Five TDD tasks: ShellState.for_character, the shell's injected-character
seams, the emit-only title, the GameFlow coordinator (+ its flow and
construct-failure tests), and the main_scene flip with a human smoke gate.
Each task carries full test code, exact commands, and a revert-and-watch-red
step per docs/traps.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A GameFlow coordinator node (new main_scene) owns the Title → Creation →
Shell sequence in one file: instantiate → inject → add_child, reusing the
existing injection seam that change_scene_to_file cannot. Title becomes
emit-only; the shell gains injected_log/injected_state seams and stops
self-seeding on the real path (seed stays as the F6 fallback), so the
created character's vitals, location, and opening narration are real.
The ⛨ saga constraint is honored structurally: _show_creation and
_start_campaign are separate, so the fourth entry path is an added arm,
not surgery on existing edges.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The human's first F6 run found four defects headless GUT could not see, all
now fixed and break-proven.
1. Fifteen Labels shipped invisible. _fonts() sets a default font and size but
never a default font_color for the base Label type, so a Label with no
type-variation inherited Godot's built-in default — WHITE — and rendered
white-on-parchment: the four race names, four race blurbs, and seven calling
names, every unreadable string on the sheet. New CardTitle / CardBody roles
(mock #3a2f1c / #6a5a3a) fix it. NOT a global default Label colour: the Title
screen has 12 bare Labels on a dark background that rely on white.
2. The PRIMARY badge covered the rolled value. The ability card is a
PanelContainer, and a Container force-fits its children, so the badge's
authored anchors were dead letters — it stretched to the card's full width
and centred over the value. Nesting it under a plain Control (not a
Container) restores absolute positioning. The badges also carried _flat()'s
12/6 card padding; a new tight pill stylebox matches the mock's 2px 9px.
3. Race cards overflowed their own border (108px card, 114px of content). Bumped
to 140. The CHOSEN badge on the calling card moved from centre to the mock's
top-right, and the ability card got its own AbilityCard variation with 16px
top headroom for the badge (ParchmentCard is shared with the shell).
4. The default window (1600x900) was larger than a 1600x900 laptop's usable
area, so the WM clamped it to 1589x752 and the run came up pillarboxed.
Default is now 1280x720, resizable; the 1920x1080 design canvas is unchanged
(canvas_items + keep scales it, so no layout number moved).
Also closes M4-b's two open copy items: the cutpurse origin fragment (it
contradicted its own blurb) and the Hint label (it omitted the roll's floor of
8, now pinned to NewGame.roll_attributes).
Guards for 1-4 are new and each was re-broken and watched go red. The overflow
guard in 3 was FIRST WRITTEN AS A TAUTOLOGY — Godot clamps Control.size up to
its combined minimum, so `min <= size` is `x <= x` — and passed against the bug,
29/29, until it was rewritten to measure against the card that clips. That is
traps.md #17 and the thirteenth cannot-fail assertion this branch has caught.
319 client tests green, content build green, theme drift guard satisfied.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Trap 12 told only the first act. The full story is the lesson: ThemeKeys.ALL excludes
the font roles by its own docstring, and the builder styles some base types directly
(RichTextLabel — which renders every line of DM prose on the creation screen). The
meta-guard written specifically to prevent a third miss contained a `continue` that
exempted exactly the gap it existed to catch.
A guard-of-a-guard with an exemption in it is not a guard.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The creation screen is done — 302 client tests (up from the 250 baseline),
content build green. Also flips the M3 Title screen from planned to done: it
shipped in a77bf03/f071392 and the roadmap never caught up, which would have
misled M4-c into thinking it must build one.
Adds six new trap species to docs/traps.md from this milestone's review
passes: substring-collision assertions, a BBCode wrapper masking an empty
ContentDB, a test asserting the script's own loop bound, a trivially-true
gating fixture, assertions already true before the action under test ran, an
"iterates everything" guard that checked three hardcoded pairs, a node-type
sweep that missed RichTextLabel, tests that called handlers instead of
pressing nodes, GUT silently skipping an unparseable class_name test file at
the old count, and a test that can hang instead of fail. Also documents the
new client-docs convention: clickable cards are Buttons with mouse_filter = 2
on every child, and pressed on a toggle_mode Button is the chosen state.
