* feat(agent-core): make subagent timeout configurable and raise default to 2h
- add `[subagent] timeout_ms` config (env `KIMI_SUBAGENT_TIMEOUT_MS` overrides) to replace the hardcoded 30-minute cap for Agent / AgentSwarm subagents
- raise the default subagent timeout from 30 minutes to 2 hours
- thread the value through tool construction so foreground and background subagents use it, with the timeout message reflecting the effective value
* feat(background): add print_background_mode with steer for multi-turn -p runs
- add `[background].print_background_mode` (`exit`/`drain`/`steer`) and
`print_max_turns`; when unset, falls back to `keep_alive_on_exit = true`
mapping to `drain`, preserving existing behavior
- core: `Session.handlePrintMainTurnCompleted()` returns `finish`/`continue`;
in `steer` mode the run stays alive so a background-task completion
`turn.steer`s the main agent into a new turn (matching background
subagents), bounded by `print_wait_ceiling_s` and `print_max_turns`
- cli: print driver follows every main turn instead of only the first and
defers `finish()` until the run quiesces or a limit is hit
- plumb `handlePrintMainTurnCompleted` through node-sdk RPC; docs + tests
A kimi -p run settled the moment the main agent's turn ended (end_turn),
so a goal created mid-run was cancelled during cleanup and a scheduled
cron task never fired in the same run.
- runPromptTurn now re-evaluates completion when the main agent goes idle
and stays alive while a goal is still active (the goal driver runs the
continuation turns) or while cron tasks with a future fire remain (their
fire steers a fresh turn). A ref'd handle keeps the event loop alive
during the wait since the cron scheduler tick is unref'd.
- a terminal goal.updated (e.g. the driver blocking a goal on a hard
budget, which emits no further turn.ended) also re-evaluates so the run
cannot hang.
- add getCronTasks RPC and Session.getCronTasks() so the print flow can
enumerate pending cron tasks.
Tool-role messages reached the snapshot/messages REST projection with
their content flattened to text, dropping image/video/audio parts, so a
ReadMediaFile result rendered as an image while streaming but fell back
to a generic tool card after a reload. Pass the raw content parts
through when a tool result carries media, matching the live tool.result
event shape the web client already parses.
* docs(changelog): sync 0.23.5 from apps/kimi-code/CHANGELOG.md
* chore: update config model doc
* docs: update config-files example with new models and services
---------
Co-authored-by: liruifengv <liruifeng1024@gmail.com>
* refactor(kosong): rename select_tools capability to dynamically_loaded_tools
Rename the `ModelCapability` bit from `select_tools` to `dynamically_loaded_tools` everywhere it is declared, detected, catalogued, and forwarded: kosong `ModelCapability`/catalog, agent-core capability resolution and the `toolSelectEnabled` gate, the SDK catalog-to-alias mapping, and the built-in catalog pruner's keep list.
The old `select_tools` spelling is removed outright rather than kept as an alias — no catalogued model or shipped configuration used the capability, so there is nothing to migrate. Client-side vocabulary (the `select_tools` builtin tool and the `tool-select` experimental flag) is intentionally untouched.
* chore: shorten changeset description
---------
Co-authored-by: fengchenchen <fengchenchen@moonshot.ai>
The web client received two sessionStatusChanged events per turn
transition: one projected client-side from the raw turn.started/turn.ended
stream, one mapped from the daemon's event.session.status_changed. After
the tag scheme in #1479 keyed the completion notification by prompt id,
the second (redundant) idle event lost the cached prompt id and fell back
to a Date.now() tag, so every turn end popped a second "Turn finished"
notification and replayed the completion sound.
Stop projecting sessionStatusChanged from the raw turn stream (turn.started,
turn.ended, and the in-flight snapshot seed). The daemon's
event.session.status_changed is the single source of status transitions:
it is computed from live daemon state (covering awaiting-approval /
awaiting-question / aborted), carries the authoritative previousStatus and
currentPromptId, and is deduped per real transition server-side. The turn
stream keeps its content responsibilities (message finalization, usage,
duration); seedInFlight keeps seeding the partially-streamed message while
status comes from the snapshot's authoritative session record.
