Livrare LOT 1 - Didi

ai_platform/modules/didi_brain/lint/reporter.py

@@ -0,0 +1,92 @@
+"""Pretty printing for the Lint pass output.
+
+Called from scripts/10_run_lint.py after a run, and from
+scripts/11_show_contradictions.py for ad-hoc inspection of the state file
+without re-running classification.
+"""
+
+from __future__ import annotations
+
+from rich.console import Console
+from rich.panel import Panel
+from rich.table import Table
+
+from lint._state import LintState, LintStats, PairVerdict
+
+console = Console()
+
+
+def render_stats(stats: LintStats) -> None:
+    t = Table(title="Lint pass stats", show_lines=False)
+    t.add_column("Metric", style="bold")
+    t.add_column("Count", justify="right")
+    t.add_row("atoms seen", str(stats.atoms_seen))
+    t.add_row("candidate pairs", str(stats.candidates_generated))
+    t.add_row("[dim]skipped (cached)[/dim]", str(stats.pairs_skipped_cached))
+    t.add_row("pairs evaluated", str(stats.pairs_evaluated))
+    t.add_row("[red]CONTRADICTORY[/red]", str(stats.contradictory))
+    t.add_row("[yellow]EQUIVALENT[/yellow]", str(stats.equivalent))
+    t.add_row("[dim]INCOMPARABLE[/dim]", str(stats.incomparable))
+    t.add_row("errors", str(stats.errors))
+    console.print(t)
+
+
+def render_contradictions(
+    state: LintState,
+    *,
+    top_n: int = 10,
+    min_confidence: float = 0.7,
+) -> None:
+    contras = [v for v in state.all_contradictions if v.confidence >= min_confidence]
+    contras.sort(key=lambda v: (-v.confidence, -v.similarity))
+
+    header = (
+        f"[bold red]CONTRADICTIONS[/bold red] "
+        f"({len(contras)} with confidence >= {min_confidence:.2f}, showing top {top_n})"
+    )
+    console.print(Panel.fit(header))
+
+    if not contras:
+        console.print(
+            "[dim]no contradictions above threshold. "
+            "The current Wikipedia-only corpus is self-consistent by design, "
+            "which is expected for a single well-curated source. "
+            "Add diverse sources to surface real disagreement.[/dim]"
+        )
+        return
+
+    for i, v in enumerate(contras[:top_n], 1):
+        console.print()
+        console.print(
+            f"[bold]#{i}[/bold]  "
+            f"confidence=[red]{v.confidence:.2f}[/red]  "
+            f"(embed sim {v.similarity:.2f})"
+        )
+        console.print(f"  [green]A:[/green] {v.atom_a_claim[:240]}")
+        console.print(f"     [dim]→ {v.atom_a_url}[/dim]")
+        console.print(f"  [red]B:[/red] {v.atom_b_claim[:240]}")
+        console.print(f"     [dim]→ {v.atom_b_url}[/dim]")
+
+
+def render_equivalents(
+    state: LintState, *, top_n: int = 10, min_confidence: float = 0.85
+) -> None:
+    equivs = [v for v in state.all_equivalents if v.confidence >= min_confidence]
+    equivs.sort(key=lambda v: (-v.confidence, -v.similarity))
+
+    header = (
+        f"[bold yellow]PARAPHRASE CLUSTERS[/bold yellow] "
+        f"({len(equivs)} with confidence >= {min_confidence:.2f}, showing top {top_n})"
+    )
+    console.print()
+    console.print(Panel.fit(header))
+
+    if not equivs:
+        console.print("[dim]no paraphrase clusters above threshold[/dim]")
+        return
+
+    for i, v in enumerate(equivs[:top_n], 1):
+        console.print()
+        console.print(f"[bold]#{i}[/bold]  confidence=[yellow]{v.confidence:.2f}[/yellow]")
+        console.print(f"  · {v.atom_a_claim[:200]}")
+        console.print(f"  · {v.atom_b_claim[:200]}")