash — is what stands out. * docs(web): record tab/split convergence + UI audit follow-through Implementation note for the tab/split work: the final three-layer view model (persistent chat/files tabs, transient preview/btw tabs, right-side detail layer), the transient-view routing rules, a per-task status table, which audit suggestions were absorbed vs intentionally skipped, and why the SettingsDialog focus item is deferred (concurrent in-flight rewrite). * feat(kimi-web): add side-tab navigation to SettingsDialog * feat(session): persist session archive state and add include_archive list filter - Replace deleteSession with archiveSession RPC and REST endpoint\n- Persist archived flag in session state and filter archived sessions by default\n- Add optional include_archive query parameter to list archived sessions\n- Expose archived flag on session responses through protocol and web types\n- Rename web session delete events/handlers to archive * feat(kimi-web): give SettingsDialog modal focus management Completes the dialog-focus baseline (task 8): wire useDialogFocus + aria-modal/tabindex into SettingsDialog now that the side-tab rewrite has landed. Focus moves into the dialog on open and returns to the opener on close; covered by a settings-dialog focus test. * refactor(workspace): centralize registry into a single workspaces.json - replace per-bucket workspace.json files with one workspaces.json registry\n- serialize registry reads/writes through an opQueue to avoid races\n- delete now removes only the registry entry, leaving the session bucket intact\n- update workspace e2e tests and scenario for the new storage model * feat(workspace): add workspace lifecycle WS events - publish event.workspace.created/updated/deleted from the registry service\n- broadcast them to every connection via the __global__ watermark\n- add protocol types/schemas and frontend mapping for real-time workspace sync\n- cover with protocol, broadcast, and exhaustive-switch tests * feat(fs): add fs:mkdir action for creating directories - add fsMkdir request/response schemas and FS_ALREADY_EXISTS (40919) error code - implement IFsService.mkdir guarded by resolveSafePath, returning the created directory entry - register the mkdir action in the fs route dispatcher with EEXIST/ENOENT mapping - add protocol schema tests and server e2e coverage * style(kimi-web): set fixed heights for all modal dialogs * feat(kimi-web): add collapsible sidebar * refactor(web): temporarily hide new workspace button in sidebar * feat(kimi-web): add starred models support to model picker and composer dropdown - Persist starred model ids in localStorage via useKimiWebClient. - Pin starred models to the top of the All tab in ModelPicker. - Show a Starred section in the Composer quick-switch dropdown, including models from other providers. - Render a star glyph on each starred model row in both pickers. - Add --star CSS variable with a brighter yellow across themes. - Add tests for starred model ordering and Composer dropdown rendering. * test(kimi-web): cover chat dock composer alignment * feat(server): expose GitHub pull request in git status and web header Add a pullRequest field to the session fs:git_status response, looked up via gh pr view with a 5s timeout, GH_NO_UPDATE_NOTIFIER/GH_PROMPT_DISABLED, and a 60s per-cwd cache.\nNormalize gh state to open/merged/closed and fail soft to null so git status never breaks.\nWire the web chat header PR badge to the active session. * feat(kimi-web): surface 5-state session status with a separate busy flag The session view-model collapsed every lifecycle state to running|idle, so awaiting-input and aborted sessions were indistinguishable and the spinner span while a session was actually waiting on the user. Session now carries the real `status` (idle/running/awaitingApproval/ awaitingQuestion/aborted) plus a separate `busy` flag (running + a real task in flight). SessionRow spins only when busy, shows awaiting tags from status as a fallback for background sessions, and a distinct aborted tag; SessionsDialog and MobileSwitcherSheet distinguish the states too. (The producers in useKimiWebClient already landed via an earlier commit; this adds the Session type, the UI, and labels so the tree type-checks.) * fix(kimi-web): persist unread dots across a page reload unreadBySession was pure in-memory state seeded empty on every load, with no localStorage persistence and no server-side read cursor — so a browser refresh dropped every sidebar unread dot. Persist the `true` entries to localStorage (compact: only unread sessions are