* fix: refuse unsupported image formats instead of poisoning sessions
Images in formats providers reject (AVIF, HEIC, BMP, TIFF, ICO) used to
pass through to the API, and the resulting HTTP 400 repeated on every
later turn because the image_url stayed in the session history.
Add a single format policy (accepted set: PNG/JPEG/GIF/WebP) enforced at
every ingestion point: ReadMediaFile refuses with a per-OS conversion
command; MCP tool results, REST uploads, and ACP prompts replace the
image with a text notice; and turn.prompt/steer gates as the last-funnel
backstop so the SDK/RPC path cannot poison a session either. Accepted
MIME aliases (image/jpg, case/whitespace) are forwarded in canonical
form, and data URLs carrying MIME parameters can no longer slip past the
gate. Remote image URLs pass through (no bytes to inspect).
* fix: canonicalize accepted data URLs with MIME parameters
The format gate compared only the MIME token when deciding whether to
rebuild a data URL, so an accepted image carrying MIME parameters
(`data:image/jpeg;charset=utf-8;base64,...`) was forwarded with its
original header. The Anthropic provider splits the data URL and
exact-matches the full header against its whitelist, so the part still
poisoned the session. Rebuild to the byte-exact canonical URL whenever
the original differs, covering aliases, case/whitespace, and parameters
with one comparison.
Addresses review feedback on PR #1536.
* fix: parse data URLs case-insensitively in the image format gate
An uppercase `;BASE64,` marker is legal (RFC 2045 encoding names are
case-insensitive), but the parser required a lowercase match and
returned null, so the gate treated the URL as remote and forwarded it:
an unsupported image could still land in the session history, and the
Anthropic provider's lowercase-only split then threw on every turn.
Match the scheme and marker case-insensitively; the canonical rebuild
emits the lowercase form.
Addresses review feedback on PR #1536.
* fix: harden image format handling against mislabeled and legacy images
Two more ways an unsupported image could reach the provider are closed:
- Bytes, not labels, decide the format. A data-URL image whose declared
MIME disagrees with its magic bytes (e.g. AVIF bytes an image search
tool labels image/png) is now gated on the sniffed format at every entry
point (MCP results, ACP, SDK/RPC prompt, REST inline and file uploads),
so a mislabel cannot slip past the gate.
- A poisoned image already in the session history no longer kills the
session: a server image-format 400 (or kosong's client-side image
rejection) now retries once with every media part replaced by a text
marker, mirroring the 413 media-degraded recovery. The recovery also
fires during compaction, and the transient-retry fallback no longer
burns the retry budget on image-format errors before the dedicated
recovery can run.
* fix: reject remote image URLs ending in an unsupported extension
Remote image URLs (MCP resource_link, REST `kind: 'url'`) carry no bytes
to sniff, so a link ending in `.avif` (or `.heic`, `.bmp`, `.tiff`,
`.ico`) would pass through and be fetched server-side — and rejected.
Reject such URLs by their path extension instead (query/fragment
ignored, case-insensitive); extensionless or accepted-extension URLs
still pass through to the provider and the 400 recovery.
* fix: tighten image format handling for parameterized MIMEs and recovery scope
Address two review findings on PR #1536:
- A declared media type with parameters (e.g. image/jpeg; charset=utf-8)
is no longer misread as unsupported: normalizeImageMime now strips
parameters, matching the data-URL parser, so an accepted image with
parameters is forwarded instead of dropped.
- The image-format recovery predicate is narrowed to specific
format/data rejection phrases, so a 400 about image count, size, or
image-input support no longer triggers a media-stripped resend that
would let the model answer blind to the user's images.
* fix
* fix: scope image format recovery to images and flag remote SVG URLs
- The media_type/mime_type recovery match now requires the message to
mention an image, so a video/audio media_type rejection surfaces
instead of triggering a blind media-stripped resend.
- unsupportedImageMimeFromUrl flags .svg URLs as image/svg+xml without
touching the shared suffix map (SVG stays text for the file tools),
so remote SVG images get the intended notice instead of a provider
rejection.
