* fix(agent-core-v2): fix wire migration rewrite race and reject unversioned logs (8 files)
- await the migration rewrite in wireRecordService.restore() so restore only resolves once the migrated log is durable and rewrite failures surface
- serialize AppendLogStore.rewrite() behind the log flush so appends arriving during the whole-file replace land after the new content
- reject wire logs missing the metadata envelope (missingWireMetadataError) in restore, session fork, and agent create instead of fabricating a current-version envelope over legacy records
* fix(agent-core-v2): stop background tasks on session close (10 files)
- add IAgentTaskService.stopAllOnExit: suppress terminal notifications, then SIGTERM → grace → SIGKILL for every active task (v1 stopBackgroundTasksOnExit parity, gated by keepAliveOnExit)
- call stopAllOnExit from agentLifecycle.remove before scope disposal, and abort live tasks in AgentTaskService.dispose as a last resort for disposal paths that bypass the graceful close
- honor [task] killGracePeriodMs in the stop grace window and bind the v1 KIMI_CODE_BACKGROUND_KEEP_ALIVE_ON_EXIT env override for keepAliveOnExit
* fix(agent-core-v2): root task persistence at the owning agent's scope
- persist task records under <sessionScope>/agents/<agentId>/tasks/ (v1's
per-agent layout) so tasks written by older versions are found on resume
- stop one agent's restore from loading, marking lost, or re-notifying
another agent's tasks
- add a per-agent isolation test covering loadFromDisk + reconcile
* fix(agent-core-v2): address task lifecycle review findings
* fix(agent-core-v2): preserve queued appends across rewrites
* test(agent-core-v2): cover rewrite cutover flush
* fix(agent-core-v2): surface append durability failures
* fix(agent-core-v2): retire released append log buffers
* fix(agent-core-v2): preserve session-level task records
* fix(agent-core-v2): harden append log cutover recovery
* fix(agent-core-v2): suppress only background exit notifications
---------
Co-authored-by: qer <wbxl2000@outlook.com>
* feat(agent-core): make subagent timeout configurable and raise default to 2h
- add `[subagent] timeout_ms` config (env `KIMI_SUBAGENT_TIMEOUT_MS` overrides) to replace the hardcoded 30-minute cap for Agent / AgentSwarm subagents
- raise the default subagent timeout from 30 minutes to 2 hours
- thread the value through tool construction so foreground and background subagents use it, with the timeout message reflecting the effective value
* feat(background): add print_background_mode with steer for multi-turn -p runs
- add `[background].print_background_mode` (`exit`/`drain`/`steer`) and
`print_max_turns`; when unset, falls back to `keep_alive_on_exit = true`
mapping to `drain`, preserving existing behavior
- core: `Session.handlePrintMainTurnCompleted()` returns `finish`/`continue`;
in `steer` mode the run stays alive so a background-task completion
`turn.steer`s the main agent into a new turn (matching background
subagents), bounded by `print_wait_ceiling_s` and `print_max_turns`
- cli: print driver follows every main turn instead of only the first and
defers `finish()` until the run quiesces or a limit is hit
- plumb `handlePrintMainTurnCompleted` through node-sdk RPC; docs + tests
* docs(changelog): sync 0.23.5 from apps/kimi-code/CHANGELOG.md
* chore: update config model doc
* docs: update config-files example with new models and services
---------
Co-authored-by: liruifengv <liruifeng1024@gmail.com>
* feat(kosong): classify HTTP 413 request-body-too-large as a dedicated error type
* feat(agent-core): lower default image downscale cap to 2000px and make it configurable
* feat(agent-core): strip media to text markers and retry when the compaction request is too large
* feat(agent-core): cap model-initiated image reads with a configurable byte budget
* feat(agent-core): resend with degraded media when the provider rejects the request body as too large
* test(agent-core): add explicit timeouts to encode-heavy image budget tests
* feat: add WebP decoding support with wasm integration
- Introduced a new WebP decoding module using @jsquash/webp's wasm decoder.
- Implemented functions to decode WebP images and check for animated WebP formats.
- Updated image compression tests to include scenarios for WebP handling, including encoding and decoding.
- Enhanced error handling for API request size limits to accommodate various error messages.
- Updated pnpm lockfile to include new dependencies for WebP encoding and decoding.
* chore(changeset): consolidate this PR's entries into one
* fix(nix): update pnpmDeps hash for merged lockfile
* feat(agent-core): refuse HEIC/HEIF reads with platform-matched conversion guidance
* feat(kosong): honor explicit anthropic max output override
Add claude-opus-4-8 output ceiling and treat explicit max_output_size/KIMI_MODEL_MAX_OUTPUT_SIZE as the final Anthropic max_tokens value. Sync configuration and environment variable docs.
* feat(kosong): drop claude-opus-4-8 ceiling
Revert the newly added claude-opus-4-8 default output ceiling while keeping explicit max_output_size overrides for Anthropic.
* feat(agent-core): enable Preserved Thinking by default on the Anthropic provider
Default thinking.keep to "all" for the Anthropic provider (Claude and Kimi in Anthropic-compatible mode) while Thinking is on, via a context_management clear_thinking_20251015 edit, mirroring the Kimi default. Reuses [thinking] keep and KIMI_MODEL_THINKING_KEEP (env > config > default "all"); off-values disable it.
* feat(kosong): route Anthropic Preserved Thinking through the beta Messages API
Force the beta endpoint (client.beta.messages.create) when thinking.keep is enabled, since clear_thinking_20251015 is only honored there. Also prepend clear_thinking to any existing context-management edits (for example clear_tool_uses) instead of replacing them, keeping it first as Anthropic requires when combining edits.
* docs: clarify Anthropic beta endpoint and compaction keep behavior
Note in code comments and bilingual docs that enabling Anthropic Preserved Thinking routes requests to the beta Messages API (client.beta.messages.create), with keep=off as the escape hatch back to the standard endpoint. Correct the resolveThinkingKeep comment to reflect that compaction shares ConfigState.provider and intentionally carries the same keep.
* test(kosong): cover Anthropic beta endpoint (streaming and forced betaApi)
Add a streaming beta-endpoint capture and a test that withThinkingKeep forces the beta endpoint even when constructed with betaApi: false, pinning down the documented behavior.