stored) and seed the map from storage on init; opening a session clears the flag and the stored entry. Covered by a reload test in the session-cache suite. Note: also carries pre-existing empty-session-flash test edits that were already part of this file's working state. * style(kimi-web): redraw collapse/expand sidebar icons Use an indent-style glyph: three lines with a directional chevron, mirrored between the collapse (left) and expand (right) states. * feat: add server-hosted web UI and document its packages - wire kimi-web into root and CI typecheck (vue-tsc) and refresh the Nix pnpm hash - consolidate per-feature changesets into a single server-hosted-web-ui entry - make agentEventProjector.shortJson resilient to stringify failures and adjust tests - add AGENTS.md for kimi-web and server; add READMEs for server and services - expand root AGENTS.md project map and clarify the flake.nix workspace-sync rule * test(kimi-web): cover empty-session flash + draft-send paths Tests and changeset for the empty-session-flash fix (the sessionsKnownEmpty / sessionLoading logic itself already landed in an earlier commit): selecting a locally-created session shows the empty composer with no loading flash, an existing session reported as empty still loads its snapshot (messageCount is not trusted), and sending straight from the draft composer does not flash the empty state. * chore: ignore generated docs and reports * style(apps/kimi-web): remove app shell top border * fix(build): build kimi-web assets before native SEA build The native SEA build embeds the Kimi web SPA from apps/kimi-code/dist-web (see scripts/native/02-sea-blob.mjs) and fails when that directory is missing. Build kimi-web and stage its assets via copy-web-assets.mjs before running build:native:sea. - flake.nix: add the web build + asset copy to buildPhase so `nix build` works. - _native-build.yml: add the same prep step before the SEA build so CI release / manual native bundles keep working. Fixes "Kimi web build output was not found at .../dist-web" in the nix build and the CI native build stage. * feat(web): hide context indicator on empty session composer * feat(kimi-web): unify detail panel layout * fix(web): improve dark toc tooltip contrast * fix(web): keep markdown code blocks mounted * fix(web): tighten dark color contrast * fix(web): close dock cards on outside click * feat(web): show session content summaries * fix(web): report web client telemetry * refactor(services): merge @moonshot-ai/services into agent-core - move services/src/** into agent-core/src/services/** and delete the standalone @moonshot-ai/services package - re-export service contracts/implementations from agent-core src/index.ts - update all server, test, and kimi-web imports to @moonshot-ai/agent-core - enable experimentalDecorators in tsconfig and adjust dev/build configs - sync workspace registry (changeset config, flake.nix, pnpm-lock) * refactor(server): remove Swagger UI and --swagger flag - drop @fastify/swagger-ui and the dev-only --swagger option - keep /openapi.json via @fastify/swagger (bundled in the SEA) - simplify the native SEA build (no swagger-ui external or asset copy) - update tests, docs, and lockfile * feat(server): add on-demand daemon for kimi web with idle shutdown - make kimi web non-blocking by spawning or reusing a single detached daemon per device (via ~/.kimi-code/server/lock), auto-picking a free port on conflict - daemon self-exits after a 1-minute grace once the last web WebSocket client disconnects (new onConnectionCountChange hook + createIdleShutdownHandler) - add getLiveLock helper for daemon discovery - hide kimi server install/uninstall/start/stop/restart/status (service-ization) for now; implementation preserved for later re-exposure * fix(web): improve mobile dialog layouts * fix(ci): resolve lint, typecheck, and nix build failures - add startBtw to IPromptService test mocks (agent-core, server) - remove useless spread in PromptService session cleanup - add assertion to concurrent-connection WS handshake test - bind idle onConnectionCountChange callback in server run - type getSessionSnapshot mock via vi.mocked in kimi-web test - update pnpmDeps hash in flake.nix Co-Authored-By: Claude <noreply@anthropic.com> * fix(web): distinguish native markdown links * fix(vis-web): enable experimentalDecorators for typecheck vis-web type-checks agent-core source (via source exports), whose services use legacy parameter decorators for DI. Without experimentalDecorators, tsc reports TS1206 "Decorators are not valid here" and the CI typecheck job