User feedback: 50+ hours of agent work, nothing demonstrably working.
Fanned out 6 deep auditors (voice, HUD, vision, memory, LLM, tests);
all reports landed at .planning/audit-2026-05-03/ with brutal-honesty
mandates. Synthesis (SYNTHESIS.md) confirmed: every modality has at
least one fatal break between code-that-passes-tests and
code-that-runs. Track A is the smallest credible path to one working
modality (text turn + animated rings).
Closed under TDD discipline:
**Item 4 — HUD idle ring static rendering (F-A1-01).**
- webview/packages/hud/src/hud/stateUniforms.ts:30 — was
`pulse: 0.0, rotate: 0.0` for idle, the all-static configuration
that rendered STANDBY as dots instead of animated rings. Now
pulse: 0.4, rotate: 0.05 — gentle ambient distinct from booting +
thinking.
- webview/packages/hud/tests/stateUniforms.test.ts — table updated;
new regression-guard `STATE_PARAMS[*] is not all-static` (7 cases,
one per HudState) prevents anyone from re-zeroing a state.
**Item 1 — CacheHints eligibility gate (likely streamTruncated cause).**
- packages/AgentCore/Sources/AgentCore/CacheHints.swift —
+ static func eligibleForSystemPrompt(_:ttl:). Anthropic's prompt
cache requires ≥1024 tokens at the breakpoint; below that, the
server returns 200 OK + immediate-EOF for `extended-cache-ttl`
hints. The orchestrator's default system prompt is ~10 tokens.
Helper returns nil for sub-threshold prompts so no cache_control
marker is emitted.
- packages/AgentCore/Sources/AgentOrchestrator/AgentOrchestrator.swift
— call sites now pass `CacheHints.eligibleForSystemPrompt(finalSystem)`
through runTurnLoop instead of unconditional `.extended1h`.
- Tests: CacheHintsEligibilityTests (6 cases), RequestBodyTests R5a/R5b
(2 cases verifying small-prompt → no cache_control in encoded JSON,
large-prompt → cache_control present).
**Item 2 — StreamOutcome diagnostic.**
- packages/AgentCore/Sources/AnthropicProvider/StreamOutcome.swift —
new pure classifier that distinguishes:
- non-2xx HTTP status
- 200 OK + 0 bytes (cache_control / auth-header rejection class)
- 200 OK + bytes + 0 frames (malformed body)
- 200 OK + frames + EOF before message_stop (mid-stream drop)
- 200 OK complete (healthy)
AnthropicProvider's read loop counts frames + bytes and logs the
summary once per stream. Production logs now distinguish failure
modes that previously all surfaced as `streamTruncatedFinal`.
- Tests: StreamOutcomeTests (7 cases, all branches).
**Item 3 — KeychainError surfacing.**
- packages/AgentCore/Sources/AnthropicProvider/AnthropicAPIKeyProvider.swift
— new builder `make(keychain:item:)` returns the
`@Sendable () async throws -> String` closure with errors
propagating verbatim. Closes the audit's hidden-401 finding:
`(try? keychainStoreLocal.get(.anthropic)) ?? ""` swallowed the
real KeychainError into an empty x-api-key, producing
`401 x-api-key header is required` indistinguishable from a
stale-key 401. Now the actual error reaches the chat panel via
AnthropicProvider → orchestrator.error → BusForwarder →
submitRejected.
- App/AppDelegate.swift — both Anthropic provider construction sites
(installAgent, installVision T3 wiring) now use the propagating
builder.
- Tests: AnthropicAPIKeyProviderTests (6 cases — itemNotFound,
unexpectedStatus, duplicateItem propagation; happy path; explicit
item; default item).