Default `thinking.keep` to "all" when Thinking is on so prior `reasoning_content` is kept across turns. Add `[thinking] keep` to config.toml and keep `KIMI_MODEL_THINKING_KEEP` as an override (env > config > default); off-values disable it.
* feat(agent-core): guide the model away from repeating denied or failed tool calls
- system.md: add a diagnose-before-retrying paragraph next to the existing
permission-denial guidance, covering failed tool calls
- permission: when the user rejects an approval on the main agent, tell the
model not to re-attempt the exact same call (sub agents already had an
equivalent hint)
* fix(agent-core): close abandoned tool exchanges and dedupe duplicate tool_use ids
A turn that dies between a recorded tool.call and its paired tool.result
(e.g. a transcript write failure mid-batch) used to leave
pendingToolResultIds open forever: every later message was stranded in
deferredMessages and user input was silently swallowed.
- runOneTurn now defensively closes any dangling tool calls when a turn
ends (completed, cancelled, or failed), synthesizing an error result
that names the cause, with a warn log and a tool_exchange_abandoned
telemetry event
- the projector drops assistant tool calls whose id already appeared
earlier (first occurrence wins): a duplicate id is wire-invalid on
strict providers and not repairable by the strict resend; reported via
the existing projection-repair log and telemetry
- resume-side closePendingToolResults now logs what it closes (warn for
a mid-history gap, info for the routine trailing interruption)
* chore: add changesets for tool exchange fixes
* fix(agent-core): scope duplicate tool_use id dedup to the strict resend
Unconditional dedup regressed providers that emit per-response counter
ids (e.g. call_0 in every step) and accept their own duplicates: later
tool exchanges silently vanished from the projected history, and a
duplicate call's own recorded result was left dangling.
- the dedupe pass is now opt-in via dedupeDuplicateToolCalls and enabled
only in strictMessages, so the normal projection keeps the history the
provider produced
- the pass also drops every tool result after the first for an id, so no
dangling tool message survives; when the kept call has no result of
its own, the surviving one is reattached by the adjacency repair
- kosong now classifies the Anthropic "tool_use ids must be unique" 400
as a recoverable request-structure error so it triggers the strict
resend
* feat(cli): wait for background subagents before exiting kimi -p
When `background.keep_alive_on_exit` is enabled, `kimi -p` now waits for
all background subagents to reach a terminal state before exiting, bounded
by `background.print_wait_ceiling_s` (default 3600s). This lets concurrent
background subagents run to completion in single-turn runs instead of being
torn down when the main agent's turn ends.
* docs: use kimi-for-coding in model overrides example
kimi-for-coding is the stable public model ID users actually configure;
kimi-k2 is the underlying model name and shouldn't appear in the config
example. Demonstrate overrides with max_context_size and display_name.
* docs: drop dangling references to commented-out experimental section
The `## experimental` section was commented out when micro_compaction
was removed, but the top-level fields table and the intro sentence still
linked to the now-dead #experimental anchor. Remove those references.
* feat: add KIMI_MODEL_THINKING_EFFORT to force a thinking effort
Send thinking effort only when the model declares it in support_efforts, and add the KIMI_MODEL_THINKING_EFFORT environment variable as an escape hatch to force a specific effort regardless of declared support.
* test: align thinking effort expectations with support_efforts gating
Update the kimi adapter e2e and compaction tests that asserted the previous pass-through behavior on models without support_efforts.
* feat: add model alias overrides
Preserve user model overrides across provider catalog refreshes and resolve effective model metadata for runtime, TUI, protocol, and ACP consumers.
* fix: apply model display name overrides
Show overridden model display names in the footer, welcome panel, status output, and model switch confirmations.
* fix: pass through kimi effort when undeclared
Keep support_efforts authoritative when declared, but pass requested Kimi thinking effort through when the model does not declare support_efforts.
* fix: honor model overrides in effort commands
Use effective model metadata for /effort choices and for always_thinking clamping when resolving thinking effort.
* fix(provider): honor base_url for google-genai and vertexai providers
The google-genai and vertexai provider types silently ignored a configured
base_url and always hit generativelanguage.googleapis.com (e.g. a Gemini-
compatible proxy URL + key could not be used). Plumb the endpoint through to
the @google/genai SDK via httpOptions.baseUrl:
- kosong: add baseUrl to GoogleGenAIOptions and inject it into the client's
httpOptions alongside the existing headers (the SDK merges headers and
overrides the base host).
- agent-core: forward provider.baseUrl in the google-genai and vertexai
branches, with GOOGLE_GEMINI_BASE_URL / GOOGLE_VERTEX_BASE_URL env
fallback. vertexai keeps deriving location from an aiplatform host.
- docs: document base_url for both providers, noting the host root only
must be given because the SDK appends the API version itself.
Covered by unit tests asserting the URL reaches the kosong config and the
SDK client's httpOptions.
* fix(provider): use the effective base_url for vertex location detection
The vertexai branch forwarded the endpoint from config `base_url` OR the
GOOGLE_VERTEX_BASE_URL env fallback, but service-account detection
(`hasVertexAIServiceEnv` / `vertexAILocation`) still derived the region from
`provider.baseUrl` only. Supplying the regional endpoint via the env fallback
(with a project but no explicit GOOGLE_CLOUD_LOCATION) therefore left location
undefined and silently downgraded Vertex ADC to API-key Gemini routing.
Resolve the effective base URL once and use it for both forwarding and location
derivation, so the env fallback behaves exactly like `base_url`. Add a
changeset for the kosong + agent-core patch release.
* feat(agent-core): rework compaction to keep only user prompts and summary
* refactor(agent-core): rewrite compaction summary as first-person handoff
Rework the full-compaction summary to read as the agent's own continuing
notes instead of a third-party report:
- compaction-instruction.md: free-form first-person continuation that
preserves exact commands, paths and outcomes, states the precise next
action, and flags claimed-but-unverified work rather than trusting it.
- compaction-summary-prefix.md: skeptical "your own working notes"
framing; drop the collaborative third-party prefix.
- system.md: add compaction-awareness guidance so the model continues
naturally from a summary and re-checks any reported "done".
