* feat: cap completion tokens to remaining context window for chat-completions
* test: cover dynamic completion budget for kimi and openai-legacy
* fix: leave compaction budget uncapped to avoid one-token summaries
* fix: add hookCount to plugins-selector test mocks
* perf(tui): cache rendered message lines across frames
Cache render(width) output in the transcript container and message components, returning cached lines when content, theme, and width are unchanged. Removes the per-frame full-transcript re-render that caused the TUI to lag as history grew.
* perf(tui): bound transcript with sliding window and step merging
Keep the TUI responsive as conversations grow by bounding the live
transcript:
- Sliding window: keep only the most recent 50 turns in the component
tree; older turns are destroyed (entry + component).
- Step merging: within each turn, keep only the most recent 30
thinking / tool steps rendered; older ones collapse into a summary.
- Expand (Ctrl+O) only reaches the most recent 3 turns.
All thresholds are overridable via KIMI_CODE_TUI_* env vars; 0
disables the corresponding feature.
* chore: add changeset for tui transcript window
* chore(tui): remove KIMI_TUI_PERF render timing log
* fix(tui): show the server token when handing off via /web
The /web slash command opened the session deep link without the bearer token, so the web UI was not authenticated and the token was never shown, unlike the kimi web subcommand. Resolve the persistent server token, append it as the #token= fragment so the browser signs in on load, and show it in green below the status line so it can be copied before the terminal exits.
* test(plugins-selector): add required hookCount to fixtures
PluginSummary/PluginInfo gained a required hookCount field, so the app's typecheck failed on fixtures that did not provide it. Add hookCount: 0 to the test summaries (none of these fixtures declare hooks).
* feat(web): auto-grow composer and add expandable editing mode
- Grow the chat textarea with its content up to a 1/4-viewport cap.
- Add an expand toggle above the send button for a taller editor; in that
mode Enter inserts a newline and Cmd/Ctrl+Enter or the button sends,
then the editor collapses back.
* fix(web): reset expanded composer state on session change
The composer instance is reused across sessions (not keyed by session id), so the expanded preference leaked into the next session's draft, leaving it stuck in the tall editor with Enter inserting newlines. Collapse back when the active session changes.
* fix(web): match expand-toggle threshold to theme resting height
The modern/kimi global theme overrides the composer min-height to 40px (the scoped default is 56px), so a hard-coded 56px threshold kept the expand toggle hidden until a third line under the default theme. Read the computed min-height from the element instead.
* fix(web): recompute expand-toggle visibility after collapsing
While expanded the computed min-height is 70vh, so a multi-line draft measured there sets isGrown=false. Collapsing did not recompute it, hiding the toggle even though the collapsed draft was still multi-line. Recompute growth after every toggle via a shared helper. The expanded state itself is unchanged and stays at 70vh until toggled or sent.
* fix(web): collapse expanded editor on slash-command submit
Known slash commands return early from handleSubmit, above the post-send collapse, so sending an expanded /goal, /btw, /compact, or skill command left an empty 70vh editor. Collapse in the slash-command path too.
* fix(web): refocus textarea after toggling expand
Clicking the expand toggle leaves focus on the button, so subsequent keystrokes do not reach the textarea and Enter would activate the button again instead of inserting a newline. Return focus to the textarea after toggling.
* fix(web): refit textarea when collapsing after image-only sends
When the expanded editor collapses on an image-only send, the text is already empty so the draft watcher never re-runs autosize; the textarea kept the inline height measured at 70vh and the collapsed cap left an oversized empty box. Route all send/steer collapses through a helper that re-runs autosize after the 70vh min-height is removed.
---------
Co-authored-by: liruifengv <liruifeng1024@gmail.com>
- add `kimi server run --allowed-host <host...>` (repeatable or
comma-separated; leading dot matches a domain suffix) and thread it
through daemon spawn into startServer
- merge CLI allowed hosts with KIMI_CODE_ALLOWED_HOSTS for both the HTTP
and WebSocket Host checks
- include the rejected host and allow guidance in the 403 error message
* feat(agent-core): support per-hook cwd and env in HookEngine
* feat(agent-core): support hooks in plugin manifest and aggregate via PluginManager
* feat(agent-core): merge plugin hooks into session hook engine
* chore: add changeset for plugin hooks
* feat(agent-core): strengthen default system prompt
Add high-confidence, prompt-only guardrails to the default agent system prompt:
- Personality/candor: extend the HELPFUL/CONCISE/ACCURATE line with CANDID, and
require plainly stating what could not be run, reproduced, or verified.
- Reminders: avoid cheerleading; voice evidence-based disagreement; deliver
complete code with no placeholders; update now-stale comments/docstrings after
a change; re-check the user's latest request before finalizing a reply.
- Context Management: explain automatic compaction — continue from the summary,
re-establish transient state with tools, do not restart from scratch.
- Output formatting: replies render as Markdown in the terminal; keep lists flat;
no emojis unless the user uses them first.
- Project Information: frame injected AGENTS.md as project context, not a
privileged instruction channel that can override system rules.
Prompt text only; no code or template-variable changes.
* feat(agent-core): hoist key working rules into the system prompt
Lift a few high-leverage rules from individual tool descriptions up into the
default system prompt, so they shape default behavior before any specific tool
is in play (kept terse and integrated, not bolted on):
- Planning: for multi-step or multi-file work, maintain a `TodoList` (one item
in_progress, mark done as it finishes) and prefer `EnterPlanMode` first when
the approach isn't settled.
- Default to making progress, not asking: once the goal is clear and sanctioned,
carry it through and work blockers yourself; ask only when the answer would
change the next step. Explicitly does not override stopping to discuss an
unclear goal or waiting for go-ahead before writing code.
- Tool routing: prefer dedicated tools (Read/Glob/Grep/Write/Edit) over raw
shell when one fits; keep Bash for genuine shell work.
- Definition of done: verify with the checks that cover the change before
marking it complete, independent of whether a TodoList is in use.
- Delegation: explore subagents also keep intermediate file contents out of your
own context — you get a conclusion back, not a pile of dumps.
Prompt text only; no code or template-variable changes.
* fix: clarify guidelines for file pattern matching and tool usage in explore.yaml and system.md
* fix(agent-core): hide the Skills section from agents without the Skill tool
Subagents (coder/explore/plan) inherit the root system prompt but lack the Skill tool, yet KIMI_SKILLS was rendered unconditionally — leaking the full skill listing into agents that cannot invoke any skill. Gate KIMI_SKILLS on the profile's tool set and wrap the '# Skills' section in {% if KIMI_SKILLS %} so it disappears for those profiles.
Also note in the Working Directory section that Bash enforces none of the workspace/secret-file guards, so the model must hold that discipline itself.
Tests: assert the Skills section renders for the root agent and is absent for Skill-less subagents; update the prompt-rendering fixtures for the new gating.