Addresses review feedback on PR #1536.
* fix: reject remote MCP images by their declared MIME type
An MCP resource_link with an extensionless or signed URL gives the
extension gate nothing to work with, and convertMCPContentBlock was
discarding the declared mimeType — an honestly-declared AVIF/HEIC link
from an image search tool still became an image_url and poisoned the
session. Reject on the declared MIME when the server provides one:
unsupported declarations become a text notice that keeps the URL so the
model can fetch and convert it; accepted declarations pass through as
before.
Addresses review feedback on PR #1536.
* fix: keep image format recovery image-specific and preserve dropped URLs in notices
- Drop the bare `media` alternative from the image-format recovery
patterns so audio/video media rejections ("unsupported media type",
"invalid media type") can never be misclassified as image errors and
blindly media-stripped; every pattern now mentions "image" literally.
- Remote image URLs rejected by their extension now keep the URL in the
replacement notice (gateImageFormatParts and the REST url path), so the
model can still fetch and convert the image — matching the declared-MIME
resource_link path.
Addresses review feedback on PR #1536.
* fix: drop malformed data URLs at ingestion instead of letting them poison the session
A `data:` URL that fails to parse (missing `;base64,` separator, empty
MIME, …) was treated like a remote URL and passed through the format
gate; the provider then rejects it on every turn, and the read-side
media-stripped recovery keeps paying that round-trip until compaction.
Detect unparseable `data:` URLs in gateImageFormatParts and replace them
with a (truncated) notice at ingestion, covering the MCP/ACP/SDK/turn
paths that share the gate.
Addresses review feedback on PR #1536.
* fix(web): hide injected system asides in user message bubbles
* fix(web): preserve literal <system> tags in user prompts
* chore: fold duplicate web changeset into caption-hiding entry
* feat(retry): harden LLM API fault tolerance against 429/overload
- retry more transient errors: 408/409/429/5xx/529, an embedded upstream
status_code=429 in OpenAI Responses stream errors, and unclassified
provider errors as a last-resort fallback
- honor server Retry-After (parsed into APIStatusError.retryAfterMs by the
OpenAI and Anthropic providers); chatWithRetry prefers it over its backoff
- align app-level backoff with claude-code (500ms base, 32s cap, factor 2,
up to 25% jitter) so high-attempt configs ride out multi-minute overload
- emit a turn.step.retrying meta line in -p --output-format stream-json
* fix(web): prevent duplicate first prompts and keep goal drives from looking idle
- Guard startSessionAndSendPrompt with a per-workspace reentry lock so a
double-click / repeated Enter during draft-session creation cannot fire
two concurrent first prompts into the same new session.
- Track goal.active in the agent event projector so turn.ended between
goal-driven continuation turns keeps the session 'running' instead of
projecting a false 'idle' that drains the local queue into a still-busy
core (turn.agent_busy).
- Show a 'starting conversation…' loading state on the empty-session
landing while the first prompt is being created and submitted.
- Persist the resolved model in startSessionAndActivateSkill so the first
skill turn on a fresh session does not fail with 'Model not set'.
* chore: add changeset for web first-prompt fixes
* fix(web): close remaining first-prompt and goal-settle gaps
- Pass the starting guard through the dock composer: draft-session
creation selects the new session before submit, which swaps the empty
composer for the dock; disabling both composers closes the last path
to a concurrent first POST. Also take the workspace lock in
startSessionAndActivateSkill / startSessionAndOpenSideChat.
- Emit the owed idle when a goal settles (blocked/paused/completed) in
the inter-turn gap after a turn.ended was projected as 'running', so
sending state, in-flight flags and queued prompts flush instead of
the session staying 'running' forever.
* style(web): fix eqeqeq lint error in first-prompt guard
* fix(web): clear owed idle when a new goal turn starts
The idle debt from a 'running' projection survived turn.started, so an
UpdateGoal('complete'|'blocked') landing mid-turn in the NEXT goal turn
synthesized an early idle. onSessionIdle could then drain queued prompts
into a core that was mid-turn again, re-opening the turn.agent_busy race
for multi-turn goals. Clear the debt on turn.started: from that point the
turn's own turn.ended carries the idle with goalActive already false.
