Compare commits
3
Commits
9098fee32a
..
master
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a68caac378 | ||
|
|
b743523fd5 | ||
|
|
ee845c9fa3 |
@@ -627,6 +627,25 @@ messages/DOM grow with explicit older loads and live updates. Offscreen web rows
|
||||
use CSS `content-visibility: auto`, which skips rendering work while retaining
|
||||
chronological DOM, selection, find and accessibility; it is not DOM virtualization.
|
||||
|
||||
Every room message, including protected tool rows and `activity.queuedMessages`,
|
||||
has a string `id`, `role`, `content`, and ISO-8601 `createdAt`. Privacy filtering
|
||||
retains this envelope and tool lifecycle metadata (`kind`, `toolCallId`,
|
||||
`toolName`, `entryId`, `status`, and available `startedAt`/`completedAt`). Protected
|
||||
tools use their public tool name as `content`; private arguments, previews, and
|
||||
errors are withheld. Result-only pages may omit initiation metadata.
|
||||
|
||||
Historical entries without a known time use `1970-01-01T00:00:00.000Z` as an
|
||||
unknown-time sentinel. For compatibility with older partial responses, clients
|
||||
may recover missing/invalid `createdAt` from `metadata.startedAt`, then
|
||||
`metadata.completedAt`, or use that sentinel; never substitute the current time.
|
||||
Older redacted tool rows containing only `id`, `role`, and `name` can retain their
|
||||
identity with a tool-name label until a complete upsert arrives. The web client
|
||||
uses the same normalization for REST, WebSocket, and queued activity, retains
|
||||
known times across partial upserts, and orders by time, numeric `entryId` (when
|
||||
present, before absent), then stable `id`. Unknown times display as “Earlier”
|
||||
without a clock time. Invalid identities or non-tool message bodies reject the
|
||||
page before advancing its replay cursor; timestamps never replace cursors.
|
||||
|
||||
### `POST /v1/agent/messages`
|
||||
|
||||
Body: `{ "content": "Check the oven", "requestId": "client-generated-uuid" }`.
|
||||
|
||||
@@ -326,6 +326,14 @@ with `metadata.kind: "tool_call"`, matching Sybil's tool renderer. REST pages an
|
||||
socket messages are upserts keyed by stable `id`. Save each returned cursor after
|
||||
applying its entire frame, even when it contains no visible messages.
|
||||
|
||||
Both message frames and queued activity use the required message envelope and
|
||||
historical timestamp compatibility rules in [REST room history](./rest.md#get-v1agentmessages).
|
||||
Protected tool redaction preserves `createdAt`, a safe string `content`, and
|
||||
available lifecycle metadata; it does not remove the row's identity or replay
|
||||
metadata. Partial tool results may omit `args`/`startedAt`; merge them without
|
||||
losing a known creation time or downgrading a completed tool on replay. Validate
|
||||
and normalize all rows before applying a frame or advancing its cursor.
|
||||
|
||||
Clients may send `{ "type": "ping" }` (receiving `{ "type": "pong" }`) or
|
||||
`{ "type": "subscribe", "after": "44" }` to change the replay cursor. Transport
|
||||
ping/pong heartbeats detect dead connections. Other writes belong on REST.
|
||||
|
||||
@@ -15,7 +15,9 @@ let package = Package(
|
||||
targets: ["Sybil"]),
|
||||
],
|
||||
dependencies: [
|
||||
.package(url: "https://github.com/gonzalezreal/swift-markdown-ui.git", from: "2.4.1")
|
||||
.package(url: "https://github.com/gonzalezreal/swift-markdown-ui.git", from: "2.4.1"),
|
||||
// Use MarkdownUI's existing parser to remove Agent image/HTML nodes structurally.
|
||||
.package(url: "https://github.com/swiftlang/swift-cmark", from: "0.7.1")
|
||||
],
|
||||
targets: [
|
||||
// Targets are the basic building blocks of a package, defining a module or a test suite.
|
||||
@@ -23,7 +25,9 @@ let package = Package(
|
||||
.target(
|
||||
name: "Sybil",
|
||||
dependencies: [
|
||||
.product(name: "MarkdownUI", package: "swift-markdown-ui")
|
||||
.product(name: "MarkdownUI", package: "swift-markdown-ui"),
|
||||
.product(name: "cmark-gfm", package: "swift-cmark"),
|
||||
.product(name: "cmark-gfm-extensions", package: "swift-cmark")
|
||||
],
|
||||
resources: [.process("Resources")]),
|
||||
.testTarget(
|
||||
|
||||
@@ -0,0 +1,87 @@
|
||||
import Foundation
|
||||
import MarkdownUI
|
||||
import cmark_gfm
|
||||
import cmark_gfm_extensions
|
||||
|
||||
/// Agent images come only from validated attachment descriptors. Rewrite parsed nodes,
|
||||
/// including reference/nested images, so neither MarkdownUI image loader receives a URL.
|
||||
enum AgentMessageMarkdown {
|
||||
static func content(_ source: String) -> MarkdownContent {
|
||||
cmark_gfm_core_extensions_ensure_registered()
|
||||
guard let parser = cmark_parser_new(CMARK_OPT_DEFAULT) else { return literal(source) }
|
||||
defer { cmark_parser_free(parser) }
|
||||
for name in ["table", "strikethrough", "autolink", "tasklist"] {
|
||||
if let ext = cmark_find_syntax_extension(name) { cmark_parser_attach_syntax_extension(parser, ext) }
|
||||
}
|
||||
source.withCString { cmark_parser_feed(parser, $0, source.utf8.count) }
|
||||
guard let document = cmark_parser_finish(parser) else { return literal(source) }
|
||||
defer { cmark_node_free(document) }
|
||||
stripImagesAndHTML(document)
|
||||
guard let markdown = cmark_render_commonmark(document, CMARK_OPT_DEFAULT, 0) else { return literal(source) }
|
||||
defer { free(markdown) }
|
||||
return MarkdownContent(String(cString: markdown))
|
||||
}
|
||||
|
||||
private static func literal(_ source: String) -> MarkdownContent {
|
||||
MarkdownContent { Paragraph { source } }
|
||||
}
|
||||
|
||||
private static func stripImagesAndHTML(_ parent: UnsafeMutablePointer<cmark_node>) {
|
||||
var child = cmark_node_first_child(parent)
|
||||
while let node = child {
|
||||
child = cmark_node_next(node)
|
||||
let type = cmark_node_get_type(node)
|
||||
if type == CMARK_NODE_IMAGE || type == CMARK_NODE_HTML_INLINE || type == CMARK_NODE_HTML_BLOCK {
|
||||
let text = type == CMARK_NODE_IMAGE ? altText(node) : htmlText(cmark_node_get_literal(node).map { String(cString: $0) } ?? "")
|
||||
let replacement = cmark_node_new(type == CMARK_NODE_HTML_BLOCK ? CMARK_NODE_PARAGRAPH : CMARK_NODE_TEXT)!
|
||||
if type == CMARK_NODE_HTML_BLOCK {
|
||||
let inline = cmark_node_new(CMARK_NODE_TEXT)!
|
||||
// cmark includes the HTML block's terminating newline in its literal.
|
||||
// It is a block delimiter, not an extra line in the visible alt text.
|
||||
cmark_node_set_literal(inline, text.trimmingCharacters(in: .newlines))
|
||||
cmark_node_append_child(replacement, inline)
|
||||
} else {
|
||||
cmark_node_set_literal(replacement, text)
|
||||
}
|
||||
cmark_node_replace(node, replacement)
|
||||
cmark_node_free(node)
|
||||
} else {
|
||||
stripImagesAndHTML(node)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private static func altText(_ parent: UnsafeMutablePointer<cmark_node>) -> String {
|
||||
var result = "", child = cmark_node_first_child(parent)
|
||||
while let node = child {
|
||||
let type = cmark_node_get_type(node)
|
||||
if type == CMARK_NODE_TEXT || type == CMARK_NODE_CODE {
|
||||
result += cmark_node_get_literal(node).map { String(cString: $0) } ?? ""
|
||||
} else if type == CMARK_NODE_SOFTBREAK || type == CMARK_NODE_LINEBREAK {
|
||||
result += " "
|
||||
} else if type != CMARK_NODE_HTML_INLINE {
|
||||
result += altText(node)
|
||||
}
|
||||
child = cmark_node_next(node)
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
||||
private static func htmlText(_ source: String) -> String {
|
||||
// HTML is never rendered. Retain ordinary text and img alt attributes as text
|
||||
// nodes; quoted '>' characters cannot expose the rest of an image attribute.
