* feat(pi): complete RPC interaction parity
* feat(pi): integrate native conversation history
* fix(pi): harden RPC lifecycle boundaries
* fix(pi): address review lifecycle and upload boundaries
* fix(pi): release history transaction on rollback deadline
* fix(pi): isolate preflight and timed-out mutations
* fix(pi): preserve retry and editor boundaries
* fix(pi): disable unavailable history synchronization
* fix(pi): gate fallback readiness on history baseline
* fix(pi): bind uploads and retire extension requests
* fix(pi): preserve canceled and legacy stream boundaries
* fix(pi): preserve native fork runtime state
* fix(pi): persist dialogs and preserve select values
* fix(pi): keep upload authorization path-stable
* feat(pi): preserve native steer semantics
Route ordinary sends during an active Pi main turn through native steer while keeping explicit queue delivery on the existing composer gestures. Persist the delivery contract across Hub replay and Web retries, and guard stale steer dispatch with streaming generations and ordered prompt fallback.
* fix(pi): queue deferred steer deliveries
Keep native steer only for the initial live emit. Reconnect replay, CLI backfill, clear-gate release, and mature delivery now downgrade turn-scoped steer intent to the durable HAPI queue without mutating stored provenance.
* fix(pi): retain abort guard through preflight miss
Treat an immediate no-active abort rejection as a possible async-preflight race. Keep the existing abort boundary alive so a late agent_start receives the compensating abort before queued work is released.
* fix(pi): queue stale steer retries
A failed send no longer reuses turn-scoped steer intent after its original Pi generation is lost. Text restoration, attachment retry, and legacy retry provenance all enter the durable HAPI queue while fresh ordinary sends retain native steer behavior.
* fix(pi): invalidate rejected abort generation
After a no-active preflight abort waits through late-start compensation, mark the target stream idle while the runtime mutation lease is still held. Waiting native steers therefore fall back instead of entering the aborted generation.
* fix(pi): queue idempotent steer retries
Track whether a localId insert created a new row. Initial inserts may retain live Pi steer, while duplicate-localId retries deliver a queue-safe view of the stored row without overwriting its original provenance.
* fix(pi): sync command-only history before fallback
Read the Pi append log before retiring a successful prompt that produced no agent lifecycle. Preserve FIFO history associations across missing entry events, and fail the wrapper closed if that mandatory synchronization cannot be completed.
* fix(web): count unseen messages by rendered block, not raw message
The "N new messages" pill counted raw DecryptedMessages while the
timeline renders folded blocks, so the two never agreed. A subagent run
is dozens of sidechain messages but a single Task card; a tool_use and
its tool_result are two messages and one card; consecutive tools collapse
into one group. The pill could read "47 new messages" when scrolling down
revealed two new rows.
collectNewUnseenIds never inspected isSidechain, and it could not: the
reducer's grouping is stateful (it needs the Task tool_use before it can
map parentToolUseId), so a per-message predicate in the store cannot
reproduce it. Adding an isSidechain check there would also invert the
error for orphan sidechain messages, which tracer.ts falls back to
emitting at the top level.
Instead, drop the store's unseen bookkeeping entirely and count what the
renderer actually produced. Watermark the visible blocks when the user
scrolls away from the tail, then count the blocks past the last one they
had seen.
The count is anchor-based rather than timestamp-based because the blocks
array is not monotonic in createdAt: messages sort by invokedAt ??
createdAt, so a queued message carries an old createdAt while sitting at
the end. Anchoring also makes prepended history free, since older blocks
land before the anchor.
Known limit, documented at the call site: once the history window fills
up, mergeIntoWindow trims incoming messages off the tail, so the pill
reports 0 instead of a count. Under-reporting is preferable here, and
returning to the tail force-refetches the latest page anyway.
* fix(web): keep unseen watermark stable across optimistic id replacement
The watermark snapshotted only block.id, but that id is not stable for
the user's own messages: mergeMessages replaces an optimistic row with a
stored row that keeps localId under a new server id, and the user block
renders with the message id. Scrolling into history while an own message
was still optimistic meant its echo anchored one block earlier and bumped
the pill by one, with no new rendered row.
Track localId alongside id in the watermark and match on either.
Reported by HAPI Bot on #1255.
* fix(web): count joined assistant cards, not pre-join blocks
visibleBlocks is still not one-to-one with rendered rows: assistant-ui
joins a run of adjacent assistant-role blocks into a single card, so a
response made of reasoning + text + a tool call was reported as three new
messages instead of one, and appending another block to an in-flight
response bumped the pill without adding a row.