* fix(web): make first-prompt starting state workspace-id-agnostic
isStartingFirstPrompt now reads from the lock set directly (size > 0)
instead of the current activeWorkspaceId. createDraftSession can swap
activeWorkspaceId to a registered id mid-flight; a workspace-keyed read
would then return false while the first prompt is still in the create/
select/submit window, re-enabling the composer and reopening the
duplicate first-submit race.
* revert(web): drop goal-aware idle projection from agentEventProjector
The goalActive / idleOwed shadow state machine grew through multiple
review rounds and still leaves edge cases (snapshot-seeded turns, mid-
turn goal updates). Roll it back to the simple 'turn.ended projects idle'
behavior. Goal-driven sessions can once again race a queued prompt into a
busy core; this is accepted as a known limitation to be resolved properly
in a follow-up that has the core emit an authoritative idle signal.
* chore: align changeset with actual fix scope
* test(web): update profile-patch expectation for model field
* feat(tui): add Kimi WebBridge install entry to /plugins panel
Surface a hardcoded Kimi WebBridge entry at the top of the Official tab in the /plugins panel. Selecting it opens the WebBridge install page in the user's browser instead of going through the plugin install flow, since WebBridge is a browser extension plus local daemon rather than an installable plugin package.
* fix(tui): restrict WebBridge open-url shortcut to the pinned row
Match the hardcoded pinned WebBridge entry by object reference instead of by id. A curated or custom marketplace entry on the Third-party tab can legitimately reuse the kimi-webbridge id; routing by id hijacked Enter on those rows and opened the WebBridge page instead of installing. The Official tab still dedupes a same-id official catalog entry so the pinned row is not duplicated.
* fix(tui): label WebBridge plugins row as "open in browser"
The previous "webpage" status did not make it clear that selecting this row opens an external page rather than installing in-app. "open in browser" states the action directly and contrasts with the install label on regular plugin rows.
* test(tui): navigate past pinned WebBridge row in marketplace install tests
Two message-flow tests pressed Enter on the Official tab assuming index 0 was the Kimi Datasource entry. The hardcoded Kimi WebBridge row now leads that tab, so move down one row before installing.
* feat(web): use sidebar fold/unfold icons for sidebar toggle
* feat(web): move settings entry to a sidebar footer row
* feat(web): fully collapse sidebar with animated width transition
* feat(web): redesign sidebar colors, spacing and macos desktop chrome
* feat(desktop): center traffic lights on the 48px header row
* fix(web): restore webkit thin scrollbars and unify sidebar icon sizes
* feat(web): add Kbd keycap component and justify sidebar search shortcut
* style(web): rework sidebar palette and pin a resident sidebar toggle
* fix(desktop): sync window appearance with web UI theme so dimmed traffic lights stay visible
* feat(web): adopt Kimi design icons in the sidebar via a local icon collection
* style(web): mute workspace group title color in the sidebar
* style(web): refine sidebar typography, unify shortcut keycaps, float workspace row actions
* style(web): cap sidebar draggable width at 480px
* style(web): derive sidebar row height from type and padding, float the kebab
* chore: add changeset for sidebar UI polish
* fix(nix): update pnpmDeps hash
* style(web): put the sidebar collapse button inside the header on non-mac
* fix(nix): update pnpmDeps hash
* feat(kosong): classify HTTP 413 request-body-too-large as a dedicated error type
* feat(agent-core): lower default image downscale cap to 2000px and make it configurable
* feat(agent-core): strip media to text markers and retry when the compaction request is too large
* feat(agent-core): cap model-initiated image reads with a configurable byte budget
* feat(agent-core): resend with degraded media when the provider rejects the request body as too large
* test(agent-core): add explicit timeouts to encode-heavy image budget tests
* feat: add WebP decoding support with wasm integration
- Introduced a new WebP decoding module using @jsquash/webp's wasm decoder.