fails. * Revert "feat(web): show session content summaries" This reverts commit 8de58eacbc. * fix(web): align active toc-bubble highlight with bubble edges * fix(web): hide conversation toc when chat pane is too narrow * feat(server): add `kimi server ps` to list active clients - add GET /api/v1/connections endpoint backed by IConnectionRegistry - record connection metadata (connectedAt, remoteAddress, userAgent) on WsConnection - add connection wire schema in @moonshot-ai/protocol - add kimi server ps CLI command with table and --json output * feat(kimi-web): add queue chip to chat dock workbar * fix(agent-core): hide console window when spawning git/gh on Windows On Windows, spawning a console-subsystem executable (gh.exe / git.exe) from the background Kimi server creates a visible console window that flashes on screen. Set windowsHide: true (a no-op on POSIX) to suppress it. * feat(server): add startup and ws connection telemetry for kimi web - bootstrap telemetry in `kimi web`/`kimi server run` via initializeServerTelemetry (ui_mode=web, honors telemetry=false) - wire the real client into KimiCore so agent-core events carry the enriched context - emit server_started after the server listens; flush telemetry on shutdown - emit ws_connected/ws_disconnected from WSGateway via WSGatewayOptions.telemetry - re-export loadRuntimeConfigSafe/resolveConfigPath from the SDK for host config reads * feat(web): dynamic page title based on session or workspace * fix(web): show recently active sessions at the top of the web session list * feat(web): show running indicator in dynamic page title * feat(kimi-web): show elapsed time for completed assistant turns * fix(kimi-web): resolve TDZ error on App mount * refactor(kimi-web): align turn duration and support multi-tab timing * feat: display per-turn wall-clock duration in web chat * feat(web): use animated spinner in page title while running * feat(server): add kill command and background server run - add `kimi server kill` to stop the running daemon (graceful API + forced PID kill) - add `POST /api/v1/shutdown` so the server can terminate itself - make `kimi server run` start in the background and print the ready banner - route `kimi web` through the same path as `server run` so it prints the banner too * fix(server): remove duplicate startBtw key in prompt e2e test Resolves eslint no-dupe-keys and TS1117 errors that broke the lint and typecheck CI jobs. * chore: bundle Inter font locally * fix(nix): update pnpmDeps hash for new font dependency The local Inter font dependency changed pnpm-lock.yaml, so refresh the fixed-output derivation hash to match what the nix builder computes. Resolves the nix build .#kimi-code CI failure. * fix(server): restore web client telemetry and stabilize skills cleanup Restore forwarding of x-kimi-client-* headers into session creation telemetry, which was dropped during the services-to-agent-core merge and left the new-session telemetry test with empty records.\n\nRetry the skills e2e sandbox cleanup to ride out ENOTEMPTY races when the core process flushes files into the sandboxed home after close(). * chore: remove trailing blank lines * chore(changeset): remove consumed changeset files These 20 changeset files were applied during the version bump and are no longer needed. * chore: clean up web release changesets * docs: clean up kimi web readme * chore: scope package lint to cli release * chore: remove temporary design docs and preview files from PR Remove files that were not intended for submission: - docs HTML research/design archives - docs/superpowers specs added during design phase - apps/kimi-web icon preview pages and one-off test script * chore(kimi-web): remove dev stub daemon The real server package is now available; the throwaway stub daemon is no longer needed for development. * test(server-e2e): accept aborted image prompt scenario * chore: update flake.nix workspace paths and add new changesets - Added new packages: daemon, server-e2e, and kimi-migration-legacy to the workspacePaths in flake.nix. - Introduced new changeset for "@moonshot-ai/kimi-code-sdk" to add host-side config helpers. - Removed outdated changesets related to server-hosted web UI and server web APIs. * feat(server): daemonize by default and fall back to port +1 - kimi server run now spawns a background daemon by default; --foreground keeps the terminal attached - default server port moves from 7878 to 58627 across CLI, web, e2e, and docs - listenWithPortRetry retries on port + 1 when a third party holds the port (capped at 100) - lock gains updatePort so status/kill/ps find the daemon on its real bound port * fix(cli): resolve oxlint unbound-method errors in server run --------- Signed-off-by: qer <wbxl2000@outlook.com> Co-authored-by: qer <wbxl2000@outlook.com> Co-authored-by: Claude <noreply@anthropic.com>	2026-06-17 20:53:46 +08:00
