Merge remote-tracking branch 'origin/ws-3-kanban-v0.13' into integration/v2.8.0

This commit is contained in:
Alan Wizemann
2026-05-09 19:09:38 +02:00
13 changed files with 1103 additions and 77 deletions
@@ -0,0 +1,158 @@
import Foundation
/// A structured signal Hermes emits when it observes worker / task
/// distress. Hermes v0.13 introduced a generic diagnostics engine that
/// attaches these to a task (cross-run signals) and/or a run (per-attempt
/// signals). Pre-v0.13 hosts never emit diagnostics so the array decodes
/// empty and downstream UI no-ops.
///
/// **Wire shape (best inference from release notes verify against live
/// JSON during integration):** an array of objects with `kind`, optional
/// `message`, optional `detected_at` (ISO-8601 string OR Unix integer,
/// matching the rest of `HermesKanbanTask`'s timestamp tolerance).
///
/// **Forward compat:** `kind` stays a `String` so a future Hermes can
/// add new diagnostic kinds without a Scarf release. `KanbanDiagnosticKind`
/// is the typed mirror it falls back to `.unknown` for unrecognized
/// kinds and renders the raw string verbatim.
public struct HermesKanbanDiagnostic: Sendable, Equatable, Identifiable, Codable {
/// Synthetic id not on the wire. Lets SwiftUI `ForEach` over a
/// diagnostic array without forcing a deterministic id from the
/// server (Hermes doesn't currently mint one).
public let id: UUID
/// Wire-side `kind` string. Compared case-insensitively via
/// `KanbanDiagnosticKind.from(_:)`.
public let kind: String
/// Human-friendly elaboration ("no heartbeat for 4m20s", "exit code
/// 0 with no complete call", etc.). May be nil; render the raw
/// `kind` then.
public let message: String?
/// ISO-8601 string. Decoder accepts Unix integer seconds (Hermes's
/// SQLite-backed shape) and converts to ISO-8601 so consumers see
/// one type same pattern as `HermesKanbanTask.decodeFlexibleTimestamp`.
public let detectedAt: String?
public init(
kind: String,
message: String? = nil,
detectedAt: String? = nil
) {
self.id = UUID()
self.kind = kind
self.message = message
self.detectedAt = detectedAt
}
enum CodingKeys: String, CodingKey {
case kind
case message
case detectedAt = "detected_at"
}
public init(from decoder: any Decoder) throws {
let c = try decoder.container(keyedBy: CodingKeys.self)
self.id = UUID()
self.kind = try c.decodeIfPresent(String.self, forKey: .kind) ?? "unknown"
self.message = try c.decodeIfPresent(String.self, forKey: .message)
// Flexible timestamp decode mirrors HermesKanbanTask's pattern.
if !c.contains(.detectedAt) {
self.detectedAt = nil
} else if let unix = try? c.decodeIfPresent(Double.self, forKey: .detectedAt) {
let date = Date(timeIntervalSince1970: unix)
self.detectedAt = Self.isoFormatter.string(from: date)
} else {
self.detectedAt = try c.decodeIfPresent(String.self, forKey: .detectedAt)
}
}
public func encode(to encoder: any Encoder) throws {
var c = encoder.container(keyedBy: CodingKeys.self)
try c.encode(kind, forKey: .kind)
try c.encodeIfPresent(message, forKey: .message)
try c.encodeIfPresent(detectedAt, forKey: .detectedAt)
}
public static func == (lhs: HermesKanbanDiagnostic, rhs: HermesKanbanDiagnostic) -> Bool {
// Compare on wire fields, not synthetic id round-trip decoding
// mints fresh ids.
lhs.kind == rhs.kind
&& lhs.message == rhs.message
&& lhs.detectedAt == rhs.detectedAt
}
private static let isoFormatter: ISO8601DateFormatter = {
let f = ISO8601DateFormatter()
f.formatOptions = [.withInternetDateTime]
return f
}()
}
// MARK: - Typed mirror
/// Typed view of `HermesKanbanDiagnostic.kind`. Models keep the raw
/// string for forward compatibility; UI helpers read this enum to pick
/// the right glyph + tint without string-matching at every callsite.
///
/// `unknown` is the fallback for any kind a future Hermes adds that
/// Scarf doesn't recognize. Views render the raw string verbatim in
/// that case so the user still sees what Hermes flagged.
// TODO(WS-3-Q5): The exact `kind` string for darwin-zombie detection is
// inferred from the v0.13 release notes ("Detect darwin zombie workers");
// confirm against live `hermes kanban show --json` output during
// integration. Same for `worker_exit_no_complete` and the heartbeat-stalled
// kinds typed mirror falls through to `.unknown` if the wire string
// drifts, and the raw string is still rendered.
public enum KanbanDiagnosticKind: String, Sendable, CaseIterable {
case heartbeatStalled = "heartbeat_stalled"
case toolErrorLoop = "tool_error_loop"
case retryCapHit = "retry_cap_hit"
case unboundedRetry = "unbounded_retry"
case darwinZombieDetected = "darwin_zombie_detected"
case spawnFailure = "spawn_failure"
case workerExitNoComplete = "worker_exit_no_complete"
case unknown
/// Map a wire string (case-insensitive) to a typed kind. Unknown
/// values fall through to `.unknown` so callers can still surface
/// the raw string.
public static func from(_ raw: String) -> KanbanDiagnosticKind {
KanbanDiagnosticKind(rawValue: raw.lowercased()) ?? .unknown
}
/// SF Symbol name to render alongside the diagnostic. View code
/// reaches through the typed enum so glyph choices live in one
/// place.
public var glyphName: String {
switch self {
case .heartbeatStalled: return "waveform.path.badge.minus"
case .toolErrorLoop: return "arrow.triangle.2.circlepath.exclamationmark"
case .retryCapHit: return "nosign"
case .unboundedRetry: return "arrow.clockwise.circle.fill"
case .darwinZombieDetected: return "apple.logo"
case .spawnFailure: return "bolt.slash"
case .workerExitNoComplete: return "figure.walk.departure"
case .unknown: return "stethoscope"
}
}
/// Severity tier for this kind drives badge tint. `.danger` for
/// terminal-class signals (retry cap hit, zombie, spawn failure);
/// `.warning` for recoverable signals (heartbeat stalled, tool
/// error loop); `.neutral` only for unknown / forward-compat kinds.
public var severity: DiagnosticSeverity {
switch self {
case .retryCapHit, .darwinZombieDetected, .spawnFailure:
return .danger
case .heartbeatStalled, .toolErrorLoop, .unboundedRetry, .workerExitNoComplete:
return .warning
case .unknown:
return .neutral
}
}
public enum DiagnosticSeverity: Sendable {
case warning
case danger
case neutral
}
}
@@ -24,6 +24,19 @@ public struct HermesKanbanRun: Sendable, Equatable, Identifiable, Codable {
/// raw string so we don't lock the typed shape.
public let metadataJSON: String?
// v0.13 (v2026.5.7) fields. Both Optional / empty-default so a v0.12
// host's run row decodes without error.
/// Per-attempt distress signals. Cross-run signals (retry cap hit,
/// etc.) hang off `HermesKanbanTask.diagnostics`; in-flight signals
/// (heartbeat stalled, darwin zombie detected) attach here.
public let diagnostics: [HermesKanbanDiagnostic]
/// Server-side unified failure counter (renamed from three separate
/// spawn / timeout / crash counters in v0.13). Optional when nil,
/// callers fall back to counting failed runs in the runs array.