* fix(agent-core): gate Agent, background-task, and TodoList guidance by tool availability
Subagents (coder/explore/plan) inherit the root system prompt but lack the Agent, TaskList, and TodoList tools, so they were shown usage guidance for tools they cannot call. Derive HAS_AGENT/HAS_TASKLIST/HAS_TODOLIST from each profile's tool set and gate those sections with inline {% if %}, so they render only for agents that hold the tool.
Root rendering is byte-identical (the inline tags collapse to the original text when the flag is set). The cross-tool secret-file guard stays shared, since explore/plan still hold Read/Grep/Glob.
Tests: assert the gated guidance is present for the root agent and absent for explore/plan, while the shared secret-file guard remains.
* refactor(agent-core): move Agent-delegation and Glob-anchor guidance into the tool descriptions
The Agent-delegation paragraph in the system prompt duplicated mechanics already documented on the Agent tool itself (new-vs-resume, zero-context briefing, foreground default / run_in_background threshold), so remove it. HAS_AGENT still gates the explore-delegation bullet, which carries the 'when to delegate' nudge the tool description deliberately omits.
Move the proactive 'anchor the pattern up front' guidance into the Glob tool description (it previously only described the reactive 'refine after hitting the cap' path) and drop the now-redundant Glob bullet from the system prompt.
Tests: drop the assertions tied to the removed Agent paragraph; HAS_AGENT gating stays covered via the explore bullet.
* test(agent-core): add guidance for blast-radius and concrete examples in agent profiles
* docs: update descriptions for skill-tool and fetch-url; enhance web-search citation instructions
* feat(agent-core): disclose enforced constraints in tool descriptions; fix GetGoal field doc
Surface runtime-enforced behavior in the Agent / AgentSwarm / AskUserQuestion / Goal
tool descriptions so the model learns the rules from the tool, not from a failed call:
- Agent: resuming excludes subagent_type (setting both is rejected)
- AgentSwarm: at least 2 items unless resuming, prompt_template required and must
contain {{item}}, distinct resulting prompts; plus Agent-vs-AgentSwarm fan-out note
- AskUserQuestion: result is {answers}; an empty answers with a dismissal note means
the user declined — fall back to best judgment instead of re-asking
- CreateGoal: creating fails when a goal already exists (use replace)
- SetGoalBudget: state the hard 1s-24h time-budget band
- UpdateGoal: do not mark blocked merely because work is hard/slow/incomplete
- GetGoal: drop the advertised self-report / evaluator-verdict fields — GoalSnapshot
never held them, so the tool never returned them
Each change is covered by a description assertion.
* fix(agent-core): soften AskUserQuestion answers-keying wording to match the code
The answers object is passed through from the host/RPC layer (QuestionAnswers is
Record<string, string | true>); this code does not key it by question text. Describe
what the keys identify instead of asserting a guarantee the code does not provide.
* feat(agent-core): tighten Bash/Grep/Write/Edit tool descriptions
- Bash: prefer the cwd argument (or absolute paths) over a cd from an earlier
call, since each call runs in a fresh shell
- Grep: note that files_with_matches is ordered most-recently-modified first
- Write: do not create documentation/README files unless the user asks
- Edit: frame replace_all with its rename-across-file use-case
Each change is covered by a description assertion.
* feat(agent-core): refine plan-mode/todo/cron tool descriptions
- ExitPlanMode: describe what a good plan contains (specific, verifiable steps
grounded in the codebase, not vague filler)
- TodoList: stop calling it useful 'in Plan mode' — plan-mode planning goes to
the plan file; TodoList tracks execution progress
- CronCreate: warn that a one-shot whose pinned day/month already passed this
year is rejected; document the 50-task session cap and the 8 KiB prompt cap
- CronCreate: drop the bench-only KIMI_CRON_NO_STALE / KIMI_CRON_NO_JITTER env
knobs from the model-facing description (CI-only; the model never sets them)
Each change is covered by a description assertion.
* refactor(agent-core): dedupe ExitPlanMode options docs into the param schema; trim EnterPlanMode workflow
- ExitPlanMode: the options field mechanics (label format, recommended, count,
single-option=plain-approval, reserved labels) now live only in the options
param describe; the tool description routes to it and keeps the yolo/manual UI
behavior it uniquely documents. The options consistency test now enforces a
single source of truth (describe) plus the schema-consistency guard, instead
of requiring the same facts in both surfaces.
- EnterPlanMode: trim the duplicated 'What Happens in Plan Mode' steps to a
pointer (the full workflow is injected unconditionally once plan mode is
active), keeping the explore-subagent recommendation.
* fix(agent-core): correct prompt/code inaccuracies found in the final audit
Every item below was re-verified against the live code:
- Skill: drop the never-fired recursion-depth cap (production never seeds depth);
keep the <kimi-skill-loaded> 'already loaded, don't re-invoke' guard
- TaskOutput: terminal_reason can also be `failed`, not just timed_out/stopped
- Grep: count_matches emits per-file `path:count`, with the total reported separately
- Plan mode: the reminder names TaskStop/CronCreate/CronDelete as blocked (they are
hard-denied by plan-mode-guard-deny)
- Bash: the failure trailer is non-zero-exit-specific; timeout/interrupt differ
- CreateGoal: replace also covers a blocked goal, not just active/paused
- UpdateGoal: it also injects the completion/blocked outcome prompt, so it does more
than 'only record the status'
- FetchURL: state the universal http/https contract instead of provider-internal SSRF
and 10 MiB limits (the primary Moonshot fetcher enforces neither)
- TodoList: query mode triggers on omitting `todos`, not on zero args
- TaskList: command/PID/exit code are shell-task fields only
- CronCreate: the returned fields include `cron`
- SetGoalBudget: turn/token budgets are rounded up to >= 1, not rejected below 1
Each change is covered by a description/param assertion; plan.test.ts snapshots
refreshed for the longer plan-mode reminder.
* fix(agent-core): gate prompt tool guidance on runtime availability, not declared profile tools
The HAS_* / Skills gating computed flags from the profile's declared tools, but
Agent/AgentSwarm only register when a subagentHost exists (ToolManager
.initializeBuiltinTools). A runtime built without a subagentHost (e.g. direct SDK
construction) therefore rendered the explore-delegation guidance for an Agent
tool the model could not call.
SystemPromptContext now carries an optional availableTools; buildTemplateVars
gates on it when present and falls back to the declared tools otherwise. useProfile
passes the profile tools minus Agent/AgentSwarm when no subagentHost is wired, so
the render reflects what the model can actually call. The normal session path
(subagentHost always defaulted) is unchanged.
* fix(agent-core): exempt the plan-mode plan file from the Write *.md ban
Plan mode writes its plan to plans/<id>.md (plan/index.ts) and the reminder tells
the model to create it with Write when missing, which contradicted Write's blanket
'do not create *.md unless asked' guard. Carve the plan file out of the ban.
* fix(agent-core): scope plan-mode prompt guidance and the Write *.md ban to runtime reality
- Gate the TodoList bullet's "enter plan mode via EnterPlanMode" suggestion
on a new HAS_ENTERPLANMODE flag. A custom profile that keeps TodoList but
drops EnterPlanMode no longer steers the model toward a tool it cannot call;
the default profile render is unchanged.
