Mike/deepi-research
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

0.2.0: per-query analysis, cross-query corroboration, expanded authority scoring

Browse Source 
- Per-query result grouping: findings analyzed under the query that produced
  them, with angle + query provenance carried through to synthesis
- Cross-query corroboration via multi-query URL counts (before global dedup);
  same-query findings no longer corroborate each other
- Robust LLM JSON parsing (code fences, trailing commas, prose prefixes)
- Expanded domain authority map to 90+ domains + LOW_AUTHORITY_DOMAINS floor;
  authority-aware source truncation in analysis prompts
- Citation integrity: authoritative bibliography replaces LLM references,
  hallucinated inline citations stripped
- Near-duplicate title detection for syndicated articles; cross-round finding
  dedup with quality-ranked 30-finding synthesis cap
- Junk result filtering, retry-with-backoff, fixed successfulSearches count
- Standalone harness (scripts/run-harness.ts) for cache-bypassing iteration
This commit is contained in:
Michael Freno
2026-08-02 12:49:07 -04:00
parent 4ece83f5c6
commit c3e0770cc4
9 changed files with 707 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@@ -10,10 +10,16 @@ pi install npm:@mikefreno/deep-research
- **Multi-round iteration**: Each round generates follow-up queries based on previous findings (depth 1-3)
- **Parallel query expansion**: Multiple diverse search queries per round (breadth 1-5) covering technical, practical, comparative, critical, and forward-looking angles
- **Sub-question decomposition**: Broad questions are broken into focused sub-topics before query generation (depth > 1)
- **Round-robin parallel execution**: Searches and analyses run concurrently within each round using bounded-concurrency worker pools, dramatically reducing total research time
- **LLM-driven analysis**: Each round's results are analyzed by an agent session to extract structured findings with confidence ratings
- **LLM-driven analysis**: Each query's results are analyzed by its own agent session (per-query provenance) to extract structured findings with confidence ratings
- **Source authority scoring**: Every source is scored by domain authority; low-quality SEO domains are penalized with a hard floor; findings are ranked by authority × confidence before synthesis
- **Cross-query corroboration**: A finding is corroborated only when its sources were independently surfaced by multiple different search queries
- **Citation integrity**: References are rebuilt from the authoritative bibliography (never the LLM's), and hallucinated inline citation numbers are stripped
- **Near-duplicate detection**: Syndicated copies of the same article are removed by title similarity, and duplicate findings across rounds are merged
- **Automatic deduplication**: Search results are deduplicated by URL across all queries
- **Graceful degradation**: Individual search or analysis failures don't crash the full research — partial results are preserved
- **Robust LLM output parsing**: JSON output with code fences, prose prefixes, or trailing commas is parsed reliably
- **Graceful degradation**: Individual search or analysis failures don't crash the full research — partial results are preserved, with retry-with-backoff for transient Firecrawl errors
- **Progress streaming**: Real-time progress widget with spinner, phase indicators, and progress bar
- **Abort support**: Research can be cancelled mid-flight via `AbortSignal`
- **Rich TUI rendering**: Compact collapsed view and detailed expanded view in the terminal UI
@@ -30,13 +36,15 @@ deep_research — multi-round deep web research via Firecrawl with iterative que
```
Parameters:
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `question` | string | — | The research question to investigate |
| `depth` | integer (1-3) | 2 | Number of research rounds |
| `breadth` | integer (1-5) | 3 | Search queries per round |
| `format` | "markdown" \| "structured" | "markdown" | Output format for the report |
| `details.showRoundDetails` | boolean | false | Include per-round search metadata in output |
| `audience` | "general" \| "expert" \| "executive" | "general" | Tone and depth for the report audience |
| `details.showRoundDetails` | boolean | false | Include per-round search metadata (incl. failed searches) in output |
### Command (interactive)