// TODO(WS-3-Q4): Verify whether v0.13 exposes this field on the per-run
// shape OR only at the task level. Tolerant decode handles either.
public let failureCount: Int?
public init(
id: Int,
taskId: String,
@@ -40,7 +53,9 @@ public struct HermesKanbanRun: Sendable, Equatable, Identifiable, Codable {
outcome: String? = nil,
summary: String? = nil,
error: String? = nil,
metadataJSON: String? = nil
metadataJSON: String? = nil,
diagnostics: [HermesKanbanDiagnostic] = [],
failureCount: Int? = nil
) {
self.id = id
self.taskId = taskId
@@ -58,6 +73,8 @@ public struct HermesKanbanRun: Sendable, Equatable, Identifiable, Codable {
self.summary = summary
self.error = error
self.metadataJSON = metadataJSON
self.diagnostics = diagnostics
self.failureCount = failureCount
}
enum CodingKeys: String, CodingKey {
@@ -77,6 +94,8 @@ public struct HermesKanbanRun: Sendable, Equatable, Identifiable, Codable {
case summary
case error
case metadata
case diagnostics
case failureCount = "failure_count"
}
public init(from decoder: any Decoder) throws {
@@ -120,6 +139,11 @@ public struct HermesKanbanRun: Sendable, Equatable, Identifiable, Codable {
} else {
self.metadataJSON = nil
}
// v0.13 diagnostics array `try?` so a malformed entry doesn't
// poison the whole run row. Empty default for pre-v0.13 hosts.
self.diagnostics = (try? c.decodeIfPresent([HermesKanbanDiagnostic].self, forKey: .diagnostics)) ?? []
self.failureCount = try c.decodeIfPresent(Int.self, forKey: .failureCount)
}
public func encode(to encoder: any Encoder) throws {
@@ -140,5 +164,7 @@ public struct HermesKanbanRun: Sendable, Equatable, Identifiable, Codable {
try c.encodeIfPresent(summary, forKey: .summary)
try c.encodeIfPresent(error, forKey: .error)
try c.encodeIfPresent(metadataJSON, forKey: .metadata)
try c.encode(diagnostics, forKey: .diagnostics)
try c.encodeIfPresent(failureCount, forKey: .failureCount)
}
}
@@ -9,8 +9,9 @@ import Foundation
/// `link`/`unlink`, `comment`, `dispatch`).
///
/// Hermes has no `update` verb `priority` / `title` / `body` /
/// `tenant` are write-once at create time. Mutations after that are
/// expressed as state transitions (status, assignee) or new comments.
/// `tenant` / `max_retries` are write-once at create time. Mutations
/// after that are expressed as state transitions (status, assignee) or
/// new comments.
public struct HermesKanbanTask: Sendable, Equatable, Identifiable, Codable {
public let id: String
public let title: String
@@ -34,6 +35,29 @@ public struct HermesKanbanTask: Sendable, Equatable, Identifiable, Codable {
public let maxRuntimeSeconds: Int?
public let currentRunId: Int?
// v0.13 (v2026.5.7) reliability + recovery fields. All Optional with
// `nil` decoded for pre-v0.13 hosts so the v2.7.5 surface keeps
// rendering unchanged when the connected Hermes hasn't shipped them.
/// Per-task retry budget set at create time via `--max-retries N`.
/// Hermes pattern is write-once no `set_max_retries` verb. Scarf
/// surfaces this read-only on the inspector header.
public let maxRetries: Int?
/// Server-supplied reason a task was auto-blocked (e.g. "worker
/// exited (code 0) without calling `kanban complete`"). Surfaced
/// verbatim in the inspector banner.
public let autoBlockedReason: String?
/// `pending` / `verified` / `rejected` / nil. Pending means a worker
/// claimed it created this card but Hermes hasn't confirmed the
/// underlying work exists. Read through `KanbanHallucinationGate.from`
/// to map to a typed mirror kept as a String at the wire level so
/// Hermes can add new gate states (e.g. `quarantined`) without a
/// Scarf release.
public let hallucinationGateStatus: String?
/// Cross-run distress signals (retry cap hit, etc.). Per-run signals
/// hang off `HermesKanbanRun.diagnostics`. Empty array for pre-v0.13
/// hosts AND for tasks the diagnostics engine hasn't flagged.
public let diagnostics: [HermesKanbanDiagnostic]
public init(
id: String,
title: String,
@@ -53,7 +77,11 @@ public struct HermesKanbanTask: Sendable, Equatable, Identifiable, Codable {
idempotencyKey: String? = nil,
lastHeartbeatAt: String? = nil,
maxRuntimeSeconds: Int? = nil,
currentRunId: Int? = nil
currentRunId: Int? = nil,
maxRetries: Int? = nil,
autoBlockedReason: String? = nil,
hallucinationGateStatus: String? = nil,
diagnostics: [HermesKanbanDiagnostic] = []
) {
self.id = id
self.title = title
@@ -74,6 +102,10 @@ public struct HermesKanbanTask: Sendable, Equatable, Identifiable, Codable {
self.lastHeartbeatAt = lastHeartbeatAt
self.maxRuntimeSeconds = maxRuntimeSeconds
self.currentRunId = currentRunId
self.maxRetries = maxRetries
self.autoBlockedReason = autoBlockedReason
self.hallucinationGateStatus = hallucinationGateStatus
self.diagnostics = diagnostics
}
enum CodingKeys: String, CodingKey {
@@ -89,6 +121,10 @@ public struct HermesKanbanTask: Sendable, Equatable, Identifiable, Codable {
case lastHeartbeatAt = "last_heartbeat_at"
case maxRuntimeSeconds = "max_runtime_seconds"
case currentRunId = "current_run_id"
case maxRetries = "max_retries"
case autoBlockedReason = "auto_blocked_reason"
case hallucinationGateStatus = "hallucination_gate_status"
case diagnostics
}
public init(from decoder: any Decoder) throws {
@@ -117,6 +153,17 @@ public struct HermesKanbanTask: Sendable, Equatable, Identifiable, Codable {
self.lastHeartbeatAt = try Self.decodeFlexibleTimestamp(c, forKey: .lastHeartbeatAt)
self.maxRuntimeSeconds = try c.decodeIfPresent(Int.self, forKey: .maxRuntimeSeconds)
self.currentRunId = try c.decodeIfPresent(Int.self, forKey: .currentRunId)
// v0.13 fields every one is `decodeIfPresent` so a v0.12 host's
// task row decodes successfully with these all nil/empty. The
// tolerant-decode contract is pinned by KanbanModelsTests.
self.maxRetries = try c.decodeIfPresent(Int.self, forKey: .maxRetries)
self.autoBlockedReason = try c.decodeIfPresent(String.self, forKey: .autoBlockedReason)
self.hallucinationGateStatus = try c.decodeIfPresent(String.self, forKey: .hallucinationGateStatus)
// Wrap diagnostics decode in `try?` so a single malformed entry
// (or the whole array being the wrong shape) doesn't poison the
// task row the rest of the decoder still produces a usable
// task. Empty default matches the `skills` pattern.
self.diagnostics = (try? c.decodeIfPresent([HermesKanbanDiagnostic].self, forKey: .diagnostics)) ?? []
}
/// Decode a timestamp that may arrive as a Unix integer or an
@@ -209,3 +256,27 @@ public enum KanbanBoardColumn: String, Sendable, CaseIterable, Identifiable {
.triage, .upNext, .running, .blocked, .done
]
}
// MARK: - Hallucination gate (v0.13)
/// Typed mirror of Hermes v0.13's hallucination-gate state. Worker-created
/// cards land in `pending` until something verifies the underlying work
/// exists; Scarf surfaces a Verify / Reject UX above the task body so the
/// user can act as the verification gate.
///
/// Kept separate from `KanbanStatus` because hallucination state is
/// orthogonal to the lifecycle a card can be `ready` *and* `pending`,
/// for example.
public enum KanbanHallucinationGate: String, Sendable, CaseIterable {
case pending
case verified
case rejected
/// Map a raw `hallucination_gate_status` string (case-insensitive) to
/// a typed gate. Returns nil for empty/nil/unknown values so callers
/// can short-circuit "no gate" branches with `if let gate = `.
public static func from(_ raw: String?) -> KanbanHallucinationGate? {
guard let raw, !raw.isEmpty else { return nil }
return KanbanHallucinationGate(rawValue: raw.lowercased())
}
}
@@ -12,17 +12,27 @@ public struct HermesKanbanTaskDetail: Sendable, Equatable, Codable {
/// to the worker as upstream context; surfacing them in the
/// inspector is useful for understanding why a task started.
public let parentResults: [String: String]
/// Envelope-level diagnostics array (sibling to `task`, not nested
/// inside it). Defensive Hermes v0.13's wire shape may attach
/// diagnostics to the task itself OR to the envelope.
/// `allDiagnostics` dedupes both sources by `(kind, detected_at)`.