- Reframe the Write *.md prohibition around intent (unsolicited docs) instead
of a blanket extension ban, so artifacts a task or project instruction
requires — the plan-mode plan file, a repo-mandated changeset — are no
longer contradicted by the tool's own rules.
* refactor(agent-core): move tool-coupled guidance into tool descriptions
The default system prompt carried tool-usage guidance behind {% if HAS_* %}
gates that re-derived, in prose, the availability the tool schema already
encodes — and the same guidance was duplicated in each tool's own
description. Drop the four gated blocks (background Bash, Agent/explore,
TodoList, EnterPlanMode) and the compaction TaskList/TodoList bullets; the
tool descriptions, shipped only when the tool is registered, already carry
the same instructions, so subagents and tool-trimmed profiles are no longer
pointed at tools they lack.
Fold the two genuinely unique lines into the tool descriptions: bash.md
gains "return control after starting a background task", agent.md gains the
context-hygiene reason to delegate. Collapse the compaction bullets into one
tool-agnostic sentence. Remove the now-unused availableTools / HAS_* render
machinery.
* fix(skill-tool): clarify no-reinvoke guard and argument handling in tool description
* feat(fetch-url): indicate content retrieval mode in output for better model context
* fix(agent-core): correct goal-budget rounding and task-output failure docs
set-goal-budget.md said turn/token budgets are "rounded up", but the code uses
Math.round — say "rounded to the nearest whole number" instead. task-output.md
implied every failed task carries terminal_reason/stop_reason, but a plain
non-zero command exit carries only status plus exit_code; describe that exit_code
path and reserve terminal_reason for non-exit endings (timeout, explicit stop,
or an internal error with no exit code).
* fix(agent-core): scope free-work guidance by role and steer one-shots near-term
The blast-radius paragraph told every profile that local work — including
editing files — may be done freely, but the read-only explore/plan subagents
render it too; scope it to "work your role permits" so it no longer undercuts
their read-only constraints.
The one-shot cron guidance leaned on a year-boundary heuristic ("avoid a
day/month already passed this year") that misfires across Dec 31 to Jan 1 and
duplicated a limit the code already enforces. Replace it with a plain near-term
nudge and leave the hard future-window guard in code.
* fix(enter-plan-mode): clarify availability of Agent tool in plan mode description
* fix(agent-core): surface Grep count_matches total and pagination in output
count_matches put the aggregate "Found N occurrences" summary and the
"Results truncated... use offset=N to see more" notice on the result's
message field, which normalizeToolResult drops before the result reaches the
model. The model saw only the path:count lines and could miss the total and,
worse, the pagination cue — so it would not know to page through truncated
counts. Append both to output after the path:count lines, the same way the
content and files_with_matches modes already inline their notices.
* fix(grep): reorder count summary and results in output for clarity
* chore(changeset): consolidate prompt-hardening changesets into one
Squash the five per-change changesets for this PR into a single concise
entry; they all bump @moonshot-ai/kimi-code (patch) for the same
system-prompt and tool-description hardening work.
* fix(agent-core): stop the agent from blocking on background tasks
Both the Agent and Bash background-launch messages invited the model to "peek
at progress" via TaskOutput, and the foreground-vs-background guidance had been
thinned to a single parameter hint. Together that led the model to launch a
background subagent and then immediately wait on it through TaskOutput —
defeating the point of background execution.
Make both launch messages take the same anti-wait stance the user-detach path
already uses (do NOT wait, poll, or call TaskOutput on it), restore
foreground-by-default guidance in the Agent background description (run in the
background only when you have other work and do not need the result to proceed),
and add a TaskOutput backstop against using it to sit and wait. Also fold the
fix into the consolidated changeset.
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).
* ci: run unit tests on windows
* fix(migration-legacy): align workdir bucket key with agent-core
computeWorkdirBucket used a local node:path-based resolve that yields backslash-separated paths on Windows, while agent-core's encodeWorkDirKey uses pathe (forward slashes on every platform). The SHA-256 inputs diverged, so migrated sessions were written to a bucket that the session picker never reads, making them invisible on Windows.
Alias computeWorkdirBucket to encodeWorkDirKey so both sides stay byte-identical, drop the local slugify copy, and update the workdir-bucket test reference accordingly.
* test(acp-adapter): expect platform-native separators in e2e-fs path
The e2e-fs test asserted the fs/readTextFile wire path as the raw POSIX targetPath, but AcpKaos.toClientPath converts '/' to '\' when the inner LocalKaos reports pathClass 'win32' (Windows). On Windows the wire path became '\Users\test\x.ts' and the assertion failed.
Mirror toClientPath in the test: expect backslash separators on win32 and the raw path otherwise. Implementation is unchanged.
* test(sdk): normalize workDir and skillDir paths in session tests
SessionStore.create/list and the skill loader normalize paths through pathe (forward slashes). The SDK tests compared the resulting workDir and skill loaded-dir against raw mkdtemp / node:path strings, which use backslashes on Windows (and node:fs realpath also returns backslashes for the skill dir), failing three toMatchObject assertions.
Build the expected paths with agent-core's normalizeWorkDir so they match the internal pathe representation on every platform. The skill dir keeps its realpath() (the loader realpaths the root) and only normalizes separators.
* test(skill): normalize realpath to forward slashes in scanner tests
resolveSkillRoots normalizes every root.path through fs.realpath followed by replacing backslashes with forward slashes (scanner.ts). The scanner tests compared root.path against node:fs realpath directly, which returns backslashes on Windows, so twenty assertions failed (toEqual / toContain / toHaveLength) even though the resolved paths were identical.
Wrap realpath at the top of the test file to mirror the implementation's normalization, so every comparison uses the same forward-slash form on every platform.
* test: skip Unix-only permission tests on Windows
The Unix file-permission assertions (mode bits like 0o600 / 0o700 and chmod 000 making a path unreadable) have no equivalent on Windows, which uses ACLs; fs.chmod there can only toggle the read-only bit. These six tests failed on Windows with mismatched mode values or a missing 40411.
Skip them on win32 via it.skipIf(process.platform === 'win32'): oauth FileTokenStorage (0600 file, 0700 dir), agent-core BackgroundTaskPersistence (0700 tasks dir), agent-core createPerIdJsonStore (0700 subdir), migration-legacy atomicWrite (0600 file), and server fs:browse (chmod 000 -> 40411).
* test(tui): make platform-sensitive assertions cross-platform
The TUI implementations are already platform-aware (pathe-style paths, pathToFileURL, quoteShellArg cmd/POSIX quoting, Alt+V on Windows for paste expansion), but the tests hard-coded POSIX expectations and failed on Windows.