|
||||
let tags = try! NSRegularExpression(pattern: #"(?s)<(?:[^>"']|"[^"]*"|'[^']*')*>"#)
|
||||
let alt = try! NSRegularExpression(pattern: #"(?is)^<img\b.*?\s+alt\s*=\s*(?:"([^"]*)"|'([^']*)'|([^\s>]+))"#)
|
||||
var result = source
|
||||
for tag in tags.matches(in: source, range: NSRange(source.startIndex..., in: source)).reversed() {
|
||||
let range = Range(tag.range, in: source)!
|
||||
let value = String(source[range])
|
||||
let match = alt.firstMatch(in: value, range: NSRange(value.startIndex..., in: value))
|
||||
let label = match.flatMap { match in
|
||||
(1...3).compactMap { Range(match.range(at: $0), in: value).map { String(value[$0]) } }.first
|
||||
} ?? ""
|
||||
result.replaceSubrange(Range(tag.range, in: result)!, with: label)
|
||||
}
|
||||
return result
|
||||
}
|
||||
}
|
||||
@@ -46,7 +46,10 @@ actor SybilAPIClient: SybilAPIClienting, AgentAPIClienting, AgentPushAPIClientin
|
||||
guard value.type == "persistent-agent", value.protocol == "pi-room.v1" else {
|
||||
throw AgentFailure(message: "Unsupported Agent room protocol.")
|
||||
}
|
||||
if configuration.authToken?.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty != false { value.capabilities?.attachments = nil }
|
||||
if configuration.authToken?.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty != false {
|
||||
value.capabilities?.attachments = nil
|
||||
value.capabilities?.assistantImages = nil
|
||||
}
|
||||
return value
|
||||
}
|
||||
|
||||
|
||||
@@ -174,9 +174,15 @@ struct AgentAttachmentCard: View {
|
||||
if attachment.kind == .image {
|
||||
ZStack {
|
||||
SybilTheme.surface
|
||||
if let image { Image(uiImage: image).resizable().scaledToFit() }
|
||||
if let image {
|
||||
Image(uiImage: image).resizable().scaledToFit()
|
||||
.accessibilityLabel("Image: \(attachment.filename)")
|
||||
.accessibilityIdentifier("agent-image-preview")
|
||||
}
|
||||
else { Image(systemName: "photo").foregroundStyle(SybilTheme.textMuted) }
|
||||
}.frame(height: 180).clipped()
|
||||
.accessibilityElement(children: .contain)
|
||||
.accessibilityIdentifier("agent-image-frame")
|
||||
}
|
||||
if let text {
|
||||
Text(text).font(.system(.caption, design: .monospaced)).lineLimit(6)
|
||||
|
||||
@@ -44,14 +44,24 @@ struct AgentAttachmentCapabilities: Codable, Equatable, Sendable {
|
||||
}
|
||||
}
|
||||
|
||||
struct AgentAssistantImageCapabilities: Decodable, Equatable, Sendable {
|
||||
var version: Int
|
||||
var supported: Bool { version == 1 }
|
||||
}
|
||||
|
||||
struct AgentCapabilities: Decodable, Sendable {
|
||||
var attachments: AgentAttachmentCapabilities?
|
||||
init(attachments: AgentAttachmentCapabilities? = nil) { self.attachments = attachments }
|
||||
private enum CodingKeys: String, CodingKey { case attachments }
|
||||
var assistantImages: AgentAssistantImageCapabilities?
|
||||
init(attachments: AgentAttachmentCapabilities? = nil, assistantImages: AgentAssistantImageCapabilities? = nil) {
|
||||
self.attachments = attachments
|
||||
self.assistantImages = assistantImages
|
||||
}
|
||||
private enum CodingKeys: String, CodingKey { case attachments, assistantImages }
|
||||
init(from decoder: Decoder) throws {
|
||||
let values = try decoder.container(keyedBy: CodingKeys.self)
|
||||
// Unknown versions or malformed future capabilities must not break text chat.
|
||||
attachments = try? values.decode(AgentAttachmentCapabilities.self, forKey: .attachments)
|
||||
assistantImages = try? values.decode(AgentAssistantImageCapabilities.self, forKey: .assistantImages)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -91,13 +101,34 @@ struct AgentAttachment: Codable, Hashable, Identifiable, Sendable {
|
||||
|
||||
extension Message {
|
||||
var agentAttachments: [AgentAttachment] {
|
||||
guard let entries = metadata?.objectValue?["agentAttachments"]?.arrayValue else { return [] }
|
||||
return entries.compactMap {
|
||||
guard let data = try? JSONEncoder().encode($0),
|
||||
guard role == .user || role == .assistant,
|
||||
let info = metadata?.objectValue,
|
||||
let entries = info["agentAttachments"]?.arrayValue else { return [] }
|
||||
if role == .assistant {
|
||||
guard info["kind"]?.stringValue == "message", info["status"]?.stringValue == "complete",
|
||||
entries.count <= 8 else { return [] }
|
||||
}
|
||||
let attachments: [AgentAttachment] = entries.compactMap { entry in
|
||||
// Inspect the original JSON before Codable can discard unknown fields. Output
|
||||
// descriptors are deliberately path/URL-free; legacy user uploads stay compatible.
|
||||
if role == .assistant {
|
||||
let safeFields: Set<String> = ["id", "kind", "filename", "mimeType", "sizeBytes", "sha256"]
|
||||
guard let fields = entry.objectValue, Set(fields.keys) == safeFields,
|
||||
fields["kind"]?.stringValue == "image" else { return nil }
|
||||
}
|
||||
guard let data = try? JSONEncoder().encode(entry),
|
||||
let attachment = try? JSONDecoder().decode(AgentAttachment.self, from: data),
|
||||
(try? attachment.validate()) != nil else { return nil }
|
||||
return attachment
|
||||
}
|
||||
if role == .assistant {
|
||||
// Reject the entire output set, including partially invalid arrays. The
|
||||
// count and per-image bounds above also bound this aggregate calculation.
|
||||
guard attachments.count == entries.count,
|
||||
Set(attachments.map(\.id)).count == attachments.count,
|
||||
attachments.reduce(0, { $0 + $1.sizeBytes }) <= 32 * 1024 * 1024 else { return [] }
|
||||
}
|
||||
return attachments
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -239,7 +239,7 @@ struct AgentPresentation {
|
||||
private(set) var suppressed = false
|
||||
private(set) var busySince: Date?