// TODO(WS-3-Q2): Confirm against live `hermes kanban show --json`
// whether diagnostics live on the task envelope, the inner task, or
// both. Current decode is tolerant of either.
public let envelopeDiagnostics: [HermesKanbanDiagnostic]?
public init(
task: HermesKanbanTask,
comments: [HermesKanbanComment] = [],
events: [HermesKanbanEvent] = [],
parentResults: [String: String] = [:]
parentResults: [String: String] = [:],
envelopeDiagnostics: [HermesKanbanDiagnostic]? = nil
) {
self.task = task
self.comments = comments
self.events = events
self.parentResults = parentResults
self.envelopeDiagnostics = envelopeDiagnostics
}
enum CodingKeys: String, CodingKey {
@@ -30,6 +40,7 @@ public struct HermesKanbanTaskDetail: Sendable, Equatable, Codable {
case comments
case events
case parentResults = "parent_results"
case envelopeDiagnostics = "diagnostics"
}
public init(from decoder: any Decoder) throws {
@@ -48,6 +59,9 @@ public struct HermesKanbanTaskDetail: Sendable, Equatable, Codable {
self.comments = (try? container.decodeIfPresent([HermesKanbanComment].self, forKey: .comments)) ?? []
self.events = (try? container.decodeIfPresent([HermesKanbanEvent].self, forKey: .events)) ?? []
self.parentResults = (try? container.decodeIfPresent([String: String].self, forKey: .parentResults)) ?? [:]
// Same `try?` shield as the rest a malformed envelope
// diagnostics array shouldn't reject the whole show response.
self.envelopeDiagnostics = try? container.decodeIfPresent([HermesKanbanDiagnostic].self, forKey: .envelopeDiagnostics)
}
public func encode(to encoder: any Encoder) throws {
@@ -56,5 +70,20 @@ public struct HermesKanbanTaskDetail: Sendable, Equatable, Codable {
try c.encode(comments, forKey: .comments)
try c.encode(events, forKey: .events)
try c.encode(parentResults, forKey: .parentResults)
try c.encodeIfPresent(envelopeDiagnostics, forKey: .envelopeDiagnostics)
}
/// Unified diagnostics view for the inspector. Combines `task.diagnostics`
/// with envelope-level diagnostics (when present) and dedupes on the
/// `(kind, detectedAt)` tuple. Wire-side dupes are unlikely but cheap to
/// filter. Empty for pre-v0.13 hosts.
public var allDiagnostics: [HermesKanbanDiagnostic] {
let onTask = task.diagnostics
let onEnvelope = envelopeDiagnostics ?? []
var seen = Set<String>()
return (onTask + onEnvelope).filter { diag in
let key = "\(diag.kind)|\(diag.detectedAt ?? "")"
return seen.insert(key).inserted
}
}
}
@@ -17,6 +17,15 @@ public struct KanbanCreateRequest: Sendable, Equatable {
public var maxRuntimeSeconds: Int?
public var createdBy: String?
public var skills: [String]
/// v0.13: per-task retry budget. `--max-retries N` is write-once at
/// create time no `set_max_retries` verb. Pass `nil` to let Hermes
/// pick its built-in default (3 as of v0.13.0). Capability-gated in
/// the create sheet on `hasKanbanDiagnostics`.
// TODO(WS-3-Q6): Confirm Hermes's global default for `max_retries`
// (v0.13 release notes don't enumerate it). The create sheet defaults
// the field to 3; if Hermes config exposes a different default, mirror
// it.
public var maxRetries: Int?
public init(
title: String,
@@ -30,7 +39,8 @@ public struct KanbanCreateRequest: Sendable, Equatable {
idempotencyKey: String? = nil,
maxRuntimeSeconds: Int? = nil,
createdBy: String? = nil,
skills: [String] = []
skills: [String] = [],
maxRetries: Int? = nil
) {
self.title = title
self.body = body
@@ -44,6 +54,7 @@ public struct KanbanCreateRequest: Sendable, Equatable {
self.maxRuntimeSeconds = maxRuntimeSeconds
self.createdBy = createdBy
self.skills = skills
self.maxRetries = maxRetries
}
/// Build the argv suffix this request maps to (everything after
@@ -78,6 +89,9 @@ public struct KanbanCreateRequest: Sendable, Equatable {
if let maxRuntimeSeconds {
args.append(contentsOf: ["--max-runtime", "\(maxRuntimeSeconds)s"])
}
if let maxRetries {
args.append(contentsOf: ["--max-retries", String(maxRetries)])
}
if let createdBy, !createdBy.isEmpty {
args.append(contentsOf: ["--created-by", createdBy])
}
@@ -321,6 +321,61 @@ public actor KanbanService {
try ensureSuccess(code: code, stdout: "", stderr: stderr, verb: "unlink")
}
// MARK: - Hallucination gate (v0.13)
/// Mark a worker-created card as user-verified flips
/// `hallucination_gate_status` from `pending` to `verified` so the
/// dispatcher can pick it up. The polling loop picks up the new
/// state on the next tick (and the VM optimistically clears the
/// pending banner immediately on the click).
///
/// **Pre-v0.13 hosts:** the verb doesn't exist; callers MUST gate
/// on `HermesCapabilities.hasKanbanDiagnostics` before invoking this.
/// A pre-v0.13 binary will surface the failure as
/// `KanbanError.nonZeroExit` with stderr containing "unknown command".
// TODO(WS-3-Q1): Confirm the exact CLI verb name for the
// hallucination-gate verify path against a v0.13 binary (`hermes
// kanban --help`). The v0.13 release notes describe "hallucination
// gate + recovery UX" but don't enumerate the verb name. This
// implementation assumes `hermes kanban verify <id>`. If Hermes ships
// it as `hermes kanban gate verify <id>`, `hermes kanban hallucination
// verify <id>`, or another name, update the args here. The Reject
// path does NOT depend on this verb (it routes through
// `archive` + a comment), so the recovery UX stays functional even
// if Verify is a stub for an early v0.13.x.
public func verify(taskId: String) async throws {
let args = ["kanban", "verify", taskId]
let (code, _, stderr) = await runHermes(args: args, timeout: 15)
try ensureSuccess(code: code, stdout: "", stderr: stderr, verb: "verify")
}
/// Reject a worker-created card as a hallucinated reference. There
/// is no dedicated `kanban reject` verb in v0.13; the right action
/// per the v0.13 release notes is to archive the card (the work
/// doesn't exist) with a comment recording the rejection reason for
/// the audit trail. Routing this through the existing `comment` +
/// `archive` verbs keeps the wire shape stable across versions.
///
/// If a future Hermes adds a dedicated `kanban reject` verb, swap
/// the body here the public surface stays "reject" returning Void.
public func rejectHallucinated(taskId: String) async throws {
// Best-effort comment first so the audit trail records the
// rejection. A failure here shouldn't block the archive log
// and continue.
do {
try await comment(
taskId: taskId,
text: "Rejected as hallucinated (no underlying work).",
author: nil
)
} catch {
#if canImport(os)
Self.logger.warning("kanban reject: comment failed, proceeding to archive (\(error.localizedDescription, privacy: .public))")
#endif
}
try await archive(taskIds: [taskId])
}
// MARK: - Drag-drop transition mapper
/// Map a board-level column transition to the right Hermes verb call.
@@ -327,4 +327,196 @@ import Foundation
#expect(stats.glanceString.isEmpty)
#expect(stats.activeCount == 0)
}
// MARK: - v0.13 (Hermes 2026.5.7) tolerant decode
//
// The contract these tests pin: a v0.13 host's task / run / detail
// JSON decodes successfully WITH the new fields populated, AND a
// pre-v0.13 (v0.12) host's task / run / detail JSON decodes
// successfully WITHOUT the new fields (everything resolves to nil
// or empty). Drift from this pair = a regression that bites every
// user not yet on Hermes v0.13.
