Caught on the 2026-05-13 Coast-Down 10-chapter Orson run: the LLM
labeled two chapters 'Chapter 1' instead of 9 and 10, and
ON CONFLICT (story_id, n) DO UPDATE silently overwrote them.
8 visible chapters from 10 successful gen+cleanup passes; 27k
words of work, ~6k buried. The audit caught the symptom but the
data damage was already done.
Fix:
- continue_story::run computes next_n from MAX(chapters.n) before
the batch loop; each iteration's authoritative n is next_n,
incremented after success.
- forge::generate + cleanup take chapter_n: Option<i32>. The gen
prompt is now 'Write Chapter N. Begin with: ## Chapter N — ...'
instead of the vague 'Write the next chapter.'
- We still parse_chapter() the LLM output but only to extract the
title; if the LLM-returned n disagrees with ours, we log a warn
and use the authoritative N at INSERT time.
The (story_id, n) unique constraint stays — it's now a defensive
catch for skald bugs, not the LLM's free-spirited numbering.
Chapter view now shows a narration card between title and prose
with three states:
- succeeded → HTML5 <audio> + voice + duration + download link
- running → 'rendering…' banner with relative start time
- none/failed → 'Render audio' POST button (spawns background
tokio task calling narrate::run)
ServeDir mounted at /audio serves WAVs from the f5-tts bind-mount
read-only. Range requests work, so 16-min chapters seek cleanly.
Deploy needs: compose mount /mnt/cache/appdata/f5-tts/audio:/audio:ro
on skald (already staged in /mnt/cache/appdata/skald/compose.yml on
Lucy).
forge.rs threads Effort::Max on gen + cleanup. Audit + summarize stay
default — they're structured-output / tool-shaped tasks where extended
thinking doesn't help. Bumps subprocess timeout from 600s to 1800s so
max-effort prose-craft has the wall clock it needs.
continue_story::run takes a chapter_count param; loops gen+cleanup per
chapter with each iteration's just-written prose appended to context.
Audit fires once at end against the combined batch vs parent canon.
Cap is 20 (~5h wall clock, ~$600 at max effort — beyond that is
operationally absurd).
CLI: 'skald continue --chapters N'. Web: numeric field on both new-
story and continue forms, 1..=20, defaults to 1.
Vendored clawdforge SDK refreshed for the Effort enum.
Cobb tried creating a story via /stories/new tonight, ticked through
the form, hit Create, then expected gen to fire. It didn't, because
the fire-now checkbox only existed on the continue form. Story sat
in 'seed' for 30 min before he asked.
Fix: same path as continue. NewStoryForm picks up an optional 'fire'
field; new_story_create spawns a tokio::spawn task that calls
continue_story::run() with parent_story_id=None semantics:
- Context is the story's own prompt (not parent's bible)
- Audit pass is skipped (no parent to compare against)
- Status flow: seed → generating → cleaning → complete
The form copy explains the audit-skip for first chapters so the
user isn't surprised to see no findings.
Also fired Cobb's pending story manually via 'skald continue
--story bd73dd19...' so it actually generates this round.
Both /stories/new and /stories/:id/continue now carry an author
<select> populated from the authors table. New-saga + continue
panels pre-select the parent story's author when continuing
(propagates the voice across sequels by default; user can override).
Background fire-generation: continue form has a 'fire generation
now' checkbox. When checked, the POST creates the seed story row
AND spawns a tokio::spawn task that calls continue_story::run()
in the background. The user redirects to the new story's detail
page and can refresh to watch status flow seed → generating →
cleaning → auditing → complete. Failure path logs to the
container's tracing output (and generation_runs rows pick up
'failed' status).
Unchecked behavior: same as before — sequel sits in 'seed' state
until 'skald continue' fires it manually. Useful for queuing
multiple drafts before committing the opus spend.
CSS adds .checkbox-label styling so the checkbox + label flow
horizontally with the rest of the form looking sane.
Compiles clean. Smoke-test: open /stories/.../continue, pick an
author, tick 'fire now,' submit. Should redirect to a 'generating'
status; opening generation log shows the running gen pass.
Big CSS overhaul + page-level adjustments toward a Norse 'museum-
quality' aesthetic (not the gaming-rune-bro variant). Restraint +
weight + carved typography.