- Rename the compaction helpers module to handoff.ts.
Update tests and regenerate snapshots for the new prompt text, and fill
in contextSummary in the restored-compaction replay expectations.
* fix(agent-core): count image/audio/video parts in token estimation
estimateTokensForContentPart returned 0 for image_url/audio_url/video_url,
so auto-compaction triggers, the overflow-shrink budget, the kept-user
budget, and the reported context size all went blind to media — a
media-heavy session could overflow the model window while the estimate
reported a near-empty context. Media parts now carry a fixed estimate
(MEDIA_TOKEN_ESTIMATE), and the content-part switch is exhaustive so a new
ContentPart kind must declare its estimate rather than silently count as
zero.
* feat(agent-core): re-surface active background tasks after compaction
Folding the live context to [recent user prompts, summary] drops the
messages that started background tasks and their status updates, so the
model could forget a task is still running and spawn a duplicate.
injectAfterCompaction now appends a system-reminder listing active
background tasks (with guidance to use TaskOutput/TaskList/TaskStop
instead of re-spawning). It runs only post-compaction and carries an
injection origin, so the next compaction drops and rebuilds it rather
than stacking copies; the all-user-role post-compaction shape is
preserved (no tool-pairing reintroduced).
* test(agent-core): add compaction scenario guards and risk probes
Adds compaction-scenarios.test.ts driving the real Agent/ContextMemory/
FullCompaction machinery:
- A guard test locking in that repeated compaction folds the prior summary
into the new one instead of stacking two summaries.
- Seven `it.fails` probes that executably reproduce known, currently-accepted
edge-case defects so the suite stays green while documenting each one
precisely; any of them will flip red (forcing removal of `.fails`) the day
the behavior is fixed. They cover: assistant/tool appended during an
in-flight summarizer call being dropped; unbounded shrink on empty
summaries; the fixed 20k kept-user budget overflowing a small model window;
a tool result orphaned when compaction starts mid-exchange; legacy
compaction records dropping their verbatim tail on replay; micro-compaction
clearing recent tool results in an overflow-shrunk suffix; and media being
discarded when the oldest kept user message is truncated.
* fix(agent-core): repair tool_use/tool_result adjacency in projected context
A tool call and its result can end up non-adjacent in history — a
background-task notification or flushed steer lands between them, or an
interrupted/nested step delays the result — which strict providers reject
with HTTP 400. The projector now moves each tool_use's result up to
immediately follow it (projection-time only; the stored history is
untouched), and full compaction projects its summarizer input with a
synthetic result for any still-open call so the summary request stays
well-formed. Micro-compaction only surfaced this latent ordering by busting
the prompt cache, so it now defaults off.
Includes projector adjacency regression tests, a context-level integration
test, and a compaction synthesize-missing guard; the prior "keeps an
unresolved tool exchange out of the compaction prompt" test is updated to
the now-well-formed (synthetic-result) behavior.
* fix(agent-core): preserve the verbatim tail when restoring legacy compactions
A pre-rework `context.apply_compaction` record used
`[summary, ...history.slice(compactedCount)]` semantics and kept a verbatim
recent tail, but it has no `keptUserMessageCount`. The reworked applyCompaction
re-folded such records into the all-user shape, dropping the recent
assistant/tool tail — so resuming a session compacted by an older version
silently lost its most recent context.
On restore of such a record (gated on records.restoring, no keptUserMessageCount,
and compactedCount < history length) reproduce the old shape instead. The
forward/live path is unchanged; the projector's tool-adjacency repair keeps the
restored tail well-formed, and compaction only runs at clean step boundaries so
the tail has no open exchange. The legacy-tail probe now passes as a regression
guard via the real restore path.
* fix(agent-core): align legacy compaction foldedLength with live restore
The transcript reducer re-derived foldedLength for pre-rework
context.apply_compaction records (no keptUserMessageCount) using the new
kept-user+summary rule, but ContextMemory's restore now reproduces the legacy
[summary, ...history.slice(compactedCount)] shape for those records. The two
diverged for legacy sessions, so MessageService's foldedLength-vs-live-history
comparison could mis-handle GET /messages (miss or misorder recent output).
The reducer now mirrors the live legacy fold: when compactedCount is below the
pre-compaction length it computes 1 + (length - compactedCount); otherwise it
falls back to the kept-user derivation. The MessageService transcript test's
fixture is corrected to a new-format record, matching its all-user live mock.
* fix(kosong): merge a follow-up user turn into the preceding tool_results
The Anthropic message merge keyed on isToolResultOnly(last) ===
isToolResultOnly(converted), which left a tool_result-only user turn
followed by a plain-text user turn unmerged. After tool-exchange repair
this shape (assistant tool_use -> tool_result -> injected notification)
produces two adjacent user messages, which strict Anthropic-compatible
backends reject with HTTP 400.
Switch to the asymmetric predicate isToolResultOnly(last) ||
!isToolResultOnly(converted): a tool-result-only running message absorbs
whatever user turn follows (parallel tool_results or a trailing text),
yielding a valid [tool_result, ..., text] message; a plain-text running
message still only absorbs plain text. [tool_result, text] is valid for
both native Anthropic (which concatenates anyway) and strict backends.
* test(agent-core): pin micro-compaction flag in the shrunk-suffix probe
The 'does not clear recent tool results when projecting a shrunk suffix'
probe is an it.fails that only documents a real defect while
micro-compaction is active. It inherited the ambient
KIMI_CODE_EXPERIMENTAL master switch, so its pass/fail flipped with the
runner: green locally (master switch on) but a hard failure in CI, where
the flag defaults off and MicroCompaction.compact() is a no-op that
leaves the tool result intact.
Enable KIMI_CODE_EXPERIMENTAL_MICRO_COMPACTION explicitly for this probe
so it deterministically exercises the micro-compaction path regardless of
the environment.
* fix(agent-core): harden full compaction against in-flight races, unbounded shrink, and media loss
Three compaction-path fixes surfaced by review, each flipping its
documenting it.fails probe to a passing it:
- Append race (CMP-02): after the summarizer returns, the post-summary
history check only compared the compacted prefix. A live step appending
to the tail while a manual/SDK compaction was in flight slipped through —
an appended assistant/tool turn is neither summarized (the summary covers
only the snapshot) nor kept (the rebuild keeps user input), so it
vanished. Now cancel when the appended tail contains a non-user message;
an appended user message is still kept (rebuild picks it up), preserving
the existing 'keeps messages appended while compacting an unchanged
prefix' behavior.
