Workplan for practical example

This commit is contained in:
2026-05-14 22:05:10 +02:00
parent 937acde0b7
commit 9d1a2088aa
3 changed files with 285 additions and 0 deletions

View File

@@ -0,0 +1,214 @@
---
id: IB-WP-0016
type: workplan
title: "Lefevre EPUB3 Infospace Readiness Pilot"
domain: markitect
repo: infospace-bench
status: active
owner: markitect
topic_slug: markitect
created: "2026-05-14"
updated: "2026-05-14"
state_hub_workstream_slug: "ib-wp-0016-lefevre-ebook-infospace-readiness"
state_hub_workstream_id: "23be7d20-b01f-4b17-9851-4d540e4c0984"
depends_on_workplans:
- IB-WP-0015
related_workplans:
- IB-WP-0014
---
# IB-WP-0016 - Lefevre EPUB3 Infospace Readiness Pilot
## Goal
Use Edwin Lefevre's `Reminiscences of a Stock Operator` EPUB3 as the next real
ebook example for `infospace-bench`, and close the gaps that prevent a serious
OpenRouter-backed full-book infospace build.
This workplan should leave us able to run a bounded command like:
```bash
infospace-bench generate from-source \
/mnt/c/Users/bernd.worsch/Downloads/LefevreEdwin-ReminiscencesOfAStockOperator.epub \
--slug reminiscences-stock-operator \
--name "Reminiscences of a Stock Operator" \
--profile trading-literature \
--provider openrouter \
--model <openrouter-model-id> \
--chapter I \
--cost-cap <cap> \
--apply
```
and then scale from one reviewed chapter to the full book without losing
provenance, reviewability, or cost control.
## Validation Baseline
Validation note: `docs/lefevre-epub3-validation.md`.
Current WP-0015 infrastructure can initialize the local EPUB and run
source-only metrics in a disposable workspace:
- source chunks: 155
- entity count: 0
- relation count: 0
- evaluation count: 0
- source-only metrics history can be written without provider calls
The run proves the basic intake path works, but also shows why a live all-book
run should wait:
- most generated chunk titles collapse to the same Gutenberg page title
- EPUB spine/chapter metadata is not yet honored deeply enough
- archive-order sorting risks confusing reading order
- non-body sections such as cover/header/footer/license need explicit policy
- plan output is too prompt-heavy for cost review on a 155-chunk book
- long-book resume needs chunk-level state, not only whole-run skip
- generated entities need cross-chunk dedupe/merge policy
## Non-Goals
- Do not commit a full generated Lefevre infospace before review.
- Do not make live OpenRouter calls in the default test suite.
- Do not store API keys or provider secrets in the infospace.
- Do not build a general-purpose EPUB conversion suite beyond what the
infospace generator needs.
## Tasks
### T01 - Spine-aware EPUB3 intake
```task
id: IB-WP-0016-T01
status: todo
priority: high
state_hub_task_id: "a672fcf9-1b80-4faf-b16d-84ca52601dc9"
```
- Parse `META-INF/container.xml` to find the package document
- Parse OPF metadata, manifest, and spine
- Follow spine reading order instead of archive-name sorting
- Preserve book title, creator, source URL, subjects, language, rights, and
modified timestamp in source provenance
- Exclude or tag cover, nav, table-of-contents, Project Gutenberg header,
transcriber notes, and license/footer material by explicit policy
- Add tests using a small EPUB3 fixture with nav, cover, body, notes, and footer
### T02 - Chapter-aware chunking and IDs
```task
id: IB-WP-0016-T02
status: todo
priority: high
state_hub_task_id: "47de1110-36d0-4d63-bf87-389746509e03"
```
- Resolve chapter labels from EPUB nav entries and in-document headings
- Generate stable IDs like `chapter-01`, `chapter-01-part-002`, not repeated
Gutenberg document titles
- Chunk within chapter boundaries with a configurable word limit
- Consider overlap or evidence-window context without duplicating headings
- Preserve page anchors where available as optional provenance
- Add tests showing `Reminiscences`-style roman numeral chapters become stable
ordered source chunks
### T03 - Scale-aware generation planning
```task
id: IB-WP-0016-T03
status: todo
priority: high
state_hub_task_id: "bee5c38a-f052-4edb-9313-b3a2ee5a6c26"
```
- Add compact plan output for long sources
- Report estimated chunks, workflow stages, provider call count, prompt word or
token estimate, and rough cost inputs
- Add CLI selection filters such as `--chapter`, `--chunk`, `--from-chapter`,
`--to-chapter`, `--max-calls`, and `--cost-cap`
- Keep full prompt inspection available, but do not make it the default for
large corpora
- Add tests proving plan output is compact and does not dump hundreds of prompts
### T04 - Trading-literature profile
```task
id: IB-WP-0016-T04
status: todo
priority: medium
state_hub_task_id: "1a1b8fde-773f-46a6-887a-3c87a425d7a3"
```
- Add or specialize a profile for trading memoir and market-structure texts
- Tune entity prompts for traders, markets, strategies, errors, psychological
patterns, institutions, instruments, and evidence-bearing claims
- Tune relation prompts for cause/effect, lesson/evidence, risk/mitigation,
actor/venue, and strategy/outcome links
- Tune evaluation criteria for groundedness, lesson clarity, historical context,
and overgeneralization risk
- Keep the generic profile usable for non-trading books
### T05 - Deterministic Lefevre acceptance fixture
```task
id: IB-WP-0016-T05
status: todo
priority: high
state_hub_task_id: "c9bbc84e-691b-4530-a79a-6ecfa9c41fdd"
```
- Add a small checked-in EPUB-like or extracted chapter fixture derived from
public-domain Lefevre structure
- Add deterministic fixture responses for source summary, entity extraction,
relation extraction, and evaluation
- Prove the fixture generates a manifest-backed infospace with stable source,
entity, relation, evaluation, metrics, history, and report artifacts
- Include a regression test for excluding Gutenberg boilerplate when requested
### T06 - OpenRouter live-run guardrails
```task
id: IB-WP-0016-T06
status: todo
priority: high
state_hub_task_id: "c6bf97c3-1c2c-4993-8f4f-97a48e01cce2"
```
- Add an optional live smoke test path that is skipped unless credentials and an
explicit opt-in environment variable are present
- Support a one-chapter OpenRouter run with selected model, bounded retries,
cost/call cap, provider metadata, and resume
- Record provider model, request IDs, timing, usage, and retry counts in run
records and generated artifact provenance
- Document how to run the smoke safely and how to stop before a full-book build
### T07 - Example output and review policy
```task
id: IB-WP-0016-T07
status: todo
priority: medium
state_hub_task_id: "5ff1f11e-49ad-4c2d-bd4c-b8cc261309bc"
```
- Define where generated Lefevre outputs live
- Decide what is committed, what remains disposable, and what needs human review
- Add a review checklist for duplicate entities, relation endpoints, weak
evidence, and over-broad trading lessons
- Add a final readiness report before generating the full book
## Acceptance
- Current local EPUB can be inspected as EPUB3 with metadata and ordered body
sections
- `generate init` can import the book as body-only ordered chapter chunks
- Chunk titles and IDs are stable, readable, and not dominated by Project
Gutenberg boilerplate
- `generate plan` gives compact cost/call planning for the full book
- A deterministic Lefevre-style fixture generates a complete infospace without
network access
- Optional one-chapter OpenRouter smoke run is explicit, bounded, resumable, and
skipped by default
- A full-book run has documented review and output policy before execution