wenhua020201-arch	8ac274369c	docs: document the kimi vis command (#827)	2026-06-16 22:49:40 +08:00
Haozhe	d1ba14562b	feat(providers): sync custom registry providers on startup refresh (#675) ... * feat(providers): sync custom registry providers on startup refresh - group registry providers by URL and retry available API keys\n- automatically add new providers and remove disappeared ones\n- coalesce duplicate source URLs to avoid false config-change reports\n- clear defaultThinking when default model is removed\n- update docs and add tests for registry sync scenarios * fix(tui): only show provider refresh status for added models Skip removed / metadata-only provider updates when reporting model list changes.\n\n add: test to enforce the behavior.	2026-06-12 17:08:40 +08:00
liruifengv	ad239cb1c0	fix(cli,tui): allow --auto, --yolo, and --plan with resumed sessions (#683) ... * fix(cli,tui): allow --auto, --yolo, and --plan with resumed sessions * docs(cli): update flag conflict docs for resumed sessions * fix(tui): apply startup permission/plan overrides after picker selection	2026-06-12 14:17:12 +08:00
liruifengv	6a4e4c75d4	feat(cli): add doctor command for config validation (#431) ... * feat(cli): add doctor command for config validation * fix(cli): format doctor validation errors * fix(cli): validate doctor config through SDK RPC * chore(changeset): simplify doctor release note	2026-06-04 21:15:18 +08:00
qer	d6febf1381	docs: fix documentation links (#389)	2026-06-03 23:23:28 +08:00
wenhua020201-arch	70ca7a9f8b	docs(zh): improve CLI section — env-vars, mcp, interaction, datasource, and more (#372) ... * docs(zh+en): improve and translate CLI section — guides, config, customization, reference zh improvements: - interaction: add image/video paste, expand approval flow, Plan/YOLO/Auto modes - slash-commands: add /btw, /reload, /reload-tui - kimi-command: add kimi login, kimi acp subcommands - environment-variables: restructure with KIMI_CODE_HOME, KIMI_DISABLE_TELEMETRY, KIMI_MODEL_* sections - mcp: fix anchor link text - datasource: rewrite as official plugin page (new) - use-in-ides: ACP IDE integration for Zed/JetBrains (new) - kimi-acp: ACP capability matrix and method coverage (new) en: full zh→en translation of all 22 CLI pages, zh/en aligned Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore: remove misplaced local-path file from upstream PR branch Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: moonshot <moonshot@moonshotdeMacBook-Pro.local> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-03 22:56:26 +08:00
Haozhe	3eafa79f39	feat(acp): implement ACP server with session lifecycle, tool streaming, and IDE integration (#368) ... This commit scaffolds the @moonshot-ai/acp-adapter package and introduces the full ACP (Agent Communication Protocol) server implementation for Kimi Code CLI, including: - Scaffold @moonshot-ai/acp-adapter workspace package with build skeleton - `kimi acp` CLI subcommand and stdout-safe logging - ACP version negotiation and AgentSideConnection wrapper - Auth gate for session creation - Session lifecycle: new, list, load with history replay - Prompt content conversion (text, image, embedded resources, resource links) - Assistant streaming with thinking support and end-turn handling - Tool call streaming (started, delta, progress) with result conversion (text / diff) - Approval handling with diff/text display blocks mapped to ACP options - Kaos read/write interface (AcpKaos) for unsaved buffer access - Session mode (yolo/auto) and model management - Config options builder with thinking toggle - MCP server forwarding from ACP to harness - Agent plan updates and available commands updates - AskUserQuestion bridged to session/request_permission - Plan review options surfaced through requestPermission - Error mapping, ext_method stubs, and graceful shutdown - IDE integration guide (Zed + JetBrains) - End-to-end tests against ACP TS SDK client	2026-06-03 21:11:30 +08:00
qer	3502d870fc	chore: scrub internal identifiers from public text (#340)	2026-06-02 21:54:42 +08:00
liruifengv	eeefa98083	feat(cli): add automatic and manual upgrades (#334)	2026-06-02 18:39:50 +08:00