- Implemented functions to decode WebP images and check for animated WebP formats.
- Updated image compression tests to include scenarios for WebP handling, including encoding and decoding.
- Enhanced error handling for API request size limits to accommodate various error messages.
- Updated pnpm lockfile to include new dependencies for WebP encoding and decoding.
* chore(changeset): consolidate this PR's entries into one
* fix(nix): update pnpmDeps hash for merged lockfile
* feat(agent-core): refuse HEIC/HEIF reads with platform-matched conversion guidance
* feat(oauth): parse boosterWallet extra usage from /usages
* feat(oauth): expose extraUsage on AuthManagedUsageResult
* feat(kimi-code): render Extra Usage section in /usage panel
* fix(kimi-code): address Task 3 review feedback for extra usage section
* feat(kimi-code): render Extra Usage section in /status panel
* feat(kimi-code): wire extraUsage into /usage and /status commands
* chore(extra-usage): address final review findings for fuel pack feature
- Update changeset to cover both kimi-code and kimi-code-sdk packages
- Add parser clamp tests and toolkit null-case test
- Replace 'as never' casts in usage-panel tests
- Wrap long import line in status-panel
* chore: temporarily log /usages raw response for debugging
* fix(oauth): accept BOOSTER balance type and drop debug log
* fix(oauth): drop reset hint from Extra Usage and revert periodEnd parsing
* fix(oauth): treat missing amountLeft as zero extra usage and drop debug log
* revert: keep missing amountLeft defaulting to 0 (fully used)
* feat(extra-usage): show monthly cap usage bar and balance in /usage and /status
* fix(extra-usage): show balance and unlimited marker when no monthly cap
* fix(extra-usage): show monthly used with unlimited marker and balance
* fix(extra-usage): label Used and use English Unlimited
* feat(extra-usage): render balance, monthly used and monthly limit as labeled rows
* fix(extra-usage): move Balance row to the bottom
* fix(extra-usage): format currency values with two decimals for column alignment
* fix(extra-usage): right-align currency values so numbers line up
* fix(extra-usage): align currency symbol and decimal point in usage rows
The r1/r2/r3 reminders injected into repeated tool results led with
prohibition verdicts and, in r2, echoed the repeated tool name and full
arguments back into the context, reinforcing the very pattern they were
meant to break. Rewrite them to state the situation factually and hand
the model a concrete next action: an expectation-setting sentence for
the next call (r1), a forced decision menu of falsify / ask-user /
conclude (r2), and a final hand-off summary without further tool calls
(r3). Detection, thresholds (3/5/8/12), force-stop, and telemetry are
unchanged.
* feat(kimi-web): add approval notification storage key and i18n copy
* feat(kimi-web): add approval notification helpers and tests
* feat(kimi-web): wire approval notifications and guard completion alerts
* fix(kimi-web): extract shouldNotifyCompletion helper and add tests
* feat(kimi-web): add approval notification settings toggle
* chore(kimi-web): add changeset and tidy notification module comment
- Align approval notification tag with spec (kimi-approval-${approvalId})
- Update module header to describe all three notification kinds
* fix(kimi-web): make notifications fire reliably
- Key completion notification tags by turn (sid + promptId) and question
tags by request id, so a stale notification left in the notification
center no longer swallows every follow-up alert in the same session
- Suppress notifications only while the window is actually focused, not
merely visible (document.hasFocus() on top of visibilityState)
- Play the attention sound when a tool needs approval, matching the
completion and question sounds
* chore(kimi-web): simplify changeset
* fix: surface provider auth error for unavailable models
When an OAuth-managed model returns 401 after a forced token refresh, the token is valid but the provider rejected it for that model (the account lacks access). Emit provider.auth_error carrying the provider's message instead of auth.login_required with a misleading "OAuth login expired. Send /login" prompt.
* fix(agent-core): preserve provider auth errors through compaction
Treat provider.auth_error like auth.login_required in the compaction path so an auth rejection during compaction surfaces the provider's message instead of being wrapped as a generic compaction failure.