Palette shift:
- Warmed-black bg (#0a0807) with subtle radial gradient grain
- Bone-cream ink (#dbcfb0) replaces the cleaner cream we had
- Oxblood accent (#a13a3a) replaces the coffee-shop soft gold
- Weathered bronze (#b08443) as secondary accent for headers + meta
- Status colors land warmer: sage-moss ok, rust crit, amber-bronze warn
Typography:
- All caps + 2-3px letter-spacing on display headers (Trajan Pro /
Cinzel chain via font-family stack — falls back to weighted serif
on machines without the carved face)
- Serif prose chain unchanged (Iowan Old Style → Hoefler → Georgia)
- Drop cap on the first paragraph of each chapter — small literary
flourish in oxblood-bronze
Ornament:
- Inline SVG knotwork divider (`ornament()` macro) — two flanking
circles + an interlace curve between them, used as section breaks.
Below the welcome h1; can be sprinkled wherever a visual register
break helps.
Pages adjusted:
- topbar: SKALD wordmark in 4-letterspaced display caps; thin
oxblood underline accent; '+ new saga' nav button on the right
- sidebar: 'STORIES' → 'SAGAS' (one of cobb's earlier asks);
story-row hover gets oxblood left-accent (not gold); per-status
pill colors (complete=ok, generating/cleaning/auditing=warn,
failed=crit, seed=warn)
- story detail: dedicated .story-actions row with '✦ continue this
saga' (primary, oxblood-bordered button) and 'generation log →'
link
- welcome panel: revised copy + ornament + 'begin a new one' link
- forms: bordered surface inputs, all-caps display labels, primary-
styled submit buttons matching the continue-saga action
Mobile (max-width: 800px):
- Single-column grid; sidebar lays out above the main panel
- Sidebar wrapped in <details open> so it's collapsible (taps the
'Sagas (N)' header). No JS — native HTML semantics.
- Chapter-list collapses word-count column on narrow
- Char-list goes single-column
- All sizes downscale (28px h1, 16px prose, etc)
Next pass after I screenshot: tune any contrast/spacing that looks
off on the actual render.
Three new pieces lock the gen pipeline:
1. seeds/authors/orson-black.md — Orson Black's soul. ~2k words,
strict-headings format per cobb's decision. Voice / Worldview /
Specifics / Pet peeves / Sense of humor / Biography (fully
fictional — synthetic literary persona; coal town Durham 1948,
father died of pneumoconiosis at 14, two winters as welder's
apprentice on the Tyne, etc) / Anchor authors (Orwell, McCarthy,
DeLillo, Judt, Modiano) / Do / Don't.
2. skald-core::forge — author-aware. Forge::generate, ::cleanup,
and ::audit now take Option<&AuthorWithRevision>. When Some:
scaffold + soul composed and passed as SystemMode::Replace —
the model BECOMES the author. When None: house neutral scaffold,
Append mode, claude defaults stay. audit() always neutral,
regardless of author. Real prompt templates ship for gen +
cleanup (the prose-craft IP we were deferring) — scaffold has
{{display_name}}, {{pass_directive}}, {{soul}} substitutions,
plus separate gen/cleanup directive blocks.
3. skald continue --story <uuid> [--author SLUG] [--direction
STR] [--target-words N] [--recent N] [--skip-audit] — the
pipeline CLI:
load story → resolve author (--flag wins, else story.author_id,
else None) → pin author/revision onto story → assemble
ContinuationContext from parent chain → run gen pass →
parse heading + insert chapter + passages → run cleanup pass
on the draft → replace chapter body + passages → run audit
pass (parent prose vs new chapter vs bible) → parse JSON
findings into audit_findings table → status flow
seed→generating→cleaning→auditing→complete.
Plus skald authors seed --slug --display-name --tagline --file
--note for loading souls from disk into the DB.
End-to-end testable: seed Orson Black, create a sequel stub via
web or SQL, fire 'skald continue' against it. Coast-Down chapter 8
in Orson's voice is the smoke test.
Migration 0004 — authors + author_revisions + stories.author_id +
stories.author_revision_id + stories.cross_story_memory +
author_corpus. Soul versioning built in from day one per cobb's
locked decisions:
- authors.id immutable identity (slug + display_name + tagline + model)
- author_revisions tracks each soul revision with n monotonic
- Partial unique index 'idx_author_revisions_current' enforces
exactly one is_current=true per author
- stories.author_revision_id pins to the exact soul used at gen
time (so 'this was the Orson Black active when chapter 8 was
written' is always recoverable)
- author_corpus tracks 'authored' + 'read' relationships for the
v0.3 cross-story memory toggle
skald-core::authors module — CRUD: get_by_slug,
get_with_current_revision, get_current_revision, get_revision,
create_or_get (idempotent), add_revision (transactional, demotes
prior is_current=true), assign_to_story (also touches
author_corpus).