- Unbounded empty/truncated shrink: an empty or truncated summary dropped
the oldest message and reset retryCount, so a model that kept returning
empty could issue ~one request per history entry. Bound the shrink
attempts by MAX_COMPACTION_RETRY_ATTEMPTS, mirroring the overflow-shrink
counter.
- Media dropped on truncation (CMP-07): truncating the oldest kept user
message replaced its whole content with one text block, discarding any
image/audio/video. Keep the non-text parts and spend the remaining budget
(maxTokens minus their cost) on truncated text.
* fix(vis): mirror legacy compaction tail in the model-mode projector
For a pre-rework context.apply_compaction record (no keptUserMessageCount),
agent-core's ContextMemory restore and the transcript reducer keep the old
[summary, ...history.slice(compactedCount)] tail — a verbatim recent tail
including assistant/tool. The vis model-mode projector always applied the
new kept-user selection, so opening an older compacted session in model
mode hid the assistant/tool tail the resumed agent still holds (and
surfaced a pre-compaction user message the agent dropped).
Branch on a missing keptUserMessageCount with compactedCount < history
length and reproduce the legacy shape, matching the agent-core restore.
* fix(agent-core): cancel compaction on any droppable user-role tail
The in-flight append guard cancelled only when the tail grew with a
non-user role. A user-role message that compaction would still drop — a
background-task notification, hook/cron reminder, or shell-command output —
slipped through: appended after the summary snapshot (so absent from the
summary) and dropped by the all-user rebuild (which keeps only real user
input), vanishing silently.
Key the guard on the same predicate applyCompaction uses (!isRealUserInput)
so it cancels whenever the appended tail holds anything compaction would
drop. A real user message is still kept, so a live user turn racing a
manual/SDK compaction continues to complete.
* fix(agent-core): exclude pre-clear prompts from legacy folded length
The transcript reducer's legacy fallback (records predating
keptUserMessageCount, compacted with no verbatim tail) re-derived the
kept-user count from the whole transcript, including messages before the
last context.clear. Live ContextMemory rebuilds _history from post-clear
messages only, so counting pre-clear prompts overstated foldedLength;
MessageService then saw context.history.length <= foldedLength and skipped
appending unflushed live tail messages, dropping recent output from the
messages endpoint for old sessions compacted after a clear.
Derive only from entries at or after clearFloor to match the live context.
* fix(agent-core): drop media when truncating the oldest kept prompt
Revert the media-preserving truncation: keeping non-text parts on the
truncated boundary message overshot the kept-user budget when the media
alone exceeded it, and reordered interleaved text/media parts. Both codex
(no media-aware truncation) and Claude Code (strips media at compaction)
decline to preserve media on a truncated message, since media cannot be
partially truncated and keeping it whole breaks the budget.
truncateUserMessage now keeps only the truncated text. Recent messages
that fit the budget are still kept verbatim with their media; only the
oldest, partially-overflowing boundary message loses its attachments.
* fix(agent-core): make manual compaction and turns mutually exclusive
A manual/SDK compaction could start while a turn was streaming, or a new
turn could launch while a compaction was in flight. Either way the turn
mutates the shared context (streaming content into an existing assistant
message, or appending new messages) during the summarizer await, and that
output is neither summarized nor preserved by the all-user rebuild —
silent loss that object-identity checks can't detect (the streamed message
is mutated in place).
Guard both directions so the agent does one of {turn, compaction} at a
time: begin() refuses a manual compaction while a turn is active, and
launch() refuses a new turn while a compaction is in progress. Auto
compaction is exempt — it runs from within the turn at a step boundary,
which blocks the turn for its duration.
* chore(changeset): consolidate compaction changesets into one
* chore(agent-core): drop external-product references from compaction comments
* test(agent-core): add Anthropic wire-compliance smoke tests for compaction
Drive real compaction output and the compaction summarizer projection
through the real Anthropic provider conversion and assert the wire request
is well-formed: strict user/assistant alternation and every tool_use
answered by an adjacent tool_result. Locks in the cross-layer guarantee
(projector merge + Anthropic consecutive-user merge + adjacency repair +
synthesizeMissing) that compacted sessions stay valid for strict
Anthropic-compatible backends.
* fix(agent-core): defer and replay inputs during manual compaction instead of rejecting
Manual/SDK compaction runs outside a turn, so the earlier guard rejected
prompts/steers that arrived while it held the context. That broke three
things: a REST/web prompt got stuck 'running' (no terminal turn event), a
background-task/cron steer was silently lost (null was read as 'buffered'
but nothing was), and a follow-up prompt could land in the window after
isCompacting cleared but before reminders were reinjected.
Reuse the existing defer-and-replay model instead of rejecting:
- steer() and launch() buffer into steerBuffer while a compaction is in
progress (returning null = buffered), mirroring how an active turn defers
input.
- FullCompaction.compactionWorker keeps isCompacting true through
refreshSystemPrompt + injectAfterCompaction (moving markCompleted and the
completed event after reinjection), then replays the buffer via
TurnFlow.onCompactionFinished — on success, on an A1 prefix/tail cancel,
and on failure/abort.
- onCompactionFinished flushes into an active turn if one exists, else
launches a fresh turn from the deferred input.
No PromptService change: a deferred prompt's eventual turn.started lets it
associate the pending prompt and clear it on turn.ended.
* fix(kosong): merge consecutive user turns for strict providers
Gemini/Vertex require strictly alternating user/model turns and reject
consecutive user turns with HTTP 400. They arise after compaction (kept
prompts + user-role summary + injected reminders) and when a turn is
steered in right after a tool result. Anthropic already merged them
inline; the Google converter did not, so post-compaction requests failed.
Extract the asymmetric merge into a shared mergeConsecutiveUserMessages
helper applied at each strict provider's conversion boundary: refactor
Anthropic to use it (behavior unchanged) and apply it at the Google
converter's exit. A conformance suite drives every strict provider with
the post-compaction shape and a steer-after-tool-result shape, asserting
no consecutive same-role turns reach the wire, so a new strict provider
cannot silently omit the merge.