Align the assertions with the implementation's platform behavior: footer-goal-badge matches the '[goal' badge prefix instead of /goal/ (toolbar tips contain '/goal'); tool-call expects backslash relative paths on win32; plan-box builds the file:// URL via pathToFileURL; custom-editor sends Alt+V on win32 for paste expansion; file-mention-provider normalizes the expected description to forward slashes; kimi-tui-startup builds the resume command with quoteShellArg; kimi-tui-message-flow builds the expected install path with resolve().
* test: align path assertions with pathe on Windows
Several test suites asserted paths produced by node:path/node:os/node:fs against values that agent-core, node-sdk and kaos normalize through pathe (forward slashes). On Windows the two forms diverge (backslashes vs forward slashes), failing about 19 assertions.
Mirror the implementation's normalization in the assertions via a local toPosix helper (or agent-core's normalizeWorkDir), so expected paths use forward slashes on every platform: kaos LocalKaos, node-sdk export/list/resume/config/transport sessions, cli FileMentionProvider, and agent-core skill-session.
* test(native): build path expectations with node:path.resolve
paths.mjs builds every path with node:path.resolve, which yields backslash-separated absolute paths on Windows. The path-helpers tests asserted against template strings that mixed the backslash appRoot with forward-slash segments, so Object.is failed on Windows even though the strings looked identical.
Build the expectations with the same resolve(appRoot, ...) helper so the separators match on every platform.
* fix: make Windows CI tests pass across all packages
Fix the remaining Windows CI failures so the Windows test job can go green. The changes fall into a few categories:
- Path separators: agent-core/node-sdk/kaos normalize paths via pathe (forward slashes); align test expectations and a couple of implementations (native cache base, workspace registry) with that.
- Platform-only services: skip launchd/systemd manager suites on win32 (Windows uses schtasks).
- Process/signal lifecycle: skip or relax tests that rely on POSIX signals / SIGTERM semantics that Windows does not support.
- Hook shell syntax: rewrite hook test commands from POSIX shell (single quotes, semicolons, stderr redirects, if/then/fi) to node -e / .cjs files that run under cmd.exe.
- CRLF: make Bash tool description stripping tolerate CRLF line endings.
- Misc: realpath short-name divergence, port-retry timing, telemetry spawn, fs-watch timing, snapshot path normalization, etc.
* fix: remove unused basename import in workspaceRegistryService
Fix lint error (no-unused-vars): basename from node:path is no longer used after switching to posixBasename from pathe.
* fix: align resume harness pathClass and wait for banner state on Windows
Two more Windows CI fixes:
- createResumeNoSideEffectKaos now reports pathClass 'win32' on Windows so tool descriptions (e.g. Glob's Windows note) match the live agent in expectResumeMatches, fixing usage/description deep-equal drift.
- kimi-tui-startup once-banner test now waits for writeBannerDisplayState to land before asserting, since the atomic write can lag behind the render on Windows.
* fix: resolve remaining Windows unit test failures
Make the new Windows CI job green across agent-core, kaos, node-sdk and server:
- Align the resume harness kaos pathClass with the live agent so platform-conditional tool descriptions (Glob's Windows note) match in expectResumeMatches instead of drifting on win32.
- Rewrite hook commands in agent-core tests as cross-platform node one-liners; single-quote echo, >&2 and ';' do not work under cmd.exe.
- Add .gitattributes enforcing LF so raw-imported templates (e.g. the compaction instruction) produce byte-identical token counts on Windows and POSIX.
- Terminate the full process tree on Windows in both the hook runner and kaos (taskkill /T /F) so grandchildren cannot outlive their parent and keep the cwd locked.
- Normalize workDir path separators in two kimi-sdk session tests to match the stored canonical form.
- Avoid cmd.exe arg-quoting pitfalls in the kaos cmd.exe test, and run the Windows process-tree kill test from a script file with the pid path passed via argv.
- Give the first fs-git e2e test more time on Windows and retry the temp-dir cleanup; skip the fs-watch overflow-burst assertion on Windows where fs-event coalescing prevents the single-window spike.
* ci: retrigger checks
* fix: resolve remaining Windows failures after merging main
- Terminate the spawned git/gh process tree on Windows in FsGitService (taskkill /T /F on timeout) so a timed-out 'gh pr view' cannot leave a grandchild holding the workspace cwd, which made the fs-git e2e cleanup fail with EPERM.
- Give the fs:git_status e2e suite a longer timeout on Windows and retry the temp-dir cleanup longer to ride out the slower child-process teardown.
- Make the third-party plugin install trust test assert the resolved install path via node:path so it matches the Windows-resolved path (D:\tmp\...) as well as the POSIX one.
* fix: align workspace registry roots and harden fs-git cleanup on Windows
- workspace-registry test: compare normalized (forward-slash) roots, since the registry and session index both store workDir via pathe.resolve (forward slashes on every platform). realpath() yields backslashes on Windows and diverged from the stored root.
- fs-git e2e: bump the temp-dir cleanup retries and the afterEach timeout, since Windows child-process teardown after server.close() is asynchronous and can keep the workspace cwd locked for several seconds.
* test: stub openUrl in kimi-tui-message-flow feedback tests
The /feedback command falls back to openUrl(FEEDBACK_ISSUE_URL) when submission fails, which spawned a real browser window on every test run. Mock #/utils/open-url (matching the existing login/message-replay/server test convention) so the suite never opens a browser.
* test: harden fs-git e2e cleanup against Windows cwd locks
On Windows, git/gh child processes and the session core process can outlive server.close() and keep the temp workspace as their cwd, so rmSync fails with EPERM even after a long retry. Add rmSyncRobust that retries and, if the cwd is still locked, swallows EPERM/EBUSY on Windows — the OS reclaims the temp dir and a cleanup hiccup must not fail an otherwise-passing test.
* test: harden server e2e cleanup against async teardown races
server.close() does not fully await the server's asynchronous teardown, so on a loaded CI runner the temp home/workspace dirs can still be held or written to when the afterEach rmSync runs, failing with EPERM (Windows) or ENOTEMPTY (Linux). Use a rmSyncRobust helper (retry + swallow EPERM/EBUSY/ENOTEMPTY) in the fs-git and question e2e cleanup. Also fix a leftover `throw err` (renamed to `throw error`) that broke the typecheck.
* feat(web): add a copy button to user messages
Mirror the assistant per-message copy button on user turns, copying the message text with the same checkmark feedback.
* fix(web): place user message copy button with undo and time
Move the copy button out of the line-number role row into the modern bubble meta row, grouped with the undo and time buttons, with matching styling and tooltip.
* feat(web): show full accumulated subagent progress
The subagent detail panel only showed the most recent 40 progress lines because the reducer truncated the accumulated output. Keep the full history so the panel reflects the entire process as it grows.
* fix(web): preserve subagent progress across task updates
The projector emits a taskCreated (without reducer-owned outputLines) right before every taskProgress, and the taskCreated branch replaced the task object outright, resetting outputLines to empty on each progress event. So the panel still only showed the latest chunk. Preserve the accumulated outputLines when replacing a task, and update the test to mirror the real taskCreated-before-taskProgress path.