Walk the blocks after the anchor and only start a new row where the
assistant run breaks.
Role assignment is the part that would drift, so rather than restating it,
visibleBlockRole moves from assistant-runtime.ts to toolGroups.ts (next to
the VisibleChatBlock definition it describes) and both the runtime and the
counter import the one copy.
Reported by HAPI Bot on #1255.
* refactor(web): extend MessageMetadata to accept aggregated turnCount
Add an optional `turnCount` prop to MessageMetadata so the same builder
can render an aggregated response-group footer when the caller has
already summed usage and dedup-joined model ids. The label set switches
to `Models` / `Total` / `N turns` only when `turnCount >= 2`, leaving
single-turn footers byte-identical with the existing
`Invoke · Model · Usage` output.
Also expose `turnCount?: number` on `HappyChatMessageMetadata` so a
later commit can inject the aggregated metadata through the library's
ThreadMessageLike payload without widening the type at the same time.
No call site passes `turnCount` yet, so this commit is behavior-neutral
on all existing surfaces (proof-of-invariance test included).
* feat(web): aggregate per-response metadata so multi-turn cards show total usage
The `@assistant-ui/react` converter joins adjacent assistant messages
into one card but only preserves `metadata.custom` from the first
block, so multi-turn responses currently show the first turn's usage
and model only.
Compute response-group aggregates in `useHappyRuntime` and inject the
sum on each group's first visible block, where the library will keep
them. Per group: usage tokens are summed across distinct turns,
model ids are dedup-joined in first-seen order, and the invoke time
is the first turn's so the footer keeps showing when the response
started (regression-guarded by unit test). `durationMs` is explicitly
cleared on aggregated blocks because the first turn's value would
otherwise leak through the join.
Turn identity prefers the CLI-stamped `localId`. When that is null
(claude code spawn sessions today emit `localId=null` on every chunk)
the aggregator falls back to a fingerprint built from `model` plus the
shared `usage` totals — every block emitted within one Claude SDK
message carries an identical usage object, so the fingerprint dedups
those chunks without merging distinct turns whose token counts
naturally differ. Tool-result chunks with no model or usage are
skipped so they cannot inflate the turn count.
Single-turn responses get no aggregate entry, so their footers stay
byte-identical with the existing behavior.
Test plan
- `assistant-runtime.test.ts` covers the six grouping scenarios spelled
out in the design note (localId-based + null-localId fingerprint
fallback) plus two defensive cases for tool_result chunks and cache
token preservation.
* fix(web): preserve explicit zero sums and count tool-group turns in response aggregator
Two correctness gaps in aggregateResponseGroups:
- addUsage folded `0 + 0` through `|| undefined`, dropping an
explicit-zero cache token sum from the aggregated metadata.
Replace the falsy fold with sumOptional(): undefined only when
both operands are absent, otherwise (a ?? 0) + (b ?? 0).
- turnSourceFromBlock returned null for tool-group blocks, so a
card whose visible-first block is a tool-group dropped its
turn entirely. Read the first underlying tool-call instead;
degrade to null only when the group somehow holds zero tools.
Unit tests cover both regressions: tool-group as the first visible
block in a response group, explicit-zero cache sums preserved, and
the empty-tool-group degrade-to-null path.
* fix(web): dedup response-group turns by adjacency rather than set membership
The fingerprint fallback (used when localId is null) compared each
turn key against a Set of every key seen in the group. A response
group whose first and third turns happened to carry the same
(model, usage) fingerprint would collapse the third turn into the
first, under-counting the visible turn count.
Switch to ordering-based dedup: each block's turn key only collides
with the immediately previous turn. Adjacent blocks within one SDK
message still collapse (their usage object is identical), but
non-adjacent fingerprint matches across separate turns stay
distinct. Behavior under localId-stamped flows is unchanged because
distinct turns always carry distinct localIds.
Unit test covers a three-turn group whose first and third turns
share a fingerprint with a different middle turn between them.
* fix(web): aggregate every tool-call in a tool-group and dedup by createdAt fingerprint
`buildVisibleChatBlocks` merges adjacent eligible tool-calls into a single
`tool-group` without checking that they share a turn. Reading only the
first underlying tool would drop every later tool turn from the aggregate,
so each tool-call in the group now contributes its own turn source.
