mirror of
https://github.com/wu736139669/hapi.git
synced 2026-10-08 19:19:42 +00:00
Attachments (Android B-M3f semantics ported verbatim): - HapiClient/Attachments/AttachmentPolicy — pure plan matrix (>4 MB recompressible image -> 2048 px JPEG q85 with .jpg rename, 50 MB hard reject, 192 MB image read cap, 512 px q80 previewUrl data-URL thumbs, data-URL parse/round-trip). - HapiClient/Attachments/ComposerAttachments — upload-on-pick tray over an AttachmentUploading seam (APIClient conforms): uploading/ready/failed chips, retained payload for retry, remove -> best-effort delete, mid-upload removal deletes the orphan on completion, consume() -> AttachmentMetadata with JPEG data-URL previewUrl, discardAllDetached + deinit orphan cleanup (Android onCleared analogue). - ChatInteractor: tray ownership, unsettled chips refuse the send with a notice, attachments-only sends post empty text, optimistic rows carry the metadata, appendDictatedText/postNotice/discardAttachments. - App: AttachmentPreparer (capped security-scoped reads, ImageIO downscale/encode with EXIF transform, HEIC-undecodable fallback), PhotosPicker multi (videos via FileRepresentation temp files), UIImagePickerController camera capture, fileImporter; composer chip row (thumb/spinner/tap-to-retry/remove) with attachment-aware send gating; user bubbles upgrade chips to off-main-decoded previewUrl thumbnails (web-sent attachments included). Dictation (Android B-M3ce port): - HapiProtocol/Models/VoiceApi — TranscriptionResponse, TranscriptionProvidersResponse, TranscriptionProviderInfo. - HapiClient/Endpoints/VoiceEndpoints — GET /api/voice/transcription/providers + multipart POST /api/voice/transcription (file/provider/mode/language, Android part order) over MultipartFormData; DictationTranscribing conformance. - HapiClient/Voice/DictationController — idle/starting/recording/ transcribing, transcribed/noProvider/error events, provider memoized (first standard-capable entry), appendTranscript port. - App: AVAudioRecorderDictation (m4a/AAC mono 44.1 kHz 96 kbps, session activate/deactivate), mic button + recording chip (elapsed + cancel), record-permission request via AVAudioApplication. Info.plist gains NSMicrophoneUsageDescription; the camera string now covers attachment capture (modern PhotosPicker needs no photo-library permission). Tests: policy matrix, tray over the real client with exact base64 upload bodies + gated in-flight scenarios, dictation controller suite with fake recorder/transport, voice endpoint request shapes, and the interactor attachment-send matrix transcribed from the Android VM tests (wire bodies byte-for-byte).
168 lines
5.8 KiB
Swift
168 lines
5.8 KiB
Swift
import HapiClient
|
|
import HapiProtocol
|
|
import HapiUI
|
|
import SwiftUI
|
|
|
|
// MARK: - User bubble
|
|
|
|
/// Operator prompt: right-aligned bubble. Whitespace is preserved and the
|
|
/// text is NOT rendered as markdown — matching the web user bubble and the
|
|
/// Android port. Image attachments with a `previewUrl` render as thumbnails
|
|
/// (decoded off-main; also covers web-sent attachments), everything else as
|
|
/// filename chips (`AttachmentPreviewView`, A-M3f); a failed optimistic row
|
|
/// gets a "Not delivered" hint that retries the send when the interaction
|
|
/// engine is present (A-M3a).
|
|
struct UserTextBlockView: View {
|
|
let block: UserTextBlock
|
|
|
|
@Environment(\.chatInteractions) private var interactions
|
|
|
|
var body: some View {
|
|
HStack(alignment: .bottom, spacing: 0) {
|
|
Spacer(minLength: 48)
|
|
VStack(alignment: .trailing, spacing: 2) {
|
|
VStack(alignment: .leading, spacing: 8) {
|
|
if !block.text.isEmpty {
|
|
Text(block.text)
|
|
.font(.subheadline)
|
|
.textSelection(.enabled)
|
|
}
|
|
if let attachments = block.attachments, !attachments.isEmpty {
|
|
VStack(alignment: .leading, spacing: 4) {
|
|
ForEach(attachments, id: \.id) { attachment in
|
|
AttachmentPreviewView(attachment: attachment)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
.padding(.horizontal, 14)
|
|
.padding(.vertical, 10)
|
|
.background(.tint.opacity(0.16))
|
|
.clipShape(
|
|
.rect(
|
|
topLeadingRadius: 16,
|
|
bottomLeadingRadius: 16,
|
|
bottomTrailingRadius: 4,
|
|
topTrailingRadius: 16
|
|
)
|
|
)
|
|
if block.status == "failed" {
|
|
if let interactions, let retryLocalId = block.localId {
|
|
Button {
|
|
interactions.retryFailedMessage(localId: retryLocalId)
|
|
} label: {
|
|
Text("Not delivered — tap to retry")
|
|
.font(.caption2)
|
|
.foregroundStyle(.red)
|
|
.padding(.trailing, 4)
|
|
}
|
|
.buttonStyle(.plain)
|
|
} else {
|
|
Text("Not delivered")
|
|
.font(.caption2)
|
|
.foregroundStyle(.red)
|
|
.padding(.trailing, 4)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// MARK: - Agent prose
|
|
|
|
/// Assistant prose: full-width markdown through the shared M2e renderer.
