* 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): record llm request trace in wire.jsonl
Add three observability record types so every request sent to the model
can be reconstructed from the wire log at the logical-request level:
- llm.tools_snapshot: content-addressed snapshot of the top-level tools
table as sent (post deferred-strip), written once per unique table
- llm.request: one record per outbound request (retries, strict resends,
and compaction rounds included) carrying the effective request params
and hash links to the system prompt and tools snapshot
- mcp.tools_discovered: the server's verbatim tools/list result plus the
agent's gating (allow-list, collisions), deduplicated by content hash
Observability records never feed state rebuild; replay only restores the
write-dedup cursors. The records/types.ts contract now documents the two
record classes explicitly (persisted is not the same as replayed).
Recording happens at the single Agent.generate choke point. The
LLMRequestLogFields side channel gains kind/projection/maxTokens/
droppedCount, chatWithRetry preserves caller-set fields, and compaction
tags its requests. The vis wire view renders the new record kinds.
* fix(agent-core): record the provider-clamped completion cap in the request trace
The llm.request trace recorded the client-requested budget cap, but
chat-completions providers tighten the actual wire value inside
withMaxCompletionTokens (remaining-context sizing, transport ceilings,
model-default resolution) — with the default budget the clamp is active
on nearly every non-empty-context request, so the recorded value did not
match what was sent.
Providers now expose the effective cap they computed as a readonly
maxCompletionTokens field on the clone, and the recorder reads it from
the effective provider at the Agent.generate choke point. This replaces
the side-channel recomputation, which is removed along with the
appliedCompletionBudgetCap helper.
* fix(agent-core): park pre-replay MCP discovery records and hash the collision outcome
Two wire-hygiene fixes for the mcp.tools_discovered trace:
Parking: the real Session ordering connects MCP servers concurrently with
agent construction, so ToolManager can observe a connected server before
agent.resume() has replayed the wire. Recording at that point bypassed
the restored dedup cursor (duplicating a 1-50KB record on every resume)
and appended a stray metadata record ahead of replay. AgentRecords now
exposes a one-shot opened latch — set when replay completes (after the
migration rewrite flushes) or when the first live record is logged — and
ToolManager parks discoveries until then, re-running the dedup check at
drain time. A frozen range-limited replay never opens; those agents are
transient previews.
Collision hashing: the dedup hash now covers the collision outcome, not
just the raw list and allow-list. Collisions depend on which other
servers hold a sanitized qualified name at registration time, so a
server can re-register with identical tools but a flipped outcome; that
gating change must produce a new record instead of being suppressed.
* fix(agent-core): skip the request trace for pre-flight-aborted calls
Mirror kosong generate()'s pre-flight abort check at the Agent.generate
choke point: a call whose signal is already aborted never reaches the
wire (generate throws before dispatching), so it must not leave an
llm.request/llm.tools_snapshot trace or a diagnostic log line claiming a
request was sent. Recording stays before dispatch for every call that
passes the gate, preserving the crash-safety of the trace.
* chore(agent-core): remove a leftover adaptive-thinking override hook
The adaptiveThinkingOverride option was a temporary local hook explicitly
marked for removal before commit. Nothing passes it, so resolution falls
back to the alias-level adaptiveThinking value in all cases; drop the
option and the dead indirection.
* fix(kosong): derive the exposed completion cap from generation kwargs
maxCompletionTokens was a field stored only by withMaxCompletionTokens,
so caps that reach the wire through other paths were invisible to the
request trace: with completion budgeting disabled via env, Anthropic
still sends the constructor-resolved max_tokens (required by the
Messages API), and constructor-level kwargs like OpenAILegacyOptions
maxTokens were likewise unreported.
Replace the stored field with a getter derived from each provider's
generation kwargs — the single source the request body reads — covering
constructor defaults, direct withGenerationKwargs configuration, and
budget application in one place. Kimi mirrors its request-time legacy
max_tokens alias normalization; openai-legacy reuses the same
normalizeGenerationKwargs the request path uses.