**Item 5 — F1 #2 chat-turn round-trip e2e tests.**
- packages/Bus/Tests/BusTests/RealWKWebViewIntegrationTests.swift —
+ 2 new tests using a real WKWebView:
- test_chatTurnRoundTrip_busOutboundReachesPageHandler — Swift
`bridge.send(.turnStarted/tokenDelta/turnEnded)` reaches the
page's onOutbound handler. This is the test the v0.12.0 audit
called out as catching BLOCKER-INT-1, INT-2, INT-3,
F-E-RACE-1, F-E-FK-1, F-E-WIRE-1 in one shot.
- test_chatTurnRoundTrip_busInboundFromJSReachesSwiftHandler —
JS-side `window.jarvisBus.send({type:'chatSubmit',...})` —
exactly what ChatInput.tsx does — reaches the bridge's
onInbound handler with the right body.
**Verification:**
- AgentCore: 215/215 (was 178; +37 across BusForwarder, CacheHints,
StreamOutcome, AnthropicAPIKeyProvider, RequestBody R5).
- Replay: 33/33.
- Bus: 57/58 (1 pre-existing failure: F-A2-01 stale `JarvisBusWorld`
assertion documented in AUDIT-FINDINGS, separate scope).
- webview/packages/hud: 94/94 (was 87; +7 stateUniforms regression-
guards + idle table updates).
- All 15 boundary grep gates: PASS.
- scripts/check-app-builds.sh: PASS.
**Audit reports retained at .planning/audit-2026-05-03/:**
- SYNTHESIS.md (consolidated, with triage plan)
- hud-audit.md, llm-audit.md, memory-audit.md, tests-audit.md,
vision-audit.md, voice-audit.md, voice.md (per-modality detail)
**Carry-forward (NOT closed this commit):**
- F-A2-01 stale WebviewBridgeOutboundTests assertion (pre-existing).
- Voice (F): models never bundled, audio graph never instantiated,
STT bridge body is `_ = chunk`, TTS engine nil. ~1 day.
- Vision (F): AVCapturePhotoOutput allocated but capturePhoto never
called; HUD camera button doesn't exist. ~1 day.
- Memory (F): Apple's stripped libsqlite3 prevents sqlite-vec from
loading; "future ops plan" has zero commits. ~3 days.
- LLM (D+): NoopBusGateway still drops tool-call events
(BLOCKER-INT-1).
- Tests (C-): 5 XCTAssertTrue(true) tautologies + multiple
rubber-stamp tests defending stubs.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
121 lines
4.7 KiB
Swift
121 lines
4.7 KiB
Swift
import XCTest
|
|
import Keychain
|
|
@testable import AnthropicProvider
|
|
|
|
/// Coverage for `AnthropicAPIKeyProvider.make(keychain:item:)` — the
|
|
/// builder that propagates `KeychainError` instead of swallowing it into
|
|
/// the empty-string fallback that produced the 2026-05-03 audit's
|
|
/// silent-401 symptom.
|
|
final class AnthropicAPIKeyProviderTests: XCTestCase {
|
|
|
|
// MARK: - Test doubles
|
|
|
|
private struct ThrowingKeychain: KeychainStore {
|
|
let error: KeychainError
|
|
func set(_ value: String, for item: KeychainItem) throws { throw error }
|
|
func get(_ item: KeychainItem) throws -> String { throw error }
|
|
func delete(_ item: KeychainItem) throws { throw error }
|
|
}
|
|
|
|
private struct StaticKeychain: KeychainStore {
|
|
let value: String
|
|
func set(_ value: String, for item: KeychainItem) throws {}
|
|
func get(_ item: KeychainItem) throws -> String { value }
|
|
func delete(_ item: KeychainItem) throws {}
|
|
}
|
|
|
|
private struct CapturingKeychain: KeychainStore, @unchecked Sendable {
|
|
// @unchecked Sendable: the captured array is mutated only inside
|
|
// a serial test method; no cross-thread access in tests.