The provider-agnostic projector stays structure-preserving: lenient
providers (OpenAI/Kimi) keep distinct turns for clearer message
boundaries; only strict providers normalize, where the requirement lives.
* feat: support multi-level thinking effort switching
- kimi provider: emit thinking.effort in the new wire format; keep reasoning_effort mirrored during the transition
- model catalog: thread support_efforts / default_effort from oauth through to /models
- config schema: add supportEfforts / defaultEffort on model aliases
- TUI: multi-segment thinking control in /model, new /effort command, footer effort display
- switch status uses displayName and distinguishes model vs effort-only changes
* docs: add thinking effort design plans
- thinking-effort-switching.md: implemented multi-level effort switching
- thinking-model-overhaul.md: follow-up refactor plan for the thinking state model
* docs: collapse thinking overhaul plan into a single PR
* refactor!: overhaul thinking config and effort resolution
Replace default_thinking and thinking.mode with a single [thinking] enabled/effort table. ThinkingEffort is now an open string ('off' | 'on' | model-declared effort); effort levels come from each model's support_efforts instead of a fixed enum.
Centralize default and always_thinking clamp logic in resolveThinkingEffort/defaultThinkingEffortFor, and honor an explicitly configured effort when an always_thinking model is forced back on.
TUI keeps a single thinkingEffort field instead of the boolean + level pair; 'on' is normalized to the model default at the UI boundary.
BREAKING CHANGE: default_thinking and thinking.mode are removed from config; migrate to [thinking] enabled/effort.
* refactor: rename residual thinking level wording to effort
Rename comments, error messages, parameter names, the SetThinkingPayload wire field (level -> effort), and TUI local variables so the thinking effort naming is consistent throughout. No behavior change.
* refactor: rename remaining camelCase thinking level identifiers to effort
Rename liveLevel/prevLevel/levelChanged/commitLevel/effectiveLevel to liveEffort/prevEffort/effortChanged/commitEffort/effectiveEffort in the TUI model picker and config commands.
* refactor: eliminate remaining thinking level wording in comments and tests
Rename levelLabel -> effortLabel, EffortSelectorOptions.levels -> efforts, and 'effort level(s)' / 'default level' / 'requested level' wording in comments, error messages, slash-command description, and test titles to effort. Also restore the withThinking(effort) parameter rename in the Kimi provider that was accidentally reverted.
* fix: address codex review feedback on thinking effort handling
- OpenAI thinkingEffortToReasoningEffort and Anthropic clampEffort now normalize 'on' / unrecognized efforts instead of throwing, so boolean non-Kimi models no longer crash on session start.
- ACP resolveCurrentThinkingEnabled treats a non-empty thinking.effort as enabled, matching agent-core's resolveThinkingEffort.
- REST promptThinkingSchema accepts any non-empty effort string so model-declared efforts are not rejected at the API boundary.
* test: align kimi e2e expectations with supportEfforts-gated reasoning_effort
The kimi provider now sends reasoning_effort only when the model declares support_efforts; boolean models (no support_efforts) send only thinking.type. Update the kimi e2e tests to drop the stale reasoning_effort expectation for the boolean test model.
* test: cover [thinking] effort parsing in config.test
Add effort = "high" to the documented [thinking] table in the config parse test and assert config.thinking.effort is resolved, so the new [thinking] effort field has direct parse coverage.
* docs: add thinking test coverage gap analysis
Capture the explore agent's test coverage review for the thinking overhaul PR, including P1/P2 gaps and the two open design questions, for follow-up test additions.
* feat(oauth): parse nested think_efforts from /models response
The /models endpoint now returns effort levels under a nested think_efforts object ({ support, valid_efforts, default_effort }). Parse it preferentially in both managed-kimi-code and open-platform model parsing, falling back to the legacy flat support_efforts / default_effort fields for older servers.
* refactor(oauth): only read nested think_efforts; gate on support=true
Drop the legacy flat support_efforts / default_effort fallback. The think_efforts object is now the single source, and its support flag gates the whole object — when support is not true, valid_efforts and default_effort are ignored entirely.
* chore: remove unused parseStringArray import in open-platform
* docs: finalize thinking effort release notes
Downgrade the changeset to minor with an English summary, drop the version-specific 'added in 1.0.0' info block, and present the deprecated config fields as a table (field / deprecated in 0.21.0 / description).
* refactor: drop temporary refresh toggles and kimi reasoning_effort mirror
Remove the always-true REFRESH_MODELS_ON_PICKER_OPEN / REFRESH_PROVIDER_MODELS_ON_STARTUP toggles and their stale re-enable TODOs, and stop sending reasoning_effort from the kimi provider (thinking.effort is the only wire field now).
* fix(tui): avoid persisting "on" as thinking effort
* fix: preserve persisted thinking effort across login and provider setup
* fix(tui): show actual thinking effort in /status and footer
* test(tui): align message-flow expectations with effort persistence and /status display
* fix(vis): rename thinkingLevel to thinkingEffort in config.update analysis
* feat(tui): redesign /plugins as a tabbed panel
Split the /plugins manager into Installed / Official / Third-party /
Custom tabs. The Official and Third-party marketplace catalogs load
lazily, so /plugins opens instantly and keeps working offline, with
fetch failures shown inline instead of closing the panel. The tab strip
is shared with the /model provider tabs via the new renderTabStrip
helper.
* fix(tui): show untiered marketplace entries and update badges
Address Codex review feedback on the /plugins tab redesign:
- Untiered marketplace entries (no `tier` field) now appear on the
Third-party tab instead of being invisible in both marketplace tabs.
- Installed plugins whose marketplace version is newer than the local
version render an `update <local> → <latest>` badge again, and
up-to-date plugins show `installed · v<version>` — restoring the
update visibility the pre-redesign marketplace UI had.
* fix(tui): decode Space for installed-plugin toggle
In terminals that send printable keys via Kitty/CSI-u sequences (e.g. VS
Code's integrated terminal), the Space key arrives as a printable char
rather than a Key.space match, so the Installed-tab Space toggle silently
stopped working. Check both matchesKey(Key.space) and the decoded
printable char to match the MCP selector and other dialogs.