* fix(web): composer model switch also updates global default model
The composer model switcher still switches the active session's model via
POST /sessions/{id}/profile (awaited, so the model pill reflects the result),
and additionally fires POST /api/v1/config with { default_model } as a
fire-and-forget side effect so new sessions inherit the chosen default. The
config request is skipped when the model already matches the current default.
* fix(web): route ModelPicker overlay selection through the default-model update
The overlay opened from the composer's "More models" row (and /model) is a
continuation of the same switch flow, so its selection now also bumps the
global default model instead of only switching the active session.
* fix(web): only persist the default model after a confirmed session switch
setModel now returns whether the switch was accepted (true for the draft
path), so the composer flow no longer writes a stale or invalid model alias
into the global config when the session-level switch failed and rolled back.
* feat(web): redesign cron reminder as a message bubble
Restyle the cron trigger notice as a right-aligned user-style message bubble that shows the scheduled prompt in full (wrapping across lines), with a small meta row beneath it for the schedule, status, job id and run time. Extract a shared MessageTime component used by both user messages and the cron reminder so the timestamp format and click-to-expand behavior stay consistent, and give the CronCreate/CronList/CronDelete tools distinct calendar icons.
* refactor(web): render cron reminders only as standalone turns
Remove the embedded cron block path from the web transcript projector so cron reminder fires always render through the standalone right-aligned bubble path.
* chore(web): simplify cron redesign changeset
Headless (`kimi -p`) failures could exit with code 0 when the event loop
drained during the shutdown cleanup (e.g. telemetry's unref'd retry backoff
when the network is blocked), because the rejection never reached the
process.exit(1) call. Set the failure exit code before any await in both
the run-prompt catch and the main catch, and keep the cleanup timeout ref'd
so the loop stays alive long enough for the rejection to propagate.
Align progressive tool disclosure with the discard-on-compaction model:
compaction no longer rebuilds loaded dynamic tool schemas. The boundary
announcement re-lists every loadable name, the model re-selects what it
still needs, and a from-memory call to a no-longer-loaded tool is
rejected by preflight with select guidance.
This removes the keep-all rebuild and its half-trigger budget heuristics
entirely: the post-compaction floor is back to users + summary, which is
structurally outside the auto-compaction trigger band, and the guard
baseline degenerates to summary + reinjected reminders. Every downstream
mechanism already treated the empty loaded set as its consistent base
state (ledger scan, pending clear at the compaction boundary, deferred
extras, preflight wording), so this is a strict simplification.
Co-authored-by: fengchenchen <fengchenchen@moonshot.ai>
* fix(agent-core): report EXIF-rotated image dimensions and raise edge cap to 3000px
Image compression now reports original dimensions in the decoded
(EXIF-rotated) space, matching the coordinate system of the sent image
and of ReadMediaFile region readback; previously portrait JPEGs
(orientation 5-8) got swapped width/height in captions. The longest-edge
downscale cap rises from 2000px to 3000px, and the default jimp resize
path is documented as the anti-aliased area-average one so it is not
accidentally switched to a point-sampled interpolation mode.
* test: shrink oversized image fixtures to fit CI timeouts
The 3600x3600 fixtures introduced for the 3000px edge cap nearly doubled
the pixel area jimp has to decode and deflate, pushing the slowest
compression tests past the 5s vitest timeout on CI runners. 3600x1800
keeps every fixture over the cap while restoring roughly the workload of
the old 2600x2600 fixtures that CI handled comfortably.
* test: pin anti-aliased downscale quality with executable guards
A 1px checkerboard probe pins the compressor to full-coverage averaging
at integer and fractional ratios, with jimp's point-sampled BILINEAR
mode kept as the executable aliasing counter-example (it collapses the
50%-gray pattern to solid black at 4:1). Also guards the other classic
downscale bugs: transparent-pixel color bleed, mean-brightness drift,
iterative recompression degradation, and zero-size collapse on extreme
aspect ratios.