The fingerprint fallback (used when the CLI does not stamp `localId`)
gains `createdAt` as a third axis. The reducer copies `msg.createdAt`
onto every derived ChatBlock, so blocks from one SDK message still
collapse to one turn, while two adjacent turns that happen to coincide
on `(model, usage)` no longer dedup against each other. Same wall-clock
millisecond collisions remain theoretically possible but are bounded by
the hub stamp resolution.
Helper layer consolidates: `turnSourceFromBlock` (single-or-null) is
gone, replaced by `turnSourcesFromBlock` returning the array directly.
Test renames clarify the contract — the existing tool-group test now
documents the same-turn collapse case — and one new test pins the
fingerprint coincidence case.
* fix(web): make tool-only response cards expose aggregate metadata
`aggregateResponseGroups` keys aggregate metadata onto a response group's
first visible block, which can be a `tool-group` when the assistant turn
starts with tools. The `toolOnly` render branch did not wire the click
toggle that the default/codex branches use, so the new Models/Total/N-turns
footer stayed unreachable for those cards.
Wrap the toolOnly content with the same cursor-pointer div used in the
sibling branches (toggleMetadata, onMetadataKeyDown, role=button,
aria-expanded). Carry `min-w-0` on the wrapper so long tool labels keep
clipping under the existing `overflow-x-hidden` on MessagePrimitive.Root.
The shared `isNestedInteractiveEvent` guard prevents the wrapper toggle
from firing when nested tool buttons or disclosures are clicked.
* feat(web): group consecutive tool-use cards
Add a web-only visible projection that groups consecutive root-level execution tools into expandable cards.
Keep approval and question tools standalone, reuse older-history loading on expand, and add regression coverage for grouping and UI behavior.
* fix(web): hydrate oldest visible tool group
Mark needsOlderHistory on the first visible grouped tool run even when earlier visible blocks are non-tool content, and add regression coverage for the boundary.
* fix(web): continue grouped history hydration
Decouple ToolGroupCard older-history chaining from the shared loading flag, invalidate stale hydration runs safely, and add regression coverage for multi-page hydration.
* fix(web): harden grouped tool hydration
- retry incomplete group hydration after transient pagination contention\n- keep approved and denied permissioned tool cards eligible for grouping\n- cover both regressions with targeted web tests
* fix(web): keep Codex permission cards standalone
- treat CodexPermission as a semantic grouping boundary even after approval\n- keep permissioned execution tools groupable while preserving permission milestones\n- add regression coverage for Codex permission eligibility and boundary behavior
* fix(web): narrow incomplete tool-group hydration
- only mark groups at the oldest visible boundary as needing older history\n- avoid auto-paginating complete groups behind text, standalone tools, or permission milestones\n- add regression coverage for the adjacent boundary cases
* feat(web): show message metadata (invoke time, duration, model) on click
* fix(cli): preserve model field on assistant messages forwarded to hub
`RawMessageSchema` validates the `message` object in Claude Code session
JSONL lines before the cli forwards each message to the hub. Zod's default
parse mode strips fields that the schema does not declare, so the
`message.model` value (e.g. `claude-sonnet-4-6`) was silently removed
before the message reached the hub. The web normalizer reads
`data.message.model` to label assistant blocks, so without this field
every assistant message fell back to a generic "AI Model" label —
defeating the per-message model attribution this PR adds.
Add `model` to `RawMessageSchema` so it survives parse and reaches the
hub intact.
* fix(web): drop dead model shorthand in result envelope normalize
The `result/success` branch in `normalizeAgentRecord` referenced a `model`
identifier that was never declared in the function scope, breaking
`bun typecheck`. The reducer that consumes the resulting `turn-duration`
event does not look at `model` on the event itself, so the shorthand was
dead code. Remove it to restore typecheck.
* refactor(web): simplify turn-duration matcher with findLastIndex
Replace the imperative reverse-scan loops in the `turn-duration` reducer
branch with `findLastIndex`. The previous fallback also had an awkward
double-loop that mutated the matched block in place; using an index plus
a single immutable update keeps the block reference clean and makes the
match priority (id-prefix > tool-call id > last assistant-like) explicit.
Behaviour is unchanged — existing reducer tests cover both the messageId
match and the fallback paths.
* fix(web): preserve per-message model across mid-session model switches
The metadata footer fell back to `Session.model` from chat context when a
message did not carry its own `model`. That session value mutates when
the user switches models mid-session, so older messages were relabeled
with the latest model — including Codex/local assistant paths
(`AGENT_MESSAGE_PAYLOAD_TYPE`) that don't populate `msg.model`.
