Documents the Brave Search path in Phase 2, batch_size setting for
parallelism, batched article tracing with build_trace_entry/batch_insert_entries,
15-minute pipeline timeout, panic handling, session cleanup background task,
SSRF checks on source pages, and the max_links change from 10 to 15.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- **Session cleanup**: an hourly background task deletes expired DB sessions (`db::sessions::delete_expired`).
- **Job store TTL**: expired job entries (older than 1 hour) are cleaned up via `JobStore::cleanup_expired`.
## Generation Lifecycle
`POST /api/v1/syntheses/generate` creates a job in the `JobStore`, then spawns two nested tasks:
- Inner task: wraps `run_generation` in a **15-minute `tokio::time::timeout`**. If the timeout fires, sends an `Error` progress event and releases the user lock.
- Outer task: monitors the inner task's `JoinHandle` for panics. If the inner task panics, sends an `Error` progress event and releases the user lock.
Progress is streamed to clients via a `tokio::sync::watch` channel (SSE endpoint subscribes to it).
---
## Initialization
## Initialization
1. **Load user settings** from DB (categories, provider, models, max_items, etc.)
1. **Load user settings** from DB (categories, provider, models, max_items, batch_size, etc.)
2. **Cleanup** — delete old article history entries (>N days, dropped only) + truncate old LLM call logs
2. **Cleanup** — delete old article history entries (>N days, dropped only) + truncate old LLM call logs
3. **Validate** — if no categories configured, there will just be the default category "Autre".
3. **Validate** — if no categories configured, the only available category will be "Autre".
4. **Load user sources** (personalized URLs like `https://openai.com/blog`)
4. **Load user sources** (personalized URLs like `https://openai.com/blog`)
9. **Batch trace buffer** — `pending_traces: Vec<ArticleHistoryEntry>` accumulates all article history writes; flushed with `db::article_history::batch_insert_entries` at phase boundaries (not per article).
---
---
@ -20,34 +35,39 @@
### 1a. Extract article links from source pages and filter against article history
### 1a. Extract article links from source pages and filter against article history
- Query `article_history` for the last source used. Reorder the personalized source so that the first source is the one following the last source used (rolling window)
- Query `article_history` for the last source used. Reorder the personalized sources so that the first source is the one following the last source used (rolling window).
- For each source, fetch the source page HTML:
- Fetch source pages with bounded concurrency of **5** (hardcoded `max_concurrent = 5`):
- If `use_llm_for_source_links` enabled: send HTML `<head>` + first 8000 chars of `<body>` to LLM → extract all article URLs up to a maximum of 10, with the most recent first. If LLM call fails, fall back to HTML parsing as described below.
- If `use_llm_for_source_links` enabled: send HTML `<head>` + first 8000 chars of `<body>` to LLM → extract all article URLs up to a maximum of **15**, with the most recent first. If the LLM call fails, fall back to HTML parsing as described below.
- **LLM call logged** with full prompt/response/timing
- **LLM call logged** with full prompt/response/timing
- Otherwise: parse HTML `<a href>` links, filter by same-domain, non-homepage path, exclude `/tag/`, `/login/`, `/contact/`,`/presentation/`,`/newsletter/`, static assets, etc. and keep only the first 10 links found
- Otherwise: parse HTML `<a href>` links, filter by same-domain, non-homepage path, exclude `/tag/`, `/login/`, `/contact/`, `/presentation/`, `/newsletter/`, static assets, etc., and keep only the first **15** links found.
- Deduplicate candidate URLs
- **SSRF check** performed on each source URL before fetching (rejects private/loopback IPs).
- Hash each URL (normalized: lowercase, strip fragments/UTM params/trailing slashes)
- Deduplicate candidate URLs (case-insensitive, cross-source via `seen_urls`).
- Query `article_history` for existing hashes → remove matches
- **Filter against article history** — hash each URL (normalized: lowercase, strip fragments/UTM params/trailing slashes), batch-query `article_history` → remove matches.
- Trace dropped articles with `status: filtered_history`
- Trace dropped articles as `status: filtered_history` (flushed immediately after this filter step).
- Add the url to `url_soucre`
- **Shuffle** remaining candidates to interleave articles from different sources.
- Track url → source in `url_source`.
### 1b. Scrape, classify and summarize articles
### 1b. Scrape, classify, and summarize articles (batched)
- For each url from step 1a:
- if the number of articles in `source_counts` for the source of the current url exceeds `max_articles_per_source`:
Processing happens in batches of `settings.batch_size` (minimum 1). For each batch:
- Trace dropped article with `status: filtered_diversity`
- Move to next url
**Batch assembly**: pull up to `batch_size` candidates from the iterator, skipping any where `source_counts[domain] >= max_articles_per_source` (traced as `filtered_diversity`).
- Fetch each URL (bounded concurrency: 5 with LLM extraction, 10 without).
- SSRF check (no private IPs), 15s timeout, 5MB body limit.