* fix(agent-core): report decoded EXIF-rotated dimensions in ReadMediaFile notes
The media note derived its original-dimensions line from the header
sniff, which reports pre-rotation values for EXIF orientation 5-8
JPEGs. The sent image and region readback both live in the decoded
(rotated) space, so portrait photos got axis-swapped coordinate
guidance. Once a decode has happened — compression or crop — its
dimensions now overwrite the sniffed ones.
* fix(agent-core): improve handling of EXIF orientation in image dimensions and metadata
* fix(agent-core): sniff EXIF orientation and step budget fallback through 2000px
Two follow-ups to the EXIF and 3000px-cap changes:
sniffImageDimensions now reads the JPEG EXIF Orientation tag (pure
header parse, both byte orders) and reports display-space dimensions
for orientations 5-8. Passthrough images — never decoded — previously
kept the pre-rotation header size in compression results and media
read notes, disagreeing with the decoded space that region readback
uses.
encodeWithinBudget steps the over-budget fallback through 2000px
before the 1000px last resort. Raising the cap to 3000px had left a
regression window: an image whose 2000px encode fits the byte budget
was sent at 1000px where the old 2000px cap used to send it at
2000px.
* fix(kimi-code): record pasted image dimensions in display space
The TUI paste path recorded attachment and original dimensions from its
raw header parser, which ignores EXIF orientation. For a portrait JPEG
the submit-time caption then contradicted the sent image's aspect and
region readback coordinates were axis-swapped. Dimensions now come from
the compression result, which reports display space on both the
compressed and passthrough paths; parseImageMeta remains only the
format/mime gate.
* feat(agent-core): add image compression and crop telemetry
Every image ingestion path now reports an image_compress event —
outcome (compressed / passthrough fast, guard, unsupported, unhelpful,
error), input/output formats, byte and pixel sizes, EXIF transposition,
and duration — and region readback reports an image_crop event with a
failure classification and the region's share of the original area.
Wiring is per call site via a new CompressImageOptions.telemetry
option, so the outcome split and timing are measured inside the
compressor while each caller only names its source: ReadMediaFile
(tool construction, like GrepTool), MCP tool results (McpOutputOptions),
server prompt ingestion (ICoreProcessService now exposes the host
telemetry client), ACP prompts (session track adapter), and TUI paste
(host.track adapter). Properties are numeric/enum only — never paths
or content — and a throwing client can never affect the compression
result.
* fix(agent-core): run the full JPEG quality ladder at fallback sizes
The fallback rescales encoded only at quality 20, so a JPEG whose
ladder failed at the fitted size collapsed straight to the lowest
quality even when the smaller size left budget headroom for a higher
rung (the realistic window is the 1000px step, where the 4x pixel
drop pays for q80/q60). Each fallback edge now walks the same
q80-to-q20 ladder as the fitted size.
* test: shrink heavy JPEG fixtures and add explicit timeouts
The fallback-ladder test runs ~11 pure-JS JPEG encodes and the EXIF
paste test decodes, rotates, and re-encodes a 6.5MP frame; both sat at
the edge of the 5s vitest timeout on CI runners. Narrower fixtures cut
the pixel area (the ladder test keeps its width above 2000px so the
full fallback chain still runs) and explicit 15s timeouts absorb runner
variance.
* fix(server): scope prompt image compression telemetry to the session
The prompt-ingestion image_compress events were emitted with the bare
host telemetry client, while every agent-side source inherits a
session-scoped client — so prompt_inline/prompt_file events could not
be correlated with their session. The route now wraps the client with
withTelemetryContext({ sessionId }) like rpc/core-impl does for
session telemetry.
* chore(changeset): consolidate image compression changesets
One entry covering the cap raise and the EXIF dimension fix, listed
for both the CLI and the SDK so the SDK changelog's compression
description (previously pinned at 2000px) stays accurate.
- Drop numeric telemetry properties whose absolute value exceeds Number.MAX_SAFE_INTEGER before enqueue, and reject them again during payload assembly as a backstop.
- Omit constrained_memory_bytes when process.constrainedMemory() is not a safe non-negative integer so Linux no-cgroup sentinels do not overflow int64 parsing downstream.
- Add telemetry tests for unsafe numeric properties and constrained_memory_bytes filtering.