Drop the mutable-context fallback: pass `messageModel ?? null` to
`MessageMetadata` and let it omit the model line when no per-message
value is available. This is correct behaviour for messages whose
producer didn't record a model, and avoids ever attributing a message
to a model that didn't generate it.
Also remove the now-unused `useHappyChatContext` import in this file.
Add reducer invariants to lock in the data flow:
- `preserves per-message model across mid-session model switches`
- `leaves model undefined when message lacks per-message model`
* fix(web): keep tool-block reference identity when applying turn-duration
`ensureToolBlock` stores the same `ToolCallBlock` instance in both
`toolBlocksById` and `blocks`. The earlier refactor cloned the matched
block via `blocks[foundIndex] = { ...b, durationMs }`, which left the
map pointing at the stale original. A subsequent permission/result
mutation through `ensureToolBlock` would then update the stale map
object while the rendered `blocks` entry never sees the completion or
result, causing tool cards to miss state transitions.
Mutate the matched block in place instead — same in-place pattern the
reducer used before — and gate the assignment on the kinds that carry a
`durationMs` field so TypeScript narrows correctly.
Add an invariant test that fires a `turn-duration` event at a tool-call
block and asserts the rendered block and `toolBlocksById.get(...)`
remain the same object reference.
* fix(web): do not render service_tier as the model id
`MessageMetadata` previously fell back to `usage.service_tier` as the
"model" when no per-message `model` was available, so messages without
their own model id could surface labels like `Model: standard_only` —
service_tier is tier metadata, not a model.
Render the model line only when a real `model` is present; if a
non-`standard` `service_tier` is the only signal, surface it as a
separate `Tier: <tier>` label so it is not mistaken for the model.
The standard tier is the implicit default and is never rendered alone.
Extract the label-building logic into `buildMessageMetadataLabels` so
it can be unit-tested without a DOM. Add tests covering: model present,
model missing with non-standard tier, default standard tier, model with
non-standard tier appended, and the empty-input case.
* fix(web): metadata toggle ignores clicks on nested interactive controls
The bubble-level click handler that opens the metadata footer wraps
interactive descendants — tool-card buttons, retry buttons, dialog
triggers (Radix `role="button"`), and the Markdown code-copy button.
Clicking any of those flips the metadata footer as a side effect, even
when the descendant is the actual target of the user's intent.
Extract the closest-ancestor check into a small `metadataToggle` helper
and route both `AssistantMessage` and `UserMessage` click paths through
it. The toggle bails out when the click target sits inside any
`button`, `a`, `input`, `textarea`, `select`, or `[role="button"]`
ancestor; plain message-body text still toggles as before.
Add unit tests covering: button target, nested span inside a button,
`role="button"` Radix-style trigger, anchor/input/textarea/select form
controls, plain message-body text (no toggle), and a non-HTMLElement
target.
* fix(cli): preserve messageId on system/turn_duration record
`web/src/chat/normalizeAgent.ts` matches each `turn-duration` event to
the assistant block carrying the same `data.messageId`. Claude code
emits that field on the `system/turn_duration` record, but
`RawJSONLinesSchema`'s system branch did not declare `messageId`, so
Zod stripped it before the cli forwarded the record to the hub. The
matcher then fell back to "the last visible block", which is wrong for
interleaved/tool-heavy turns and silently attaches the duration to the
wrong assistant block.
Add `messageId: z.string().optional()` to the system schema so the id
survives parse and reaches the web reducer. Tests cover the preserved
case, the legacy case without `messageId`, and the previously-fixed
`message.model` case so Zod strip regressions on adjacent fields stay
locked in.
* fix(web): metadata toggle accepts SVG event targets
`isClickOnNestedControl` only walked up via `closest` when the click
target was an `HTMLElement`. The copy / retry / Markdown code-copy
buttons render SVG icons, so clicking the icon makes the event target
an `SVGElement` (not an `HTMLElement`) — the guard returned false and
the bubble-level click flipped the metadata footer anyway.
Widen the type check to `Element`, which is the common super-class of
both `HTMLElement` and `SVGElement` and also exposes `closest`. Plain
text targets and non-Element targets still behave as before.
Add a regression test that mounts an icon-only button (`<button><svg>
<path/></svg></button>`) and asserts both the `<svg>` and `<path>`
targets walk up to the enclosing button.