Human F6 confirmation of the rendered screen against the mock is still
outstanding and is not claimed here.
TDD task-by-task: NewGame's public seeded roll -> the eleven fragments ->
CreationCopy -> CreationDraft -> the theme -> the scene -> the docs.
Both of traps.md's bugs get a named guard rather than a hope: the pipeline test
that asserts what the screen SHOWED is what construct BUILT (and a step that
re-breaks the code to prove the test can fail), and a no-default-parameters rule
on the two new public functions.
Also corrects the spec: PrimaryCTA already has a disabled stylebox.
The mock's screen over M4-a's proven model. Five mock/model reconciles
recorded: the skills section the mock never drew, seven callings not five,
nameplate cards with prose on selection, a minus button, no portrait arrows.
No AI call anywhere — the DM's entrance is the shell, one screen later.
The screen shows the roll by calling the same pure roll_attributes(seed)
construct does, so it displays numbers without ever handing one over.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Six bugs this project shipped into a branch, what let each through, and the
guard that now catches it. They share a shape: the test passed, and the test
was wrong.
- a regression test that constructed its own correct object, so reverting the
bug left the suite green
- GDScript default params turning an arity change into a silent miscompile,
invisible to a grep for the renamed field (grep cannot see positional args)
- a determinism test comparing two runs that would change together
- a closed move vocabulary that was not bounded, because the model could repeat
a tag and choose an amount in unary
- a roster written down in four places with only one pair guarded — including a
shipped authoring skill that would have emitted origins allowing zero callings
- generated content that has a client consumer
Linked from CLAUDE.md §18 and docs/README.md. Also records M4-a on the roadmap
with its live end-to-end proof.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
The canon-log schema and NewGame code already migrated to race_id/
calling_id + allowed_callings, but two copies of the roster outside
that schema were missed, and no parity test guards them:
- docs/canon-log.md (the cross-boundary contract doc) still documented
the OLD player shape and allowed_classes. Anyone building a player
block from the doc would get a 422.
- .claude/skills/world-building's schema reference still emitted
allowed_classes with two dead calling ids (assassin, priest). Author
a new origin with that skill and it fails origin.schema.json
(additionalProperties: false, allowed_callings required) AND, if that
ever loosened, silently allows zero callings at runtime.
Also:
- add schema tests rejecting a dead class_id field and an unknown
calling_id (priest)
- guard NewGame._validate's container types (spend/skills) so a
malformed JSON round-trip (null spend, string skills) produces a
front-loaded error list instead of a GDScript runtime crash
- extend the no-mechanics-in-content test to db.races, not just
db.callings
- rewrite the roadmap's M4 bullet: the two contract migrations landed;
only the creation screen and title->creation->shell flow remain
client: 250/250. api: 74 passed, 2 skipped. content_build --check: clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
class_id is the rulebook's word; the world has callings — that was the whole §17
reconcile. The contract the Narrator reads should say what the world says. There
are no saves (M9) and no deployed clients, so this is as cheap as it will ever be
and strictly more expensive every milestone after.
race_id reaches the log because the AI must be able to describe the player:
api/app/prompts.py rendered 'a sellsword' and now renders 'a beastfolk cutpurse'.
It humanizes the id (the model must never read 'hedge_mage') and picks the right
article ('an elf', not 'a elf').
LogPlayer's hardcoded CLASSES const is deleted — the roster is Callings.IDS. A
parity test reads the JSON Schema from the client and asserts its enum equals the
code, so the two sides of the HTTP boundary cannot drift.