|
||||
private var seenTools: Set<String> = []
|
||||
static let quietTools: Set<String> = ["user_message", "notify_parent", "clock_wait", "event_decision"]
|
||||
static let quietTools: Set<String> = ["user_message", "output_image", "notify_parent", "clock_wait", "event_decision"]
|
||||
|
||||
mutating func receive(_ event: AgentEvent, before: AgentRoomState, after: AgentRoomState, replay: Bool, now: Date) {
|
||||
switch event {
|
||||
@@ -249,7 +249,7 @@ struct AgentPresentation {
|
||||
.sorted { AgentCursor.less($0.agentEntryCursor ?? "0", $1.agentEntryCursor ?? "0") }
|
||||
if !replay {
|
||||
for message in fresh {
|
||||
if message.isAgentPublicReply && !message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty { suppressed = true }
|
||||
if message.isAgentPublicReply && (!message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty || !message.agentAttachments.isEmpty) { suppressed = true }
|
||||
else if message.role == .user { suppressed = false }
|
||||
else if message.toolCallMetadata?.status == "initiated",
|
||||
!Self.quietTools.contains(message.toolCallMetadata?.toolName ?? ""), !seenTools.contains(message.agentToolID) { suppressed = false }
|
||||
|
||||
@@ -275,7 +275,9 @@ private struct AgentMessageRow: View {
|
||||
ForEach(message.agentAttachments) { attachment in
|
||||
AgentAttachmentCard(attachment: attachment, room: room)
|
||||
}
|
||||
if !message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty || message.agentAttachments.isEmpty {
|
||||
MessageBubble(message: message, isSending: false, streamingAssistantPresentation: nil, isForking: false, onFork: nil, agentStyle: true)
|
||||
}
|
||||
HStack(spacing: 6) {
|
||||
Text(own ? "You" : "Sybil")
|
||||
Text(message.createdAt, style: .time)
|
||||
|
||||
@@ -223,14 +223,14 @@ struct MessageBubble: View {
|
||||
)
|
||||
}
|
||||
|
||||
if isStreamingAssistant {
|
||||
if isStreamingAssistant && !agentStyle {
|
||||
StreamingAssistantContentView(
|
||||
content: message.content,
|
||||
isSending: isSending,
|
||||
presentation: matchingStreamingAssistantPresentation
|
||||
)
|
||||
} else if !message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty {
|
||||
SybilMessageText(content: message.content, format: isUser ? .literal : .markdown)
|
||||
SybilMessageText(content: message.content, format: isUser ? .literal : .markdown, agentStyle: agentStyle)
|
||||
}
|
||||
}
|
||||
.padding(.horizontal, isUser || agentStyle ? 14 : 2)
|
||||
|
||||
@@ -7,6 +7,7 @@ struct SybilMessageText: View {
|
||||
enum Format { case literal, markdown }
|
||||
var content: String
|
||||
var format: Format
|
||||
var agentStyle = false
|
||||
|
||||
static func literalContent(_ text: String) -> MarkdownContent {
|
||||
// Pasted CRLF/CR and blank lines containing spaces or tabs have the same
|
||||
@@ -31,7 +32,7 @@ struct SybilMessageText: View {
|
||||
#if DEBUG
|
||||
let _ = AgentRenderDiagnostics.record("messageTextBuild")
|
||||
#endif
|
||||
Markdown(format == .literal ? Self.literalContent(content) : MarkdownContent(content))
|
||||
Markdown(format == .literal ? Self.literalContent(content) : agentStyle ? AgentMessageMarkdown.content(content) : MarkdownContent(content))
|
||||
.tint(SybilTheme.primary)
|
||||
.foregroundStyle(format == .literal ? SybilTheme.text : SybilTheme.text.opacity(0.95))
|
||||
.markdownTheme(.sybilReadable)
|
||||
|
||||
@@ -14,10 +14,15 @@ private func sampleAttachment(_ id: String = "opaque-server-id", data: Data = or
|
||||
AgentAttachment(id: id, kind: .file, filename: name, mimeType: "application/octet-stream", sizeBytes: data.count,
|
||||
sha256: SHA256.hash(data: data).map { String(format: "%02x", $0) }.joined(), workspacePath: "/runtime/provided/\(name)")
|
||||
}
|
||||
private func descriptorData(capability: Bool = true) throws -> Data {
|
||||
private func descriptorData(capability: Bool = true, assistantImages: Bool = false) throws -> Data {
|
||||
var object: [String: Any] = ["id": "root", "title": "Sybil", "type": "persistent-agent", "model": "fixture", "protocol": "pi-room.v1", "websocket": "/v1/agent/ws",
|
||||
"activity": ["state": "idle", "isThinking": false, "queued": 0, "backgroundWorkers": 0, "tools": [], "queuedMessages": []]]
|
||||
if capability { object["capabilities"] = ["attachments": try JSONSerialization.jsonObject(with: JSONEncoder().encode(attachmentLimits)), "future": true] }
|
||||
if assistantImages {
|
||||
var capabilities = object["capabilities"] as? [String: Any] ?? [:]
|
||||
capabilities["assistantImages"] = ["version": 1]
|
||||
object["capabilities"] = capabilities
|
||||
}
|
||||
object["unknown"] = ["additive": true]
|
||||
return try JSONSerialization.data(withJSONObject: object)
|
||||
}
|
||||
@@ -124,6 +129,126 @@ private func requestBytes(_ request: URLRequest) -> Data {
|
||||
}
|
||||
|
||||
@Suite(.serialized) struct AgentAttachmentTests {
|
||||
@Test @MainActor func assistantCapabilityDoesNotAdmitInputAndRequiresToken() async throws {
|
||||
AttachmentURLProtocol.install { request in
|
||||
#expect(request.url!.path == "/api/v1/agent") // Never upload or submit references.
|
||||
return (200, [:], try descriptorData(capability: false, assistantImages: true))
|
||||
}
|
||||
let session = attachmentSession(); defer { session.invalidateAndCancel() }
|
||||
for token in [nil, " ", "synthetic-test"] {
|
||||
let client = SybilAPIClient(configuration: .init(baseURL: URL(string: "https://fixture.invalid/api")!, authToken: token), session: session)
|
||||
let descriptor = try await client.agentDescriptor()
|
||||
#expect(descriptor.capabilities?.attachments == nil)
|
||||
#expect((descriptor.capabilities?.assistantImages?.supported == true) == (token == "synthetic-test"))
|
||||
let draft = AgentAttachmentDraft()
|
||||
draft.configure(client: client, storage: nil); draft.updateCapability(descriptor.capabilities?.attachments)
|
||||
#expect(!draft.supportsAttachments)
|
||||
#expect(draft.add(filename: "original.bin") { .init(filename: "original.bin", mimeType: "application/octet-stream", data: originalBytes) } == nil)
|
||||
await #expect(throws: AgentAttachmentIssue.self) { try await client.agentUpload(file: .init(filename: "original.bin", mimeType: "application/octet-stream", data: originalBytes), uploadID: UUID().uuidString) }
|
||||
await #expect(throws: AgentAttachmentIssue.self) { try await client.agentSubmit(AgentSubmission(content: "", requestID: "output-only", attachments: [sampleAttachment()])) }
|
||||
}
|
||||
for json in [#"{"assistantImages":{"version":2}}"#, #"{"assistantImages":{"version":"future"}}"#] {
|
||||
#expect(try JSONDecoder().decode(AgentCapabilities.self, from: Data(json.utf8)).assistantImages?.supported != true)
|
||||
}
|
||||
}
|
||||
|
||||
@Test func assistantDescriptorsRequireCompletedAssistantImageAndSafeFields() throws {
|
||||
let image = AgentAttachment(id: "output-image", kind: .image, filename: "landscape.png", mimeType: "image/png", sizeBytes: 12, sha256: String(repeating: "a", count: 64))
|
||||
var row = Message(id: "outbound:1", createdAt: Date(), role: .assistant, content: "", metadata: .object([
|
||||
"kind": .string("message"), "status": .string("complete"), "agentAttachments": .array([image.metadataValue])]))
|
||||
#expect(row.agentAttachments == [image])
|
||||
for role in [MessageRole.system, .tool] {
|
||||
var wrong = row; wrong.role = role
|
||||
#expect(wrong.agentAttachments.isEmpty)
|
||||
}
|
||||
for (key, value) in [("kind", "tool_call"), ("kind", "other"), ("status", "queued"), ("status", "streaming")] {
|
||||
var wrong = row, fields = row.metadata!.objectValue!
|
||||
fields[key] = .string(value); wrong.metadata = .object(fields)
|
||||
#expect(wrong.agentAttachments.isEmpty)
|
||||
}
|
||||
var descriptors: [JSONValue] = [sampleAttachment().metadataValue]
|
||||
for key in ["workspacePath", "sourcePath", "privatePath", "url", "sourceURL", "downloadUrl", "external", "future"] {
|
||||
var fields = image.metadataValue.objectValue!; fields[key] = .string("/private/synthetic.png")
|
||||
descriptors.append(.object(fields))
|
||||
}
|
||||
for (key, value) in [("filename", "../private.png"), ("filename", "https://example.invalid/a.png"), ("mimeType", "image/svg+xml"), ("sha256", "bad")] {
|
||||
var fields = image.metadataValue.objectValue!; fields[key] = .string(value)
|
||||
descriptors.append(.object(fields))
|
||||
}
|
||||
for descriptor in descriptors {
|
||||
row.metadata = .object(["kind": .string("message"), "status": .string("complete"), "agentAttachments": .array([descriptor])])
|
||||
#expect(row.agentAttachments.isEmpty)
|
||||
row.metadata = .object(["kind": .string("message"), "status": .string("complete"), "agentAttachments": .array([image.metadataValue, descriptor])])
|
||||
#expect(row.agentAttachments.isEmpty) // No valid prefix from an invalid output set.
|
||||
}
|
||||
let maximum = (0..<8).map { index in
|
||||
var item = image; item.id = "image-\(index)"; item.sizeBytes = 4 * 1024 * 1024
|
||||
return item
|
||||
}
|
||||
row.metadata = .object(["kind": .string("message"), "status": .string("complete"), "agentAttachments": .array(maximum.map(\.metadataValue))])
|
||||
#expect(row.agentAttachments == maximum) // Exactly eight IDs and 32 MiB.
|
||||
let tooMany = (0..<9).map { index in
|
||||
var item = image; item.id = "image-\(index)"
|
||||
return item
|
||||
}
|
||||
var tooLarge = maximum; tooLarge[0].sizeBytes += 1
|
||||
for invalid in [tooMany, [image, image], tooLarge] {
|
||||
row.role = .assistant
|
||||
row.metadata = .object(["kind": .string("message"), "status": .string("complete"), "agentAttachments": .array(invalid.map(\.metadataValue))])
|
||||
#expect(row.agentAttachments.isEmpty)
|
||||
row.role = .user
|
||||
#expect(row.agentAttachments == invalid) // These new output limits do not change legacy input parsing.