* feat(web): clean up subagent progress text
Drop the noisy 'Started a step' line and summarize tool calls with a concise target (path / command / pattern) instead of the full JSON args, so the subagent progress panel shows what the subagent is actually doing.
* fix(web): strip numeric index from subagent tool result names
Some subagents name tool calls with a trailing index (e.g. Read_0, Bash_4), which surfaced in tool.result progress lines since the label did not resolve. Strip the index before resolving the label.
* fix(web): bound non-subagent task output and subagent progress text
Restore a tail cap for background bash/tool task output (which can grow without bound) while keeping subagent progress in full, and cap individual subagent tool.progress chunks so a single huge output cannot dominate the panel.
* feat(web): group and fold subagent progress output
Drop the noisy 'Finished' lines, group tool output under its call, and fold long output (first 5 + last 2 lines, expandable) so the subagent progress panel shows the call rhythm at a glance.
* feat(web): show edit diffs inline in tool call cards
Render a line-by-line diff inside Edit/Write tool cards in the web chat, reusing the existing diff-line style from the changes panel. The diff is built client-side from the tool input, so no protocol or server changes are needed; the header chip now shows real +/- counts.
* fix(web): extend diff line backgrounds through horizontal scroll
Diff rows were only as wide as the viewport, so the add/del background stopped where long lines overflowed and the area revealed by horizontal scroll had no color. Size each row to its content so the background paints the full line.
* fix(web): make all diff rows fill the longest line width
Size the diff container to the longest line and have every row fill it, so add/del backgrounds form one continuous band across the whole horizontal scroll instead of stopping at each line's own length.
* fix(web): resolve oxlint errors in diff line builder
Use Array.at(-1) and Array.from instead of index access and new Array(length), which oxlint flags as errors.
* fix(web): show tool output for failed edit/write calls
When an Edit/Write call fails, render the tool output (the failure reason) instead of the requested diff, so error cards explain why no change was applied.
* fix(web): fall back to tool output for replace_all and append edits
A single-pair diff misrepresents replace_all edits (which change many occurrences) and from-empty diffs misrepresent append writes (which extend an existing file). Skip the synthetic diff in those cases and render the truthful tool output instead.
* feat(web): open edit diffs in the right-side detail panel
Move the Edit/Write diff out of the inline tool-card body into the shared right-side detail layer, opened by clicking the card (like the subagent detail panel). The panel shows the line diff when it faithfully represents the operation, otherwise the tool output (replace_all, append, errors), so failed calls explain why no change was applied.
* feat(web): toggle detail panels closed when their trigger is clicked again
Clicking the same Edit/Write card, file link, or git-status area a second time now collapses the right-side detail panel, matching the existing thinking / compaction / subagent toggle behavior.
* fix(web): cap client-side edit diff to avoid freezing on large inputs
The line-level LCS allocates an (oldLines+1) x (newLines+1) matrix and runs eagerly when an Edit/Write card renders. For large edits (e.g. a 5k x 5k block, ~25M cells) this can freeze or exhaust the chat. Cap the matrix at 1M cells and fall back to the raw tool output beyond that.
* fix(web): keep the edit diff panel in sync with live tool state
Store only the tool id and re-derive the diff panel payload from the live tool call in the session turns, so a panel opened while the tool is still running reflects later status/output changes (e.g. an eventual error shows the failure output instead of the stale attempted diff).
* fix(web): do not render a synthetic diff for Write calls
Write only reports the new content, so the client cannot tell a new file from an overwrite of an existing one. A from-empty diff showed overwrites as all additions and no deletions, which is misleading. Fall back to the tool output for every Write (append already did).
* fix(web): also cap diff output rows, not just the LCS matrix
The matrix-size cap alone let through asymmetric edits (e.g. one line replaced by hundreds of thousands) whose small matrix still produced a huge row array that the chip computed on render. Cap each side's line count too, so the diff output is bounded.
* fix(web): keep edit/write cards expandable when the diff panel is unwired
Clicking an Edit/Write card opens the right-side diff panel, but the nested ChatPane in the side chat does not wire that event, so the click became a no-op and the card could no longer expand to show its output. Gate the panel behavior behind a toolDiffPanel prop (enabled only in the main conversation); elsewhere the cards expand inline as before.
* fix(web): close the tool diff panel when its target disappears
When a session resync removes the tool call an open diff panel is showing, toolDiffTarget becomes null but detailTarget stayed 'toolDiff', leaving an empty aside that Escape would not close. Gate sidePanelVisible on toolDiffVisible so the panel collapses once its target is gone.
* fix(reload): re-inject plugin session-start reminder after /reload
Reload reloaded plugins and resumed the session, but the model kept seeing the stale plugin session-start reminder from before the reload, so plugin skill changes only took effect in a fresh session.
Append a fresh plugin_session_start reminder to the main agent after reload, gated on a new forcePluginSessionStartReminder flag that only the explicit /reload command sets, so config and experiment toggles that reuse the reload RPC do not spam the transcript.
* fix(reload): keep reload result fresh and neutralize stale plugin reminder
Append the plugin session-start reminder before constructing ResumeSessionResult so SDK callers reading getResumeState() see the refreshed plugin context instead of a pre-reload snapshot.
When a plugin with a prior plugin_session_start reminder is disabled or removed, append a neutralizing reminder so the model does not keep following stale plugin instructions.
* fix(reload): neutralize stale plugin reminder after compaction
A full compaction folds the discrete plugin_session_start reminder into a compaction_summary, so the origin-only scan no longer detects it. Also treat a compaction_summary in history as a signal to neutralize, so disabling or removing a plugin after compaction still emits a superseding 'no active plugin session starts' reminder.
* fix(reload): thread plugin reminder option through KimiHarness.reloadSession
KimiHarness.reloadSession is a public SDK entry point; forward forcePluginSessionStartReminder to both the active-session and RPC reload paths so SDK callers using the harness can opt into the refreshed plugin reminder too.
* feat(server): bind `kimi server` to 0.0.0.0 by default
- change DEFAULT_SERVER_HOST to 0.0.0.0 and default --insecure-no-tls on
so a bare `kimi server run` clears the non-loopback TLS gate
- add LOCAL_SERVER_HOST (127.0.0.1) for connectable URLs when bound to the
wildcard, used by lockConnectHost and the service status URL
- pin the OS-supervised install to --host 127.0.0.1 so the always-on
service stays loopback-only
* feat(server): make --host opt-in for LAN binding
- default kimi server run/web binds 127.0.0.1 when --host is omitted
- treat bare --host as 0.0.0.0 while keeping --host <host> explicit
- update server help/banner text and host binding tests
* 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(web): render plan review card with plan body and approach choices
The ExitPlanMode plan_review approval in the web UI now renders the plan body as Markdown with one button per approach option, plus Revise and Reject-and-Exit, with the selected label threaded back to the server.
The approval header keeps APPROVAL REQUIRED and the minimize control on the title row and shows the plan path on a second line, and the plan body uses up to half the viewport height.