The deserter allowed three callings that no longer exist. He now allows all seven;
a thematic gate is a content decision for the Greywater authoring.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
TDD, green suite at every boundary. Task 4 is deliberately one cross-cutting
commit: the origin's key and the log's player field are read on both sides of
the HTTP boundary, so renaming them in separate tasks would leave a suite red
at the seam.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
The rules a character is made of, with no screen attached. Races, callings and
skills become static tables in code; blurbs stay content (hand-written, like
items/), so the content BOM stops blocking the engine. The sheet stores only
what was rolled or chosen and derives the rest — one source of truth, and the
M5 level curve becomes a function change rather than a migration.
Creation is seeded. The creation Dictionary carries a seed, not a stat block:
construct reconstructs the RNG and rolls the attributes itself, so the same
seed yields an identical character and the UI cannot inject a number. §10's
seeding argument, applied where the races spec says it first matters.
3d6 with a hard floor of 8. Straight 3d6 puts a ~9% chance on a primary the +3
pool cannot rescue — a Hedge-Mage with a -1 MAG modifier is not grit, it is the
"fine" §7 forbids, paid for twenty hours.
Lands the two migrations the races spec said to do at M4 and not silently:
class_id -> calling_id (the contract should say what the world says) and a
required race_id, so api/app/prompts.py can render "a beastfolk cutpurse"
instead of "a sellsword".
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
All seven callings are now named; no [CANON-TBD] remains in the specs.
Reaver (Barbarian). To reave is to raid — occupational, like Sellsword and
Trapper, naming what he does for money rather than what he is inside. That is
the rule the five mock names already obeyed and that §8's own list broke: a
calling is what a village calls you, not what a rulebook calls you. Bearsark
and Wildman were rejected for naming a condition; Breaker for being generic.
Bloodsworn (Warlock) was not a new coinage — the cosmology minted it a day
after the races spec was written ("what the Margreave calls bloodsworn",
rule.blood-price), and the cosmology spec had already applied it. It is the
exact FTH-axis mirror of Bonesetter: one channels the Warden, one pacts a king
of the Seven. Accepted cost, recorded in the spec: alone among the callings it
names a condition rather than a trade — the villain who pacts Ghaul is
bloodsworn too. A second, occupational word (Cursewright, Hexman) was
considered and rejected as a distinction the player will never feel.
Also retires the stale "reconcile class names" note on M4 and records the two
contract migrations that milestone owes: the canon log's `race` field, and the
deserter origin's dead allowed_classes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
Both roadmaps still described the copper currency change as pending. It is
merged. The marker moves to M4, M8's line now says what it still owes (the
price table — nothing is priced yet), and a "Landed out of band" section
records the two items that shipped outside a milestone: the currency value
type, and the once-per-reply move cap its review turned up.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
The tag extractor returns every occurrence of a move tag and the validator is
a pure membership test, so MoveApplier applied duplicates. A model repeating a
tag N times therefore picked an amount in unary — the AI choosing a number,
which is the §2 breach the bounded vocabulary exists to prevent.
The currency fix (8e1238c) closed this for denominations only. Generalizing it
to every move that names a thing covers real items too — three give_item(amulet)
tags are one amulet, not three — and lets the currency special case be deleted
rather than kept alongside a second mechanism. ID_MOVES is reused from
MoveValidator instead of restated.
Also caps adjust_disposition on the reply's NET swing. MAX_DELTA was clamped
per tag, so three +15s moved standing by 45 — precisely the wholesale swing its
own comment says it forbids. Applied in emission order, so a later
become_hostile still floors what came before it.
offer_quest and reveal needed no change: add_quest self-guards on has_quest and
mark_revealed is idempotent.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
The existing test varied the move name and the denomination together, so a
name-only or denom-only key would have passed it too. Two assertions nail it:
give_item(gold)+give_item(silver) kills a name-only key, and
give_item(gold)+accept_item(gold) kills a denom-only key.
The spec now records the per-reply ceiling as a decision rather than an
accident, and flags the pre-existing non-currency duplicate-tag path as open.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
Money stops being a flat `coin` and becomes copper, stored as a single
int, formatted only at the display edge.