* feat(agent-core): add thinkingKeep passthrough for Kimi providers and update tests
* 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.
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.
* 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(tui): include shell commands in input history
Shell commands entered through the `!` prompt are now saved to input history. Recalling one restores bash mode, and in bash mode Up only cycles through previous shell commands while a normal prompt browses all history.
* docs(interaction): document shell command recall in input history
Note that shell commands are now saved to input history and can be recalled in Shell mode, in both the English and Chinese interaction guides.
* feat(pi-tui): add setHistoryFilter and onRecall to editor history
Add two first-class hooks to the editor's history navigation: setHistoryFilter to limit which entries Up/Down visit, and onRecall to decorate a recalled entry before it is shown. Draft restore, direction-aware cursor placement, and undo behavior are unchanged.
* refactor(tui): use pi-tui history filter for shell command recall
Replace the CustomEditor navigateHistory shadow with pi-tui's setHistoryFilter + onRecall hooks, wired in the editor-keyboard controller. This keeps pi-tui's draft-restore and direction-aware cursor behavior intact (the shadow dropped both) and moves the shell/prompt filtering and mode-restore logic into the business layer.
* feat(pi-tui): save and restore host state with the history draft
Add onHistoryDraftSave/onHistoryDraftRestore hooks so hosts can stash their own state when entering history browsing and restore it when the user navigates back to the draft. The saved host state is discarded when browsing ends any other way (typing, submit), mirroring the editor draft lifecycle.
* fix(tui): restore input mode when returning to the history draft
Wire pi-tui's history draft save/restore hooks to the editor input mode. Without this, recalling a shell entry and then pressing Down back to an empty draft left the editor in bash mode, so the next typed message was submitted as a shell command.
* fix(pi-tui): capture host draft state before running the history filter
Fire onHistoryDraftSave before the history filter runs when entering browse, so the host's filter can read the browse-entry mode rather than a mode that changes as entries are recalled. The captured state is still only committed once a matching entry is found.
* fix(tui): lock history filter to the browse-entry mode
Lock the history filter to the input mode captured when entering browse. Previously the filter read inputMode live, so after recalling a shell entry (which flips to bash mode) a second Up would only show shell commands.
* 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): slim WebSearch to query-only; fetch page content via FetchURL
The coding search backend no longer honors `limit`/`enable_page_crawling` and
always returns full page content, which was token-heavy and frequently
truncated. Realign the web tools around a search+fetch split:
- WebSearch request sends only `text_query`; the tool exposes only `query`.
- Search results drop inline page content and add the source site; full page
content is now fetched on demand via FetchURL.
- Add a citation reminder to both WebSearch and FetchURL results (in the
FetchURL front note so it survives body truncation).
- Update tool descriptions and reference docs accordingly.
* fix(agent-core): satisfy no-base-to-string lint and drop redundant | undefined
- Assert the exact serialized WebSearch request body instead of String()-coercing
a BodyInit, fixing the type-aware no-base-to-string lint error.
- Drop redundant `| undefined` from WebSearchResult optional fields per AGENTS.md.
- Add changeset.
* chore(changeset): bump agent-core to minor for WebSearch input-contract change
Removing the `limit`/`include_content` tool inputs tightens a closed
(`additionalProperties: false`) schema, so previously-valid args are now
rejected — an incompatible change for a released package. Bump minor rather
than patch.
* feat(web): add Mermaid diagram rendering and off-thread KaTeX/Mermaid workers
Enable Mermaid diagram support in the web chat via markstream-vue's enableMermaid(). Set up Web Workers for both KaTeX rendering and Mermaid parsing using markstream-vue's pre-built workers (katexRenderer.worker, mermaidParser.worker), keeping heavy computation off the main thread during live streaming.
* fix(web): skip Mermaid SVG subtrees in file link and markdown link rewriters
processFileLinks() uses a TreeWalker that scans all text nodes in mdRef.