* fix(tui): open custom marketplaces on the Third-party tab
When `/plugins marketplace <source>` points at a custom catalog whose
entries omit `tier`, those entries are classified into the Third-party
tab. Opening on Official left the visible tab empty and Enter could not
install anything, unlike the old marketplace picker which showed all
entries from the supplied source. Open on Third-party when a custom
source is supplied; the default catalog still lands on Official.
* docs(plugins): drop open-url wording and hyphenate Shift-Tab
Address Codex review feedback:
- The marketplace Enter action is install/update only (open-url rows were
removed), so say "install or update" instead of "open or install" and
drop the leftover changeset sentence about setup URLs.
- Use `Shift-Tab` (hyphen) instead of `Shift+Tab` to match the docs
typography convention.
* fix(tui): keep marketplace selection valid while loading
When the Official/Third-party catalog is still loading, `entries` is empty
and pressing ↓ computed `Math.min(-1, selectedIndex + 1)` = -1. The later
Enter then read `entries[-1]` and the first install silently did nothing.
Clamp the index to 0 while there are no entries.
* fix(tui): count tab separators in tab-strip fit check
renderTabStrip declared a strip to fit whenever the sum of tab cell widths
fit, but the returned string also inserts single spaces between tabs via
`segments.join(' ')`. At widths around 43-45 columns for a four-tab strip
this declared a fit while the joined line was wider, so the trailing tab
got truncated instead of showing the `<`/`>` scroll markers. Count the
inter-tab separators in both the full-fit check and the scrolling window
fit check.
* docs(plugins): fix Kimi Datasource redirect anchor
The datasource.md redirect pointed at ./plugins.html#kimi-datasource, but
plugins.md no longer has a `## Kimi Datasource` heading — it is now
`## Official Plugins`. Update the en/zh redirect targets and fallback
links to #official-plugins / #官方插件 so the link lands on an existing
anchor.
* docs(plugins): restore concise Kimi Datasource section
The `## Official Plugins` section had replaced the original
`## Kimi Datasource` section, leaving the datasource.md redirect pointing
at a missing anchor and the Datasource capabilities/usage unreachable.
Restore a concise `## Kimi Datasource` section (intro + OAuth login +
install steps + usage) in both en and zh so the #kimi-datasource anchor
is valid again and the content is reachable.
* docs(plugins): restore Installing-from-GitHub subheading
The tab-redesign rewrite had dropped the `### Installing from GitHub` /
`### 从 GitHub 安装` subheading and its lead sentence, leaving only the
four URL forms. Restore the heading and lead sentence in both en and zh.
* docs(plugins): expand Kimi Datasource and tidy marketplace docs
- Condense the Official / Third-party / Custom tab overview and trust-badge note
- Trim the custom marketplace JSON section to the minimal id + source shape
- Move and expand the Kimi Datasource section with install, usage, and coverage
* docs(plugins): fix heading style and drop Next steps section
- Use sentence case for the Datasource headings (How to use, What you can do)
- Rename the Datasource caveat heading to Billing and limitations / 计费与限制 to avoid a duplicate Notes / 注意事项 anchor
- Remove the Next steps section, which linked back to the on-page Datasource anchor
* fix(tui): repaint plugins panel from current theme palette
The /plugins panel and MCP selector captured a palette snapshot at construction. In auto theme mode, applyResolvedAutoTheme swaps currentTheme.palette and re-renders without remounting the open panel, so it kept stale colors until closed.
Read currentTheme.palette during render instead, drop the colors opt from both components and their call sites, and add a regression test that switches palettes on a mounted panel.
* fix(tui): repaint model tab strip from current theme palette
TabbedModelSelectorComponent cached a palette snapshot in opts and used it only for the tab strip. In auto theme mode the inner model list repaints from currentTheme but the strip kept the old colors until the dialog was closed.
Read currentTheme.palette on the render path instead, drop the colors opt and its three call sites, and add a regression test that switches palettes on a mounted selector and asserts the strip repaints. This removes the last palette snapshot among editor-replacement dialogs.
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.
* 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.
* feat(agent-core): cap AgentSwarm concurrency via env var
Add KIMI_CODE_AGENT_SWARM_MAX_CONCURRENCY to limit how many subagents run concurrently during the initial ramp, so large swarms do not trip provider rate limits as easily. Leave it unset to keep the previous uncapped ramp behavior.
* chore: drop ignored agent-core from changeset
* fix(agent-core): fail fast on invalid AgentSwarm concurrency cap
* feat(update): roll out automatic updates in staged batches via CDN manifest
* chore: remove changeset
* refactor(update): single-source the CDN latest file names
* refactor(update): reuse the CDN latest URL constants in update checks
* refactor(update): drop the test-only CDN base override
* fix: preserve first launch attribution
* fix: use refreshed rollout manifest for telemetry
* fix: abort hung cdn update checks
* fix: preserve update cache with bad manifest
* chore: remove review report from branch
* 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.
* fix: clean up background tasks on session exit
* Stop background tasks on session close
Change versioning for agent-core and kimi-code to patch.
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
---------
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
* Refactor theme
* custom theme support
* docs: add custom themes guide
Document the custom theme file location, the color token reference, selecting a theme via /theme and tui.toml, and fallback behavior. Link it from the customization sidebar and the tui.toml theme field.
* feat(skill): add built-in custom-theme skill
Guides the model (or a manual /custom-theme run) to author a theme JSON in ~/.kimi-code/themes/: docs token reference, deliberate color choices, hex validation, and how to apply via /theme or /reload-tui. Note in the write-tui skill to keep the token set in sync across colors.ts, the schema, the docs, and this skill. Enrich the custom-theme changeset to cover all three usage paths.
* chore: remove theme research report
* fix(tui): resolve lint errors after main merge
Remove unused chalk/currentTheme/ResolvedTheme imports left by the theme refactor; break the theme <-> pi-tui-theme import cycle by dropping the markdown/editor theme getters from the Theme class (consumers call createMarkdownTheme directly); fix unused vars/params, a floating promise, and a redundant union type.