Web v0.1 forms (the second feedback bucket — 'no way to make new
stories', 'no options for sequels'): handlers + form panels +
POST routes for /stories/new and /stories/:id/continue. Both
create a story stub with status='seed'; actual generation will be
fired by 'skald continue' (next commit) walking seed rows.
Norse visual revamp + mobile collapse deferred — vetting full gen
is the priority per cobb's 'green light for v0.3'. Coming back to
the aesthetic after the pipeline works end-to-end against a real
Orson Black-authored Chapter 8 of Coast-Down.
Read-only inspector built on axum + maud (per CLAUDE.md locked
stack). No JS, no htmx yet (v0.2). Single inline stylesheet:
dark serif aesthetic — looks like a writer's tool, not a
developer's CRUD app.
Routes:
- GET / — welcome panel
- GET /stories/:id — story detail
- GET /stories/:id/chapters/:n — chapter prose + summary
- GET /stories/:id/runs — generation log
Sidebar always shows the story list with chapter count, word
total, summary coverage ratio (e.g. '5/7 summ'), status badge.
Story detail panel:
- metabar (status / chapter count / word count / character count
/ canon fact count / 'updated 3h ago' / generation-log link)
- Chapters list with summary-present indicators (✓ summary / ○ no
summary)
- Bible — characters (split real / fictional, key facts truncated
to 220 chars)
- Bible — canon (collapsible <details> per category)
Chapter view:
- Summary aside box (if generated; otherwise CLI hint)
- Full prose body, paragraph-split, serif typography, 68ch column
Generation log view:
- table of every gen/cleanup/audit/summary run for the story,
oldest to newest, with status colored (succeeded/failed/running)
Wired into 'skald serve' alongside /health.
Smoke test: http://lucy:7780/ when image redeploys.
Re-vendored from clawdforge@d4c3a9d. RunRequest now carries
`system_mode: Option<SystemMode>` where SystemMode is Append (the
default, current behavior — append to claude's base prompt) or
Replace (new — replaces claude's base prompt entirely).
Replace mode is the unlock for v0.3 author personas: Orson Black /
Bay / Kayos as authors can't have Claude's default helpful-honest
defaults bleeding through. Replace makes the model BECOME the
persona instead of 'Claude playing the persona.'
Existing skald::summarize call stays on default (Append) — the
summarizer is more 'tool-use over text' than persona, and Claude's
defaults help there. The gen + cleanup passes will switch to
Replace once authors are wired (next step).
Captures the late-session design pivot:
- Authors live in DB as named entities with soul.md-style markdown
- Soul replaces opus's default system prompt via clawdforge (append
today, replace via clawdforge enhancement later)
- Per-story cross_story_memory toggle for cross-corpus pulls
- Audit pass STAYS NEUTRAL — authors write/revise, audit checks
- Schema sketch (migration 0004), soul template, 4 seed-author proposals
- 6 open questions for cobb to decide
Doc is IN PROGRESS — will lock once cobb steers on the open
questions, then migration + code follow.
The old parent_coverage was raw-prose / parent-words — a signal of
'how much actual prose opus is reading.' But the more actionable
signal is 'is every chapter represented somehow' which sits at 1.0
for any parent with summaries (or placeholders) for older chapters.
Add chapter_coverage = 1.0 when every chapter has either a summary
or full-recent-prose row in the context. Keep prose_coverage as
the precise raw-words metric for ops that care about token budget.
Deprecate parent_coverage with a one-release shim (renames to
prose_coverage).
show_context CLI prints both percentages.
The serve loop wrapped axum::serve in tokio::time::timeout(15s),
which caps the WHOLE serve future, not just the shutdown drain.
Net effect: skald-serve cleanly returned Ok after 15 seconds every
time, docker restart picked it up, container went through the
exit-loop. Made any long-running docker exec (like summarize, with
opus calls that take 60-180s) racy at best, dead at worst — the
embedded postgres got 'database system was not properly shut down'
every 15s on the dot.
Fix: move the 15s deadline INSIDE the shutdown future. axum::serve
runs forever; the shutdown future fires on SIGTERM/SIGINT, then
gives in-flight requests 15s, then forces exit. Container only
goes down on a real signal.
Same bug exists in cwho-panel (copy-pasted from there). Fixing
there in a separate commit.
skald summarize --story <uuid> walks every chapter without an
existing summary, calls Forge::summarize() (clawdforge → opus →
~250 words of plot/character/setting/threads), and inserts the
result into chapter_summaries.
