…lic-moment

Introduce deterministic phrasing variants for symbolic moment replies

…ch fails

Agent-Logs-Url: https://github.com/DHCross/Shipyard/sessions/1d7203b3-5835-47ff-abf7-b57cbfd9e007

Co-authored-by: DHCross <45954119+DHCross@users.noreply.github.com>

… errors

When a Symbolic Moment read stalled mid-stream, three defects compounded:

- The Gemini reader had no per-chunk watchdog, so a stalled stream hung
  until Vercel's maxDuration killed the route, bypassing the labeled
  fallbacks in resolveReplyIntegrity.
- The client inserted an empty assistant bubble on the first DATA frame,
  leaving a ghost behind whenever no CHUNK followed.
- The outer try/catch wrapped post-stream enrichment, so a vault-sync or
  blind-mirror throw appended a generic "channel issue" bubble even when
  the reply had already streamed in.

Server: add idle (60s first-chunk / 30s subsequent) + overall (170s)
watchdogs around the Gemini reader. On stall, cancel the reader and set
providerFinishReason='stream_stall' so the existing integrity pipeline
emits GENERATION_INCOMPLETE with a Clouded Skies fallback instead of
a hung connection.

Client: defer assistant-bubble insertion until the first non-empty CHUNK,
add a 75s/45s defense-in-depth read timeout, and harden enrichment
(applyVaultAction, materializeAssistantBlindMirror, extractCheckpointQuestion)
in local try/catch blocks. Track in-flight render state in a ref so the
outer catch can suppress the redundant error bubble when the reply
already rendered. Defensively scrub any empty-text ghost on error.

Adds RAVEN_STREAM_FIRST_CHUNK_MS / RAVEN_STREAM_CHUNK_IDLE_MS /
RAVEN_STREAM_OVERALL_MS env knobs and three new integrity tests
covering the Clouded Skies stall path.

https://claude.ai/code/session_018fAnZmYcnz8i9bqS3Nsjn6

- UI_REVIEW.md: full screen survey, token-vs-view matrix, ranked fix list
- RavenDesignTokens.swift: add RavenTypography enum + View extension modifiers
  (.ravenTitle, .ravenBody, .ravenCaption, .ravenMono)
- RaveniOSApp.swift: UITabBarAppearance — cosmos dark chrome, ravenAmber selected tint
- ChatView.swift: cosmosBackground shell, amber accents, token typography,
  cosmos-tinted bubbles/input/banners, dim white text on dark field
- SessionSealedCard.swift: cosmos dark panel, amber CTA, token-driven dividers
- VaultView.swift: PRIMARY badge + active checkmark → ravenAmber
- ModeSelectorView.swift: icon/checkmark/ModePill → ravenAmber accent
- TodayScreenView.swift: cosmosBackground, ravenAmber replaces cyan throughout

No behavioral changes. ViewModels, API clients, auth flows untouched.

…hoke

Raven's first ElevenLabs response was stuttering because the reverb chain
(ConvolverNode + 1.6s impulse buffer + dry/wet gains) was lazily built on
the first sendText() call, racing the audio that was already trying to
play. Subsequent responses reused the cached graph and played cleanly.

Build the chain inside unlock() — which runs on the user's "Enable Audio"
gesture — and pass a silent 1-sample buffer through it so the convolver
allocates its kernel before any TTS audio arrives.

1. Fix effect cleanup bug: auto-play effect was not calling stop() on
   unmount, potentially leaving audio playing after component destroys.
   Now properly stops audio when dependencies change.

2. Add per-message replay button: users can click "Replay" next to "Copy"
   to re-synthesize and play the Raven response again. Button is:
   - Disabled while audio is already playing
   - Uses same normalization as auto-play (normalizeReflectionSpeechText)
   - Calls stop() before replaying to ensure clean state
   - Does not interfere with auto-play state tracking

3. Code review:
   - No master volume control (dry 0.82 + wet 0.35 reverb mix is fixed)
   - Abort/stop logic is solid and handles race conditions
   - Audio context suspension/resume works correctly
   - Message lifecycle cleanup was the only issue found