New template system for project documentation with standardized
frontmatter (title, description, type, status, decision_refs).
Templates for architecture, design, briefing, workshop, and test-plan
document types. Enables context-aware loading alongside the existing
wiki template system.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Per D-122 (all NPCs generated), these 18 character profiles and roster
index are superseded by the generator pipeline. Keeping named NPCs in
the wiki anchors generators to specific patterns instead of exploring
the design space. The Kael Davan profile is preserved as a generator
quality exemplar in wiki/_templates/character-exemplar.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Every wiki entry now has a one-line description field for context-aware
loading. Covers factions, technology, concepts, contraband, locations,
star-systems, authoring guides, and triangles (29 files).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
All 14 wiki templates now include a `description` frontmatter field for
context-aware document loading. Agents can filter by description before
loading full files, reducing context window pressure.
Added character-exemplar.md preserving the Kael Davan Tier 1 profile as
generator quality target (D-122). Updated GOVERNANCE.md to document the
new field in the entry creation workflow.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Gemma 2B is picked and embedded — the provenance policy text was
an unnecessary addition. The model choice is final.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Single-consonant difference undermined cultural distinctiveness.
"Arvenis" extends past the collision point while staying in Vael's
polysyllabic register.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update content-structure-canonical.md to reflect Krenn NEVER block
and behavior_modifiers now present. Fix base-text-authoring-guide
example to match actual RON primitive format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
D-141→D-142 reference in zone-type templates, name pool
cross-contamination resolved (zero overlaps across cultures),
modifier coverage expanded to 2+ per category, authority_response
differentiated Krenn/Osse, gendered pronouns removed from neutral
templates, Osse ungrounded lore terms replaced, dual_lens dead
properties stripped from environmental YAML, overheard.yaml
annotated as legacy (#664).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three scalability-focused authoring guides for content production
across 300+ systems:
- base-text-authoring-guide.md: elevation checklist, quality test
- culture-authoring-guide.md: 8-step workflow, modifier contract,
cross-cultural contrast test, one-day-per-culture target
- content-structure-canonical.md: directory template, surviving
structure audit, culture RON field reference
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
D-140: Paula's six rules for dialogue re-voicing quality — secret-tier
passthrough, epistemic weight, access tier feel, named entity
passthrough, relationship-specific lines, culture register override.
D-142: Zone-type template architecture — three-layer behavior system,
31 zone types for v1.0, POI three-tier system, scale math for 300+
systems with 300+ cultures. Amend D-123 (baked vs pre-voiced modes),
supersede D-124 (resolved by two-spike strategy).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move behavior_primitives from per-location zone specs into global
zone-type template files (content/global/zone-types/). Location specs
now declare zone_type and contain only metadata (role weights, social
sites, economic/density levels). Primitives are culture-neutral and
reusable across all 300+ systems. Scrub Krenn-specific language.
New files: rural_agricultural.ron, industrial_freight.ron
Modified: krenn-rural-zone.ron, krenn-industrial-zone.ron (metadata only)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Author two new culture RON files (culture-vael.ron, culture-osse.ron)
with voice_persona, voice_examples, occasional_injections, explicit
NEVER blocks, and behavior_modifiers (7 categories each). Add
behavior_modifiers to culture-krenn.ron and explicit NEVER block.
Modifier categories: work_pace, physical_manner, social_signal,
task_completion, environmental_scan, offduty_posture, authority_response.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
W1/A2: add SimBridge.CONNECTED guard before send_input in toggle handler
W2/A1: assert PlatformInfo != null in HardwareDetector._ready();
add ordering comment in project.godot [autoload] section
W3: replace FileAccess.open() with get_file_as_string() in
read_benchmark_cache() — auto-closes, no leak
W4/A3: add _extract_bool_setting() helper in game_state.gd that handles
both {"Bool": true} and plain bool; push_warning on type mismatch
S5: sync _pre_battery_pref from GameState after load_ai_pref() in
HardwareDetector._ready() — closes race if system starts on battery
S6: separate "red" TPT status into its own arm with STATUS_RED dot and
label colour — three-colour mapping: green/yellow/red now distinct
A4: replace DebugConsole.PREFS_PATH compile-time dependency in
_save_ai_pref() with local SETTINGS_CFG_PATH constant
S7 (battery CI guard) already applied by Hoshe in test file.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Close Q-015 as obsolete (D-122 eliminates hand-authored FRIEND).
Update Q-033 reframe to reference D-139 composable behaviors.
Replace franchise-specific "Starflyer's agents" with generic
"hostile actors" in D-018 (perception.md).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
D-141: client-side PlatformInfo autoload centralizing all OS queries.
Q-059: resolved — full interface scope (23 properties, 7 categories).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
config_dir, benchmark_cache_path, executable_path, model_dir were
populated in _init_paths() but missing from the diagnostics dict.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Player autonomy wins: AI Dialogue toggle is only greyed out for RAM fail
(< 1.6 GB free). Battery suspend shows a warning label instead of
disabling the toggle — player can override the auto-suspend at any time.
Changes:
- settings_dialog: toggle disabled = hw_status == "fail" only
- settings_dialog: add _ai_battery_warning_label (STATUS_YELLOW) shown
when _ai_inference_suspended; hidden when plugged back in via
set_ai_inference_suspended()
- settings_dialog: is_ai_dialogue_toggle_enabled() no longer checks
_ai_inference_suspended
- settings_dialog: set_ai_inference_suspended() updates warning label
visibility, not toggle disabled state
- ui-strings: add settings.ai_battery_warning "High battery usage"
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Platform abstraction:
- New PlatformInfo autoload (extends Node, registered first in project.godot).