Side effects:
- generation_runs row per chapter (kind='summary', status flow
running → succeeded|failed). Errors update the row + bail; happy
path closes it with ended_at + tokens.
- ON CONFLICT (chapter_id) means re-running with --force replaces
the previous summary cleanly.
CLI:
skald summarize --story <uuid> # only-missing
skald summarize --story <uuid> --force # re-summarize all
Reads from env (loaded by skald.env in the container):
CLAWDFORGE_URL — base URL of clawdforge HTTP service
CLAWDFORGE_TOKEN — app-level bearer (per-app, not the admin token)
SKALD_MODEL — defaults to 'opus'
This is the first subcommand that actually exercises the forge.
Unlocks ContinuationContext::assemble's coverage metric (was stuck
at 24%% on Coast-Down because the 5 placeholder summaries don't
actually carry the prose). After running summarize against
Coast-Down: coverage should jump to ~100%% and the context blob
for any sequel becomes fully canon-faithful without dragging the
full ~21k words of earlier-chapter prose along.
Forge prompt template for summarize ships REAL (not stubbed) — it's
the simplest pass and has a well-defined shape. The gen/cleanup/
audit prompts remain stubs pending the deeper prose-craft session.
skald-core::context is the bridge between 'rows in postgres' and
'prompt-ready markdown blob.' ContinuationContext::assemble(pool,
parent_story_id, recent_n) pulls:
- parent story meta (title, series, total word count)
- characters split real / fictional
- canon_facts grouped by category
- chapter summaries for everything older than the recent window
- FULL prose for the last recent_n chapters
render_markdown() formats it with the most-condensed data first
(characters, canon) and the richest detail last (recent chapter
prose). Opus reads it linearly so by the time it's writing the new
chapter, the previous chapter's prose is freshest in its context
window.
The 'continuation reads ≥85% of parent' rule lands here via
parent_coverage() which counts recent prose + summaries-as-proxy
(250 words / summary) against parent word_count. The web UI / CLI
can warn before firing a gen pass if coverage is below threshold.
New CLI subcommand:
skald show-context --story <uuid> --recent <N>
Assembles + prints the blob to stdout (eprintln'd stats summary
goes to stderr). No LLM call — pre-flight inspection so we see
what would be sent before paying for it. Useful for prompt-eng
work in the next session.
Module structure now:
skald-core/
config.rs ForgeConfig
context.rs ContinuationContext (new)
db.rs connect_and_migrate
forge.rs Forge — three-pass orchestration
ingest.rs markdown parser
models.rs row types
lib.rs MIGRATOR + module exports
skald/
main.rs clap CLI
serve.rs axum + /health + migrations
import.rs skald import-markdown
show_context.rs skald show-context (new)
The Rust SDK already existed at Sulkta-Coop/clawdforge clients/rust/ — async,
reqwest-based, bearer-auth, exposes Client::run() + Session for multi-turn.
Vendoring it into vendor/clawdforge so skald is self-contained: no
git-submodule + no needing the clawdforge repo cloned next to skald.
Trade-off accepted: updates require manual re-copy until both sides
stabilize and we publish to a private cargo registry.
What landed:
- vendor/clawdforge/ — full SDK source from Sulkta-Coop/clawdforge HEAD.
Pinned in skald-core/Cargo.toml as a path dep.
- skald-core/src/forge.rs — three-pass orchestration shell. Forge wraps
clawdforge::Client; generate() / cleanup() / audit() each build a
RunRequest with the right system prompt + model alias (always opus),
call client.run(), return a PassOutput.
Prompt templates are TODO stubs (SYSTEM_GEN_TODO etc) — filling in the
actual prose-craft prompts is its own deep session.
- skald-core/src/config.rs — ForgeConfig { base_url, app_token, model }.
Resolved by the binary from env (CLAWDFORGE_URL + CLAWDFORGE_TOKEN);
lib stays env-agnostic.
- skald-core::AuditFinding + AuditResponse — parse shape for what the
third-Opus canon audit returns, ready to map onto audit_findings rows.
- docs/tts-pipeline.md — full plan for v0.2 narration + post-TTS audit
chain. Whisper-large-v3 STT does text-to-text verification on every
render; an optional Gemini Flash audio pass catches subjective issues
(prosody, tone) Whisper can't see. Reroll loop on crit findings.
What's still stubbed:
- Prompt templates in forge.rs (gen / cleanup / audit) — placeholders
that describe the role but don't constrain output shape yet.
