Regenerated MsgPack fixtures for protocol v14 (examine_result and
character_pressure fields). Updated golden test, serialization
assertions, and cross-language fixture generator.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Background tier state machines (#95), NPC vision (#115), player-
awareness behavior (#244), skill system & combat flag (#91), social
propagation (#249), examine mechanic (#242), character pressure
framework (#248), save state data model (#256), tell state wiring
(#337). Protocol version bumped 13→14 for examine_result and
character_pressure snapshot fields.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
14 tickets across server (9), client (3), copy (2). Examine mechanic,
NPC awareness, social propagation, minimap, dialogue UI, save state
data model, and blocker-clearing work for Sprint 19.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- monologue.rs: tracing::warn on unrecognized trigger in fallback arm
- disclosure.rs: borrow-sequencing comment, first() simplification note
- trait_modifiers.rs: delegate parse_confidence to KnowledgeConfidence::try_from
- npc_knowledge_transfer.rs: fix misleading "draw randomly" comment,
document one-directional transfer behavior
- graph.rs: document intentional no-retrigger after contradiction
- dialogue.rs: explain entity grant guardrail asymmetry (D-079)
- knowledge/mod.rs: document one-tick monologue lag from system ordering
- poi_discovery.rs: document D-079 carve-out for direct KG write
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pass PR description inline instead of writing to /tmp/pr-body.md
and cat-ing it back — matches the tea-comment wrapper approach.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
record_incomplete_interaction now uses Heard/Close source instead of
DirectObservation, preventing false inoculation against contradiction
detection. Wired exclude_high_trust_entities (Loyal trait) filter into
derive_disclosure_candidates — facts from Friendly-relationship source
entities are excluded from disclosure pool.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move CLI reference material, endpoint configs, and orchestration
patterns to .claude/rules/ (auto-loaded). CLAUDE.md now focuses on
project identity, safety rules, and workflow conventions.
Update cross-references in ticket, docs-search, and git-commit
skills to point to new rules/ locations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduces 5 rules files following Anthropic's recommended pattern
for splitting large CLAUDE.md files. Rules auto-load every session
and separate CLI reference material from core project identity.
- tea-cli.md: Gitea CLI reference, PR creation, protected branches
- git-safety.md: staging rules, commit conventions (from git-commit skill)
- project-structure.md: full annotated directory tree
- team-patterns.md: model selection, large content push pattern
- local-services.md: Gitea/Qdrant/Ollama endpoints
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reviews must run from main. Added step 0 hard stop if current branch
is not main, preventing repeated misuse from team branches.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Heartbeat rule for agent spawn prompts (15-min progress check) and
team lead proactive checks (bottleneck detection pattern).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Version field round-trip, mismatch detection, serde_default migration
pattern, all TellCategory and VerbKind variant coverage.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
tell_state reads KG for other-entity relationship state (MVP boundary
per D-082). Contradiction monologue fires with pre-resolved entity names,
shifts ToldBy source to PersonOfInterest. Full THE FRIEND arc event chain.
Implements D-082 step 1, D-083 event chain.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
transfer_npc_knowledge system runs after conversations with trust-gated
fact exchange, confidence capping at KnowsOf, ToldBy source construction.