The approved model (1g = 100s = 10,000c, store everything in copper) said
money should stay an inventory item under one `copper` id. It can't. §6 is
what kills it: `give_item(x)` adds exactly 1 and carries no quantity, and
`gifts_given` is a global one-shot keyed by item id — so a single `copper`
id would be givable once, for one copper, for the whole campaign.
So the purse is one int on GameState, and the three denominations are
content items that exist only to let a bounded move name a unit —
give_item(gold) is +10,000c. Three ids, not three buckets: the
change-making problem never arises because there is only ever one number.
A quantity arg on the move was rejected — it hands the model an unbounded
integer to invent, which is the §2 line.
Currency routes to the purse and never enters `inventory`, so it can't
appear in an inventory grid by construction. No filter needed.
Prices remain content and remain M8.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYa9u7Kdxv5gX4AnwWexy8
Implements the docs restructure half of the content-track design (the
currency item is code and stays unbuilt). Content stops being unbounded:
the work is now a countable checklist with an end.
content/roadmap.md — new. Three sections, only one of which is ever the
work:
Spine Greywater Docks + one dungeon, patron Ghaul the Yoke; the
cosmology touching ground. Plus what is already canon.
BOM ~57 discrete pieces for a complete, playable game, per
milestone. Numbers, not vibes.
Backlog Everything the slice does not need. Not a debt — where ideas
go to be safe.
Its rule: never author anything that is not in the Bill of Materials.
The BOM carries a Fixed/Variable column — the seven-campaign saga spec's
only ask of this table. ~37 fixed / ~20 variable: a second town costs the
20, not the 57. That is also the exact split v2 generation would need.
content/lore/canon-roadmap.md becomes a pointer (older specs and plans
reference the old path). An items-and-prices table does not belong under
lore/.
docs/roadmap.md — M4..M9 each gain a "Content it consumes →" line into
the BOM.
world-building skill — SKILL.md and evals.json now point at
content/roadmap.md, and the skill is told to respect the BOM rule: ideas
that arrive during authoring go to the Backlog, not into the world.
Build + --check green; generated content/world and content/server are
byte-identical. No Python touched.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Applies the seven-campaign saga direction spec (021c248) to the docs it
was written to protect. No new milestone, no new content, no BOM line.
docs/roadmap.md — a "Guarded direction" section, and a ⛨ saga note on the
four milestones that would otherwise foreclose the shape:
M3 don't hardcode the title flow so a saga entry path can't be added
M4 keep construct()'s `creation` a plain Dictionary; the scene must not
become its only producer
M5 the level curve is no longer open — L20 across 7 tiers; enemy stat
blocks carry tier; no scaling multiplier, ever
M9 the save is two objects (Saga + Campaign); humiliations move to the
Saga or they die with the campaign
races-and-classes spec — the deferred "XP curve → M5" line now inherits the
ceiling rather than choosing one.
canon-roadmap — what the saga asks of content: a tier field when the
item/quest namespaces land, and a fixed-vs-variable mark on each BOM line
when the BOM is written. Tiers 2-7 and the other six kings go to the
Backlog.
Content build --check green; no generated content touched.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A direction spec: one character, seven campaigns (one per demon king),
one saga — then it ends. The character, companions, deeds and level carry
between campaigns; the world does not.
Deliberately adds no milestone and no BOM line. Its real payload is a set
of guardrails on milestones that are about to be built blank and would
otherwise foreclose the shape:
- M5 owes a level curve — design it to a ceiling of 20 across 7 tiers,
with tiered enemy stat blocks and never a scaling multiplier.
- M9 owes a save format — two objects (Saga + Campaign), not one blob.
Humiliations move to the Saga or they die with the campaign.
- M3/M4 — don't foreclose a saga entry path; don't couple construct() to
the creation scene.
- Build tool — add tier:1..7 when the item/quest namespaces land.