* refactor(cli): rely on Zod passthrough for jsonl envelopes
`RawMessageSchema` and the `system` branch of `RawJSONLinesSchema` were
declared with Zod's default `strip` mode, so any field the cli did not
explicitly enumerate was silently dropped before the hub forwarded the
record. The metadata pipeline lost `message.model` and
`system/turn_duration.messageId` exactly that way, and each gap took a
separate fix.
Switch both schemas to `.passthrough()` so undeclared fields survive
parse and reach the web reducer verbatim. Future SDK additions no
longer require another schema patch.
Add tests asserting that unknown keys on assistant messages and
unknown keys on system records (alongside the existing `messageId`
case) are preserved end-to-end through the schema.
* refactor(web): clean up dead metadata propagation surface
Several knobs were added to thread metadata through the chat tree but
ended up unused or redundant; consolidate them so the data flow has a
single canonical path.
- Drop the unreachable `data.type === 'result' && data.subtype ===
'success'` branch in `normalizeAgentRecord`. Claude's `result`
records are consumed by `claudeRemote` as session-completion signals
and never forwarded to the hub; the cli `RawJSONLinesSchema`
discriminator does not include `result`, so these records are
rejected before they reach `normalizeAgentRecord` either way.
- Stop threading `invokedAt` through the inner `normalizeAssistantOutput`
/ `normalizeUserOutput` / `normalizeAgentRecord` calls. Every caller
in `normalizeDecryptedMessage` already overwrites it via the outer
spread, so the inner copies were dead writes. Set `invokedAt` only at
the outer boundary.
- Remove the `model?: string | null` field from `HappyChatContextValue`
and the `model` prop on `HappyThread` / `SessionChat`. Its only
consumer (`AssistantMessage` mutable-fallback) was removed when the
per-message model attribution fix landed; the prop has no readers
now.
- Match the existing `as Partial<HappyChatMessageMetadata> | undefined`
cast pattern in `AssistantMessage` and `UserMessage` instead of the
non-`Partial` cast that pretended every field was present even when
`custom` is undefined.
- Rename `AgentEvent.turn-duration.messageId` to `targetMessageId` so a
reader does not confuse the duration's target with the surrounding
envelope id; the wire field on Claude's `system/turn_duration` record
stays `messageId` (vendor name) and is mapped at the normalize
boundary.
No behaviour change. All existing tests pass.
* fix(web): turn-duration matcher and cli-output merge precedence
Two reducer-level metadata-correctness bugs surfaced during a hostile
self-review.
1. Turn-duration matcher silently dropped the duration when
`targetMessageId` resolved to a non-duration-bearing block. The
existing pipeline did `findLastIndex(b => b.id === targetId || ...)`
first; if that hit an `agent-event` or `user-text` block (id-prefix
collision), the kind guard at the assignment site failed and the
duration was never attached. The fallback search ran only when the
first pass returned -1, not when the kind check rejected the match.
Fold the kind filter into every search predicate via a typed
`isDurationTarget` helper so the priority `target-bearing match >
tool-call id > last duration-bearing block` is exhaustive.
2. `mergeCliOutputBlocks` had asymmetric metadata precedence between
the command-name block (`prev`) and the stdout follow-up (`block`):
`invokedAt` and `model` preferred prev, but `durationMs` and `usage`
preferred block. Only the command-name block carries first-class
metadata; the stdout follow-up is a synthetic split. Use prev as the
primary source uniformly and fall back to block only when prev is
missing the field.
Tests cover the fallback path on the matcher and both precedence
scenarios on the merger.
* fix(web): preserve tool-call invokedAt across tool-result update
`ensureToolBlock` is called twice for the same tool: first with the
seed from the assistant's tool-use block, then with the seed from the
matching tool-result message. The second call's `seed.invokedAt` came
from the tool-result message and was unconditionally overwriting the
tool-call's original invokedAt. The rendered "Invoke" timestamp on a
tool card therefore showed when the result was processed, contradicting
the column header.
Guard the assignment so the timestamp survives the second call —
`existing.invokedAt ??= seed.invokedAt` semantics — while still letting
the first call set the value when the tool is created. `durationMs`,
`usage`, and `model` continue to overwrite because their values come
from the result message's usage block and are intentionally newer.
Add a regression test that fires a tool-use followed by a tool-result
with a later invokedAt and asserts the tool block keeps the original.
* fix(web): metadata footer UX, accessibility, and label hardening
Bundle the remaining UI surface fixes for the metadata footer.
- Make the bubble interactive only when there is metadata to disclose.