Mermaid diagrams render as inline SVG, and diagram labels containing
file-path-like strings (e.g. src/App.vue) would be replaced with HTML
<button> elements inside SVG <text> nodes, corrupting the rendered diagram.
processMarkdownLinks() similarly queries a[href] inside SVGs; while
isLocalLink() mostly filters these out, explicitly skipping SVG subtrees
is safer.
Add svg to the closest() exclusion in processFileLinks(), and skip
links inside svg in processMarkdownLinks().
* fix(web): satisfy worker import lint
* chore: align mermaid dependency versions
* chore: change mermaid workers changeset to patch
---------
Co-authored-by: qer <wbxl2000@outlook.com>
* 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): open undo selector on double-Esc
Pressing Esc twice while idle now opens the undo selector, equivalent to running /undo with no arguments. Esc during streaming, compaction, or with a popup open keeps its cancel/close behavior and does not arm the double-press.
* fix(tui): disarm double-Esc undo on any intervening key
A pending double-Esc was only cleared by text changes, so a sequence like Esc, Ctrl-C, Esc within the window still opened the undo selector. Fire an onNonEscapeInput hook for every non-Escape key and clear the pending state there, so the shortcut only triggers for two consecutive Escape presses.
* refactor(agent-core): use ripgrep for Glob tool
Glob now shares Grep's ripgrep subprocess plumbing: it respects .gitignore by default, supports brace patterns natively, adds an include_ignored option, and returns only files.
* fix(glob): address review findings on ripgrep migration
- Run rg with cwd pinned to the search root so glob patterns containing
a slash (e.g. src/**/*.ts) match under an absolute search root.
- Keep include_dirs as a deprecated, ignored parameter so older calls
are not rejected by parameter validation.
- Surface stdout truncation and drop half-written trailing paths when
the rg output buffer is capped.
- Document that a bare pattern (e.g. *.ts) matches recursively, and sync
user docs, the explore profile prompt, and the TUI summary to the new
files-only / gitignore behavior.
- Add real-ripgrep integration tests covering sort order, recursion,
brace patterns, and the absolute-search-root case.
* fix(glob): keep partial results on traversal errors
---------
Co-authored-by: hynor <hynor@users.noreply.github.com>
Co-authored-by: Kai <me@kaiyi.cool>
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.
* feat(feedback): support attaching logs and codebase
Add an attachment picker to /feedback (none / logs / logs + codebase).
Codebase uploads scan the working directory with sensitive files excluded
and are sent through a new multipart upload API on the oauth/node-sdk layers.
* fix(feedback): fall back to logs when codebase scan fails
* tiny fix
* fix(feedback): make diagnostic uploads partial-safe
* refactor(feedback): reuse harness session export and normalize upload url types
* docs(slash-commands): note optional feedback attachments
* refactor(feedback): reorganize feedback upload modules
Move the attachment orchestration out of tui/commands/info.ts into a
dedicated feedback/feedback-attachments.ts, and split the former
codebase-upload/attach.ts into a generic multipart uploader
(feedback/upload.ts) and an archive lifecycle module
(feedback/archive.ts). Both session and codebase archives now flow
through a single upload lifecycle, which also removes the temp-dir
leak that occurred when codebase packaging failed.
Rename FeedbackCodebaseArchive to FeedbackArchive and the
codebase-upload/ directory to codebase/ so module boundaries match
their actual responsibilities (scan + package only).
* feat: add shell mode (`!`) to the CLI
Add shell mode, letting users run shell commands directly from the prompt
with `!`. Output streams live into the transcript, supports backgrounding
(ctrl+b), cancellation (Esc / Ctrl+C), input queuing while running, and
enters the conversation context with resume support.
* feat(kimi-code): show shell mode label on editor border and add tip
Render a "! shell mode" label on the top-left of the editor border while the editor is in `!` bash mode, so the active mode is visible at a glance. Also add a rotating toolbar tip (`! to run a shell command`) to surface the feature.
* feat(kimi-code): refine shell mode queue, history, and display
- Keep `!` commands out of input history so they never resurface as bare text stripped of their `!`.