7Sageer	3c5dee8836	feat(cli): add kimi provider subcommand for non-interactive provider management (#313) ... * feat(cli): add `kimi provider` subcommand Add a non-interactive equivalent of the TUI `/provider` command: - `kimi provider add <url> --api-key <key>` imports every provider in a custom api.json registry, persisting `source` so the next TUI launch refreshes the model list automatically. - `kimi provider remove <id>` deletes a provider and its model aliases. - `kimi provider list [--json]` prints configured providers with model counts and source labels. - `kimi provider catalog list [providerId] [--filter] [--url] [--json]` browses the public models.dev catalog. - `kimi provider catalog add <providerId> --api-key <key> [--default-model]` imports a known provider straight from the catalog. All actions reuse `fetchCustomRegistry`, `applyCustomRegistryProvider`, `fetchCatalog`, and `applyCatalogProvider` from the existing oauth/SDK helpers. * fix(cli): satisfy oxlint rules in provider subcommand - Use `Array#toSorted()` instead of `Array#sort()` to avoid mutating arrays returned from `Object.keys()` / `Object.entries()`. - Drop redundant boolean-literal comparisons on `model.capability.*` fields (already typed as `boolean | undefined`). - Remove the unnecessary `source as Record<string, unknown>` assertion in `providerSourceLabel` — `ProviderConfig.source` is already typed that way in the schema. - Drop the empty-object fallback in `{ ...(config.models ?? {}) }` inside the test harness. * fix(cli): address review findings on provider subcommand P1 — `provider add`: `harness.removeProvider` re-reads the config from disk (see `agent-core/src/rpc/core-impl.ts removeKimiProvider`), so calling it mid-loop discarded providers we had already applied in memory but not yet persisted. Importing a registry that added a new provider then replaced an existing one silently lost the new one. Drop every stale id up front in a single batch, then apply each entry against the resulting fresh config. P2 — `catalog add`: `applyCatalogProvider` always writes `defaultThinking`. Hardcoding `false` would silently disable thinking for thinking-capable models when the user had it on. Thread the prior `defaultThinking` through. P2 — `catalog add`: `removeProvider` clears `defaultModel` when it pointed at one of the provider's aliases, so capturing `previousDefaultModel` AFTER the removal yielded `undefined`. Capture both `defaultModel` and `defaultThinking` BEFORE the removal so re-importing a configured provider (e.g. to rotate the api key) preserves the user's chosen default. Tests: - `makeHarness` now models the on-disk semantics of `removeProvider` (clears `defaultModel` when an alias matches, returns fresh disk view), so behavior that depended on the buggy in-memory mock is exercised honestly. - Three new regression tests, each verified to fail against the pre-fix handler. * fix(cli): address follow-up review on catalog default semantics Two more findings on `catalog add`: P2 — `default_thinking` fallback to `false` was wrong even after the previous fix. `resolveThinkingLevel` (agent-core/.../thinking.ts:23) treats `defaultThinking === false` as an explicit "off" request and silently disables thinking before per-model defaults kick in. A first-time `kimi provider catalog add anthropic --default-model claude-opus-4-7` was therefore still persisting `default_thinking = false` for thinking-capable models. The handler now always restores the previous `defaultThinking` (including `undefined`) — the only way to let the runtime resolver pick the per-model default. P2 — Restoring `default_model` was unconditional, even when the refreshed catalog no longer ships that model. `applyCatalogProvider` drops the old aliases and only populates the current catalog, so restoring an alias the catalog no longer contains would point `default_model` at a non-existent entry and break the next session. The handler now checks whether the alias still resolves and clears it otherwise. Test harness: - The fake `setConfig` now mirrors the real `mergeConfigPatch` semantics (deep-merge with `undefined` keys skipped), so tests can honestly assert that `setConfig({defaultModel: undefined})` does NOT wipe a key from disk — only `removeProvider` can. Two new regression tests, each verified to fail against the pre-fix handler. --------- Co-authored-by: 7Sageer <158020838+7Sageer@users.noreply.github.com>	2026-06-02 14:58:47 +08:00
liruifengv	07dd604c3c	feat: add /auto slash command and --auto CLI flag (#163) ... * feat: add /auto slash command and --auto CLI flag * feat: add /auto slash command and --auto CLI flag	2026-05-28 20:24:50 +08:00
Kaiyi	842e699a64	Kimi For Coding	2026-05-22 15:54:50 +08:00