|
||||
}
|
||||
row.role = .user
|
||||
row.metadata = .object(["agentAttachments": .array([sampleAttachment().metadataValue])])
|
||||
#expect(row.agentAttachments == [sampleAttachment()])
|
||||
}
|
||||
|
||||
@Test @MainActor func imageOnlyAssistantLiveAndHistoryUseSameMergeAndAuthenticatedLoader() async throws {
|
||||
let png = try #require(UIGraphicsImageRenderer(size: CGSize(width: 24, height: 16)).image { context in
|
||||
UIColor.systemTeal.setFill(); context.fill(CGRect(x: 0, y: 0, width: 24, height: 16))
|
||||
}.pngData())
|
||||
let attachment = AgentAttachment(id: "output/opaque", kind: .image, filename: "landscape.png", mimeType: "image/png", sizeBytes: png.count,
|
||||
sha256: SHA256.hash(data: png).map { String(format: "%02x", $0) }.joined())
|
||||
let row = Message(id: "outbound:1", createdAt: Date(timeIntervalSince1970: 1), role: .assistant, content: "", metadata: .object([
|
||||
"kind": .string("message"), "status": .string("complete"), "entryId": .number(1), "agentAttachments": .array([attachment.metadataValue])]))
|
||||
let page = AgentPage(conversationId: "fixture-root", messages: [row], cursor: "1", hasMore: false)
|
||||
let encoder = JSONEncoder(); encoder.dateEncodingStrategy = .iso8601
|
||||
let bytes = try encoder.encode(page)
|
||||
var envelope = try JSONSerialization.jsonObject(with: bytes) as! [String: Any]; envelope["type"] = "messages"
|
||||
let decodedEvent = try AgentEvent.decode(JSONSerialization.data(withJSONObject: envelope))
|
||||
let event = try #require(decodedEvent)
|
||||
let room = SybilAgentRoom(); defer { room.stop() }
|
||||
try room.receive(event); room.flush()
|
||||
var history = AgentRoomState()
|
||||
try history.apply(AgentCoding.decoder().decode(AgentPage.self, from: bytes))
|
||||
// Replay must not duplicate a completed output; no current capability is needed.
|
||||
try room.receive(event); room.flush()
|
||||
#expect(AgentTranscript(messages: room.messages).displayed == AgentTranscript(messages: history.messages).displayed)
|
||||
#expect(room.messages.count == 1); #expect(room.messages[0].content.isEmpty)
|
||||
#expect(room.messages[0].agentAttachments == [attachment])
|
||||
var presentation = AgentPresentation()
|
||||
presentation.receive(event, before: AgentRoomState(), after: history, replay: false, now: Date())
|
||||
#expect(presentation.suppressed)
|
||||
|
||||
AttachmentURLProtocol.install { request in
|
||||
#expect(request.url!.absoluteString == "https://fixture.invalid/api/v1/agent/attachments/output%2Fopaque/content")
|
||||
#expect(request.httpMethod == "GET")
|
||||
#expect(request.value(forHTTPHeaderField: "Authorization") == "Bearer synthetic-test")
|
||||
return (200, ["Content-Length": String(png.count)], png)
|
||||
}
|
||||
let session = attachmentSession(); defer { session.invalidateAndCancel() }
|
||||
let client = SybilAPIClient(configuration: .init(baseURL: URL(string: "https://fixture.invalid/api")!, authToken: "synthetic-test"), session: session)
|
||||
let downloads = AgentAttachmentDownloads()
|
||||
#expect(try await downloads.data(for: attachment, client: client) == png)
|
||||
AttachmentURLProtocol.install { _ in Issue.record("Verified output should be cached"); return (500, [:], Data()) }
|
||||
#expect(try await downloads.data(for: attachment, client: client) == png)
|
||||
AttachmentURLProtocol.install { _ in (200, [:], Data(repeating: 0, count: png.count)) }
|
||||
await #expect(throws: AgentAttachmentIssue.self) { try await client.agentDownload(attachment) }
|
||||
let unauthenticated = SybilAPIClient(configuration: .init(baseURL: URL(string: "https://fixture.invalid/api")!), session: session)
|
||||
await #expect(throws: AgentAttachmentIssue.self) { try await unauthenticated.agentDownload(attachment) }
|
||||
}
|
||||
|
||||
@Test func additiveCapabilityAndDistinctMetadata() throws {
|
||||
let old = try AgentCoding.decoder().decode(AgentDescriptor.self, from: descriptorData(capability: false))
|
||||
#expect(old.capabilities == nil)
|
||||
|
||||
@@ -347,6 +347,33 @@ struct AgentTests {
|
||||
#expect(presentation.isTyping(now: now.addingTimeInterval(7.3)))
|
||||
}
|
||||
|
||||
@Test func outputImageActivityKeepsImageReplyTypingSuppressed() throws {
|
||||
var presentation = AgentPresentation(), state = AgentRoomState()
|
||||
let now = Date(timeIntervalSince1970: 100)
|
||||
state.activity.isThinking = true
|
||||
presentation.sent(now: now, activity: state.activity)
|
||||
#expect(presentation.isTyping(now: now.addingTimeInterval(0.3)))
|
||||
let image = AgentAttachment(id: "image", kind: .image, filename: "image.png", mimeType: "image/png", sizeBytes: 12, sha256: String(repeating: "a", count: 64))
|
||||
var reply = agentMessage("image-reply", entry: "1", info: ["status": .string("complete"), "agentAttachments": .array([image.metadataValue])])
|
||||
reply.content = ""
|
||||
let page = agentPage([reply], cursor: "1")
|
||||
var after = state; try after.apply(page)
|
||||
presentation.receive(.messages(page), before: state, after: after, replay: false, now: now.addingTimeInterval(1))
|
||||
state = after
|
||||
#expect(presentation.suppressed)
|
||||
|
||||
after.activity.tools = [.init(id: "output-activity", name: "output_image", status: "initiated")]
|
||||
presentation.receive(.activity("root", after.activity), before: state, after: after, replay: false, now: now.addingTimeInterval(2))
|
||||
state = after
|
||||
#expect(!presentation.isTyping(now: now.addingTimeInterval(3)))
|
||||
|
||||
let tool = agentPage([agentMessage("output-tool", entry: "2", role: .tool, info: ["toolName": .string("output_image"), "status": .string("initiated")])], cursor: "2")
|
||||
try after.apply(tool)
|
||||
presentation.receive(.messages(tool), before: state, after: after, replay: false, now: now.addingTimeInterval(4))
|
||||
#expect(presentation.suppressed)
|
||||
#expect(!presentation.isTyping(now: now.addingTimeInterval(5)))
|
||||
}
|
||||
|
||||
@Test func socketURLAndAuthentication() throws {
|
||||
let config = APIConfiguration(baseURL: URL(string: "https://sybil.bajor.cloud/api/?accidental=query")!, authToken: " token ")
|
||||
#expect(try config.agentWebSocketURL().absoluteString == "wss://sybil.bajor.cloud/api/v1/agent/ws")
|
||||
|
||||
@@ -6,6 +6,57 @@ import UIKit
|
||||
|
||||
@Suite @MainActor
|
||||
struct MessagePresentationTests {
|
||||
@Test func agentMarkdownKeepsAltAndFormattingWithoutImageOrHTMLNodes() {
|
||||
let source = """
|
||||
**Caption** 
|
||||
|
||||
![Reference landscape][photo]
|
||||
|
||||
[](https://example.invalid)
|
||||
|
||||
> ](data:image/png;base64,AAAA)
|
||||
|
||||
<picture><source srcset="https://images.invalid/source.png"><img src="https://images.invalid/html.png" alt="HTML landscape" title="a > b"></picture>
|
||||
|
||||
[Useful link](https://example.invalid)
|
||||
|
||||
[photo]: https://images.invalid/reference.png
|
||||
"""
|
||||
let content = AgentMessageMarkdown.content(source)
|
||||
let html = content.renderHTML(), plain = content.renderPlainText()
|
||||
for label in ["Inline landscape", "Reference landscape", "Linked landscape", "Nested inner", "HTML landscape"] {
|
||||
#expect(plain.contains(label))
|
||||
}
|
||||
#expect(!html.contains("<img")); #expect(!html.contains("<picture")); #expect(!html.contains("<source"))
|
||||
#expect(!html.contains("images.invalid")); #expect(!html.contains("/private/"))
|
||||
#expect(html.contains("<strong>Caption</strong>"))
|
||||
#expect(html.contains(#"href="https://example.invalid""#))
|
||||
// Normal chat still uses unmodified MarkdownUI content.