The ExitPlanMode tool card also gains a link to the plan file, currently hidden behind a flag until the server can read files outside the workspace.
* fix(web): hide misleading shortcut numbers on plan review actions
When a plan review has approach options, the option buttons already own [1]/[2]/[3]. Revise and Reject-and-Exit advertised the same numbers even though those keys approve an option, so hide their shortcut labels whenever options are present.
- bcryptjs is a CommonJS package whose index.js re-exports via
`module.exports = require("./dist/bcrypt.js")`
- Node's cjs-module-lexer cannot detect named exports through that
require() indirection, so `import { compare, hash } from 'bcryptjs'`
threw "Named export 'compare' not found" under the tsx dev runner
(make dev), even though vitest and the esbuild bundle handled it fine
- switch to the default import and destructure, which works across tsx,
vitest and the bundled binary
* test(server): add API surface snapshot guardrail
Boot startServer on port 0 and snapshot the documented v1 route table derived from /openapi.json paths, plus the reachability of doc/meta endpoints (/healthz, /openapi.json, /asyncapi.json, /). Gives later auth/--host phases an intentional diff when routes change. M0 makes no production behavior change.
* test(server): add e2e server harness with token support
Add test/helpers/serverHarness.ts: boot() wraps startServer with an isolated lock + home dir and returns a handle (server, address, baseUrl, wsUrl, token, close) plus authedFetch/authedWs that carry Authorization: Bearer <token> (and the kimi-code.bearer.<token> WS subprotocol). serviceOverrides is the generic DI seam later phases use to inject a fixed-token auth service; IAuthTokenService is not referenced yet. closeAll() tears down every booted server and socket. M0 makes no production behavior change; typecheck-only gate.
* feat(server): add privateFiles 0600 atomic write/read utility
* feat(server): add per-start tokenStore
* feat(server): add env-based bcrypt password hash utility
* feat(server): add IAuthTokenService DI seam
* feat(server): add global onRequest auth hook with bypass + redaction
* fix(server): stop reflecting Host header in /asyncapi.json
* feat(server): add WS bearer subprotocol constant and parser
* feat(server): enforce bearer token auth on WS upgrade
* feat(server): add Host header allowlist middleware
* feat(server): add Origin/CORS middleware
* feat(server): wire Host/Origin checks into HTTP and WS
* feat(server): wire token auth, Host/Origin, and WS auth into start.ts
* fix(server): create lock file with 0600 permissions
* fix(server): suppress debug routes on non-loopback binds
* feat(kimi-code): read server token and send Authorization on CLI calls
* feat(kimi-code): inject server token into /web URL fragment
* feat(server): add bindClassify for loopback/lan/public classification
* feat(kimi-code): register --host flag and pass it through the daemon
* feat(server): require password and TLS opt-out on non-loopback binds
* feat(server): rate-limit repeated auth failures on non-loopback binds
* feat(server): disable shutdown and terminals on public binds by default
* feat(server): add security response headers on non-loopback binds
* test(server): cover LAN/public host-exposure hardening end to end
* docs(server): add deployment security and threat-model guide
* changeset: minor kimi-code for server auth and host exposure
* feat(kimi-web): add server bearer-token auth support
* fix: repair CI for server auth and host exposure
- Replace native @node-rs/bcrypt with pure-JS bcryptjs so the ESM CLI
bundle and the SEA native bundle both build without native-addon
require issues (node-rs/bcrypt broke the ESM smoke and the SEA
check-bundle allowlist).
- Remove dead cleanup references (stopSpinner, authLogoBlinkTimer) in
apps/kimi-web App.vue that failed vue-tsc.
- Fix lint: drop empty spread fallbacks in the e2e auth-header merge,
void the intentionally-async WS upgrade listener, add missing
assertions to satisfy jest/expect-expect, and convert a ternary
statement to if/else.
- Send the bearer token in the snapshot perf/smoke tests so they pass
under the new global auth hook.
- Refresh the pnpmDeps hash in flake.nix for the updated lockfile.
* feat(server): persist bearer token and add rotate-token command
- persist the server bearer token in <home>/server.token (0600) and reuse it across restarts instead of per-start server-<pid>.token
- add `kimi server rotate-token` to regenerate the token; the token store reloads on mtime/inode change so rotation applies without restart
- print the token and Vite-style Local/Network URLs in the startup banner
- allow non-loopback binds with bearer-token-only auth (password now optional) and update SECURITY.md
- surface daemon boot failures immediately with the exit reason and log tail instead of waiting for the spawn timeout
* feat(server): print full token URLs and re-print links after rotate
- Drop the ready-panel border so token URLs print in full for copying; keep the Kimi sprite beside the title.
- Re-print Local/Network access links after `server rotate-token` (host/port from the lock).
- Extract shared access-URL helpers into access-urls.ts.
- Unify link and token colors between the banner and rotate-token.
* feat(server): dim URL #token= fragment and de-highlight token
- Render the `#token=…` fragment in a dim gray so the host/port stands out in the banner and rotate-token links.
- De-highlight the standalone token; set it off with surrounding whitespace instead of color.
- Add splitTokenFragment helper.
* refactor(cli): polish server ready banner and rotate-token output
- move version onto the ready banner title line; drop the separate
Ready:/Version: rows and the startup-time metric
- reorder rotate-token output so the new token sits between the
invalidation note and the access links
- update server CLI tests for the new layout
* feat(server): warn on reuse and refine ready banner
- Warn when `server run` reuses an already-running daemon (its options are not applied) and show the running server's actual URLs.
- Show a `Network: off use --host 0.0.0.0 to enable` hint on loopback binds.
- Move the version onto the title line and drop the startup-time metric.
* fix(web): relabel auth dialog to token and cover full page
- Relabel the server auth dialog from "password" to "token"; the server accepts the bearer token, with the password only as a fallback.
- Make the auth dialog overlay fully opaque so it covers the whole page instead of revealing the login page underneath.
* fix: resolve CI failures on web auth PR
- Replace chalk.yellow named color with chalk.hex(darkColors.warning)
in the server reuse notice to satisfy the chalk named color guard.
- Update pnpmDeps hash in flake.nix to match the regenerated
pnpm-lock.yaml so the Nix build succeeds.
- Retry rmSync in ws-broadcast e2e teardown to ride out EBUSY /
ENOTEMPTY races while the server flushes files after close().
* test(server): update API surface snapshot for warnings route
The feat/web-auth branch adds GET /api/v1/sessions/{session_id}/warnings
(packages/server/src/routes/sessions.ts), so the API surface guardrail
snapshot needs to record the new documented v1 route.
* perf(web): page session list per workspace on first load
Load only the first page of sessions per workspace instead of draining every session up front, so the initial request count scales with the number of workspaces rather than the total number of sessions. The per-workspace "show more" button now fetches the next page on demand, and searching lazily loads the full list so results stay complete.
