feat(input): add diff_compress module + prior-review compaction helpers

Two pure stdlib helpers that shrink what lands in the model prompt: * compress_diff(diff, *, context=2) — re-renders a unified diff so each hunk keeps only unchanged lines on either side of its +/- lines. File headers + hunk headers + +/- lines preserved verbatim. Pure-context hunks dropped (rare but legal — git emits them on whitespace-only diffs). Collapsed gaps of >=5 lines emit a single '@@ … N context line(s) omitted … @@' marker so the reviewer knows code was elided. Smaller gaps stay silent — the marker would be longer than the elision. * extract_finding_bullets(review_body) — pulls the lines of a prior review that look like a pragent finding (- **[SEVERITY]** path:line — …) and drops everything else. The model already has the diff; repeating the prose is just token burn. No I/O, no network. Tolerant of malformed input — never raises. 14 unit tests cover both helpers, including an anchor-preservation check against parse_diff_anchors to guarantee compress-then-anchor still works. Wiring in ai_review/opencode_review lives in the next commit.
2026-08-20 16:12:33 +00:00
parent f59b906395
commit 770581bf53
2 changed files with 417 additions and 0 deletions
@@ -0,0 +1,248 @@
+"""Unit tests for pragent pilot diff_compress. No network."""
+import os
+import sys
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+ROOT = os.path.abspath(os.path.join(HERE, "..", ".."))
+sys.path.insert(0, os.path.join(ROOT, "pilot"))
+
+import diff_compress  # noqa: E402
+from diff_compress import compress_diff, extract_finding_bullets  # noqa: E402
+
+
+# ---------------------------------------------------------------------------
+# compress_diff
+# ---------------------------------------------------------------------------
+
+
+_DIFF = """\
+diff --git a/src/a.py b/src/a.py
+index 1..2 100644
+--- a/src/a.py
+++ b/src/a.py
+@@ -1,10 +1,11 @@
+ ctx1
+-removed
+added
+ ctx2
+ ctx3
+ ctx4
+ ctx5
+ ctx6
+ ctx7
+extra
+ ctx8
+@@ -20,3 +21,4 @@
+ tail1
+ tail2
+tail3
+ tail4
+diff --git a/binary.bin b/binary.bin
+new file mode 100644
+index 0..1
+Binary files differ
+"""
+
+
+def test_compress_diff_default_context_two():
+    text, orig, kept = compress_diff(_DIFF, context=2)
+    # +/- lines preserved
+    assert "+added" in text
+    assert "-removed" in text
+    assert "+extra" in text
+    assert "+tail3" in text
+    # 2 context lines around +/- kept, the rest collapsed
+    assert "ctx2" in text and "ctx3" in text
+    assert "ctx4" not in text  # outside the +/- window
+    # Binary files pass through
+    assert "Binary files differ" in text
+    # File headers preserved
+    assert "diff --git a/src/a.py b/src/a.py" in text
+    assert orig > kept
+
+
+def test_compress_diff_context_zero_strips_context():
+    text, orig, kept = compress_diff(_DIFF, context=0)
+    assert "+added" in text and "-removed" in text and "+extra" in text
+    # Context lines dropped (only +/- survive)
+    assert " ctx1" not in text
+    assert "ctx2" not in text
+    assert orig > kept
+
+
+def test_compress_diff_negative_disables_compression():
+    text, orig, kept = compress_diff(_DIFF, context=-1)
+    assert text == _DIFF
+    assert orig == kept
+
+
+def test_compress_diff_collapsed_gap_marker():
+    # Two +/- lines separated by 14 context lines, context=2 — the gap between
+    # them is 10 dropped lines (between the +/- windows), which exceeds the
+    # 5-line marker threshold. The marker tells the reviewer there's more code
+    # between the kept hunks.
+    middle = "\n".join(f" m{i}" for i in range(14)) + "\n"  # trailing \n!
+    diff = (
+        "diff --git a/x.py b/x.py\n"
+        "--- a/x.py\n"
+        "+++ b/x.py\n"
+        "@@ -1,21 +1,23 @@\n"
+        + " c1\n c2\n"           # ctx near +a (kept with context=2)
+        + "+a\n"
+        + middle
+        + "+b\n"
+        + " c1\n c2\n"           # ctx near +b (kept with context=2)
+    )
+    text, _, _ = compress_diff(diff, context=2)
+    assert "+a" in text and "+b" in text
+    assert "@@ …" in text and "context line(s) omitted" in text
+
+
+def test_compress_diff_strips_no_newline_marker():
+    diff = (
+        "diff --git a/x.py b/x.py\n"
+        "--- a/x.py\n"
+        "+++ b/x.py\n"
+        "@@ -1,2 +1,2 @@\n"
+        " a\n"
+        "-b\n"
+        "\\ No newline at end of file\n"
+        "+c\n"
+        "\\ No newline at end of file\n"
+    )
+    text, _, _ = compress_diff(diff, context=2)
+    assert "\\ No newline" not in text
+    assert "-b" in text and "+c" in text
+
+
+def test_compress_diff_empty_and_none():
+    text, orig, kept = compress_diff("", context=2)
+    assert text == ""
+    assert orig == 0 and kept == 0
+    text, orig, kept = compress_diff(None, context=2)  # type: ignore[arg-context]
+    assert text == ""
+    assert orig == 0 and kept == 0
+
+
+def test_compress_diff_pure_context_hunk_drops_body():
+    # A hunk that's *only* context lines (rare but legal — `git diff` emits
+    # these when the post-image differs only in whitespace outside the visible
+    # hunk) collapses entirely: file headers stay, the empty hunk header
+    # itself drops. The reviewer doesn't need to re-read unchanged code.