* fix(tui): address custom theme review feedback
- await applyTheme before refreshing terminal theme tracking, so
switching to "auto" installs the watcher against the new state
- invalidate the transcript on automatic (terminal-driven) theme
changes so already-rendered entries repaint
- rebuild UsagePanel bodies on invalidate (previously a no-op); /usage,
/status, /mcp and /plugins now repaint on a theme switch
- repaint the compaction header on invalidate
- validate a custom theme before applying it from the /theme picker
- hide reserved dark/light/auto names from the custom theme list
- escape the theme name when writing tui.toml
- stop the custom theme loader writing warnings to the raw terminal
- remove a stray hello.ts
* refactor(tui): polish custom theme feature
- footer and todo-panel read the currentTheme singleton directly at
render time instead of caching a palette copy; drop their setColors
methods and the manual setColors calls on every theme change
- support "base": "dark" | "light" in custom theme files so a partial
light theme inherits the light palette for unspecified tokens
- reconcile the docs and the custom-theme skill with the silent
invalid-color fallback (no terminal warning)
* refactor(tui): live-repaint the agent swarm progress panel
Read the currentTheme palette through a getter instead of caching it at
construction time, so the swarm progress panel recolors on a theme switch
like the rest of the transcript. Drops the now-unused `colors` option.
* chore: remove plan.md
* docs: update custom theme guide
* docs: document custom theme skill command
* fix(skill): make custom theme user-triggered only
* feat: honor HTTP_PROXY/HTTPS_PROXY/NO_PROXY for all outbound traffic
Install a global undici dispatcher at CLI startup so every in-process fetch
(LLM APIs, MCP HTTP, web tools, telemetry, sign-in, update checks) honors the
standard proxy variables, and propagate NODE_USE_ENV_PROXY to spawned stdio
MCP child processes. Loopback hosts always bypass the proxy; an invalid proxy
URL is reported and ignored rather than aborting startup.
* feat: support SOCKS proxies via ALL_PROXY
Recognize SOCKS proxies (socks5/socks5h/socks4/socks alias) from ALL_PROXY or a
socks-scheme HTTP(S)_PROXY, routing traffic through a custom undici connector
backed by the socks client (reusing undici's own TLS handling for https).
HTTP(S) proxies keep precedence; NO_PROXY and loopback are honored for the SOCKS
path too. Child stdio MCP node processes honor HTTP(S) proxies via
NODE_USE_ENV_PROXY; SOCKS applies to the main process only.
* fix: address proxy review comments (env masking, child NO_PROXY, nix hash)
- Resolve HTTP(S)_PROXY explicitly via the first non-blank casing so a blank
lowercase var can no longer mask a populated uppercase one (the dispatcher
installed but went direct), and coerce a SOCKS-scheme value sitting in an
HTTP(S) var to '' so it is never handed to EnvHttpProxyAgent.
- Reconcile a child's NO_PROXY override across both casings using the first
non-blank value run through resolveNoProxy, so a per-server config override
is not shadowed by the injected lowercase value, keeps the loopback bypass,
and passes '*' through verbatim.
- Update flake.nix pnpmDeps hash for the added socks/undici dependencies.
* fix(proxy): honor http ALL_PROXY, match port-qualified NO_PROXY, note child Node version
- Honor an http-scheme ALL_PROXY as the catch-all fallback for both http and
https (scheme-specific HTTP(S)_PROXY still wins), so an ALL_PROXY-only setup
no longer installs a no-op dispatcher and connects direct.
- Make the SOCKS-path NO_PROXY matcher port-aware: a `host:port` entry now
matches only that port (with IPv6-safe parsing for `::1` / `[::1]:443`).
- Document that child stdio MCP proxying via NODE_USE_ENV_PROXY only applies on
Node versions that support it (>= 22.21 / >= 24.5).
* fix(proxy): IPv6 + wildcard NO_PROXY and per-server child proxy edges
- Strip IPv6 brackets from a SOCKS proxy host (e.g. ALL_PROXY=socks5://[::1]:1080)
so the socks client connects to the bare address.
- Add the bracketed [::1] to the loopback bypass: undici's EnvHttpProxyAgent
only exempts IPv6 loopback when the NO_PROXY entry is bracketed (it mis-parses
bare ::1). The SOCKS-path matcher normalizes brackets on both sides.
- Match *.domain wildcard (and host:port) NO_PROXY entries in the SOCKS matcher.
- Compute the child stdio proxy env from the MERGED env so a proxy declared only
in a server's config.env also enables NODE_USE_ENV_PROXY.
* fix(proxy): synthesize HTTP(S)_PROXY from ALL_PROXY for child processes
proxyEnvForChild now hands spawned stdio MCP children the resolved
HTTP_PROXY/HTTPS_PROXY (in both casings), synthesizing them from an http-scheme
ALL_PROXY when no scheme-specific variable is set. Node's --use-env-proxy reads
HTTP_PROXY/HTTPS_PROXY (not ALL_PROXY), so an ALL_PROXY-only parent now proxies
the child consistently with the main process. Shared resolveHttpProxyUrls helper
is reused by createProxyDispatcher and proxyEnvForChild.
* chore(changeset): tighten proxy changeset wording
* docs: fix code fence language and add cross-references (zh/en)
- slash-commands: add 'sh' language tag to /goal example code block
- config-files: link experimental section to env-vars#runtime-switches
- env-vars: link KIMI_CODE_EXPERIMENTAL_* rows to config-files#experimental
* docs: improve goals.md formatting and clarity (zh/en)
- Merge redundant opening paragraphs into one with concrete examples
- Use colons before code examples (not periods)
- Bold state names in lifecycle list (complete/paused/blocked)
- Replace prose keyboard shortcut description with table
- Remove draft product-background text from EN queue section
* docs: move goals after sessions in sidebar (zh/en)
Goal mode builds on multi-turn sessions, so it reads more naturally
after the sessions page in the guides navigation.
* feat(env): migrate kimi-cli model request params and auto-update toggle
Migrate still-relevant environment variables from kimi-cli:
- KIMI_MODEL_TEMPERATURE / KIMI_MODEL_TOP_P: sampling params applied
globally to any kimi provider (not tied to KIMI_MODEL_NAME).
