Commit Graph
11 Commits
Author SHA1 Message Date
jpmschweitzerandClaude Opus 4.6 aa79dd97e7 fix(simulation): Clippy cleanup and CI enforcement (#635)
Fix all Clippy warnings across the server codebase (2411 insertions, 1341
deletions). Raise type-complexity-threshold to 750 and too-many-arguments
to 12 in .clippy.toml for idiomatic Bevy ECS system signatures. The server
now passes `cargo clippy -- --deny warnings` cleanly.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 10:33:15 +01:00
jpmschweitzerandClaude Opus 4.6 e8263e209e refactor(data): rename Krenn to Van Maanen's Star
System S-057 assigned to real star GJ 35 (Van Maanen's Star, DG white
dwarf at 13.9 ly). Renamed across all content, server code, docs,
decisions, wiki lore, and config files. 224 files updated.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 00:23:26 +01:00
jpmschweitzerandClaude Opus 4.6 51414b0b63 fix(simulation): address PR #89 review — version comment, settings contract, docs, dead process recovery
Must-fix: protocol version comment now references PROTOCOL_VERSION
(no hardcoded number), settings delete is idempotent no-op.

Suggestions addressed: BehaviorModifier dedup claim dropped, hash
collision safety documented, FK pragma in test store, columns_to_value
consolidated, modifier_hint mismatch logging, OffDuty test coverage,
batching tradeoff documented, unknown value_type warning, occluded
text risk documented, dead child respawn in voice worker, INJECT
block ambiguity documented.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-13 09:34:33 +01:00
jpmschweitzerandClaude Opus 4.6 1a4fd578cc feat(simulation): voice pipeline integration — Factual bypass, observer wiring, tell iteration (#650 #652 #651)
ContentType::Factual bypasses LLM for fact-bearing lines (numbers,
denials). Observer enrichment systems rewrite dialogue/conversation
text with voiced versions before snapshot assembly. Friendly and
RoutineDeviation tells get concrete surface-pattern examples.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-13 09:11:44 +01:00
jpmschweitzerandClaude Opus 4.6 9f34d030d7 feat(voice): complete Spike 2 voice pipeline with quality-tested prompt engine
Spike 2 delivers the full voice pipeline: queue → worker pool → sr-voice
child process (stdio JSONL) → cache → disk. Three rounds of quality testing
with Paula, Mellanie, and Gestalt produced iterative prompt improvements.

Prompt engine (prompt_builder.rs):
- Example-based epistemic marker integration (not keyword lists)
- Length-aware Angry tell variant (preserves facts on long content)
- Double-prompt technique: REMEMBER block repeats constraints near OUTPUT:
- Imperative injection framing (composition engine controls frequency)
- Anti-invention constraint ("do not add information not in the input")
- Universal RULES cleaned: worldbuilding moved to culture personas

Worker pool (worker.rs):
- Output post-processor strips after first newline (prevents prompt leakage)
- Watchdog poll loop (1s ticks) replaces blocking sleep for cancel
- Child health check before writing (try_wait)

Test infrastructure:
- voice_pipeline.rs: end-to-end test, auto-detects real sr-voice or mock
- voice_quality_batch.rs: 39 edge-case prompts for quality review
- mock-stdio.sh: Python JSONL mock for CI (no model needed)
- Makefile targets: test-voice-mock, test-voice-real

Quality results (Gemma 2B Q4_K_M, CPU ~13 t/s):
- Epistemic markers: naturally integrated (round 1 comma-lists fixed)
- Tell differentiation: 3/5 working (Nervous, Guarded, Angry)
- Information preservation: ~90% (up from ~70%)
- Prompt leakage: eliminated
- Open: Friendly/RoutineDeviation tells inert (#651), Factual bypass (#650)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 19:20:06 +01:00
jpmschweitzerandClaude Opus 4.6 e93a9e8b70 fix(voice): address PR review findings — 3 critical, 5 warning, 4 suggestion
Critical fixes:
- Pause mechanism: workers now hold requests during pause instead of
  dropping them. Queue and worker pool share the same AtomicBool flag
  via VoiceQueue::paused_flag(). Submit() rejects while paused.
- Seed type: sr-voice accepts u64 seeds over IPC (explicit u32 truncation
  for llama.cpp sampler, documented).