Difficulty is fixed at world-construction time from the campaign index,
never during play. That prohibition is the whole design; a world that
re-levels with the player is a treadmill.
The canon-log contract does not change: party[].disposition,
humiliations[] and established_facts[] already exist, and player still
admits no number. The Saga becomes the source; the canon log a projection
of it. The seam is one optional fourth arg to NewGame.construct().
Greywater at tier 1 under Ghaul is, unintentionally, already campaign 1.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Content (lore, economy, items, quests, map) was untracked and unbounded.
Bound it: a second roadmap (content/roadmap.md) with Spine / Bill of
Materials / Backlog, demand-driven by the milestone that consumes it.
- Vertical slice = one town + one dungeon (adopt + deepen Greywater).
- Ghaul the Yoke is the ledger chain's patron, so the quest chain and
the cosmology are one object, not two.
- Economy splits per §18: the loop is code (M8), the numbers are content.
Currency = 1g/100s/10,000c, copper as the stored atom; lands before M7.
- Build tool needs `item` + `quest` namespaces; locations already exist.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Delete the Duncarrow scaffolding while preserving the schema/disposition-gate
infrastructure it carries: reparent rule.disposition-ladder into a new
mechanics.md, stand up a synthetic status:candidate specimen (validated but
never emitted), repoint the skill/tests/evals. Zero real game content; the
in-flight NPC redesign and the hand-authored POC seed JSON stay out of scope.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HuHRPE7VfppUJEaoGBEUqZ
Adds the FTH-axis calling mapping to the cosmology spec: Bonesetter
channels the Warden, the Bloodsworn (names the [CANON-TBD] warlock
calling) pacts one of the Seven, Hedge-Mage is a pointed outsider,
martials unaligned. Luck-immunity intent kept as flavor and flagged for
the M5/Improviser reconcile (§7-sensitive), not built here.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HuHRPE7VfppUJEaoGBEUqZ
Establishes the good-god/seven-demon-lords cosmology as the game's
overarching content theme, mapped onto the content schema as canon
entities, with the world-building skill updated to reconcile all future
authoring against it. Duncarrow scaffolding decoupled now, purged in a
follow-up.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HuHRPE7VfppUJEaoGBEUqZ
Lock the NPC identifier: full namespaced id (npc.mera-fenn) is canonical
everywhere — stored data, client dict key, and the /npc/speak wire. The API
load_npc changes from a filename lookup to an id-indexed load (matching the
client's ContentDB), reads persona from content/server, and resolves the
client's reveal-set fact_ids to topic bodies. Legacy Fenn keeps working; no
migration required. First task of the runtime-consumption cycle.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HuHRPE7VfppUJEaoGBEUqZ
Schema lock built bottom-up from the Duncarrow specimen (candidate-town.md):
- disposition rungs as bands over the engine integer (code owns numbers)
- town fact = engine reveal-topic (authoring layer over §6, no new runtime)
- MD bible -> build -> JSON; split by role (game vs server), secrecy as lint
- canon home: content/lore (source) -> content/world + content/server (built)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HuHRPE7VfppUJEaoGBEUqZ
Settles the §17 class-name reconcile (charter §8 vs mock callings) in
favor of the gritty callings, and gives every race trait a concrete rule.
Feeds M4 character creation; combat ability kit deferred to M5.
- Resolution model: deterministic value vs DC, LCK selects the borderline
band (§7) — flat mods, no random d20, no advantage.
- 5 saves (LCK owns none); death saves = LCK.
- Races: features only, no stat mods; Nightsight ruling for darkvision.
- 7 callings (charter-7), 2 names [CANON-TBD]; casters=MP, martials=cooldowns.