@Test func decodeV013TaskFields() throws {
let json = """
{
"id": "t_v013",
"title": "v0.13 task",
"status": "blocked",
"max_retries": 5,
"auto_blocked_reason": "worker exited without `kanban complete`",
"hallucination_gate_status": "pending",
"diagnostics": [
{"kind": "worker_exit_no_complete", "message": "exit code 0 with no complete call", "detected_at": 1778160614},
{"kind": "darwin_zombie_detected", "detected_at": "2026-05-09T12:00:00Z"}
]
}
"""
let task = try JSONDecoder().decode(HermesKanbanTask.self, from: Data(json.utf8))
#expect(task.maxRetries == 5)
#expect(task.autoBlockedReason?.contains("kanban complete") == true)
#expect(task.hallucinationGateStatus == "pending")
#expect(task.diagnostics.count == 2)
#expect(task.diagnostics.first?.kind == "worker_exit_no_complete")
#expect(task.diagnostics.last?.detectedAt?.contains("2026") == true)
}
@Test func decodeV012TaskHasNoNewFields() throws {
// The most damaging failure mode is a v0.12 user upgrading Scarf
// and having the board stop loading because a v0.13-only field
// is required. Pin the contract.
let json = """
{"id": "t_legacy", "title": "v0.12 task", "status": "ready"}
"""
let task = try JSONDecoder().decode(HermesKanbanTask.self, from: Data(json.utf8))
#expect(task.maxRetries == nil)
#expect(task.autoBlockedReason == nil)
#expect(task.hallucinationGateStatus == nil)
#expect(task.diagnostics.isEmpty)
}
@Test func decodeMalformedDiagnosticTolerated() throws {
// If Hermes emits a malformed diagnostics value, the rest of the
// task should still decode. We use try? on the diagnostics decode
// so a single bad entry doesn't reject the whole row.
let json = """
{
"id": "t_x",
"title": "x",
"status": "ready",
"diagnostics": "not-an-array"
}
"""
let task = try JSONDecoder().decode(HermesKanbanTask.self, from: Data(json.utf8))
#expect(task.id == "t_x")
// Diagnostics field couldn't decode treat as empty.
#expect(task.diagnostics.isEmpty)
}
@Test func hallucinationGateMirrorMapsKnownValues() {
#expect(KanbanHallucinationGate.from("pending") == .pending)
#expect(KanbanHallucinationGate.from("verified") == .verified)
#expect(KanbanHallucinationGate.from("REJECTED") == .rejected) // case-insensitive
#expect(KanbanHallucinationGate.from(nil) == nil)
#expect(KanbanHallucinationGate.from("") == nil)
// Unknown wire values fall through to nil so the banner stays
// hidden; future Hermes versions can add `quarantined` etc.
// without a Scarf release.
#expect(KanbanHallucinationGate.from("quarantined") == nil)
}
@Test func diagnosticKindMirrorMapsKnownValues() {
#expect(KanbanDiagnosticKind.from("heartbeat_stalled") == .heartbeatStalled)
#expect(KanbanDiagnosticKind.from("DARWIN_ZOMBIE_DETECTED") == .darwinZombieDetected)
// Unknown kinds fall through to .unknown so views can render
// the raw string verbatim.
#expect(KanbanDiagnosticKind.from("future_kind_v014") == .unknown)
}
@Test func diagnosticSeverityMapping() {
#expect(KanbanDiagnosticKind.retryCapHit.severity == .danger)
#expect(KanbanDiagnosticKind.darwinZombieDetected.severity == .danger)
#expect(KanbanDiagnosticKind.heartbeatStalled.severity == .warning)
#expect(KanbanDiagnosticKind.workerExitNoComplete.severity == .warning)
#expect(KanbanDiagnosticKind.unknown.severity == .neutral)
}
@Test func createRequestArgvIncludesMaxRetries() {
let req = KanbanCreateRequest(title: "t", maxRetries: 5)
let argv = req.argv()
#expect(argv.contains("--max-retries"))
#expect(argv.contains("5"))
}
@Test func createRequestArgvOmitsMaxRetriesWhenAbsent() {
let req = KanbanCreateRequest(title: "t")
let argv = req.argv()
#expect(!argv.contains("--max-retries"))
}
@Test func decodeRunWithDiagnostics() throws {
let json = """
{
"id": 1,
"task_id": "t_x",
"status": "failed",
"started_at": 1778160000,
"ended_at": 1778160300,
"outcome": "crashed",
"error": "OOM",
"diagnostics": [
{"kind": "retry_cap_hit", "message": "3/3 retries exhausted"}
],
"failure_count": 3
}
"""
let run = try JSONDecoder().decode(HermesKanbanRun.self, from: Data(json.utf8))
#expect(run.diagnostics.count == 1)
#expect(run.diagnostics.first?.kind == "retry_cap_hit")
#expect(run.failureCount == 3)
}
@Test func decodeRunWithoutDiagnostics() throws {
// v0.12 run row no diagnostics, no failure_count, must still
// decode cleanly.
let json = """
{"id": 1, "task_id": "t_x", "status": "running", "started_at": 1778160000}
"""
let run = try JSONDecoder().decode(HermesKanbanRun.self, from: Data(json.utf8))
#expect(run.diagnostics.isEmpty)
#expect(run.failureCount == nil)
}
@Test func taskDetailMergesEnvelopeAndTaskDiagnostics() throws {
// Hermes's wire shape may put diagnostics on the task envelope OR
// on the inner task. `allDiagnostics` dedupes by (kind, detected_at)
// so a server emitting both sides doesn't surface dupes.
let json = """
{
"task": {
"id": "t_y",
"title": "y",
"status": "blocked",
"diagnostics": [
{"kind": "heartbeat_stalled", "detected_at": "2026-05-09T12:00:00Z"}
]
},
"comments": [],
"events": [],
"diagnostics": [
{"kind": "heartbeat_stalled", "detected_at": "2026-05-09T12:00:00Z"},
{"kind": "retry_cap_hit"}
]
}
"""
let detail = try JSONDecoder().decode(HermesKanbanTaskDetail.self, from: Data(json.utf8))
let merged = detail.allDiagnostics
#expect(merged.count == 2)
#expect(merged.contains(where: { $0.kind == "heartbeat_stalled" }))
#expect(merged.contains(where: { $0.kind == "retry_cap_hit" }))
}
@Test func taskDetailWithoutEnvelopeDiagnosticsDecodes() throws {
// Pre-v0.13 task detail no envelope diagnostics. Must decode.
let json = """
{
"task": {"id": "t_z", "title": "z", "status": "ready"},
"comments": [],
"events": []
}
"""
let detail = try JSONDecoder().decode(HermesKanbanTaskDetail.self, from: Data(json.utf8))
#expect(detail.envelopeDiagnostics == nil)
#expect(detail.allDiagnostics.isEmpty)
}
@Test func diagnosticDecodesUnixTimestamp() throws {
let json = """
{"kind": "spawn_failure", "detected_at": 1778160614}
"""
let diag = try JSONDecoder().decode(HermesKanbanDiagnostic.self, from: Data(json.utf8))
#expect(diag.kind == "spawn_failure")
// Decoder normalizes Unix int ISO-8601 string.
#expect(diag.detectedAt?.contains("2026") == true)
}
}
@@ -55,9 +55,22 @@ final class KanbanBoardViewModel {
var assigneeFilter: String? // nil = all assignees
var showArchived: Bool = false
/// Optimistic moves keyed by task id; cleared when the polled
/// response includes the same status the optimistic move set.
private var optimisticOverrides: [String: String] = [:]
/// Optimistic in-flight overrides keyed by task id; cleared when the
/// polled response confirms the new state.
/// - Status side: drag-drop column moves.
/// - Hallucination-gate side (v0.13): Verify clicks flip `pending`
/// `verified` locally so the banner disappears immediately.
/// The override entry is dropped from the dictionary entirely once
/// both sides are nil (no override needed).
private struct OptimisticOverride {
var status: String?
var hallucinationGate: KanbanHallucinationGate?
var isEmpty: Bool {
status == nil && hallucinationGate == nil
}
}
private var optimisticOverrides: [String: OptimisticOverride] = [:]
/// Tasks dropped into invalid columns produce a transient "denied"
/// banner. Stored as an explicit error to support the Cmd-Z style
/// undo we don't ship in v2.7.5 but want to leave room for.
@@ -177,8 +190,10 @@ final class KanbanBoardViewModel {
// Optimistic mutation flip the local row's status to a
// value within the destination column's range. We pick a
// representative status per column.
let optimisticStatus = optimisticStatus(for: destination)
optimisticOverrides[taskId] = optimisticStatus
let optimisticStatusValue = optimisticStatus(for: destination)
var override = optimisticOverrides[taskId] ?? OptimisticOverride()
override.status = optimisticStatusValue
optimisticOverrides[taskId] = override
let svc = service
Task {
@@ -190,11 +205,11 @@ final class KanbanBoardViewModel {
// without waiting for the 5s tick.
await refresh()
} catch let err as KanbanError {
optimisticOverrides.removeValue(forKey: taskId)
clearStatusOverride(for: taskId)
lastError = err.errorDescription
logger.warning("kanban move failed: \(err.errorDescription ?? "", privacy: .public)")
} catch {
optimisticOverrides.removeValue(forKey: taskId)
clearStatusOverride(for: taskId)
lastError = error.localizedDescription
}
}
@@ -269,6 +284,48 @@ final class KanbanBoardViewModel {
return task
}
// MARK: - Hallucination gate (v0.13)
/// User confirmed the worker-created card is real. Optimistically
/// flip the gate to `verified` so the banner disappears immediately;
/// the polling loop confirms the new state on the next tick. On
/// failure (e.g. the verb name is wrong on this v0.13.x build), the
/// override is cleared and the error surfaces in `lastError`.
func verifyHallucination(taskId: String) {
var override = optimisticOverrides[taskId] ?? OptimisticOverride()
override.hallucinationGate = .verified
optimisticOverrides[taskId] = override
Task {
do {
try await service.verify(taskId: taskId)
await refresh()
} catch let err as KanbanError {
clearHallucinationOverride(for: taskId)
lastError = err.errorDescription
logger.warning("kanban verify failed: \(err.errorDescription ?? "", privacy: .public)")
} catch {
clearHallucinationOverride(for: taskId)
lastError = error.localizedDescription
}
}
}
/// User rejected the worker-created card as a hallucinated reference.