Warning fixes:
- HashMap → BTreeMap in cache.rs and worker.rs (D-010 determinism mandate).
  Added Ord derives to CacheKey, ContentType, TellCategory.
- VoicePipe::generate() watchdog kills child after 120s timeout to prevent
  indefinite blocking on read_line.
- VoiceCacheStore Drop impl calls save_all() on shutdown.
- trait-modifiers.ron: fixed 3 wrong trait names (Impulsive→Compassionate,
  Methodical→Incurious, Stubborn→Ruthless) to match PersonalityTrait enum.

Suggestion fixes:
- Worker spawn: log error + reduce pool instead of panic on thread failure.
- on_battery(): added macOS detection via pmset.
- Epistemic markers: lowercased constants, removed redundant to_lowercase().
- cache.rs: documented non-atomic write tradeoff.
- queue.rs: reprioritize() bypasses pause check (it runs during pause).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 18:11:46 +01:00
jpmschweitzerandClaude Opus 4.6 0b0fa8c04e refactor(voice): replace HTTP with stdin/stdout IPC for sr-voice workers
Gemma 2 T&C compliance: exposed HTTP ports allow mods or external code
to reach the model, complicating license enforcement. Switch to piped
stdin/stdout (JSONL protocol) so the model is only reachable through
the game server's internal queue.

- worker.rs: VoicePipe owns Child + piped stdin/stdout, VoiceProcessConfig
  replaces port-based config, workers spawn their own sr-voice child
- hardware.rs: remove VoiceInstanceManager (port/process lifecycle),
  replace with evaluate_scaling() free function + HardwareProbe::voice_config()
- sr-voice: add --stdio flag to serve command, new stdio.rs JSONL mode
- Remove ureq dependency from server crate (no longer needed)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 17:57:32 +01:00
jpmschweitzerandClaude Opus 4.6 be6f2a3db9 feat(voice): add hardware detection + dynamic sr-voice instance management (Phase 4)
GPU-aware scaling: NVIDIA (nvidia-smi), AMD (sysfs VRAM), Apple Silicon
(unified memory). GPU mode detected at install, persisted to settings.
Scaling ceiling: (free_resource - existing_llm_usage) / 2 / per_instance_cost.
VoiceInstanceManager spawns/stops sr-voice processes on unique ports.
Battery detection scales to 1 worker.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 17:32:20 +01:00
jpmschweitzerandClaude Opus 4.6 fafa1c49b8 feat(voice): stub voice cache lookup for behavior text (Phase 3)
Add lookup.rs with voiced_behavior() — ready to wire into a behavior-serving
system once one exists (Q-058). Tell behaviors always passthrough (never
re-voiced). Cache miss returns base text (graceful degradation).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 17:13:15 +01:00
jpmschweitzerandClaude Opus 4.6 82a911f3aa feat(voice): add cache, queue, and worker modules (D-138, Spike 2 Phase 2)
MessagePack voice cache with per-zone persistence and version invalidation.
Priority work queue with crossbeam bounded channel, backpressure, pause/resume,
and zone-change reprioritization. Inference worker pool with empty output guard
and graceful degradation to base text.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 17:09:24 +01:00
jpmschweitzerandClaude Opus 4.6 33030fcc58 feat(engine): voice pipeline Phase 1 — composition engine and data model
Add the voice pipeline composition engine (D-138 Spike 2, Phase 1):

- voice/prompt_builder.rs: full prompt assembly from culture profile,
  tell state, and base text. Handles occasional injection gating,
  epistemic marker extraction, content-length-gated tell injection.
  16 unit tests.

- blueprint.rs: CultureProfile gains voice_persona, voice_examples,
  occasional_injections fields. NpcBlueprint gains tell_behaviors.
  OccasionalInjection struct with kind discriminator (oath/faith/
  hesitancy/etc), frequency, and tell-suppression gating.

- culture-krenn.ron: v2 voice injector from Spike 1 — persona block,
  3 examples, oath injection at 0.25 frequency.

- D-138 amended: Phi-3 dropped entirely, exact Gemma 2B provenance
  documented. Model file renamed to gemma2.gguf.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 16:35:39 +01:00