|
|
struct AgentTextBlockView: View {
|
|
let block: AgentTextBlock
|
|
|
|
var body: some View {
|
|
MarkdownView(markdown: block.text)
|
|
.frame(maxWidth: .infinity, alignment: .leading)
|
|
}
|
|
}
|
|
|
|
/// Extended thinking: collapsed to a subdued one-liner, expanding in place to
|
|
/// the full reasoning markdown (still subdued — it is meta-content).
|
|
struct AgentReasoningBlockView: View {
|
|
let block: AgentReasoningBlock
|
|
@State private var expanded = false
|
|
|
|
var body: some View {
|
|
VStack(alignment: .leading, spacing: 4) {
|
|
Button {
|
|
withAnimation(.easeInOut(duration: 0.15)) {
|
|
expanded.toggle()
|
|
}
|
|
} label: {
|
|
Label(
|
|
expanded ? "Reasoning" : "Reasoning…",
|
|
systemImage: expanded ? "chevron.down" : "chevron.right"
|
|
)
|
|
.font(.caption)
|
|
.foregroundStyle(.secondary)
|
|
}
|
|
.buttonStyle(.plain)
|
|
if expanded {
|
|
MarkdownView(markdown: block.text)
|
|
.opacity(0.75)
|
|
.padding(.leading, 8)
|
|
}
|
|
}
|
|
.frame(maxWidth: .infinity, alignment: .leading)
|
|
}
|
|
}
|
|
|
|
// MARK: - Event rows
|
|
|
|
/// Compact centered status row for the `'event'` family (limits, compaction,
|
|
/// switches, errors, turn duration, …); wording via `eventPresentation`.
|
|
struct AgentEventBlockView: View {
|
|
let block: AgentEventBlock
|
|
|
|
var body: some View {
|
|
let presentation = eventPresentation(block.event)
|
|
Text([presentation.icon, presentation.text].compactMap { $0 }.joined(separator: " "))
|
|
.font(.caption)
|
|
.foregroundStyle(.secondary)
|
|
.multilineTextAlignment(.center)
|
|
.lineLimit(3)
|
|
.frame(maxWidth: .infinity)
|
|
.padding(.horizontal, 24)
|
|
.padding(.vertical, 2)
|
|
}
|
|
}
|
|
|
|
// MARK: - CLI output
|
|
|
|
/// `<local-command-stdout>` / slash-command echo: terminal-styled monospace
|
|
/// panel (no header chrome — this is transcript, not a code sample).
|
|
struct CliOutputBlockView: View {
|
|
let block: CliOutputBlock
|
|
|
|
var body: some View {
|
|
TerminalTextView(text: block.text)
|
|
}
|
|
}
|
|
|
|
/// Shared terminal-look panel (cli output + tool stdout).
|
|
struct TerminalTextView: View {
|
|
let text: String
|
|
var isError = false
|
|
|
|
@Environment(\.hapiTheme) private var theme
|
|
|
|
var body: some View {
|
|
ScrollView(.horizontal, showsIndicators: false) {
|
|
Text(text)
|
|
.font(.system(size: 12, design: .monospaced))
|
|
.foregroundStyle(isError ? AnyShapeStyle(theme.danger) : AnyShapeStyle(theme.textPrimary))
|
|
.textSelection(.enabled)
|
|
.padding(.horizontal, 12)
|
|
.padding(.vertical, 8)
|
|
}
|
|
.frame(maxWidth: .infinity, alignment: .leading)
|
|
.background(theme.codeBackground)
|
|
.clipShape(RoundedRectangle(cornerRadius: 10, style: .continuous))
|
|
}
|
|
}
|