**Phase A — Scrape batch in parallel** (`JoinSet`):
- HTML parsing heuristics for title (`<title>`, `og:title`), date (meta tags, JSON-LD, `<time>`), body (strip scripts/nav), soft-404 detection
- SSRF check (no private IPs), 15s timeout, 5MB body limit.
- If article scraped body text is empty (scrape failure, soft 404, too old):
- HTML parsing heuristics for title (`<title>`, `og:title`), date (meta tags, JSON-LD, `<time>`), body (strip scripts/nav), soft-404 detection.
- Trace dropped articles in `article_history` with `status: filtered_empty`
- If article body is empty, is a soft-404, or is too old: trace as `filtered_empty` / `filtered_too_old` and skip.
- Move to next url
- Send article (title + first 500 chars of body) + categories + "Autre" to LLM. LLM returns `{title, summary, category}` mapping the article to a category. The LLM generates the summary and a also a title if the provided title is empty
**Phase B — Classify/summarize batch in parallel** (`JoinSet`):
- **LLM call logged** with full prompt/response/timing
- Check rate limit before classifying (waits up to 60s, then errors).
- Add the article to `article_scraped` and increase `filled_counts`
- Send article (title + first 500 chars of body) + categories + "Autre" to LLM. LLM returns `{title, summary, category}`. If the title was empty, the LLM also generates one.
- if number of articles in the category of this artcile exceeds `max_items_per_category`: change the article catgeory to "Autre"
- **LLM call logged** with full prompt/response/timing.
- If the total number of articles in `article_scraped` exceeds `number of categories (including Autre) × max_items_per_category` then exit for loop and move to synthesis generation
- **`assign_category()`** helper: validates category, falls back to "Autre" if category is unknown or full. If "Autre" is also full, drops the article.
- Add the article to `article_scraped`, increment `filled_counts`, increment `source_counts[domain]`.
**Early exit**: after each batch, if total articles across all categories ≥ `(num_categories + 1) × max_items_per_category`, stop and move to Phase 2.
**Trace flush**: all pending traces accumulated during Phase 1 are batch-inserted into `article_history` after Phase 1 completes.
---
---
@ -57,34 +77,80 @@
### 2a. Compute category gaps
### 2a. Compute category gaps
- For each user category: `needed = max - already_filled`
- For each user category: `needed = max_items_per_category - already_filled`
- Only proceed if any category needs more
- Only proceed if any category needs more articles.
### 2b. LLM web search pass
### 2b. Choose path: Brave Search or LLM web search
- Build search prompt with theme, categories, gap counts ("find N articles for category_1, M for category_2")
The path is selected by the `settings.use_brave_search` flag.
- **LLM call logged** with full prompt/response/timing.
#### 2c-B. Filter LLM search results
Same **`filter_phase2_url()`** logic as Path A (homepage, cross-phase dedup, history, diversity). Accepted URLs are added to `seen_urls`. Traces are **batch-flushed** after this filter step.
#### 2d-B. Scrape LLM search results (sequential)
- For each accepted item: call `scrape_single_article` (SSRF check, 15s timeout, 5MB limit).
- If scrape fails or article is too old/empty: trace as appropriate and skip.
- Otherwise: keep the LLM-provided title and summary (no re-classification LLM call). Add to `article_scraped`, increment `source_counts[domain]`.
- Traces are batch-flushed after all items are processed.
---
---
## Save + Record
## Save + Record
- **Sanitize** — strip `\u0000` null bytes from JSON (PostgreSQL rejects them in JSONB)
- **Error if empty** — if all scraped article lists are empty, return an error.
- **Save synthesis** — insert into `syntheses` table with `job_id`, `week` (ISO week), `sections` (JSONB), `status: completed`
- **Order sections** — user-defined categories first (in order), then "Autre" if non-empty.
- **Record used articles** — insert each article URL into `article_history` with `status: used`, `synthesis_id`, `job_id`, and category name (for future dedup + provenance)
- **Sanitize** — strip `\u0000` null bytes from JSON (PostgreSQL rejects them in JSONB).
- **Save synthesis** — insert into `syntheses` table with `job_id`, `week` (ISO week), `sections` (JSONB), `status: completed`.
- **Record used articles** — for each article in the final synthesis, build a trace with `status: "used"`, `synthesis_id`, and the correct `source_type` (`personalized_source`, `brave_search`, or `web_search` inferred from `url_source`). Batch-insert into `article_history`.
---
## Shared Helpers
- **`build_trace_entry()`** — constructs an `ArticleHistoryEntry` from an `ArticleTrace` struct (replaces the old 11-positional-parameter `trace_article` function). Never writes to DB directly; caller accumulates in `pending_traces`.
- **`assign_category()`** — validates LLM-returned category against the classification list, falls back to "Autre", drops article if "Autre" is also full.
- **`filter_phase2_url()`** — async helper applying homepage/dedup/history/diversity filters for Phase 2 (both Brave and LLM paths).