|
||||
#expect(MarkdownContent(source).renderHTML().contains("<img"))
|
||||
#expect(AgentMessageMarkdown.content("<img src='https://images.invalid/a.png' alt='HTML landscape'>\n").renderHTML() == "<p>HTML landscape</p>\n")
|
||||
}
|
||||
|
||||
@Test func agentMarkdownRetainsCodeTablesAndEscapesImageLikeAltText() {
|
||||
let source = """
|
||||
``
|
||||
|
||||
```html
|
||||
<img src="literal-code">
|
||||
```
|
||||
|
||||
| Image | Value |
|
||||
| --- | --- |
|
||||
|  | **Kept** |
|
||||
|
||||
<IMG ALT='' SRC='ignored'>
|
||||
"""
|
||||
let html = AgentMessageMarkdown.content(source).renderHTML()
|
||||
#expect(html.contains("<table>")); #expect(html.contains("Table alt"))
|
||||
#expect(html.contains("<strong>Kept</strong>"))
|
||||
#expect(html.contains("<img src=")); #expect(html.contains("![literal]"))
|
||||
#expect(html.contains("![literal alt]")); #expect(!html.contains("<img"))
|
||||
}
|
||||
|
||||
@Test func userMarkupRemainsLiteral() {
|
||||
let source = "**bold** [link](https://example.invalid) `code`\n- item\n<script>literal</script>"
|
||||
let content = SybilMessageText.literalContent(source)
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
Run with Python + aiohttp, then xcodebuild test -scheme SybilAgentUI.
|
||||
"""
|
||||
import asyncio
|
||||
import base64
|
||||
import datetime
|
||||
import json
|
||||
import hashlib
|
||||
@@ -23,6 +24,8 @@ reply_tasks = set()
|
||||
attachments = {}
|
||||
uploads = {}
|
||||
attachment_capability = True
|
||||
assistant_image_capability = False
|
||||
fail_image_download = False
|
||||
next_upload_error = None
|
||||
blocked_proxy = False
|
||||
transcript_comparison = False
|
||||
@@ -95,6 +98,7 @@ async def reply(content):
|
||||
|
||||
async def route(request):
|
||||
global read_cursor, cursor, busy, attachment_capability, next_upload_error, blocked_proxy, transcript_comparison, push_available, auth_required
|
||||
global assistant_image_capability, fail_image_download
|
||||
path = request.path
|
||||
log.append(dict(method=request.method, path=path, query=dict(request.query)))
|
||||
if path == '/control':
|
||||
@@ -106,6 +110,7 @@ async def route(request):
|
||||
reply_tasks.clear()
|
||||
messages.clear(); requests.clear(); attempts.clear(); cursor = 0; read_cursor = 0; busy = False
|
||||
attachment_capability = True; next_upload_error = None; blocked_proxy = False; transcript_comparison = False
|
||||
assistant_image_capability = False; fail_image_download = False
|
||||
push_installations.clear(); push_retired.clear(); push_requests.clear(); log.clear()
|
||||
push_available = True; auth_required = False
|
||||
for i in range(body.get('count', 3)):
|
||||
@@ -120,6 +125,16 @@ async def route(request):
|
||||
transcript_comparison = True
|
||||
elif action == 'capability':
|
||||
attachment_capability = body.get('enabled', True)
|
||||
assistant_image_capability = body.get('assistantImages', False)
|
||||
elif action == 'assistant-image':
|
||||
# Synthetic output supplied by XCTest, never a workspace file or provider.
|
||||
data = base64.b64decode(body['png'], validate=True)
|
||||
descriptor = dict(id='fixture-output-image', kind='image', filename='fixture-landscape.png',
|
||||
mimeType='image/png', sizeBytes=len(data), sha256=hashlib.sha256(data).hexdigest())
|
||||
attachments[descriptor['id']] = dict(descriptor=descriptor, data=data)
|
||||
fail_image_download = body.get('failFirstDownload', False)
|
||||
row = message(body.get('content', ''), info={'agentAttachments': [descriptor]})
|
||||
await broadcast(dict(type='messages', **page([row])))
|
||||
elif action == 'upload-error':
|
||||
next_upload_error = body
|
||||
elif action == 'blocked-proxy':
|
||||
@@ -190,6 +205,8 @@ async def route(request):
|
||||
descriptor = dict(id='fixture-root', title='Sybil Agent', type='persistent-agent', model='fixture', protocol='pi-room.v1', websocket='/v1/agent/ws', activity=activity())
|
||||
if attachment_capability:
|
||||
descriptor['capabilities'] = {'attachments': CAPABILITY}
|
||||
if assistant_image_capability:
|
||||
descriptor.setdefault('capabilities', {})['assistantImages'] = dict(version=1)
|
||||
return web.json_response(descriptor)
|
||||
if path == '/api/v1/agent/push/config':
|
||||
if not push_available:
|
||||
@@ -263,6 +280,9 @@ async def route(request):
|
||||
uploads[upload_id] = (identity, attachment_id)
|
||||
return web.json_response({'attachment': descriptor}, status=201)
|
||||
if path.startswith('/api/v1/agent/attachments/') and path.endswith('/content'):
|
||||
if fail_image_download:
|
||||
fail_image_download = False
|
||||
return attachment_error(503, 'fixture_retry', 'Synthetic image unavailable. Retry the download.')
|
||||
attachment_id = path.removeprefix('/api/v1/agent/attachments/').removesuffix('/content')
|
||||
stored = attachments.get(attachment_id)
|
||||
if stored is None:
|
||||
|
||||
@@ -65,6 +65,59 @@ final class AgentUITests: XCTestCase {
|
||||
return try XCTUnwrap(json["attachment"] as? [String: Any])
|
||||
}
|
||||
|
||||
func testAssistantImageOnlyLiveRetryAndHistoryWithoutInputCapability() async throws {
|
||||
app.terminate()
|
||||
try await control(["action": "reset", "count": 0])
|
||||
try await control(["action": "capability", "enabled": false, "assistantImages": true])
|
||||
try await control(["action": "push-available", "enabled": false])
|
||||
app.launch(); openAgent()
|
||||
XCTAssertFalse(app.buttons["agent-attach"].exists)
|
||||
let image = UIGraphicsImageRenderer(size: CGSize(width: 320, height: 180)).image { context in
|
||||
UIColor.systemTeal.setFill(); context.fill(CGRect(x: 0, y: 0, width: 320, height: 180))
|
||||
UIColor.systemYellow.setFill(); context.cgContext.fillEllipse(in: CGRect(x: 225, y: 25, width: 50, height: 50))
|
||||
UIColor.systemIndigo.setFill()
|
||||
context.cgContext.move(to: CGPoint(x: 0, y: 180)); context.cgContext.addLine(to: CGPoint(x: 120, y: 55))
|
||||
context.cgContext.addLine(to: CGPoint(x: 250, y: 180)); context.cgContext.fillPath()
|
||||
}
|
||||
try await control(["action": "reply", "content": "\n\n<img src='http://127.0.0.1:8799/blocked-html.png' alt='HTML landscape'>"])
|
||||
try await control(["action": "assistant-image", "content": "", "png": try XCTUnwrap(image.pngData()).base64EncodedString(), "failFirstDownload": true])
|
||||
XCTAssertTrue(app.staticTexts["fixture-landscape.png"].waitForExistence(timeout: 8))
|
||||
XCTAssertTrue(app.buttons["Retry download"].waitForExistence(timeout: 8))
|
||||
let imageFrame = app.otherElements["agent-image-frame"]
|
||||
XCTAssertTrue(imageFrame.exists)
|
||||
let placeholder = imageFrame.frame
|
||||
XCTAssertGreaterThan(placeholder.width, 0)
|
||||
XCTAssertEqual(placeholder.height, 180, accuracy: 1)
|
||||
app.buttons["Retry download"].tap()
|
||||
let preview = app.images["agent-image-preview"]
|
||||
XCTAssertTrue(preview.waitForExistence(timeout: 8))
|
||||
XCTAssertEqual(preview.label, "Image: fixture-landscape.png")
|
||||
XCTAssertLessThanOrEqual(preview.frame.height, 180)
|
||||
XCTAssertEqual(imageFrame.frame.width, placeholder.width, accuracy: 1)
|
||||
XCTAssertEqual(imageFrame.frame.height, placeholder.height, accuracy: 1)
|
||||
let loadedSize = imageFrame.frame.size
|
||||
XCTAssertTrue(app.staticTexts["Markdown landscape"].exists)
|
||||
XCTAssertTrue(app.staticTexts["HTML landscape"].exists)
|
||||
XCTAssertFalse(app.buttons.matching(NSPredicate(format: "label BEGINSWITH %@", "Copy workspace path:")).firstMatch.exists)
|
||||
capture("agent-assistant-image-live")
|
||||
|
||||
// Previously saved output remains visible when both capabilities disappear.