|
|
final class Box: @unchecked Sendable {
|
|
var requested: [KeychainItem] = []
|
|
}
|
|
let box = Box()
|
|
let value: String
|
|
func set(_ value: String, for item: KeychainItem) throws {}
|
|
func get(_ item: KeychainItem) throws -> String {
|
|
box.requested.append(item)
|
|
return value
|
|
}
|
|
func delete(_ item: KeychainItem) throws {}
|
|
}
|
|
|
|
// MARK: - Error propagation (KP-1..KP-3)
|
|
|
|
/// KP-1: itemNotFound throws verbatim — does NOT collapse to empty
|
|
/// string. This is the literal regression the 2026-05-03 audit named.
|
|
func test_propagates_itemNotFound() async {
|
|
let kc = ThrowingKeychain(error: .itemNotFound)
|
|
let provider = AnthropicAPIKeyProvider.make(keychain: kc, item: .anthropic)
|
|
|
|
do {
|
|
_ = try await provider()
|
|
XCTFail("provider must throw, not silently substitute empty string")
|
|
} catch let err as KeychainError {
|
|
XCTAssertEqual(err, .itemNotFound)
|
|
} catch {
|
|
XCTFail("expected KeychainError, got \(error)")
|
|
}
|
|
}
|
|
|
|
/// KP-2: unexpectedStatus also propagates verbatim with its OSStatus.
|
|
func test_propagates_unexpectedStatus() async {
|
|
let kc = ThrowingKeychain(error: .unexpectedStatus(-25300))
|
|
let provider = AnthropicAPIKeyProvider.make(keychain: kc, item: .anthropic)
|
|
|
|
do {
|
|
_ = try await provider()
|
|
XCTFail("provider must throw")
|
|
} catch let err as KeychainError {
|
|
XCTAssertEqual(err, .unexpectedStatus(-25300))
|
|
} catch {
|
|
XCTFail("expected KeychainError, got \(error)")
|
|
}
|
|
}
|
|
|
|
/// KP-3: duplicateItem also propagates (less likely on read, but the
|
|
/// contract is total — every KeychainError variant flows through).
|
|
func test_propagates_duplicateItem() async {
|
|
let kc = ThrowingKeychain(error: .duplicateItem)
|
|
let provider = AnthropicAPIKeyProvider.make(keychain: kc, item: .anthropic)
|
|
|
|
do {
|
|
_ = try await provider()
|
|
XCTFail("provider must throw")
|
|
} catch let err as KeychainError {
|
|
XCTAssertEqual(err, .duplicateItem)
|
|
} catch {
|
|
XCTFail("expected KeychainError, got \(error)")
|
|
}
|
|
}
|
|
|
|
// MARK: - Happy path (KP-4..KP-5)
|
|
|
|
/// KP-4: when the keychain returns a value, the provider relays it.
|
|
func test_returns_value_on_success() async throws {
|
|
let kc = StaticKeychain(value: "sk-ant-test-12345")
|
|
let provider = AnthropicAPIKeyProvider.make(keychain: kc, item: .anthropic)
|
|
let key = try await provider()
|
|
XCTAssertEqual(key, "sk-ant-test-12345")
|
|
}
|
|
|
|
/// KP-5: provider passes the requested item through unchanged. Locks
|
|
/// in the contract that callers can target a different item without
|
|
/// the builder substituting `.anthropic` silently.
|
|
func test_uses_specified_item() async throws {
|
|
let kc = CapturingKeychain(value: "_")
|
|
let other = KeychainItem(service: "com.example.test", account: "test-account")
|
|
let provider = AnthropicAPIKeyProvider.make(keychain: kc, item: other)
|
|
_ = try await provider()
|
|
XCTAssertEqual(kc.box.requested, [other])
|
|
}
|
|
|
|
/// KP-6: default `item` parameter is `.anthropic`.
|
|
func test_default_item_is_anthropic() async throws {
|
|
let kc = CapturingKeychain(value: "_")
|
|
let provider = AnthropicAPIKeyProvider.make(keychain: kc)
|
|
_ = try await provider()
|
|
XCTAssertEqual(kc.box.requested, [.anthropic])
|
|
}
|
|
}
|