Owns all OS queries: power state monitoring (30s poll), memory (on demand),
file path resolution (user_data_dir, config_dir, benchmark_cache_path,
install_dir, executable_path, cache_dir, model_dir).
- PowerProfile enum (FULL/BATTERY/POWER_SAVER), power_profile_changed signal.
Uses OS.callv("get_power_info") to defer resolution to runtime — avoids
compile errors on Godot 4.6 headless builds without power API.
HardwareDetector refactor:
- check_ram() now delegates to PlatformInfo.refresh_memory() + free_memory_mb.
All direct OS.get_memory_info() calls removed.
- classify_power_state(int) and should_suspend_inference(int) delegate to
PlatformInfo for single source of truth.
- check_power_state() → {power_state, classification, should_suspend}.
- Battery suspend/resume: on PowerProfile.BATTERY, stores pre-battery pref and
sends ChangeSettings(false) to server. On FULL restore, sends ChangeSettings
with saved pref if it was enabled. inference_suspended member tracks state.
Settings dialog:
- is_ai_inference_suspended() / set_ai_inference_suspended(bool) — testable API
per Hoshe's test contract. Reads HardwareDetector.inference_suspended on open.
- Toggle now disabled when battery-suspended OR hardware fails (not only fail).
- get_ai_dialogue_label_text() wired to UIStrings ("settings.ai_dialogue_toggle")
instead of hardcoded string.
Cleanup:
- Deleted ai_dialogue_detector.gd and .uid (orphaned duplicate, dead code).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements the full AI-Enhanced Dialogue feature for Sprint 26:
- HardwareDetector autoload (extends Node): three-layer detection —
Layer 1 RAM classification (pass/marginal/fail, thresholds 2GB/1.6GB),
Layer 2 TPT benchmark cache (green/yellow/red, thresholds 6/3 t/s),
Layer 3 degradation monitoring (>40% drop → yellow). load_ai_pref()
restores toggle state from user://settings.cfg on startup.
- Settings dialog AI section: toggle, colored status dot, status message
label, testable API (get_ai_dialogue_label_text, set_ai_dialogue_
hardware_status, is_ai_dialogue_toggle_enabled). Only RAM "fail" greys
out toggle — player always overrides yellow/red recommendations (D-138).
- GameState.ai_enhanced_dialogue_enabled (default true, opt-out model).
GameState.settings_response (v20 one-shot settings dump from server).
apply_snapshot() hydrates ai_enhanced_dialogue_enabled from full dump.
- Protocol v19→v20, settings_response decoding in decode_snapshot().
Protocol converted to extends Node autoload (enables test has_method).
encode_change_settings() helper for test inspection.
- InputMapper: CHANGE_SETTINGS, REQUEST_ALL_SETTINGS, DELETE_SETTING.
SimBridge: wire mappings for all three. RequestAllSettings queued after
handshake to hydrate client state from server SQLite on connect.
settings_response carry-forward in receive_bytes().
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Clears stale .git/index.lock files before git write commands.
Claude Code's internal git status polling leaves orphan locks
(anthropics/claude-code#11005) that block add/commit/merge/push.
The hook checks lsof/fuser before removing — only stale locks are
cleared, never locks held by live processes. Read-only git commands
are skipped entirely.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
tea-comment now accepts @/path/to/file.md syntax to read comment body
from a file, avoiding $() subshells that break permission matching.
Updated pr-review skill and tea-cli rules with the new pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
- line_pool.rs: add trace! when active_situations is empty (Layer 2
will silently filter all lines — important for content debugging)
- knowledge_grant.rs: document serde(untagged) ambiguity hazard; add
KnowledgeGrant::validate() for load-time field validation
- monologue.rs: annotate trigger_monologue as schedule ordering anchor;
fix stale "periodic trigger cooldown tracking" doc reference in
trigger_event_monologue (COOLDOWN_TICKS removed in #655)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
These permissions are only needed by the main worktree for PR reviews,
not by team worktrees. Moved from shared settings.json to local.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds Read permissions for all team worktree directories so review
agents spawned from main can read source files directly instead of
falling back to git diff.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Per-player settings via rusqlite (bundled, zero runtime dep). Server
owns the settings DB; client sends ChangeSettings commands over IPC.
Extensible key-value with typed columns (String/Int/Float/Bool).
Protocol bumped to v20 with settings_response in ObserverSnapshot.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
Delete the hand-authored YAML content pipeline (server/src/content/) superseded
by the v0.2 generator-first approach (D-122, D-128). Runtime ECS types that were
co-located with content loading have been extracted to dedicated simulation modules:
- simulation/triangle.rs: TriangleState, TriangleCrisisEventQueue, tick/resolve systems
- simulation/line_pool.rs: LinePoolIndex, AccessTier, TrustTier, Mood, LinePoolIndexResource
- simulation/knowledge_grant.rs: KnowledgeGrant, Prerequisites
Monologue systems (trigger_monologue, trigger_recognition_monologue,
trigger_event_monologue) now use hardcoded fallback lines only; the
ContentStoreResource branch and select_pool_line function are removed.
Deleted: content/{loader,types,line_pool,hot_reload,spawn,instantiation,entanglement,mod}.rs
Deleted: tests/{content_loading,content_runtime,content_scaling,template_instantiation,template_schema}.rs
Deleted: bin/line_preview.rs (v0.1 tool)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Points auto-memory to ~/Projects/settled-reach/.memory so all
worktrees share a single memory root outside the git tree.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