/// Routes through `comment` + `archive` per `KanbanService.rejectHallucinated`
/// so there's an audit trail for why the card disappeared.
func rejectHallucination(taskId: String) {
Task {
do {
try await service.rejectHallucinated(taskId: taskId)
await refresh()
} catch let err as KanbanError {
lastError = err.errorDescription
} catch {
lastError = error.localizedDescription
}
}
}
// MARK: - Private helpers
private func mergePolledTasks(_ polled: [HermesKanbanTask]) {
@@ -282,25 +339,75 @@ final class KanbanBoardViewModel {
filtered = polled
}
let presentIds = Set(filtered.map(\.id))
// Drop optimistic overrides for tasks Hermes confirmed.
for (id, optimistic) in optimisticOverrides {
if let row = filtered.first(where: { $0.id == id }) {
if columnFromStatus(optimistic) == columnFromStatus(row.status) {
// Drop optimistic overrides for tasks Hermes confirmed. Two
// independent sides clear them separately so a Verify click
// still in-flight survives a status-side poll confirmation, and
// vice versa.
for (id, override) in optimisticOverrides {
guard let row = filtered.first(where: { $0.id == id }) else {
if !presentIds.contains(id) {
// Task no longer in the polled set (archived, deleted,
// or filtered out). Drop the override entirely.
optimisticOverrides.removeValue(forKey: id)
}
} else if !presentIds.contains(id) {
// Task no longer in the polled set (archived, deleted,
// or filtered out). Drop the optimistic entry.
continue
}
// Status side optimistic move confirmed.
if let optStatus = override.status,
columnFromStatus(optStatus) == columnFromStatus(row.status) {
optimisticOverrides[id]?.status = nil
}
// Hallucination-gate side optimistic verify/reject confirmed.
if let optGate = override.hallucinationGate,
KanbanHallucinationGate.from(row.hallucinationGateStatus) == optGate {
optimisticOverrides[id]?.hallucinationGate = nil
}
if optimisticOverrides[id]?.isEmpty ?? true {
optimisticOverrides.removeValue(forKey: id)
}
}
tasks = filtered
}
/// Drop the status side of a task's override (preserving any
/// in-flight hallucination-gate optimistic state).
private func clearStatusOverride(for taskId: String) {
guard var override = optimisticOverrides[taskId] else { return }
override.status = nil
if override.isEmpty {
optimisticOverrides.removeValue(forKey: taskId)
} else {
optimisticOverrides[taskId] = override
}
}
/// Drop the hallucination-gate side of a task's override (preserving
/// any in-flight status-side drag-drop).
private func clearHallucinationOverride(for taskId: String) {
guard var override = optimisticOverrides[taskId] else { return }
override.hallucinationGate = nil
if override.isEmpty {
optimisticOverrides.removeValue(forKey: taskId)
} else {
optimisticOverrides[taskId] = override
}
}
/// Effective hallucination gate for a task the optimistic override
/// wins if one is in flight; otherwise the polled value. View code
/// reads through this so the banner / dim state matches the moment-
/// after-click experience.
func effectiveHallucinationGate(_ task: HermesKanbanTask) -> KanbanHallucinationGate? {
if let override = optimisticOverrides[task.id]?.hallucinationGate {
return override
}
return KanbanHallucinationGate.from(task.hallucinationGateStatus)
}
/// Return the effective board column for a task the optimistic
/// override wins if one is in flight; otherwise the polled status.
private func effectiveColumn(_ task: HermesKanbanTask) -> KanbanBoardColumn {
if let overrideStatus = optimisticOverrides[task.id] {
if let overrideStatus = optimisticOverrides[task.id]?.status {
return columnFromStatus(overrideStatus)
}
return columnFromStatus(task.status)
@@ -13,6 +13,7 @@ import ScarfDesign
/// tenant.
struct KanbanBoardView: View {
@State private var viewModel: KanbanBoardViewModel
@Environment(\.hermesCapabilities) private var capabilitiesStore
/// When non-nil, a project board hosts this view. Drives header
/// chrome (subtitle, hidden tenant filter) and create-sheet
@@ -33,6 +34,15 @@ struct KanbanBoardView: View {
self.projectName = projectName
}
/// Convenience read for the v0.13 diagnostics flag gates the
/// max_retries field, hallucination banner, diagnostics rendering,
/// and the auto-blocked reason banner. Pre-v0.13 hosts get the
/// v2.7.5 surface unchanged. Treats a missing store as "off" so
/// harness contexts (Previews) don't accidentally surface gated UI.
private var supportsKanbanDiagnostics: Bool {
capabilitiesStore?.capabilities.hasKanbanDiagnostics ?? false
}
@State private var inspectorTaskId: String?
@State private var showingCreateSheet = false
@State private var blockSheetTaskId: String?
@@ -71,7 +81,8 @@ struct KanbanBoardView: View {
KanbanCreateSheet(
assignees: viewModel.assignees,
tenantPrefill: viewModel.tenantFilter,
projectWorkspacePath: viewModel.projectPath
projectWorkspacePath: viewModel.projectPath,
supportsKanbanDiagnostics: supportsKanbanDiagnostics
) { request in
_ = try await viewModel.createTask(request)
}
@@ -188,7 +199,9 @@ struct KanbanBoardView: View {
onDrop: { ref in
handleDrop(ref.id, on: column)
},
canCreate: column == .upNext || column == .triage
canCreate: column == .upNext || column == .triage,
supportsKanbanDiagnostics: supportsKanbanDiagnostics,
effectiveHallucinationGate: { viewModel.effectiveHallucinationGate($0) }
)
}
Spacer(minLength: ScarfSpace.s4)
@@ -208,6 +221,8 @@ struct KanbanBoardView: View {
service: viewModel.service,
taskId: taskId,
availableAssignees: viewModel.assignees,
supportsKanbanDiagnostics: supportsKanbanDiagnostics,
effectiveHallucinationGate: { viewModel.effectiveHallucinationGate($0) },
onClose: { inspectorTaskId = nil },
onClaim: {
viewModel.attemptMove(taskId: taskId, to: .running)
@@ -232,6 +247,15 @@ struct KanbanBoardView: View {
},
onReassign: { profile in
viewModel.reassignTask(taskId: taskId, to: profile)
},
onVerifyHallucination: {
viewModel.verifyHallucination(taskId: taskId)
},
onRejectHallucination: {
viewModel.rejectHallucination(taskId: taskId)
// Card vanishes from active board after archive close
// the inspector so it doesn't dangle on a deleted task.
inspectorTaskId = nil
}
)
}
@@ -24,12 +24,40 @@ struct KanbanTaskRef: Transferable {
/// - **Running** gets a blue left-edge accent + live shimmer
/// - **Blocked** gets a warning left-edge accent + glyph
/// - **Done** dims to 0.7 opacity (0.55 in dark mode)
/// - **Hallucination-gate pending** (v0.13+) dims to 0.6 + glyph and
/// shows a one-line auto-blocked reason in the footer when present.
struct KanbanCardView: View {
let task: HermesKanbanTask
let onTap: () -> Void
/// True when the connected Hermes is on v0.13+ gates the
/// hallucination dim/glyph, auto-block sub-line, and diagnostics
/// dot on the card. Pre-v0.13 hosts see the v2.7.5 chrome unchanged.
let supportsKanbanDiagnostics: Bool
/// Optimistic-aware accessor. Pre-v0.13 always nil. Otherwise delegates
/// to the board VM so a Verify click un-dims the card immediately.