|
||||
try await control(["action": "capability", "enabled": false, "assistantImages": false])
|
||||
app.terminate(); app.launch(); openAgent()
|
||||
XCTAssertTrue(preview.waitForExistence(timeout: 8))
|
||||
XCTAssertEqual(imageFrame.frame.width, placeholder.width, accuracy: 1)
|
||||
XCTAssertEqual(imageFrame.frame.height, placeholder.height, accuracy: 1)
|
||||
print("Assistant image frame sizes: placeholder=\(placeholder.size), live=\(loadedSize), history=\(imageFrame.frame.size)")
|
||||
XCTAssertEqual(app.staticTexts.matching(NSPredicate(format: "label == %@", "fixture-landscape.png")).count, 1)
|
||||
XCTAssertFalse(app.buttons["agent-attach"].exists)
|
||||
capture("agent-assistant-image-history")
|
||||
let state = try await control(["action": "state"])
|
||||
let log = try XCTUnwrap(state["log"] as? [[String: Any]])
|
||||
XCTAssertFalse(log.contains { ($0["path"] as? String)?.hasPrefix("/blocked-") == true })
|
||||
XCTAssertGreaterThanOrEqual(log.filter { ($0["path"] as? String) == "/api/v1/agent/attachments/fixture-output-image/content" }.count, 3)
|
||||
XCTAssertTrue((state["requests"] as? [String: Any])?.isEmpty == true)
|
||||
}
|
||||
|
||||
func testAttachmentHistoryDownloadAndReload() async throws {
|
||||
let original = Data("Synthetic original text. <script>plain text only</script>".utf8)
|
||||
let file = try await uploadOriginal(name: "fixture-original.txt", mime: "text/plain", bytes: original)
|
||||
|
||||
@@ -0,0 +1,55 @@
|
||||
import type { Message } from "./api";
|
||||
|
||||
// The runtime also uses the Unix epoch for historical entries without a time.
|
||||
// The transcript renders these as "Earlier", without inventing a send time.
|
||||
export const UNKNOWN_AGENT_TIME = "1970-01-01T00:00:00.000Z";
|
||||
const object = (value: unknown): Record<string, unknown> | undefined => value !== null && typeof value === "object" && !Array.isArray(value)
|
||||
? value as Record<string, unknown> : undefined;
|
||||
const timestamp = (value: unknown): string | undefined => {
|
||||
if (typeof value !== "string" || !value.trim()) return undefined;
|
||||
const time = Date.parse(value);
|
||||
return Number.isFinite(time) && time !== 0 ? new Date(time).toISOString() : undefined;
|
||||
};
|
||||
|
||||
export function agentMessageTime(message: Pick<Message, "createdAt" | "metadata">): string | undefined {
|
||||
const info = object(message.metadata);
|
||||
return timestamp(message.createdAt) ?? timestamp(info?.startedAt) ?? timestamp(info?.completedAt);
|
||||
}
|
||||
|
||||
/** Normalize historical/partial rows at both transports, before state or cursors change. */
|
||||
export function normalizeAgentMessage(value: unknown): Message {
|
||||
const message = object(value);
|
||||
if (!message || typeof message.id !== "string" || !message.id
|
||||
|| typeof message.role !== "string" || !["system", "user", "assistant", "tool"].includes(message.role)) throw new Error("Invalid agent message.");
|
||||
const info = object(message.metadata);
|
||||
// Older runtime REST redaction emitted protected tool rows with only id/role/name.
|
||||
// Keep their identity for a later complete upsert; never discard a whole page.
|
||||
const content = typeof message.content === "string" ? message.content
|
||||
: message.role === "tool" && message.content == null ? (typeof message.name === "string" ? message.name : "Tool") : undefined;
|
||||
if (content === undefined) throw new Error("Invalid agent message.");
|
||||
const createdAt = agentMessageTime(message as Message) ?? UNKNOWN_AGENT_TIME;
|
||||
const needsToolMetadata = message.role === "tool" && info?.kind !== "tool_call";
|
||||
if (message.createdAt === createdAt && message.content === content && !needsToolMetadata) return message as Message;
|
||||
return { ...message, content, createdAt,
|
||||
...(needsToolMetadata ? { metadata: { ...info, kind: "tool_call" } } : {}),
|
||||
} as Message;
|
||||
}
|
||||
|
||||
function cursor(message: Message): bigint | undefined {
|
||||
const entryId = object(message.metadata)?.entryId;
|
||||
if ((typeof entryId === "number" && Number.isSafeInteger(entryId) && entryId >= 0)
|
||||
|| (typeof entryId === "string" && /^\d+$/.test(entryId))) return BigInt(entryId);
|
||||
}
|
||||
|
||||
/** One total order for history, queue snapshots and optimistic rows, including ties. */
|
||||
export function compareAgentMessages(left: Message, right: Message): number {
|
||||
const byTime = Date.parse(agentMessageTime(left) ?? UNKNOWN_AGENT_TIME) - Date.parse(agentMessageTime(right) ?? UNKNOWN_AGENT_TIME);
|
||||
if (byTime) return byTime;
|
||||
const a = cursor(left), b = cursor(right);
|
||||
if (a !== b) {
|
||||
if (a === undefined) return 1;
|
||||
if (b === undefined) return -1;
|
||||
return a < b ? -1 : 1;
|
||||
}
|
||||
return left.id < right.id ? -1 : left.id > right.id ? 1 : 0;
|
||||
}
|
||||
@@ -1,5 +1,6 @@
|
||||
import type { Message } from "./api";
|
||||
import { agentAttachments, attachmentCaption, parseAgentAttachment, type AgentAttachment } from "./agent-attachments.ts";
|
||||
import { compareAgentMessages, normalizeAgentMessage } from "./agent-messages.ts";
|
||||
|
||||
export const AGENT_OUTBOX_STORAGE_KEY = "sybil.agent.optimistic-outbox.v1";
|
||||
export type AgentDeliveryStatus = "sending" | "queued" | "complete" | "failed" | "unconfirmed";
|
||||
@@ -165,7 +166,7 @@ export function createAgentOptimisticOutbox(options: {
|
||||
metadata: { kind: "message", status: row.status, channel: "sybil", requestId: row.requestId, ...(row.attachments?.length ? { agentAttachments: row.attachments } : {}), ...(row.error ? { error: row.error } : {}) },
|
||||
});
|
||||
}
|
||||
return [...displayed.values()].sort((a, b) => a.createdAt.localeCompare(b.createdAt));
|
||||
return [...displayed.values()].map(normalizeAgentMessage).sort(compareAgentMessages);
|
||||
},
|
||||
snapshot(): AgentOutboxRow[] { return [...rows.values()].map(row => ({ ...row })); },
|
||||
};
|
||||
|
||||
+38
-24
@@ -1,6 +1,7 @@
|
||||
import type { Message } from "./api";
|
||||
import { parseAgentAttachment, type AgentAttachment, type AgentAttachmentCapability } from "./agent-attachments.ts";
|
||||
import { agentPushCursor, agentPushSourceId, agentPushUuid } from "./agent-push.ts";
|
||||
import { agentMessageTime, compareAgentMessages, normalizeAgentMessage, UNKNOWN_AGENT_TIME } from "./agent-messages.ts";
|
||||
|
||||
export type AgentActivity = {
|
||||
state: "idle" | "thinking" | "tool" | "waiting" | "error";
|
||||
@@ -57,7 +58,9 @@ function mergeMessage(previous: Message, incoming: Message): Message {
|
||||
const prior = metadata(previous), next = metadata(incoming);
|
||||
// A delayed activity snapshot must not demote an already placed user message.
