daybook/docs/llm_posting_helper.md
peter 07328a3412 Fix issues #002-#006 found by the LLM test harness
- #006 (high, data loss): make_room_for() no longer deletes unkept
  artifacts on a doomed request - checks whether eviction can possibly
  succeed before deleting anything. Also fixed a related latent bug found
  while testing: the function returned evicted Artifact objects after
  calling .delete() on them, so their .id was always None (Django clears
  pk on delete); now returns ids captured beforehand.
- #003: added server-side field-length validation (source/title/
  source_name/source_id/theme) on POST and PATCH, matching the model's
  own max_length limits, which were previously unenforced on the ingest
  path entirely.
- #004: ported daybook_post.py's content-shape validation
  (html_fragment/html_full/deck/markdown) to the server, closing the gap
  for any client that doesn't go through the helper script.
- #005: PATCH now rejects wrong-typed `tags` (previously silently wiped
  existing tags) and rejects immutable fields (content/source/kind/day)
  with 400 instead of silently no-op'ing them.
- #002: deleted the misleading skills/daybook-posting/.env.example (a
  zero-dependency script that never reads .env files) and clarified
  SKILL.md/docs/llm_posting_helper.md that these must be real
  process/shell env vars.

Adds tests/unit/ for storage-layer tests. 46 tests passing (was 25).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-02 13:38:59 +01:00

113 lines
3.2 KiB
Markdown

# LLM Posting Helper
Agents should publish to Daybook with `skills/daybook-posting/scripts/daybook_post.py` instead of hand-building HTTP, JSON, curl, or PowerShell multipart requests.
The project also keeps `scripts/daybook_post.py` as a compatibility wrapper.
The helper is intentionally zero-dependency and uses only Python's standard library. It works on Windows and Linux.
## Configuration
Set these as real process/shell environment variables — the helper reads
`os.environ` directly and has no `.env` file support. Copying values into a
`.env` file in the working directory does nothing; export/`$env:`/`set`
them, or set them in your agent harness's own env config.
```text
DAYBOOK_URL=http://127.0.0.1:8001
DAYBOOK_TOKEN=your-personal-api-token
DAYBOOK_SOURCE=agent
```
`DAYBOOK_TOKEN` is a personal per-user token, from Settings → Account in the app — not a token shared across users. Override these per environment.
## Commands
Check the instance:
```bash
python skills/daybook-posting/scripts/daybook_post.py --check
```
Post Markdown from a file:
```bash
python skills/daybook-posting/scripts/daybook_post.py --kind markdown --title "Build Report" --content-file report.md --tags build,report
```
Post Markdown from stdin:
```bash
cat report.md | python skills/daybook-posting/scripts/daybook_post.py --kind markdown --title "Build Report"
```
Post a deck:
```bash
python skills/daybook-posting/scripts/daybook_post.py --kind deck --title "Deployment Plan" --content-file deck.html
```
`deck.html` must contain top-level `<section>...</section>` blocks.
Post an image/PDF/binary file:
```bash
python skills/daybook-posting/scripts/daybook_post.py --file diagram.svg --title "Architecture Diagram"
python skills/daybook-posting/scripts/daybook_post.py --file report.pdf --title "Generated Report"
```
Render CSV/JSON/code as Markdown today:
```bash
python skills/daybook-posting/scripts/daybook_post.py --file results.csv --as-markdown --title "Results CSV"
```
Dry run:
```bash
python skills/daybook-posting/scripts/daybook_post.py --kind markdown --title "Draft" --content-file report.md --dry-run
```
The artifact URL is printed as the final stdout line.
## Validation Guardrails
The helper validates common LLM mistakes before sending:
| Kind/input | Validation |
|---|---|
| `deck` | Must contain `<section`. |
| `html_fragment` | Must not contain `<!doctype`, `<html`, or `<body`. |
| `html_full` | Must contain `<!doctype` and `<html`. |
| `markdown` | Must not be blank. |
| `.svg` upload | Forces `image/svg+xml`. |
| `.pdf` upload | Forces `application/pdf`. |
## Metadata
Use repeatable `--meta key=value` flags:
```bash
python skills/daybook-posting/scripts/daybook_post.py \
--kind markdown \
--title "Run Summary" \
--content-file summary.md \
--meta run_id=run-001 \
--meta model=gpt-5.5
```
Or pass a JSON object:
```bash
python skills/daybook-posting/scripts/daybook_post.py --kind markdown --title "Run Summary" --content-file summary.md --meta-json '{"run_id":"run-001"}'
```
## Skill Wrapper
A thin LLM-facing wrapper lives at:
```text
skills/daybook-posting/SKILL.md
```
Its key instruction is: do not hand-build requests; use `scripts/daybook_post.py`.