let effectiveHallucinationGate: (HermesKanbanTask) -> KanbanHallucinationGate?
init(
task: HermesKanbanTask,
supportsKanbanDiagnostics: Bool = false,
effectiveHallucinationGate: @escaping (HermesKanbanTask) -> KanbanHallucinationGate? = { _ in nil },
onTap: @escaping () -> Void
) {
self.task = task
self.supportsKanbanDiagnostics = supportsKanbanDiagnostics
self.effectiveHallucinationGate = effectiveHallucinationGate
self.onTap = onTap
}
@Environment(\.colorScheme) private var colorScheme
/// Cached gate read derived once per body eval rather than recomputed
/// in each subview helper.
private var hallucinationGate: KanbanHallucinationGate? {
guard supportsKanbanDiagnostics else { return nil }
return effectiveHallucinationGate(task)
}
var body: some View {
Button(action: onTap) {
VStack(alignment: .leading, spacing: ScarfSpace.s2) {
@@ -66,13 +94,22 @@ struct KanbanCardView: View {
}
.buttonStyle(.plain)
.scarfShadow(.sm)
.opacity(task.isDone ? doneOpacity : 1.0)
// v0.13: hallucination-pending cards dim to 0.6 to signal "needs
// verification before running" without making them unreadable.
// Done cards stay at the established doneOpacity (0.7 / 0.55).
.opacity(cardOpacity)
.draggable(KanbanTaskRef(id: task.id)) {
// Drag preview the live card with a heavier shadow.
self.dragPreview
}
}
private var cardOpacity: Double {
if task.isDone { return doneOpacity }
if hallucinationGate == .pending { return 0.6 }
return 1.0
}
private var titleRow: some View {
HStack(alignment: .top, spacing: ScarfSpace.s2) {
statusGlyph
@@ -82,7 +119,15 @@ struct KanbanCardView: View {
.lineLimit(2)
.multilineTextAlignment(.leading)
Spacer(minLength: 0)
if needsAssignmentWarning {
// v0.13 hallucination glyph takes precedence over the
// unassigned glyph the hallucination state is the more
// specific signal (a worker created this card; verify it).
if hallucinationGate == .pending {
Image(systemName: "questionmark.diamond.fill")
.foregroundStyle(ScarfColor.warning)
.font(.system(size: 11, weight: .semibold))
.help("Worker-created — verify before running")
} else if needsAssignmentWarning {
Image(systemName: "exclamationmark.triangle.fill")
.foregroundStyle(ScarfColor.warning)
.font(.system(size: 11, weight: .semibold))
@@ -186,13 +231,37 @@ struct KanbanCardView: View {
}
private var footerRow: some View {
HStack(spacing: ScarfSpace.s2) {
Text(relativeTimeLabel)
.scarfStyle(.caption)
.foregroundStyle(ScarfColor.foregroundFaint)
Spacer(minLength: 0)
if let priority = task.priority, priority >= 70 {
priorityIndicator(priority)
VStack(alignment: .leading, spacing: 2) {
// v0.13: server-supplied auto-blocked reason. Renders verbatim
// (truncated to one line; full reason in the inspector).
// Pre-v0.13 hosts always have task.autoBlockedReason == nil.
if supportsKanbanDiagnostics,
KanbanStatus.from(task.status) == .blocked,
let reason = task.autoBlockedReason, !reason.isEmpty {
Text(reason)
.scarfStyle(.caption)
.foregroundStyle(ScarfColor.danger)
.lineLimit(1)
.truncationMode(.tail)
.help(reason)
}
HStack(spacing: ScarfSpace.s2) {
Text(relativeTimeLabel)
.scarfStyle(.caption)
.foregroundStyle(ScarfColor.foregroundFaint)
Spacer(minLength: 0)
// v0.13: diagnostics dot small stethoscope glyph when
// any cross-run distress signal is attached. Matches the
// chip count in the inspector.
if supportsKanbanDiagnostics, !task.diagnostics.isEmpty {
Image(systemName: "stethoscope")
.font(.system(size: 9))
.foregroundStyle(ScarfColor.warning)
.help("\(task.diagnostics.count) diagnostic signal\(task.diagnostics.count == 1 ? "" : "s")")
}
if let priority = task.priority, priority >= 70 {
priorityIndicator(priority)
}
}
}
}
@@ -17,6 +17,38 @@ struct KanbanColumnView: View {
let onCreate: () -> Void
let onDrop: (KanbanTaskRef) -> Void
let canCreate: Bool
/// True when the connected Hermes is on v0.13+. Forwarded to each
/// `KanbanCardView` so the hallucination dim/glyph + diagnostics dot
/// + auto-block sub-line gate uniformly.
let supportsKanbanDiagnostics: Bool
/// Optimistic-aware accessor forwarded to cards. Default is
/// "no override" so Previews and harness contexts still render
/// without wiring up a board VM.
let effectiveHallucinationGate: (HermesKanbanTask) -> KanbanHallucinationGate?
init(
column: KanbanBoardColumn,
tasks: [HermesKanbanTask],
isLive: Bool,
readyPillCount: Int,
onTaskTap: @escaping (HermesKanbanTask) -> Void,
onCreate: @escaping () -> Void,
onDrop: @escaping (KanbanTaskRef) -> Void,
canCreate: Bool,
supportsKanbanDiagnostics: Bool = false,
effectiveHallucinationGate: @escaping (HermesKanbanTask) -> KanbanHallucinationGate? = { _ in nil }
) {
self.column = column
self.tasks = tasks
self.isLive = isLive
self.readyPillCount = readyPillCount
self.onTaskTap = onTaskTap
self.onCreate = onCreate
self.onDrop = onDrop
self.canCreate = canCreate
self.supportsKanbanDiagnostics = supportsKanbanDiagnostics
self.effectiveHallucinationGate = effectiveHallucinationGate
}
@State private var isTargeted = false
@@ -36,7 +68,11 @@ struct KanbanColumnView: View {
.padding(.top, ScarfSpace.s4)
} else {
ForEach(tasks) { task in
KanbanCardView(task: task) {
KanbanCardView(
task: task,
supportsKanbanDiagnostics: supportsKanbanDiagnostics,
effectiveHallucinationGate: effectiveHallucinationGate
) {
onTaskTap(task)
}
}
@@ -14,6 +14,12 @@ struct KanbanCreateSheet: View {
/// Pre-filled project workspace path on per-project boards. When
/// non-nil, the workspace picker is locked to "Project Dir".
let projectWorkspacePath: String?
/// True when the connected Hermes is on v0.13+ gates the
/// `--max-retries` field and decides whether to strip newlines from
/// the title at submit time. Pre-v0.13 hosts may truncate at the
/// first `\n`; we keep the multi-line input rendering on either way
/// since a taller `TextField` is harmless on v0.12.
let supportsKanbanDiagnostics: Bool
/// Closure invoked when the user submits VM owner constructs the
/// `KanbanService.create` call.
let onSubmit: (KanbanCreateRequest) async throws -> Void
@@ -33,6 +39,11 @@ struct KanbanCreateSheet: View {
@State private var skillsInput: String = ""
@State private var tenant: String = ""
@State private var sendToTriage: Bool = false
/// v0.13: per-task retry budget. Toggle-gated so the user can opt
/// into "send the flag" vs. "let Hermes pick its default" (the
/// release notes default to 3 see TODO in KanbanCreateRequest).
@State private var maxRetriesEnabled: Bool = false
@State private var maxRetries: Int = 3
@State private var isSubmitting: Bool = false
@State private var submitError: String?
@FocusState private var titleFocused: Bool
@@ -62,6 +73,9 @@ struct KanbanCreateSheet: View {
assigneePicker
workspaceField
priorityField
if supportsKanbanDiagnostics {
maxRetriesField
}
skillsField
if projectWorkspacePath == nil {
tenantField
@@ -114,10 +128,60 @@ struct KanbanCreateSheet: View {
// MARK: - Fields
private var titleField: some View {
// v0.13 server tolerates multi-line titles. We keep the
// multi-line input rendering on for ALL versions of Hermes
// visually a taller TextField is harmless on v0.12 and decide
// at submit time whether to strip newlines (see `makeRequest`).