|
||||
if (prior?.status === "complete" && next?.status === "queued") return previous;
|
||||
if (prior?.kind !== "tool_call" || next?.kind !== "tool_call") return { ...previous, ...incoming };
|
||||
const priorTime = agentMessageTime(previous), nextTime = agentMessageTime(incoming);
|
||||
if (prior?.kind !== "tool_call" || next?.kind !== "tool_call") return { ...previous, ...incoming,
|
||||
createdAt: nextTime ?? priorTime ?? UNKNOWN_AGENT_TIME };
|
||||
const terminal = prior.status === "completed" || prior.status === "failed";
|
||||
const staleStart = terminal && next.status === "initiated";
|
||||
const merged = staleStart ? { ...defined(next), ...defined(prior) } : { ...defined(prior), ...defined(next) };
|
||||
@@ -65,23 +68,32 @@ function mergeMessage(previous: Message, incoming: Message): Message {
|
||||
const oldArgs = object(prior.args), newArgs = object(next.args);
|
||||
if (oldArgs && (!newArgs || Object.keys(newArgs).length === 0)) merged.args = oldArgs;
|
||||
return { ...previous, ...incoming, ...(staleStart ? { content: previous.content, name: previous.name } : {}),
|
||||
createdAt: previous.createdAt < incoming.createdAt ? previous.createdAt : incoming.createdAt, metadata: merged };
|
||||
createdAt: priorTime && nextTime ? (priorTime < nextTime ? priorTime : nextTime) : priorTime ?? nextTime ?? UNKNOWN_AGENT_TIME, metadata: merged };
|
||||
}
|
||||
|
||||
/** Replays and separate tool-start/result pages update stable rows instead of duplicating them. */
|
||||
export function mergeAgentMessages(previous: readonly Message[], incoming: readonly Message[]): Message[] {
|
||||
const messages = new Map(previous.map(message => [message.id, message]));
|
||||
for (const message of incoming) {
|
||||
const messages = new Map(previous.map(normalizeAgentMessage).map(message => [message.id, message]));
|
||||
for (const message of incoming.map(normalizeAgentMessage)) {
|
||||
const prior = messages.get(message.id);
|
||||
messages.set(message.id, prior ? mergeMessage(prior, message) : message);
|
||||
}
|
||||
return [...messages.values()].sort((a, b) => {
|
||||
const byTime = a.createdAt.localeCompare(b.createdAt);
|
||||
if (byTime) return byTime;
|
||||
const left = messageCursor(a), right = messageCursor(b);
|
||||
if (left !== null && right !== null && left !== right) return BigInt(left) < BigInt(right) ? -1 : 1;
|
||||
return a.id.localeCompare(b.id);
|
||||
});
|
||||
return [...messages.values()].sort(compareAgentMessages);
|
||||
}
|
||||
|
||||
function parseAgentPage(value: unknown): AgentMessagesPage {
|
||||
const page = object(value);
|
||||
if (!page || typeof page.conversationId !== "string" || !Array.isArray(page.messages) || typeof page.hasMore !== "boolean") throw new Error("Invalid agent messages frame.");
|
||||
if (page.cursor !== null) normalizeAgentCursor(page.cursor);
|
||||
if (page.beforeCursor != null) normalizeAgentCursor(page.beforeCursor);
|
||||
return { ...page, beforeCursor: page.beforeCursor ?? null, messages: page.messages.map(normalizeAgentMessage) } as AgentMessagesPage;
|
||||
}
|
||||
function parseAgentActivity(value: unknown): AgentActivity {
|
||||
const activity = object(value);
|
||||
if (!activity || (activity.tools !== undefined && !Array.isArray(activity.tools))
|
||||
|| (activity.queuedMessages !== undefined && !Array.isArray(activity.queuedMessages))) throw new Error("Invalid agent activity frame.");
|
||||
return { ...activity, tools: activity.tools ?? [],
|
||||
queuedMessages: ((activity.queuedMessages ?? []) as unknown[]).map(normalizeAgentMessage) } as AgentActivity;
|
||||
}
|
||||
export const createAgentRoomState = (): AgentRoomState => ({
|
||||
conversationId: null, messages: [], cursor: "0", readCursor: "0", activity: null,
|
||||
@@ -99,6 +111,7 @@ function readSource(state: Pick<AgentRoomState, "sourceId" | "cursor" | "readCur
|
||||
return incoming;
|
||||
}
|
||||
export function applyAgentPage(state: AgentRoomState, page: AgentMessagesPage): AgentRoomState {
|
||||
page = parseAgentPage(page);
|
||||
if (state.conversationId !== null && state.conversationId !== page.conversationId) throw new Error("Agent conversation changed; reload the page.");
|
||||
// Validate before changing state. Failed delivery/decoding cannot advance replay position.
|
||||
const cursor = page.cursor === null ? state.cursor : advanceAgentCursor(state.cursor, page.cursor);
|
||||
@@ -132,7 +145,7 @@ export function applyAgentEvent(state: AgentRoomState, event: AgentRoomEvent): A
|
||||
if (event.type === "read_state") return applyAgentReadState(state, event);
|
||||
if (event.type !== "activity") return state;
|
||||
if (state.conversationId !== null && state.conversationId !== event.conversationId) throw new Error("Agent activity belongs to a different conversation.");
|
||||
return { ...state, conversationId: event.conversationId, activity: event.activity };
|
||||
return { ...state, conversationId: event.conversationId, activity: parseAgentActivity(event.activity) };
|
||||
}
|
||||
export function agentUnreadCount(state: AgentRoomState): number {
|
||||
return state.messages.filter(message => {
|
||||
@@ -153,15 +166,12 @@ export function parseAgentRoomEvent(raw: string): AgentRoomEvent | null {
|
||||
|| (event.updatedAt !== null && typeof event.updatedAt !== "string")
|
||||
|| (event.sourceId !== undefined && event.sourceId !== null && !agentPushSourceId(event.sourceId)))) throw new Error("Invalid Agent read frame.");
|
||||
if (event.type === "messages") {
|
||||
if (typeof event.conversationId !== "string" || !Array.isArray(event.messages) || typeof event.hasMore !== "boolean") throw new Error("Invalid agent messages frame.");
|
||||
if (event.cursor !== null) normalizeAgentCursor(event.cursor);
|
||||
for (const item of event.messages) {
|
||||
const message = object(item);
|
||||
if (!message || typeof message.id !== "string" || typeof message.content !== "string" || typeof message.createdAt !== "string"
|
||||
|| !["system", "user", "assistant", "tool"].includes(String(message.role))) throw new Error("Invalid agent message.");
|
||||
return { ...parseAgentPage(event), type: "messages" };
|
||||
}
|
||||
if (event.type === "activity") {
|
||||
if (typeof event.conversationId !== "string") throw new Error("Invalid agent activity frame.");
|
||||
return { ...event, activity: parseAgentActivity(event.activity) } as AgentRoomEvent;
|
||||
}
|
||||
if (event.type === "activity" && (typeof event.conversationId !== "string" || !object(event.activity))) throw new Error("Invalid agent activity frame.");
|
||||
return event as AgentRoomEvent;
|
||||
}
|
||||
export function agentAuthFrame(token: string | null, cursor: string, presenceSessionId?: string): string {
|
||||
@@ -197,12 +207,16 @@ export class AgentRoomClient {
|
||||
}
|
||||
return value as T;
|
||||
}
|
||||
descriptor(signal?: AbortSignal): Promise<AgentDescriptor> { return this.request("", { signal }); }
|
||||
messages(after: string, signal?: AbortSignal): Promise<AgentMessagesPage> {
|
||||
return this.request(`/messages?${new URLSearchParams({ after: normalizeAgentCursor(after), limit: "200" })}`, { signal });
|
||||
async descriptor(signal?: AbortSignal): Promise<AgentDescriptor> {
|
||||
const value = object(await this.request("", { signal }));
|
||||
if (!value || typeof value.id !== "string") throw new Error("Invalid agent descriptor.");
|
||||
return { ...value, activity: parseAgentActivity(value.activity) } as AgentDescriptor;
|
||||
}
|
||||
history(before?: string, signal?: AbortSignal): Promise<AgentMessagesPage> {
|
||||
return this.request(`/messages?${new URLSearchParams({ ...(before === undefined ? {} : { before: normalizeAgentCursor(before) }), limit: "100" })}`, { signal });
|
||||
async messages(after: string, signal?: AbortSignal): Promise<AgentMessagesPage> {
|
||||
return parseAgentPage(await this.request(`/messages?${new URLSearchParams({ after: normalizeAgentCursor(after), limit: "200" })}`, { signal }));
|
||||
}
|
||||
async history(before?: string, signal?: AbortSignal): Promise<AgentMessagesPage> {
|
||||
return parseAgentPage(await this.request(`/messages?${new URLSearchParams({ ...(before === undefined ? {} : { before: normalizeAgentCursor(before) }), limit: "100" })}`, { signal }));
|
||||
}
|
||||
readState(signal?: AbortSignal): Promise<AgentReadState> { return this.request("/read-state", { signal }); }
|
||||
markRead(cursor: string, signal?: AbortSignal, sourceId?: string | null): Promise<AgentReadState> {
|
||||
|
||||
@@ -7,6 +7,15 @@ const canonical = (id, content = "Hello", time = "2026-10-14T12:01:00.000Z") =>
|
||||
metadata: { kind: "message", entryId: 123, status: "complete", channel: "sybil" },
|
||||
});
|
||||
const deferred = () => { let resolve, reject; const promise = new Promise((yes, no) => { resolve = yes; reject = no; }); return { promise, resolve, reject }; };