- context.rs (assemble the LLM context blob from DB rows) — entire module
TBD.
- No CLI subcommand yet for invoking forge — that comes after context.rs.
Naming note: in Rust 2024 'gen' is a reserved keyword (for generators),
so the method is Forge::generate(), not Forge::gen().
Closes the TTS schema layer. The v0.2 render pipeline auto-runs an
audit chain after each chapter narration:
F5 render → narration_runs (succeeded)
→ ffmpeg chunk into ~30s windows
→ Whisper-large-v3 STT each chunk
→ word-level diff vs source chapter text
→ mismatches → narration_findings (kind=pronunciation|skip|insert)
→ ffmpeg silence/clip detect → narration_findings (kind=glitch)
→ (optional) Gemini Flash audio review pass
→ narration_findings (kind=prosody|tone)
→ unresolved crits trigger automatic re-roll with new seed
Distinct from audit_findings: that table is canon/continuity at the
text layer, populated by the third-Opus canon-audit pass.
narration_findings is audio-quality only, populated by detectors
that consume the rendered WAV.
The 'detector' field captures which model produced the finding so
we can tune thresholds per detector when one over- or under-flags.
cobb's audio agent intuition was right: STT-and-diff catches the
'name came out wrong' case airtight, and a separate audio-native
LLM call catches the subtler 'this sentence sounded weird' cases
Whisper can't see.
TTS layer landed as schema-only — synthesis pipeline ships in v0.2.
Putting the tables in v0.1 means imports already carry the right
shape; we won't need a 'migrate every existing story' pass later.
Decisions locked 2026-05-13:
- Engine: F5-TTS (best 8GB FOSS option, mid-2026 SOTA)
- Default voice source: LJ Speech (Linda Johnson, PD released
specifically for TTS training — airtight for sharing/uploading
generated audio. The 'AI-consent-released' license posture is
the difference between 'should be fine' and 'definitely fine.')
- Variety voices: Hi-Fi TTS speaker IDs (Apache 2.0, same consent
shape). LibriVox is optional but never default.
- Pronunciation overrides DB layer (story-scoped + global) to fix
proper-noun mispronunciation — the actual TTS-quality gap on
Cobb's bar of 'must not wake me up.' Pre-pass with Opus extracts
proper nouns + IPA, operator verifies, table caches forever.
Tables:
- voices — name, license, reference_path/text, sample_rate, default flag
- pronunciation_overrides — story-scoped or global, IPA/arpabet
- narration_runs — TTS audit trail mirroring generation_runs
- stories.preferred_voice_id FK
Unique constraints:
- one default voice (partial index)
- one row per (story, word) override
- one global row per word
Skald is a generic story-writer. The database is the product; the
binary is the tooling. Everything story-specific lives in rows, not
in code. cwho's monorepo + binary-per-role pattern transplanted to
this domain.
What this commit ships:
- Cargo workspace (resolver=3, edition 2024): skald-core (lib) +
skald (bin)
- Migration 0001: stories, characters, canon_facts, chapters,
chapter_summaries, passages (vector(1536)), generation_runs,
audit_findings, tags. pgvector + pg_trgm extensions. ivfflat
index deferred until we have data (post-import the first ~1k
passages and add the index).
- skald-core::ingest — markdown parser for the cwho/coast-down shape:
'# Title' → '## Chapter N — date' headings → '# Continuity Bible'
section with character roster (real + fictional sub-sections) +
setting / mystery / historical / liberty / hook sub-sections.
Decomposed into structured rows; original bullet body preserved
in key_facts/body fields for fidelity. 6 unit tests cover the
shape.
- skald-core::db — Postgres connection pool + migration runner.
- skald-core::models — row types via sqlx::FromRow.
- skald binary — clap CLI: 'serve' (http + migrations) and
'import-markdown' (one-shot ingest).
- Dockerfile — multi-stage: rust:1.95-bookworm builder, pgvector/
pgvector:pg17 runtime, tini under PID 1, custom entrypoint.sh
that boots embedded postgres then execs skald serve.
- compose.yml — singleton container, postgres data in volume,
story corpus mounted read-only at /seed.
Decisions locked 2026-05-13:
1. DB in same container 'till we have a real working tool' (cobb)
2. postgres+pgvector (NOT sqlite) — keeps semantic-search story
3. Network-not-socket connection (postgresql://localhost:5432) from
day one so future split is config-only, not code-rewrite
Not yet wired:
- Web UI
- clawdforge calls (gen → cleanup → canon-audit pipeline)
- Embedding pass
- TTS sidecar