+    diff = (
+        "diff --git a/x.py b/x.py\n"
+        "--- a/x.py\n"
+        "+++ b/x.py\n"
+        "@@ -1,3 +1,3 @@\n"
+        " a\n"
+        " b\n"
+        " c\n"
+    )
+    text, _, _ = compress_diff(diff, context=2)
+    assert text == "diff --git a/x.py b/x.py\n--- a/x.py\n+++ b/x.py\n"
+    assert "@@ -1,3" not in text  # empty hunk header dropped
+
+
+def test_compress_diff_wide_window_keeps_more_context():
+    narrow, _, _ = compress_diff(_DIFF, context=0)
+    wide, _, wide_kept = compress_diff(_DIFF, context=10)
+    assert wide_kept > len(narrow)
+
+
+# ---------------------------------------------------------------------------
+# extract_finding_bullets
+# ---------------------------------------------------------------------------
+
+
+_BODY = """\
+🤖 **AI Review** · pragent pilot · glm-5.2:cloud · `abcdef12`
+
+Adds the salvavoid void-death item-rescue module. Risk is moderate on the
+PlayerDeathEvent item/inventory path. New findings (not in prior review):
+orphaned chest left in world on rescue failure, missing module-enabled check.
+
+- **[HIGH]** `src/main/java/dev/marcospaulo/canalhandia/VoidProtection.java:162` — drop duplication race. fix: use ItemMeta to write inventory once. (ref: https://example.com)
+- **[MEDIUM]** `src/main/java/dev/marcospaulo/canalhandia/VoidProtection.java:67` — O(n^2) spiral. fix: cap radius. (https://example.com/spiral)
+- **[LOW]** `src/main/java/dev/marcospaulo/canalhandia/VoidProtection.java:3` — package-info javadoc missing.
+
+_4 inline comment(s) posted below._
+<!-- pragent:sha=abcdef1234567890 -->
+"""
+
+
+def test_extract_finding_bullets_basic():
+    bs = extract_finding_bullets(_BODY)
+    assert len(bs) == 3
+    assert any("HIGH" in b and "VoidProtection.java:162" in b for b in bs)
+    assert any("MEDIUM" in b for b in bs)
+    assert any("LOW" in b for b in bs)
+
+
+def test_extract_finding_bullets_drops_prose():
+    bs = extract_finding_bullets(_BODY)
+    joined = "\n".join(bs)
+    # The summary prose is dropped.
+    assert "Adds the salvavoid" not in joined
+    assert "PlayerDeathEvent item/inventory path" not in joined
+    # The inline-comment footer is dropped.
+    assert "inline comment(s) posted below" not in joined
+    # The sha marker is dropped.
+    assert "pragent:sha=" not in joined
+
+
+def test_extract_finding_bullets_accepts_lowercase_summary_bullets():
+    # `summary_bullets` renders `- **[HIGH]**` (bold); older reviews used
+    # `- [high]` (plain). Both should match.
+    text = (
+        "- [critical] `a.py:1` — bug. fix: fix it.\n"
+        "- **[HIGH]** `b.go:9` — race.\n"
+    )
+    bs = extract_finding_bullets(text)
+    assert len(bs) == 2
+    assert "CRITICAL" in bs[0].upper() or "critical" in bs[0]
+    assert "HIGH" in bs[1]
+
+
+def test_extract_finding_bullets_empty_and_prose_only():
+    assert extract_finding_bullets("") == []
+    assert extract_finding_bullets("   \n  \n") == []
+    assert extract_finding_bullets("Just some prose, no bullets here.") == []
+    assert extract_finding_bullets("- This is a regular bullet, not a finding.") == []
+
+
+def test_extract_finding_bullets_keeps_indented_subbullets():
+    # A finding may carry continuation lines below it (rare in pragent output
+    # but legal). We only pull the matching line itself — sub-bullets stay
+    # with their parent as prose.
+    text = (
+        "- **[HIGH]** `a.py:1` — bug.\n"
+        "  sub-bullet continuation that the reviewer wrote\n"
+        "- **[LOW]** `b.go:2` — nit.\n"
+    )
+    bs = extract_finding_bullets(text)
+    assert len(bs) == 2
+    assert all("sub-bullet continuation" not in b for b in bs)
+
+
+def test_compress_diff_preserves_anchors_for_post_change_lines():
+    # Sanity: a finding anchored on a context line that compress_diff keeps
+    # must still be a valid anchor after compression. We re-run the parser the
+    # ai_review core uses, so a regression here surfaces as misanchored
+    # inline comments in production.
+    import ai_review
+    diff = (
+        "diff --git a/x.py b/x.py\n"
+        "--- a/x.py\n"
+        "+++ b/x.py\n"
+        "@@ -10,4 +10,5 @@\n"
+        " ctx_a\n"
+        " ctx_b\n"
+        "+new\n"
+        " ctx_c\n"
+        " ctx_d\n"
+    )
+    text, _, _ = compress_diff(diff, context=1)
+    anchors = ai_review.parse_diff_anchors(text)
+    assert 12 in anchors["x.py"]  # +new
+    # ctx_a is within 1 line of +new at line 12, so kept.
+    assert 11 in anchors["x.py"]