POI data model with PointOfInterest component and proximity-based discovery
via KnowledgeGranted events. Implements D-080. Closes Q-024.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contradiction files:
- Add role/access/trust back to all lines (schema-required)
- prerequisite: → prerequisites: (plural, matching schema)
- Remove cooldown entirely — fire-once enforced by trigger semantics
(contradiction_detected fires once per KG state change), not magic numbers
Tutorial files:
- Remove cooldown: -1 — same reasoning, first_* triggers are one-time
Server:
- Document cooldown: Option<i32> on MonologueLine — None means no
per-line cooldown, fire-once relies on trigger design
CHANGELOG:
- Move displaced entries from ### Fixed back to ### Changed
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Single-command wrapper that handles temp file creation and cleanup
so tea comment works reliably with multi-line strings. Pre-approved
in settings.json, referenced in CLAUDE.md and pr-review skill.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds explicit exception to worktree boundary rules: agents may
remove their own worktree's stale index.lock file from the shared
.git directory, but never another worktree's lock.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- interaction_list.gd: skip queue_redraw() when position unchanged (Tyre #4)
- time_display.tscn: widen bounding rect 154x44→184x54, add clip note
for #314 wireframe (Tyre #3)
- test_time_display_sprint17.gd: document private state access pattern
in header (Tyre #5), add upper bound assertion for D-031 1439 max (Hoshe #6)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- constants.gd: clamp format_game_time input to 0..1439 (Hoshe #2)
- interaction_list.gd: add public hide_list() wrapper (Hoshe #3, Tyre #1)
- main.gd: call hide_list() instead of private _hide()
- time_display.gd: cache font geometry in update_from_state(), use boolean
_has_data flag instead of string guard (Tyre #2)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fix test API mismatches: time display tests target InsertOverlay/
TimeDisplay and time_display.gd; E-Talk tests rewritten to target
interaction_list.gd _cache_entity_relationship() and _relationship_color
state. Phase 2 tests (name, tier hint) marked as skip placeholders.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Phase 1: interaction_list.gd shows a 3px left-edge accent bar in
D-033 relationship color (teal/green/amber/red) at 85% alpha.
Cross-references entity_id against visible_entities via
_cache_entity_relationship(). NPC name and tier hint deferred to
Phase 2 (requires server protocol extension).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Time display on InsertOverlay (CanvasLayer 10) shows station local
time (HH:MM), day phase with cycle-tinted color, and day number.
Reads SimulationTime from GameState.game_time via update_from_state().
Adds Constants.format_game_time() helper for testability.
Placeholder layout — position refines when #314 wireframe lands.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add model selection section to CLAUDE.md covering /model sonnet[1m]
and opus[1m] for extended context sessions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Delegate sprint-status to a haiku subagent (sprint-plan pattern) so
intermediate artifacts (sweep JSON, template read, PR list) stay out
of the main context window. Trim sweep JSON output by removing unused
fields (ok, sprint.status, priority, ticket_id) and shortening issue
detail strings. Condense output template by moving rendering rules
into SKILL.md and simplifying the bookkeeping table to two columns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
10 lines per character teaching 5 core mechanics diegetically:
movement/exploration, fog of perception, sound model, NPC interaction,
insert/HUD. Detective lines in analytical register, smuggler lines in
street-smart fragments. Fires on first-time events (first_move,
first_fog_encounter, first_sound_heard, first_npc_proximity,
first_insert_open, etc.). _tut_ ID discriminator, cooldown -1.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Source-named contradiction monologue for both detective and smuggler.
Detective: Sera/Kael location contradiction (Phase 2 blindsiding +
Phase 3 pattern recognition with Torek avoidance). Smuggler: Kael in
B-7 with unrecognized contact (Phase 2 gut reaction + Phase 3
behavioral pattern accumulation). Cognitive-dissonance-not-accusation
tone per D-083. 16 hand-authored lines total (8 per character).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pixel-precise wireframe and visual specification for the neural lattice
overlay HUD (#314). Covers smuggler (social network view) and detective
(investigation overlay) variants via lattice_profile parameter.
Specifies: time display, entity markers, location labels, border arrows,
commission grid, inventory icons, stance indicator, and all interaction
states. Includes implementation notes for Stig (#263 time display).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Orchestrates sprint sweep + tea pr list to produce a consistent
health report: tickets by status, PR cross-reference, bookkeeping
issues, and open work by team summary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Structured JSON output with tickets grouped by status, per-team
summary counts, and bookkeeping issue detection (unassigned
in_progress, stale backlog, assigned but done).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