- Make `!` commands non-steerable: Ctrl-S skips them (they stay queued to run after the current task) and the steer hint is only shown when something is actually steerable.
- Render queued `!` commands with a `$` prompt and the shell-mode hue so they read as commands, not as text to send to the model.
- Echo executed shell commands with a `$` prompt instead of `!`.
* fix(kimi-code): sanitize shell output and harden rendering
Captured shell command output can contain terminal control sequences (colours, cursor moves, alternate-screen switches, OSC hyperlinks, carriage-return spinners, bells). pi-tui's Text passes strings straight to the terminal, so any unhandled sequence was executed by the terminal and fought with pi-tui's own cursor control, producing the blank-screen-plus-leftover-characters mess after running commands like pnpm dev or a nested TUI.
- Sanitize CSI (incl. private modes), OSC, single-char ESC and C0 control chars (keeping newline and tab) in both the finished/resume view (previously unsanitized) and the running tail.
- Make the sanitize, format, and ShellRunComponent render paths never-throw, and cap the live running buffer, so a misbehaving command cannot crash the TUI.
- Dispose transcript children on clear so ShellRunComponent's timer is released on /clear or session switch.
* fix(kimi-code): render shell command echo with $ instead of sparkles
The shell command echo is a 'user' transcript entry, so UserMessageComponent prefixed it with the USER_MESSAGE_BULLET (sparkles), producing 'sparkles $ command'.
Add an optional bullet override to UserMessageComponent / TranscriptEntry and set it to an empty string for the shell echo (both live and resume), so the '$ command' content sits at the leading column where the sparkles marker used to be. Normal user messages keep the sparkles bullet.
* fix(kimi-code): enter shell mode when pasting a !-prefixed command
The bash-mode trigger only handled the single ! keystroke, so a pasted !cmd was inserted as literal text in prompt mode and submitted as a normal message.
After pi-tui inserts pasted content, detect an empty-prompt buffer that now starts with !, switch to bash mode, and strip the leading ! so the buffer holds only the command, matching the typed ! path.
* fix(kimi-code): restore shell mode when recalling a queued command
recallLastQueued() dropped the queued item's mode, and the Up-arrow recall only restored the text. A queued ! command (queued while another command runs, which resets the editor to prompt mode) therefore came back as a normal prompt and was submitted as a message instead of a shell command.
Return the full QueuedMessage from recallLastQueued() and restore editor.inputMode (plus the onInputModeChange sync) from the recalled item's mode.
* feat(kimi-code): use violet as the shell mode color
Replace the claude-code-style magenta/rose shellMode token with a violet that is distinct from plan-mode blue, the user role amber, success green, error red, and the teal accent.
Custom themes that omit the token fall back to this new default via the base+overrides merge, so existing custom themes keep working unchanged.
* chore: refine the shell mode changeset
* docs: document shell mode
Add a Shell mode section to the interaction guide and list the ! and Ctrl+B shortcuts in the keyboard reference, in both English and Chinese.
* test(protocol): include shell events in volatile classification check
shell.output and shell.started were added as volatile event types for shell mode; update the snapshot test's volatile-type list and count accordingly.
* fix(agent-core): surface shell command failure reason with no output
When a ! shell command fails without producing stdout/stderr (non-zero exit with no output, timeout, spawn failure), the failure reason lived only in the tool result's output and the TUI showed '(no output)'. Fold it into stderr so the live view and replay show what went wrong.
* fix(kimi-code): decode CSI-u ! to enter shell mode
In terminals with the Kitty keyboard protocol (VSCode integrated terminal, Kitty), pressing ! arrives as a CSI-u sequence, so the raw normalized === '!' comparison never matched and shell mode could not be entered by typing !. Decode with printableChar before comparing, matching every other printable-key check in the TUI.
* fix(kimi-code): do not steer while a shell command is running
Ctrl-S steers queued input into the running turn, but a shell command is not an agent turn, so steering during streamingPhase === 'shell' would launch a turn before the command output is recorded. Keep Ctrl-S a no-op during shell runs; queued messages stay queued.
