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