To keep per-workspace paging working for sessions created with cwd only, the workspace registry now also surfaces directories that have sessions but were never explicitly registered.
* fix(web): trust server hasMore for session pagination
Stop deriving per-workspace hasMore from the workspace session_count. After a local archive/delete the count is stale (archiveSession only removes the local session), so loadedCount < total stayed true after the server returned its final page and re-fetched empty pages forever. The server's page.hasMore is authoritative for whether more pages exist, so use it directly and keep session_count only as a label total.
* fix(web): fall back to global session walk when no workspaces listed
When /workspaces is unavailable or empty on older or partially-failing daemons while /sessions still works, the per-workspace initial load produced no sessions and the sidebar rendered blank. Reuse the existing global walk as a fallback in that case so history still shows.
* fix(agent-core): keep workspace deletion durable
Record deleted workspace ids as tombstones in the registry and skip them during derived registration. Deleting a workspace only removes its registry entry (session buckets stay on disk by design), so without the tombstone the next derived-registration scan recreated the workspace, making deletion non-durable for any workspace with history. An explicit re-add clears the tombstone.
* fix(web): track session paging cursor per workspace
Compute the load-more cursor from the end of the last fetched page instead of the oldest loaded session. A deep-linked older session appended out of band would otherwise become the cursor, so the next page started after it and skipped every session between the first page and the deep link.
* fix(web): load more sessions in the mobile switcher
The mobile switcher still used the old local display-expansion logic, but each workspace now starts with only the first page of sessions. Wire its show-more button to loadMoreSessions (matching the desktop sidebar) so workspaces with more sessions can page beyond the first page on mobile.
* fix(agent-core): align derived workspace id with its session bucket
Session buckets are keyed by normalizeWorkDir (resolve, not realpath), so registering a derived workspace via createOrTouch (which realpaths) produced a different workspace id for a symlinked cwd, and per-workspace session lookups then read the wrong bucket and returned empty. Register derived workspaces with the resolved bucket key instead.
* fix(agent-core): skip archived-only buckets in derived registration
A bucket that only contains archived sessions would otherwise be registered as an empty workspace on a plain GET /workspaces, surfacing an empty sidebar group that the old session-derived fallback (which ignored archived sessions) kept hidden. Skip derived buckets with no active sessions.
* refactor(agent-core): derive workspaces from the session index on the fly
Stop persisting derived workspaces into the registry. Persisting made the registry a second data source that drifted from the session store (symlinked cwds, archived-only buckets, deleted/unmounted roots), each producing a bug. Instead compute derived workspaces fresh in list() from the session index and resolve their ids in resolveRoot() via the same index, so the session store stays the single source of truth. The deletion tombstone is kept so explicitly removed workspaces are not re-derived.
* fix(agent-core): tombstone derived workspaces on delete
After deriving workspaces from the session index, derived ids are valid list results but absent from the registry file, so delete() threw before writing the tombstone and DELETE on a derived workspace 404ed and reappeared on the next list(). Resolve the derived id and write the tombstone for it too.
* fix(web): use local session count once a workspace is fully loaded
mergedWorkspaces kept the server session_count as a floor even after a workspace had no more pages, so archiving the last session left the header showing 1 until a reload. Once a workspace is fully loaded (hasMore === false) the local count is exact, so prefer it; keep the server count as a floor only while pages remain.
- deliver session.meta.updated to every connection instead of only
session subscribers, so title changes sync across all clients
- emit session.meta.updated when a session is explicitly renamed
* fix(web): coalesce streaming token updates into one render per frame
* fix(server): disable Nagle on WebSocket socket for lower streaming latency
* fix(web): flush pending streaming deltas before re-subscribing
* fix(web): flush pending streaming deltas before forgetting a session
The focus-driven clipboard image hint spawned wl-paste/xclip on every
terminal focus event. On Wayland this perturbs seat focus and re-triggers
the focus event, creating a feedback loop that made the terminal window
repeatedly gain and lose focus and broke IME input.
Limit the probe to macOS and Windows, which use the in-process native
module and do not perturb focus. Image paste is unaffected.
Resolve#1090
* feat(web): render LaTeX math in chat via KaTeX
* fix(web): keep literal prose dollars out of KaTeX inline math
Enabling KaTeX turned plain prose with two dollar-prefixed tokens
(`Check $PATH before $HOME`, `costs $5 and $10`) into a single
inline formula, since markstream's $…$ tokenizer has no
"no whitespace inside the delimiters" rule.
Add a postTransformTokens guard that turns a single-$ inline span back
into literal text when its content starts or ends with whitespace. Real
inline math is written tight (`$E=mc^2$`, `$\frac{1}{2}$`), while
the prose false-positives always have whitespace inside the delimiters,
so this keeps inline/block math working while leaving prices, env vars,
and ranges as readable text. Code spans are already excluded by the
tokenizer, and running on the flat token stream also covers dollars
nested inside lists and blockquotes.
Addresses the Codex review comment on PR #1035.
* fix(web): reject compact currency ranges before rendering math
The literal-dollar guard only caught prose whose content had whitespace
inside the delimiters, so a compact range like `costs $5/$10` still
rendered `5/` as a formula and dropped the second dollar. (markstream's
own currency check rejects `-`/`~` ranges but not `/`.)
Extend the guard to also reject a single-$ span whose content is a
numeric amount with a trailing range connector (`/`, `-`, `~`,
en/em dash) -- a complete formula never ends in a dangling operator.
Scoped to digit-led content so symbolic math is left alone, and numeric
math that is not a range (`$5/2$`, `$5-2$`, `$0.5$`) still
renders. Added tests for the range cases and the non-range math.
Addresses the follow-up Codex review comment on PR #1035.
* fix(web): treat shell/path dollar pairs as literal text
Adjacent shell variables and PATH-like values (`Use \$HOME/bin:\$PATH`,
`\$PATH:\$HOME`) were still rendered as math, because the prose-dollar
guard only looked at the span's own content (whitespace inside the
delimiters, or a trailing numeric range connector) and never at what
touches the delimiters from the outside.
Replace the two bespoke heuristics with the two industry-standard rules,
now driven by the surrounding text tokens:
- Pandoc (tex_math_dollars): no whitespace immediately inside the
delimiters.
- GitHub: each \$ must be bounded on its outer side by whitespace, a
line boundary, or structural punctuation. A letter or digit there
means a second prose token, so the span is literal text.
The GitHub outer-boundary rule subsumes the old numeric-range check (a
closing \$ in \$5/\$10 is followed by a digit) and also catches
shell/path cases Pandoc's inner rule misses. Normal math -- including
bare \$x\$, \$x^2\$., and (\$x^2\$) -- still renders. Added
tests for shell/path values and punctuation-wrapped math.
Addresses the third Codex review comment on PR #1035.
* fix(web): render math next to CJK punctuation and quotes
The outer-boundary guard only accepted ASCII punctuation, so a formula
followed by full-width punctuation or wrapped in typographic quotes was
misclassified as prose: `公式为 \$E=mc^2\$，其中` and `“\$x\$”`
showed raw dollars instead of rendering.
