mirror of
https://github.com/stablyai/orca.git
synced 2026-10-21 00:03:46 +00:00
* fix(agent-status): clear answered Claude question waits at answer time An answered AskUserQuestion left the amber "waiting" indicator on sidebar rows and tabs until the agent's next tool hook or turn end — unbounded linger while the model thinks or streams after the answer (measured 17s for a 1000-word reply, 44s for 3000 words). Root cause is an event-shape change: newer Claude reports the AskUserQuestion wait as PermissionRequest (not the PreToolUse shape #7852 special-cased), so the wait inherited real-permission stickiness and shouldKeepClaudePermissionVisible swallowed the answer-time PostToolUse(AskUserQuestion) working event — the identity match can never succeed because the question's PermissionRequest carries no inheritable tool_use_id. That silently undid #8311 for questions. Two scoped changes, both keyed on the tool name rather than the hook event name: - Sticky permission hold now exempts AskUserQuestion waits, so the real answer-time hook (when Claude sends one) clears the wait as #8311 intended. - New guarded inference for the hook Claude may never send: the submit keystroke (Enter or digit quick-select) into a pane whose fresh status is a waiting AskUserQuestion synthesizes the post-answer state, exactly mirroring the existing interrupt inference (renderer baseline capture, main-process re-validation, listener lead-state sync so child-driven refreshes cannot resurrect the dismissed question). Real permission waits (other tools) keep their sticky semantics; batched input and pastes never match the submit classifier. Verified live against a real claude CLI: waiting -> working within ~50ms of both Enter and digit answers, question card dropped, unanswered questions still hold amber, permission stickiness covered by tests. * fix(agent-status): guard question answer inference Keep multi-question, multi-select, and free-text selector interactions waiting until the full prompt is submitted. Wire native-chat answers into the same guarded inference only after every paced runtime write succeeds, with cancellation and delivery-failure coverage. * chore(skills): refresh manifest for rc.2 * fix(agent-status): verify native chat answer delivery * fix(agent-status): await verified question delivery * fix(agent-status): pin native-chat answer baseline before delivery The native-chat question-answered inference read the live pane status at settle time (after the paced send + remote acceptance, which can span seconds on SSH). If a replacement AskUserQuestion became current in that window, the settle callback minted a fresh baseline from the new question and the server cleared *its* wait — dismissing a question the user never answered. Capture the answered question's baseline before delivery and have the inference getter return it, so the server re-validates against the pinned baseline and rejects a changed status — the same capture-then-revalidate contract the terminal keystroke path already uses. Also hoist the shouldStepNativeChatAskAnswer predicate to a single evaluation. Regression test swaps the live status between sendAnswer and settle and asserts the answered question's baseline is used (fails against the prior live-read getter).
84 lines
3.1 KiB
TypeScript
84 lines
3.1 KiB
TypeScript
import type { AgentType } from './agent-status-types'
|
|
|
|
/** Baseline snapshot the renderer captured when it observed the submit
|
|
* keystroke. The main process re-validates every field against its own
|
|
* cached status so a racing real hook always wins over the inference. */
|
|
export type AgentQuestionAnsweredInferenceRequest = {
|
|
paneKey: string
|
|
baselineUpdatedAt: number
|
|
baselineStateStartedAt: number
|
|
baselinePrompt: string
|
|
baselineAgentType: AgentType | undefined
|
|
}
|
|
|
|
/** True for the AskUserQuestion tool across the casing variants different
|
|
* agents emit (`AskUserQuestion` / `ask_user_question` / `askUserQuestion`).
|
|
* Why: this is the structured "pick an option" prompt whose full input the
|
|
* clients render as a live card. */
|
|
export function isAskUserQuestionTool(toolName: string | undefined): boolean {
|
|
return toolName?.replaceAll(/[^a-z0-9]/gi, '').toLowerCase() === 'askuserquestion'
|
|
}
|
|
|
|
const QUESTION_ANSWER_ENTER_INPUTS: ReadonlySet<string> = new Set([
|
|
'\r',
|
|
'\n',
|
|
'\r\n',
|
|
'\x1b[13u',
|
|
'\x1b[13;1u'
|
|
])
|
|
const QUESTION_ANSWER_DIGIT_INPUTS: ReadonlySet<string> = new Set('123456789')
|
|
|
|
export function isPotentialQuestionAnsweredSubmitInput(data: string): boolean {
|
|
return QUESTION_ANSWER_ENTER_INPUTS.has(data) || QUESTION_ANSWER_DIGIT_INPUTS.has(data)
|
|
}
|
|
|
|
function readSingleSelectOptionCount(interactivePrompt: string | undefined): number | null {
|
|
if (!interactivePrompt) {
|
|
return null
|
|
}
|
|
try {
|
|
const parsed = JSON.parse(interactivePrompt) as { questions?: unknown }
|
|
if (!Array.isArray(parsed.questions) || parsed.questions.length !== 1) {
|
|
return -1
|
|
}
|
|
const [question] = parsed.questions as { multiSelect?: unknown; options?: unknown }[]
|
|
if (!question || question.multiSelect === true || !Array.isArray(question.options)) {
|
|
return -1
|
|
}
|
|
return question.options.length
|
|
} catch {
|
|
// Why: malformed JSON can be a length-capped multi-question payload. It is
|
|
// not equivalent to an older hook omitting tool input, so fail closed.
|
|
return -1
|
|
}
|
|
}
|
|
|
|
/** True only when one keystroke is enough to finish the whole prompt.
|
|
* Why: digits merely advance multi-question prompts and toggle multi-selects;
|
|
* the synthetic "Type something" row also opens an editor instead of
|
|
* submitting. Without the prompt-shape gate those partial choices clear the
|
|
* waiting indicator while Claude is still blocked on more input. */
|
|
export function isQuestionAnsweredSubmitInput(
|
|
data: string,
|
|
interactivePrompt: string | undefined
|
|
): boolean {
|
|
if (!isPotentialQuestionAnsweredSubmitInput(data)) {
|
|
return false
|
|
}
|
|
const optionCount = readSingleSelectOptionCount(interactivePrompt)
|
|
if (optionCount === -1) {
|
|
return false
|
|
}
|
|
if (QUESTION_ANSWER_ENTER_INPUTS.has(data)) {
|
|
// Older hook payloads can omit tool input; Enter remains the conservative
|
|
// fallback because it is the ordinary submit path for a question.
|
|
return true
|
|
}
|
|
if (optionCount === null) {
|
|
return false
|
|
}
|
|
// Claude adds a final "Type something" row after the declared options.
|
|
// Only declared option numbers complete a single-select immediately.
|
|
return Number(data) <= optionCount
|
|
}
|