VStack(alignment: .leading, spacing: 4) {
ScarfSectionHeader("Title")
ScarfTextField("What needs doing?", text: $title)
.focused($titleFocused)
TextField(
"What needs doing?",
text: $title,
axis: .vertical
)
.lineLimit(1...4)
.textFieldStyle(.plain)
.scarfStyle(.body)
.padding(.horizontal, ScarfSpace.s3)
.padding(.vertical, ScarfSpace.s2)
.background(
RoundedRectangle(cornerRadius: ScarfRadius.md, style: .continuous)
.fill(ScarfColor.backgroundSecondary)
)
.overlay(
RoundedRectangle(cornerRadius: ScarfRadius.md, style: .continuous)
.strokeBorder(ScarfColor.borderStrong, lineWidth: 1)
)
.focused($titleFocused)
}
}
/// v0.13: per-task retry budget. Toggle gates whether `--max-retries`
/// is sent at all so the user can preserve "let Hermes pick the
/// default" semantics by leaving the toggle off.
private var maxRetriesField: some View {
VStack(alignment: .leading, spacing: 4) {
ScarfSectionHeader(
"Max retries",
subtitle: "0 = no retries. Defaults to 3."
)
HStack(spacing: ScarfSpace.s3) {
Toggle("Override default", isOn: $maxRetriesEnabled)
.toggleStyle(.switch)
.labelsHidden()
Stepper(value: $maxRetries, in: 0...20) {
Text("\(maxRetries)")
.scarfStyle(.bodyEmph)
.frame(minWidth: 24, alignment: .trailing)
.foregroundStyle(
maxRetriesEnabled
? ScarfColor.foregroundPrimary
: ScarfColor.foregroundFaint
)
}
.disabled(!maxRetriesEnabled)
Spacer()
}
}
}
@@ -307,7 +371,14 @@ struct KanbanCreateSheet: View {
}
private func makeRequest() -> KanbanCreateRequest {
let trimmedTitle = title.trimmingCharacters(in: .whitespacesAndNewlines)
var trimmedTitle = title.trimmingCharacters(in: .whitespacesAndNewlines)
// Pre-v0.13 hosts may truncate titles at the first `\n`. Strip
// newlines client-side when we know the connected Hermes hasn't
// shipped multi-line title support replace with a space to
// keep the user's intent visible. v0.13+ keeps newlines verbatim.
if !supportsKanbanDiagnostics {
trimmedTitle = trimmedTitle.replacingOccurrences(of: "\n", with: " ")
}
let trimmedBody = bodyText.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedAssignee = assignee.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedTenant = tenant.trimmingCharacters(in: .whitespacesAndNewlines)
@@ -330,6 +401,14 @@ struct KanbanCreateSheet: View {
}
}
// Belt-and-suspenders: the `maxRetriesField` is only rendered
// when `supportsKanbanDiagnostics` is true, but gate again here
// so a programmatic state change can't smuggle the flag onto a
// pre-v0.13 host (where the verb would error).
let resolvedMaxRetries: Int? = (supportsKanbanDiagnostics && maxRetriesEnabled)
? maxRetries
: nil
return KanbanCreateRequest(
title: trimmedTitle,
body: trimmedBody.isEmpty ? nil : trimmedBody,
@@ -342,7 +421,8 @@ struct KanbanCreateSheet: View {
idempotencyKey: nil,
maxRuntimeSeconds: nil,
createdBy: nil,
skills: parsedSkills
skills: parsedSkills,
maxRetries: resolvedMaxRetries
)
}
}
@@ -8,6 +8,16 @@ import ScarfDesign
struct KanbanInspectorPane: View {
@State private var viewModel: KanbanTaskDetailViewModel
let availableAssignees: [HermesKanbanAssignee]
/// True when the connected Hermes is on v0.13+ gates the
/// hallucination banner, max_retries chip, diagnostics block,
/// and auto-blocked reason banner. Pre-v0.13 hosts see the v2.7.5
/// inspector unchanged.
let supportsKanbanDiagnostics: Bool
/// Resolves an effective hallucination gate the board VM owns the
/// optimistic-override merge so the banner disappears immediately on
/// Verify before the polled state confirms the new gate. Falls back
/// to the wire-level value when no override is in flight.
let effectiveHallucinationGate: (HermesKanbanTask) -> KanbanHallucinationGate?
let onClose: () -> Void
let onClaim: () -> Void
let onComplete: () -> Void
@@ -15,6 +25,8 @@ struct KanbanInspectorPane: View {
let onUnblock: () -> Void
let onArchive: () -> Void
let onReassign: (String?) -> Void
let onVerifyHallucination: () -> Void
let onRejectHallucination: () -> Void
@State private var selectedTab: DetailTab = .comments
@@ -30,16 +42,22 @@ struct KanbanInspectorPane: View {
service: KanbanService,
taskId: String,
availableAssignees: [HermesKanbanAssignee] = [],
supportsKanbanDiagnostics: Bool = false,
effectiveHallucinationGate: @escaping (HermesKanbanTask) -> KanbanHallucinationGate? = { _ in nil },
onClose: @escaping () -> Void,
onClaim: @escaping () -> Void,
onComplete: @escaping () -> Void,
onBlock: @escaping () -> Void,
onUnblock: @escaping () -> Void,
onArchive: @escaping () -> Void,
onReassign: @escaping (String?) -> Void = { _ in }
onReassign: @escaping (String?) -> Void = { _ in },
onVerifyHallucination: @escaping () -> Void = {},
onRejectHallucination: @escaping () -> Void = {}
) {
_viewModel = State(initialValue: KanbanTaskDetailViewModel(service: service, taskId: taskId))
self.availableAssignees = availableAssignees
self.supportsKanbanDiagnostics = supportsKanbanDiagnostics
self.effectiveHallucinationGate = effectiveHallucinationGate
self.onClose = onClose
self.onClaim = onClaim
self.onComplete = onComplete
@@ -47,6 +65,8 @@ struct KanbanInspectorPane: View {
self.onUnblock = onUnblock
self.onArchive = onArchive
self.onReassign = onReassign
self.onVerifyHallucination = onVerifyHallucination
self.onRejectHallucination = onRejectHallucination
}
var body: some View {
@@ -159,6 +179,16 @@ struct KanbanInspectorPane: View {
ScarfBadge(workspace, kind: .neutral)
.fixedSize()
}
// v0.13: max_retries chip. Read-only Hermes
// has no `update --max-retries` verb. The
// `if let` guards pre-v0.13 hosts (always nil)
// and the explicit capability gate adds
// belt-and-suspenders.
if supportsKanbanDiagnostics, let maxRetries = task.maxRetries {
ScarfBadge("retries: \(maxRetries)", kind: .neutral)
.fixedSize()
.help("Max retries set at create time. Hermes has no update verb — re-create the task to change this.")
}
if let tenant = task.tenant, !tenant.isEmpty {
ScarfBadge(tenant, kind: .brand)
.fixedSize()
@@ -251,13 +281,18 @@ struct KanbanInspectorPane: View {
// MARK: - Body
/// Inline health banner shown above the task body when something
/// requires user attention. Two conditions trigger today:
/// 1. Task is in `ready`/`todo` with no assignee explains that
/// the dispatcher silently skips unassigned tasks.
/// 2. The most recent run ended in a non-success outcome
/// (`stale_lock`/`crashed`/`gave_up`/`timed_out`/`spawn_failed`/
/// `reclaimed`/`failed`) surfaces the error so the user
/// doesn't have to dig into the Runs tab to discover it.
/// requires user attention. Stack vertically (multiple can apply at
/// once on a v0.13 task e.g. unassigned + hallucination pending +
/// last-run-blocked).
/// Order top-to-bottom:
/// 1. **Hallucination gate (v0.13+)** pending worker-created card.
/// User must verify or reject before any other action makes sense.
/// 2. **Auto-blocked reason (v0.13+)** server-supplied reason
/// overrides the generic "Last run: blocked" banner.
/// 3. Task is in `ready`/`todo` with no assignee explains that the
/// dispatcher silently skips unassigned tasks.
/// 4. The most recent run ended in a non-success outcome surfaces
/// the error so the user doesn't have to dig into the Runs tab.
@ViewBuilder
private func healthBanner(for task: HermesKanbanTask) -> some View {
let status = KanbanStatus.from(task.status)
@@ -292,25 +327,137 @@ struct KanbanInspectorPane: View {
// Also suppress for `done` (terminal success).
let suppressFailureBanner = (status == .running) || (status == .done)
if needsAssignee {
bannerRow(
icon: "exclamationmark.triangle.fill",
tint: ScarfColor.warning,
title: "Won't run automatically",
message: "Unassigned tasks are silently skipped by Hermes's dispatcher. Add an assignee to get this scheduled."