Invert the boundary check from an allow-list of ASCII punctuation to a
deny-list of ASCII letters/digits. A \$ glued to an ASCII letter/digit
still means a second prose token (\$PATH:\$HOME, \$5/\$10), but
whitespace, line boundaries, and every other character -- full-width
punctuation, CJK ideographs, curly quotes -- is now a valid math
boundary, which is the correct behavior for localized prose.
Addresses the fourth Codex review comment on PR #1035.
* fix(web): preserve later math after literal-dollar spans
A prose dollar in front of a real formula in the same inline run
(`costs $5 and formula $x$`, `Use \$HOME before $E=mc^2$`) exposed
the core limit of the token-level guard: markstream's tokenizer greedily
pairs the first literal \$ with the formula's opening \$ before any hook
runs, so converting that span back to text could only blank it -- the
later formula's opening \$ was already consumed and the formula rendered
as raw text.
Move the guard from postTransformTokens to a source-level preprocessor
that runs before tokenization. escapeProseDollars protects code spans,
fenced code blocks, and \$\$…\$\$ display math, then pairs single \$
delimiters using the Pandoc (tight delimiters) and GitHub-style
outer-boundary rules: any \$ without a valid partner is escaped as
\\\$, so the tokenizer leaves it literal while real formulas -- including
ones that come after a prose dollar -- still parse as math.
The component now preprocesses each markdown segment's text and the
postTransformTokens hook is gone. Rewrote the tests around the
string-in/string-out helper, including the prose-before-formula case,
code spans, fenced code, and block math.
Addresses the fifth Codex review comment on PR #1035.
* fix(web): protect indented code blocks before escaping dollars
The dollar-escaping preprocessor stashed fenced code blocks, inline code,
and display math, but not 4-space / tab indented code blocks. So a
snippet like ` echo \$HOME` had its dollar rewritten to `\\$HOME`,
and because Markdown renders backslashes literally inside code, the web
chat corrupted the code to show a stray backslash.
Add an indented-code regex and protect those lines too. Also make the
placeholder restore iterative, so nested protected regions (e.g. inline
code that looks like display math) restore correctly instead of leaving
a placeholder behind.
Addresses the sixth Codex review comment on PR #1035.
* fix(web): do not treat list-continuation lines as indented code
The indented-code regex protected every 4-space line, but inside a list
item a 4-space indent is a normal continuation paragraph, not a code
block (code under a list marker needs deeper indentation). So a message
like `- total\n costs \$5 and \$10` had that nested line
stashed as "code", leaving its dollars un-escaped -- and the KaTeX
parser then rendered the price range as math.
Narrow the indented-code rule to a run of 4-space / tab lines that is
preceded by a blank line (or the start of the text). That still protects
real top-level indented code blocks and deeper-indented code inside
lists, while letting 4-space list-continuation lines get their dollars
escaped.
Addresses the seventh Codex review comment on PR #1035.
* refactor(web): render only $$…$$ display math, drop single-$ inline
Enable KaTeX for display math only: disable markstream's inline math rule
(`md.inline.ruler.disable('math')`) via customMarkdownIt, leaving the
`math_block` rule for $$…$$. Single $ now stays literal everywhere, so
prices, env vars, shell paths, and code are never mis-rendered as math --
with no escaping, no code detection, and no preprocessor.
This removes the escapeProseDollars normalization layer and all of its
code-protection machinery (the 8 review comments it attracted were
symptoms of trying to make a lax single-$ tokenizer behave). Display
$$…$$ math continues to render via KaTeX.
Changeset updated to describe display-math-only support.
Avoid concurrent session snapshot requests when resync_required fires repeatedly, while still allowing one queued rerun after the in-flight reload settles.
* 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.
* fix(kimi-code): show clipboard image paste hint only once per image
The footer hint repeated on every terminal focus whenever an image remained in the clipboard, which became noisy. Replace the 30s time-based cooldown with a per-image gate: the hint shows once for a given image and stays quiet until the clipboard is observed empty and a new image appears.
* fix(kimi-code): suppress clipboard image hint for images present at startup
The footer hint fired during initialization whenever an image was already in the clipboard, treating it as new. The first clipboard observation after start now only establishes a baseline, so only images copied during the session trigger the hint.
* fix(kimi-code): show hint for first image copied after startup
* fix(kimi-code): make clipboard image probe non-blocking
The startup baseline probe in ClipboardImageHintController calls clipboardHasImage(), which on Linux/WSL ran wl-paste/xclip/powershell via spawnSync. The probe only reaches its first await after those synchronous calls, so a slow or wedged helper could freeze the TUI launch for up to the 1s-2s tool timeouts even when the user never focuses with an image.
Add an async runCommandAsync built on spawn with timeout-based kill, and route the Linux/WSL image detection through it so the event loop is never blocked. Keep the synchronous runCommand for the explicit paste-read path.
* chore: add changeset for non-blocking clipboard probe
* chore: simplify clipboard image hint changeset
PgUp/PgDn are often captured by terminal or tmux scrollback, so add Ctrl+U and Ctrl+D as full-page up and down alternatives, matching the existing PgUp/PgDn behavior.
When compaction is in progress and the editor has a draft, Ctrl-C now clears the draft first instead of cancelling compaction, matching the streaming behavior. The clear-text logic is shared between the compaction and streaming branches.
* fix(agent-core): surface git context failures for explore subagents
collectGitContext collapsed every git failure (spawn error, non-zero exit, timeout) into null, so explore subagents silently lost git context with no signal. Now a definitive 'not a git repository' injects an explicit unavailable signal so the subagent does not waste turns probing git history, while other failures are logged and surface as an empty block. The block is all-or-nothing so a partial snapshot (e.g. a timed-out status making a dirty tree look clean) is never shown.
* fix(agent-core): use rev-parse for branch to support git < 2.22
`git branch --show-current` was added in Git 2.22 and fails (exit 129) on older Git even in a valid repository. Because the branch probe is fatal, this dropped the whole git-context block for older-Git users. Switch to `git rev-parse --abbrev-ref HEAD`, which is supported across Git versions, and filter the `HEAD` output produced in detached-HEAD state.
* fix(agent-core): show whatever git info is available in explore context
Git probes fail in perfectly normal states — no `origin` remote, no commits yet (unborn branch), detached HEAD, older Git — so a failed probe no longer aborts the whole collection. Each probe is now best-effort: failures are logged and their section is omitted, and the block is dropped only when nothing useful was collected. Branch is read via `symbolic-ref --short HEAD`, which works in unborn repositories and on older Git; it fails in detached-HEAD state, where the Branch section is just omitted.
* fix(web): stop dismissing questions after a 60 second timeout
The server's question broker auto-expired AskUserQuestion requests after 60s, which dismissed the question even when the user simply needed more time. Remove the timeout, and the now-unused expires_at field, so a question stays pending until the user answers or explicitly dismisses it.