- KIMI_MODEL_THINKING_KEEP: Moonshot preserved-thinking passthrough
(thinking.keep), injected only while Thinking is on.
- KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE):
fully disables the update preflight.
Wires env -> provider in Agent.get llm() via applyKimiEnvGenerationParams,
reusing kosong's existing GenerationKwargs / thinking.keep support.
KIMI_MODEL_MAX_TOKENS is intentionally untouched: it already flows through
the completion-budget path.
* fix(env): apply Kimi sampling params to compaction requests too
Sink KIMI_MODEL_TEMPERATURE / KIMI_MODEL_TOP_P into ConfigState.provider so
every request built from config.provider — main loop and full-history
compaction alike — carries them, matching kimi-cli where these live on the
shared create_llm provider. thinking.keep stays in Agent.llm because it
depends on the runtime thinking state (compaction runs thinking-off and
correctly skips it).
Splits applyKimiEnvGenerationParams into applyKimiEnvSamplingParams (applied
at provider construction) and applyKimiEnvThinkingKeep (applied in Agent.llm).
Addresses PR review feedback about compaction requests bypassing the wrapped
provider.
Inline, model-invocable skill to inspect and safely edit kimi-code's own config.toml and tui.toml (copy to a candidate, Edit, validate with kimi doctor, timestamped backup, then overwrite). Also documents tui.toml on the config files page (en + zh).
* 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>
* feat(tui): add /provider command, custom registry import, and tabbed model selector
- add "/provider" slash command for managing AI providers with CRUD UI
- add custom registry import via api.json URL and Bearer token
- introduce tabbed model selector grouped by provider
- add fetchCustomRegistry and applyCustomRegistryProvider in oauth package
- replace deprecated "/connect" command with unified "/provider" flow
- update provider and slash-command documentation
* feat(tui): background provider model refresh at startup
- add `refreshAllProviderModels` utility supporting managed OAuth, open platforms and custom registries
- wire background refresh into `KimiTUI` startup via `AuthFlowController`
- add `providerSwitchHint` option to `ModelSelector` and enable it in `TabbedModelSelector`
- update `TabbedModelSelector` hint wording from "switch" to "provider"
* feat: force adaptive thinking via KIMI_MODEL_ADAPTIVE_THINKING
Add the KIMI_MODEL_ADAPTIVE_THINKING env var and a matching
adaptive_thinking model-alias field that force adaptive thinking
(thinking: { type: 'adaptive' }) on or off, overriding the Anthropic
model-name version inference.
This lets custom-named staff endpoints that back an adaptive-capable
model opt in even when the model name does not encode a parseable Claude
version (which would otherwise fall back to budget-based thinking).
The kosong AnthropicChatProvider resolves the adaptive decision once in
withThinking() as `_adaptiveThinking ?? supportsAdaptiveThinking(model)`
and threads it through clampEffort/supportsEffortParam so forced adaptive
also unlocks the max effort level.
* fix: make adaptive_thinking imply the thinking capability
A model alias that sets adaptive_thinking=true (or env
KIMI_MODEL_ADAPTIVE_THINKING=true) without listing a thinking
capability previously resolved to thinking=false for custom-named
endpoints not in the capability catalog. The model picker then
classified the alias as "thinking unsupported" and forced thinking
off (persisting default_thinking=false).
Treat a forced adaptive flag as advertising the thinking capability
in resolveModelCapabilities, so the config.toml one-field opt-in
agrees with the KIMI_MODEL_* env path (which already defaults
capabilities to include thinking).
* fix: honor adaptiveThinking in the model picker, not the capability resolver
The earlier resolveModelCapabilities change had no observable effect:
modelCapabilities.thinking is consumed only for completion-budget and
media gating, never to decide whether thinking is dispatched or whether
the model picker offers a thinking toggle.
The mechanism that actually forced thinking off for an adaptive_thinking
alias is the TUI model picker, which reads ModelAlias.capabilities
directly (availableModels comes straight from config.models). Revert the
resolver change and instead make thinkingAvailability() treat
adaptiveThinking=true as a thinking toggle, so a custom-named config.toml
alias configured with only `adaptive_thinking = true` is no longer
classified "unsupported" (which forced thinking off and persisted
default_thinking=false on select). The KIMI_MODEL_* env path was already
covered by DEFAULT_CAPABILITIES.
* feat: define model via KIMI_MODEL_* environment variables
Add a KIMI_MODEL_* environment-variable channel that synthesizes a
provider (__kimi_env__) and model alias (__kimi_env_model__) in memory
and selects it as the default model, without editing config.toml.
Supports provider type (kimi/anthropic/openai), base URL, API key,
context size, capabilities, anthropic max_output_size, openai
reasoning_key, and full thinking settings.
Runtime config reads go through a new loadRuntimeConfig wrapper; the
config.toml write-back paths keep using readConfigFile so the
synthesized model is never persisted back to disk.
* feat: env-model defaults and friendly welcome model name
- KIMI_MODEL_MAX_CONTEXT_SIZE defaults to 262144 (256K) when unset
- KIMI_MODEL_CAPABILITIES defaults to image_in,thinking when unset
- TUI welcome banner shows the model display name / id instead of the
internal __kimi_env_model__ alias key
* fix: never persist env model to config.toml; validate default_thinking
- Strip the synthesized __kimi_env__ provider / __kimi_env_model__ model
(and a default_model pointing at it) in writeConfigFile, so the env model
and its shell API key cannot be persisted via a getConfig -> setConfig
patch round-trip (e.g. running /login or /connect in env-model mode).
- Reject a non-empty but unparseable KIMI_MODEL_DEFAULT_THINKING value
(fail-fast) instead of silently keeping config.toml's existing default.
* fix: preserve on-disk default_model when stripping env model; fix thinking docs
- stripEnvModelConfig restores config.toml's default_model from raw instead of
erasing it when the runtime default points at the env alias, so a real
default_model survives a getConfig -> setConfig round-trip.
- Correct KIMI_MODEL_DEFAULT_THINKING docs: unset follows the global default
(Thinking on), not Off.
* fix: restore env-injected fields to on-disk values in stripEnvModelConfig; update tests for thinking behavior