- Flags two contract migrations for M4: canon-log gains `race`; deserter
origin's allowed_classes migrates to new calling ids.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Editor-first Title screen from mock: warm atmosphere (GPUParticles embers,
AnimationPlayer glow, palette-uniform shader bg), logo block, keyboard/mouse
menu (New Game -> shell, Quit works, rest inert), footer. Plus a single
/VERSION source of truth read by both the API (startup + /version) and the
client (synced into project.godot config/version, read via ProjectSettings).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Capture the direction change from M3-b: UI screens are authored editor-first
as .tscn node trees (previewable/arrangeable in the Godot editor), scripts do
on-load work only — never build the tree in _ready(). Add ADR 0001, a
"UI scene conventions" how-to in client/docs, a §16 mandate in the charter,
and mark M3-a/M3-b done in the roadmap.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The exploration HUD frame: two-panel tabletop split, DM narration book
wired to the proven /dm/narrate loop (prose-only + refire), thin tested
ShellState for HUD readouts, inert system dock + command bar as faithful
placeholder. Pure-core/thin-shim per the house pattern.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
First of three M3 cycles (Theme -> shell 2a -> Title). Palette.gd consts
as the single source of truth; game_theme.tres for flat-bordered UI;
shaders for the three signature surfaces. EB Garamond replaces
proprietary Georgia. Proof is a human-eyeballed showcase harness.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The aliveness POC (M0-M2) is proven, so redefine the project as the tactical
CRPG the /mockups describe. Charter: §1 reframed (Code of Conquest / The
Margreave), §10 combat = tactical + action-economy but GRIDLESS (tokens are
flavor, no positional rules), §15 = button-driven actions + free-text NPC
dialogue (Adjudicator reshaped to the optional free-text escape hatch), §16
adopts /mockups as the UI/systems bible, §17 rewritten to the game's scope.
Two conflicts flagged not silently decided (§18): damage determinism (§7 vs
mock ranges → M5) and class names (§8 vs mock callings → M4).
Roadmap: M0-M2 kept as the built engine; M3-M9 re-sequenced around the mock
screens (Theme+shell → creation → combat → dialogue → inventory/sheet → world
systems → framing/AI-flavor/persistence). Streaming stays shelved; v2 NPC
ideas preserved, re-homed to M6.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
M2 (prove aliveness) build-complete + live-proven; feel confirmed in playtest.
Active build focus is now M3 (make it a game), starting with the Adjudicator.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Flip considering-state to done+merged+live-confirmed. Strike the streaming
item — the considering-state reframes the wait and is tested/live; real
streaming's transport rework + mid-stream failure surface isn't worth it for
the POC. Streaming spec retained as a record (banner SHELVED). Includes the
human's folded-in further-down roadmap ideas.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
5 TDD tasks: ConsideringPhrases (pure) + authored considering.json;
ProxyConfig.request_timeout_seconds (default 35s, reject <=0); HttpTransport
applies it (closes the infinite-hang gap); ConsideringIndicator node shim
(Timer rotates a Label); wire both harnesses around the await.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Pivot M2 anti-freeze from streaming to a lighter considering-state: a rotating
in-character 'the Master considers…' indicator (authored content, §13 spirit)
on the proven non-streaming loop, plus the HttpTransport request-timeout fix so
a hung call yields to the fallback instead of spinning forever. Meets §14's
anti-freeze goal by reframing the wait; near-zero new failure surface. Streaming
design PARKED (banner + roadmap ○), revisit if playtest shows the wait hurts.
Conscious §14 deviation recorded per §18.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Real token streaming to hide the ~2s call (§14). Proxy emits its own minimal
NDJSON (delta/done/error); /dm/narrate becomes a 200 stream (422 stays sync,
model errors become an in-stream frame). Client reworks to an HTTPClient
poll-loop StreamTransport behind a testable seam; hold-back tag filter;
keep-partial mid-stream degrade; folds in the HttpTransport timeout fix.
Narrator first; NPC fast-follow.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
M2 core experiment. Server owns persona+knowledge (spoilers/IP, no DB);
client owns live state and computes available_moves. Free text straight
to the NPC prompt (no Adjudicator). Sibling NpcService + pure MoveValidator;
moves validated against state, invalid dropped, prose always kept (§6).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