)
} else if hadFailedEndedRun, let lastEndedRun, !suppressFailureBanner {
let label = (lastEndedRun.outcome ?? lastEndedRun.status).lowercased()
let detail = lastEndedRun.error ?? lastEndedRun.summary ?? "no details"
bannerRow(
icon: "exclamationmark.octagon.fill",
tint: ScarfColor.danger,
title: "Last run: \(label)",
message: detail
)
// v0.13: hallucination-gate state. Read through the VM's
// optimistic-aware accessor so a Verify click takes effect
// before the polled state confirms. Belt-and-suspenders gate
// on capability flag.
let hallucination: KanbanHallucinationGate? = supportsKanbanDiagnostics
? effectiveHallucinationGate(task)
: nil
// v0.13: structured auto-blocked reason. Renders the server's
// string verbatim; takes precedence over the generic "Last run:
// blocked" banner.
let autoBlockedReason: String? = (supportsKanbanDiagnostics
&& status == .blocked
&& (task.autoBlockedReason?.isEmpty == false))
? task.autoBlockedReason
: nil
// Suppress the generic last-run banner when the more specific
// server-side reason supersedes it.
let suppressGenericFailure = autoBlockedReason != nil
VStack(alignment: .leading, spacing: ScarfSpace.s2) {
if hallucination == .pending {
hallucinationBanner
}
if let reason = autoBlockedReason {
bannerRow(
icon: "exclamationmark.octagon.fill",
tint: ScarfColor.danger,
title: "Auto-blocked",
// Verbatim Hermes-side message is the source of truth.
message: reason
)
}
if needsAssignee {
bannerRow(
icon: "exclamationmark.triangle.fill",
tint: ScarfColor.warning,
title: "Won't run automatically",
message: "Unassigned tasks are silently skipped by Hermes's dispatcher. Add an assignee to get this scheduled."
)
}
if hadFailedEndedRun, let lastEndedRun,
!suppressFailureBanner, !suppressGenericFailure {
let label = (lastEndedRun.outcome ?? lastEndedRun.status).lowercased()
let detail = lastEndedRun.error ?? lastEndedRun.summary ?? "no details"
bannerRow(
icon: "exclamationmark.octagon.fill",
tint: ScarfColor.danger,
title: "Last run: \(label)",
message: detail
)
}
// v0.13: cross-run diagnostics on the task header.
if supportsKanbanDiagnostics, !task.diagnostics.isEmpty {
diagnosticsBlock(task.diagnostics)
}
}
}
/// v0.13 hallucination-gate banner Verify / Reject affordances for
/// worker-created cards waiting on user verification.
private var hallucinationBanner: some View {
HStack(alignment: .top, spacing: ScarfSpace.s2) {
Image(systemName: "questionmark.diamond.fill")
.foregroundStyle(ScarfColor.warning)
.font(.system(size: 13, weight: .semibold))
VStack(alignment: .leading, spacing: 4) {
Text("Created by a worker — verify before running")
.scarfStyle(.captionStrong)
.foregroundStyle(ScarfColor.foregroundPrimary)
Text("A worker claimed it created this card; Hermes hasn't confirmed the underlying work exists. Verify the card matches a real follow-up, or reject if it's a hallucinated reference.")
.scarfStyle(.caption)
.foregroundStyle(ScarfColor.foregroundMuted)
HStack(spacing: ScarfSpace.s2) {
Button("Verify", action: onVerifyHallucination)
.buttonStyle(ScarfPrimaryButton())
Button("Reject", action: onRejectHallucination)
.buttonStyle(ScarfDestructiveButton())
}
.padding(.top, 2)
}
Spacer(minLength: 0)
}
.padding(ScarfSpace.s2)
.background(
RoundedRectangle(cornerRadius: ScarfRadius.md, style: .continuous)
.fill(ScarfColor.warning.opacity(0.10))
)
.overlay(
RoundedRectangle(cornerRadius: ScarfRadius.md, style: .continuous)
.strokeBorder(ScarfColor.warning.opacity(0.4), lineWidth: 1)
)
}
/// v0.13 diagnostics block renders a list of distress signals.
/// Used both at the task-header level (cross-run signals) and per
/// run on the Runs tab (in-flight signals). Wraps in a horizontal
/// scroll so a long diag list doesn't blow out inspector width.
private func diagnosticsBlock(_ diags: [HermesKanbanDiagnostic]) -> some View {
VStack(alignment: .leading, spacing: 4) {
Text("Diagnostics")
.scarfStyle(.captionUppercase)
.foregroundStyle(ScarfColor.foregroundFaint)
ScrollView(.horizontal, showsIndicators: false) {
HStack(spacing: 4) {
ForEach(diags) { diag in
diagnosticBadge(diag)
}
}
}
}
.padding(.top, 4)
}
@ViewBuilder
private func diagnosticBadge(_ diag: HermesKanbanDiagnostic) -> some View {
let kind = KanbanDiagnosticKind.from(diag.kind)
let badgeKind: ScarfBadgeKind = {
switch kind.severity {
case .danger: return .danger
case .warning: return .warning
case .neutral: return .neutral
}
}()
// Render the raw kind string view code stays in sync with
// whatever future kinds Hermes ships. The typed mirror picks
// the badge tint and tooltip glyph; the verbatim wire string
// is the user-facing label.
ScarfBadge(diag.kind, kind: badgeKind)
.help(diag.message ?? diag.kind)
}
private func bannerRow(
icon: String,
tint: Color,
@@ -562,6 +709,9 @@ struct KanbanInspectorPane: View {
private func runRow(_ run: HermesKanbanRun) -> some View {
VStack(alignment: .leading, spacing: 2) {
HStack(spacing: ScarfSpace.s2) {
// Render the wire-side outcome / status string verbatim so
// v0.13's richer outcome strings ("zombied reclaimed by
// reaper", etc.) surface unchanged.
ScarfBadge(run.outcome ?? run.status, kind: outcomeKind(run.outcome ?? run.status))
if let profile = run.profile {
Text(profile)
@@ -585,6 +735,12 @@ struct KanbanInspectorPane: View {
.foregroundStyle(ScarfColor.danger)
.frame(maxWidth: .infinity, alignment: .leading)
}
// v0.13: per-run diagnostics. Gated on capability so a future
// server-side change can't accidentally surface partial UX
// on a pre-v0.13 host.
if supportsKanbanDiagnostics, !run.diagnostics.isEmpty {
diagnosticsBlock(run.diagnostics)
}
}
.padding(ScarfSpace.s2)
.background(
@@ -619,23 +775,32 @@ struct KanbanInspectorPane: View {
@ViewBuilder
private var primaryAction: some View {
if let task = viewModel.detail?.task {
switch KanbanStatus.from(task.status) {
case .ready, .todo:
Button("Start", action: onClaim)
.buttonStyle(ScarfPrimaryButton())
.help("Atomically claim this task and start the worker. Moves it to Running.")
case .running:
Button("Complete", action: onComplete)
.buttonStyle(ScarfPrimaryButton())
.help("Mark this task as Done. You'll be prompted for an optional result summary.")
case .blocked:
Button("Unblock", action: onUnblock)
.buttonStyle(ScarfPrimaryButton())
.help("Return this task to the Up Next queue so the dispatcher can pick it up again.")
case .triage:
EmptyView()
default:
// v0.13: when the hallucination gate is pending, suppress the
// primary action the banner provides Verify / Reject as the
// gate. Showing "Start" alongside the banner would let the
// user dispatch a card Hermes hasn't confirmed exists.
if supportsKanbanDiagnostics,
effectiveHallucinationGate(task) == .pending {
EmptyView()
} else {
switch KanbanStatus.from(task.status) {
case .ready, .todo:
Button("Start", action: onClaim)
.buttonStyle(ScarfPrimaryButton())
.help("Atomically claim this task and start the worker. Moves it to Running.")
case .running:
Button("Complete", action: onComplete)
.buttonStyle(ScarfPrimaryButton())
.help("Mark this task as Done. You'll be prompted for an optional result summary.")
case .blocked:
Button("Unblock", action: onUnblock)
.buttonStyle(ScarfPrimaryButton())
.help("Return this task to the Up Next queue so the dispatcher can pick it up again.")
case .triage:
EmptyView()
default:
EmptyView()
}
}
}
}