|
||||
|
||||
test("display sorts partial server rows and tied entry cursors consistently", () => {
|
||||
const box = createAgentOptimisticOutbox({ submit: async () => assert.fail("no send"),
|
||||
storage: { read: () => [], write: () => {} }, changed: () => {} });
|
||||
const rows = [canonical("z"), { id: "tool:1:partial", role: "tool", name: "owner_phone_context" },
|
||||
{ ...canonical("a"), metadata: { entryId: 124 } }];
|
||||
assert.deepEqual(box.display(rows).map(row => row.id), ["tool:1:partial", "z", "a"]);
|
||||
assert.deepEqual(box.display([...rows].reverse()), box.display(rows));
|
||||
});
|
||||
function fixture(submit, legacy = {}) {
|
||||
let stored = null;
|
||||
let serial = 0;
|
||||
|
||||
@@ -21,6 +21,91 @@ const sourceA = "4599d348-e053-4937-987d-1392746fb2ce", sourceB = "22222222-2222
|
||||
const deferred = () => { let resolve; const promise = new Promise(yes => { resolve = yes; }); return { promise, resolve }; };
|
||||
const sourceRoom = () => applyAgentPage(applyAgentReadState(createAgentRoomState(), { sourceId: sourceA, cursor: "90", updatedAt: null }), page("100", [message(100)]));
|
||||
|
||||
test("redacted historical tool rows survive REST loading, socket replay and outbox rendering", async () => {
|
||||
const redacted = { id: "tool:1:protected", role: "tool", name: "owner_phone_context" };
|
||||
const input = page("3", [message(1), redacted, message(3)]);
|
||||
const client = new AgentRoomClient({ fetch: async () => Response.json(input) });
|
||||
let state = createAgentRoomState();
|
||||
await syncAgentHistory(client, "0", update => { state = applyAgentPage(state, update); });
|
||||
const initial = state.messages;
|
||||
assert.deepEqual((await client.history()).messages, (await client.messages("0")).messages,
|
||||
"recent/older history uses the same boundary as forward replay");
|
||||
const row = initial.find(row => row.id === redacted.id);
|
||||
assert.equal(row.createdAt, "1970-01-01T00:00:00.000Z", "unknown times are stable, never fabricated as now");
|
||||
assert.equal(row.content, "owner_phone_context");
|
||||
assert.equal(state.cursor, "3");
|
||||
const event = parseAgentRoomEvent(JSON.stringify({ type: "messages", ...input }));
|
||||
state = applyAgentEvent(state, event);
|
||||
assert.deepEqual(state.messages, initial, "replaying partial history is idempotent");
|
||||
const box = createAgentOptimisticOutbox({ submit: async () => assert.fail("no send"),
|
||||
storage: { read: () => [], write: () => {} }, changed: () => {} });
|
||||
assert.deepEqual(box.display(agentDisplayMessages(state)), initial);
|
||||
});
|
||||
|
||||
test("partial tool updates retain known time, terminal metadata and chronological ordering", () => {
|
||||
const id = "tool:1:partial";
|
||||
const start = message(2, "tool", { id, metadata: { kind: "tool_call", entryId: 2, status: "initiated", startedAt: "2026-10-14T10:00:02.000Z" } });
|
||||
const done = message(3, "tool", { id, createdAt: undefined, metadata: { kind: "tool_call", entryId: 3, status: "completed", completedAt: "2026-10-14T10:00:03.000Z" } });
|
||||
const partial = { id, role: "tool", name: "owner_phone_context" };
|
||||
const rows = mergeAgentMessages([message(1), start], [done, partial, start, message(4)]);
|
||||
assert.deepEqual(rows.map(row => row.id), ["entry:1", id, "entry:4"]);
|
||||
assert.equal(rows[1].createdAt, start.createdAt);
|
||||
assert.equal(rows[1].metadata.status, "completed");
|
||||
assert.equal(rows[1].metadata.completedAt, done.metadata.completedAt);
|
||||
assert.equal(mergeAgentMessages([], [done])[0].createdAt, done.metadata.completedAt);
|
||||
assert.equal(mergeAgentMessages([partial], [start])[0].createdAt, start.createdAt);
|
||||
});
|
||||
|
||||
test("an unknown historical tool start never masks a known completion timestamp", () => {
|
||||
const unknown = "1970-01-01T00:00:00.000Z", known = "2026-10-14T10:00:03.000Z";
|
||||
const start = message(2, "tool", { id: "tool:1:historical", createdAt: unknown,
|
||||
metadata: { kind: "tool_call", entryId: 2, status: "initiated", startedAt: unknown } });
|
||||
const done = message(3, "tool", { id: start.id, createdAt: known,
|
||||
metadata: { kind: "tool_call", entryId: 3, status: "completed", completedAt: known } });
|
||||
for (const rows of [[start, done], [done, start], [{ ...start, metadata: { ...start.metadata, ...done.metadata } }]]) {
|
||||
const merged = mergeAgentMessages([], rows);
|
||||
assert.equal(merged[0].createdAt, known);
|
||||
assert.equal(merged[0].metadata.status, "completed");
|
||||
}
|
||||
});
|
||||
|
||||
test("missing, null, invalid and tied timestamps have stable ordering independent of arrival order", () => {
|
||||
const rows = [message(11, "assistant", { createdAt: null }), message(2, "assistant", { createdAt: undefined }),
|
||||
message(3, "assistant", { createdAt: "not-a-date" }), message(4, "assistant", { createdAt: 0 }),
|
||||
message(5, "assistant", { createdAt: null, metadata: { kind: "message" } })];
|
||||
const expected = ["entry:2", "entry:3", "entry:4", "entry:11", "entry:5"];
|
||||
assert.deepEqual(mergeAgentMessages([], rows).map(row => row.id), expected);
|
||||
assert.deepEqual(mergeAgentMessages([], [...rows].reverse()).map(row => row.id), expected);
|
||||
const tied = [message(11, "assistant", { createdAt: "2026-10-14T10:00:00Z" }), message(2, "assistant", { createdAt: "2026-10-14T11:00:00+01:00" })];
|
||||
assert.deepEqual(mergeAgentMessages([], tied).map(row => row.id), ["entry:2", "entry:11"]);
|
||||
});
|
||||
|
||||
test("REST descriptors and socket activity normalize partial queued messages consistently", async () => {
|
||||
const pending = message(1, "user", { id: "inbound:sybil:partial", createdAt: undefined, metadata: { kind: "message", status: "queued" } });
|
||||
const value = { id: "1", activity: activity([pending]) };
|
||||
const client = new AgentRoomClient({ fetch: async () => Response.json(value) });
|
||||
const descriptor = await client.descriptor();
|
||||
const fromRest = applyAgentEvent(createAgentRoomState(), { type: "activity", conversationId: descriptor.id, activity: descriptor.activity });
|
||||
const fromSocket = applyAgentEvent(createAgentRoomState(), parseAgentRoomEvent(JSON.stringify({ type: "activity", conversationId: "1", activity: value.activity })));
|
||||
assert.deepEqual(agentDisplayMessages(fromRest), agentDisplayMessages(fromSocket));
|
||||
assert.equal(agentDisplayMessages(fromRest)[0].createdAt, "1970-01-01T00:00:00.000Z");
|
||||
const malformed = { ...pending, content: undefined };
|
||||
assert.throws(() => applyAgentEvent(fromRest, { type: "activity", conversationId: "1", activity: activity([malformed]) }), /Invalid agent message/);
|
||||
assert.equal(fromRest.cursor, "0");
|
||||
});
|
||||
|
||||
test("invalid message bodies fail at both transport boundaries before advancing replay", async () => {
|
||||
for (const malformed of [null, { role: "assistant", content: "missing ID" }, message(2, "assistant", { content: null }), message(2, ["assistant"])]) {
|
||||
const input = page("3", [message(1), malformed]);
|
||||
const client = new AgentRoomClient({ fetch: async () => Response.json(input) });
|
||||
let applied = false;
|
||||
await assert.rejects(syncAgentHistory(client, "0", () => { applied = true; }), /Invalid agent message/);
|
||||
await assert.rejects(client.history(), /Invalid agent message/);
|
||||
assert.equal(applied, false);
|
||||
assert.throws(() => parseAgentRoomEvent(JSON.stringify({ type: "messages", ...input })), /Invalid agent message/);
|
||||
}
|
||||
});
|
||||
|
||||
test("tool starts and results merge across replay without downgrading completed cards", () => {
|
||||
const start = message(2, "tool", { id: "tool:1:call1", metadata: { kind: "tool_call", entryId: 2, status: "initiated", args: { query: "cookie" }, startedAt: "2026-10-14T10:00:00Z" } });
|
||||
const done = message(3, "tool", { id: start.id, metadata: { kind: "tool_call", entryId: 3, status: "completed", resultPreview: "found" } });
|
||||
@@ -312,7 +397,7 @@ test("client uses Sybil auth and routes while websocket credentials remain in th
|
||||
let token = "first-session-token";
|
||||
const client = new AgentRoomClient({ baseUrl: "https://sybil.example/api/", token: () => token, fetch: async (url, init) => {
|
||||
calls.push({ url, init }); return new Response(JSON.stringify(init.method === "POST"
|
||||
? { id: 1, status: "queued", messageId: "inbound:sybil:request-1" } : { cursor: "0", updatedAt: null }), { status: 200 });
|
||||
? { id: 1, status: "queued", messageId: "inbound:sybil:request-1" } : url.includes("/messages?") ? page("0") : { cursor: "0", updatedAt: null }), { status: 200 });
|
||||
} });
|
||||
await client.messages("0");
|
||||
token = "second-session-token";
|
||||
|
||||
Reference in New Issue
Block a user