* fix(agent-core): escape bash tag delimiters in shell output
Shell command output is arbitrary text; if it contains a bash tag delimiter such as </bash-stdout>, the recorded pseudo-XML wrapper breaks and replay extracts the wrong slice. Escape the content when wrapping it in agent-core and unescape when extracting during replay, so output survives round-trip intact.
* docs: document the shellMode theme token
The shellMode color token was added to the palette but not propagated to its mirrors. Add it to the custom-theme docs token table, the theme JSON schema, and the custom-theme skill token list.
* feat(agent-core): reset background task deadline on detach
Add a resettable deadline timer to BackgroundManager and let tasks register a detach timeout; when a foreground task is moved to the background, its deadline resets to the background default counted from the detach moment.
Wire this into shell mode so ! commands run with a 3-minute foreground timeout and get 10 minutes once detached to the background, instead of staying bounded by the original 60-second foreground deadline.
* feat(agent-core): lower shell mode foreground timeout to 2 minutes
* feat(plugins): source Superpowers from GitHub and show update badges
Source the Superpowers plugin from its GitHub release (v6.0.3) instead of a vendored copy, and drop the explicit version field.
Derive marketplace entry versions from GitHub source URLs when the version field is omitted, keeping the source URL the single source of truth.
Show update badges for installed plugins on the /plugins Installed tab.
* docs(plugins): document Installed tab update badges
* fix(plugins): stamp GitHub source version in CDN catalog
Older CLIs only read the explicit marketplace version and cannot derive it from a GitHub source URL. When publishing the CDN catalog, stamp the version derived from a pinned GitHub source so those clients still surface update badges.
The source plugins/marketplace.json keeps no explicit version; the version is derived at build time instead.
* feat(plugins): resolve latest version for bare GitHub sources at runtime
Point the Superpowers marketplace entry at the bare GitHub repo URL so it tracks the latest release instead of a pinned tag.
When a marketplace entry omits version and its source is a bare GitHub repo URL, resolve the latest release tag at load time (via the /releases/latest redirect) to fill the version for update detection.
Revert the build-time version stamping; it is no longer needed. Older CLIs that only read the explicit catalog version will no longer see update badges for Superpowers, since the catalog no longer carries one.
* feat(plugins): make Enter update and add I for details on Installed tab
On the Installed tab, Enter now installs the available update when one is present, and falls back to opening plugin details otherwise.
Add the I key to always open plugin details, so details remain reachable when Enter is occupied by an update. Update the installed hint, docs and changeset accordingly.
* feat(plugins): show installing state inside the plugins panel
Move the "Installing … from marketplace" notice from a transient status message into the plugins panel itself, so the user sees progress in the interactive card while an install or update is in flight.
* feat(plugins): highlight reload hint and add dev:cli:marketplace
Highlight "Run /new or /reload to apply plugin changes." in warning color after plugin install and remove, and make the two notices symmetric.
Add a root dev:cli:marketplace script that points the dev CLI at the production marketplace instead of the local dev server.
* fix(plugins): dedupe install success notice
Drop the redundant showNotice on marketplace installs so the success message is shown only once, symmetric with remove.
* fix(plugins): reset installing state on install failure
When a marketplace or Custom-tab install rejects, clear the installing state and return to the list so the user can retry, instead of leaving the panel stuck on the one-way "Installing…" view.
The Write tool previously failed when a parent directory was missing, forcing a manual mkdir round trip. It now creates missing parents recursively before writing.
* 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.
* feat(tui): add ctrl+t to expand the todo list
Toggle between the truncated view and the full list; the shortcut only takes effect while the list actually overflows.
* docs(keyboard): document ctrl+t todo expand shortcut
* chore(changeset): mark todo expand shortcut as patch
* docs(agents): clarify minor vs patch in gen-changesets skill
* fix(tui): clear pending exit when toggling the todo list
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.