Without the guard, every non-Claude session bubble (Codex / Cursor /
Gemini, none of which populate `model`/`usage`/`durationMs` in the web
layer) showed a pointer cursor and reacted to clicks even though
`MessageMetadata` rendered nothing — false-positive interactivity.
- Add keyboard support: when the bubble is interactive it now exposes
`role="button"`, `tabIndex=0`, `aria-expanded`, and an `Enter`/`Space`
key handler so screen readers and keyboard-only users can disclose
the footer the same way mouse users do.
- Fix nullish-vs-falsy bugs in the label builder: a 0 ms turn or a 0
unix-epoch invokedAt no longer hides their lines. Use explicit
`!= null` / `>= 0` checks.
- Rename the token total to "billable tokens" so the explicit exclusion
of cache I/O is signalled in the label rather than implied by the
number alone.
- Tag the queued/sending status spans with `role="status"` (and an
accessible label) so they are announced by AT and so the metadata
toggle's `closest('button, ..., [role="status"]')` filter does not
accidentally fire when a user clicks a status icon.
- Add the native `<summary>` element and `[role="status"]` to the
toggle's nested-control selector. Tool cards already render their
expandable bodies as `<details><summary>` — clicking the summary now
expands the disclosure without also flipping the metadata footer.
Tests cover: native `<summary>` target, `role="status"` target, the
billable label, durationMs=0 surfaced, invokedAt=0 surfaced,
invokedAt=null/undefined hidden.
* fix(web): expose cli-output metadata via dedicated toggle button
CliOutputBlock renders the entire card as a Dialog trigger <button>, so
the bubble-level click handler on the cli-output branch never opened the
metadata footer by mouse — every click landed inside that button and
isClickOnNestedControl bailed out. The wrapping div with role="button"
was also a nested-interactive a11y anti-pattern.
Drop the wrapper's role/onClick/tabIndex/keyDown on the cli-output
branch and render an explicit "Show metadata" / "Hide metadata" button
beneath the card. The dialog trigger keeps its full hit area; the
metadata footer is now reachable by both mouse and keyboard.
* fix(web): exclude toggle wrapper from nested-control guard
The bubble-level toggle wrappers in AssistantMessage / UserMessage
carry role="button" for keyboard accessibility. Without excluding
currentTarget, closest('[role="button"]') from any inner click matches
the wrapper itself and the toggle bails out — making the metadata
footer unreachable for mouse users (keyboard Enter/Space still worked,
which is why unit tests and bot review missed it).
Walk currentTarget out of the match: a nested control is one whose
closest matching ancestor is *not* the wrapper itself.
* fix(web): apply nested-control guard on keyboard activation too
The mouse path bailed via isClickOnNestedControl, but the keyboard path
on the metadata-toggle wrapper did not. Pressing Enter or Space on a
focused descendant control (e.g. Markdown code-copy button) bubbled the
keydown up and the wrapper toggled metadata alongside the descendant's
own activation.
Generalize the helper to isNestedInteractiveEvent over both
MouseEvent and KeyboardEvent and call it from onMetadataKeyDown in
AssistantMessage and UserMessage.
Add ability to resume inactive sessions and automatically continue with new
session ID. Includes message merging for preserving conversation history,
UI improvements to allow sending during inactive state, and database schema
migration. close#87
Move duplicate isObject, asString, asNumber, and safeStringify functions from multiple modules into a centralized shared/src/utils.ts module and update imports across cli, server, and web packages. This eliminates code duplication and improves maintainability.
Add comprehensive support for handling reasoning blocks throughout the chat pipeline, including normalization, reconciliation, type definitions, and UI rendering. Implements collapsible reasoning group component with auto-expand during streaming and shimmer indicator.
Implement CLI output message type for displaying command output from user/assistant messages. Adds CliOutputBlock component and type with detection logic based on message metadata and CLI tags. Includes merging of adjacent CLI output blocks for cleaner presentation. Enhance layout throughout components with proper overflow handling and width constraints for improved text wrapping and scrolling behavior.
Use the cached message converter from @assistant-ui/react to prevent
re-converting all messages on every render. The previous implementation
called convertMessage for every ChatBlock on each render cycle, creating
new objects (Date, arrays, metadata) that triggered unnecessary state
updates and re-render storms.
The new implementation:
- Uses useExternalMessageConverter which internally caches via WeakMap
- Memoizes callbacks with useCallback for stable references
- Memoizes the adapter object to prevent subscription churn
