pilot: dedupe + repo config + inline comments w/ suggestions

- Dedupe: Gitea-as-state. Scan existing reviews for a hidden  marker matching the head sha; skip if present (kills duplicate reviews on label-toggle / re-fire). Prior review bodies fed back as 'already said' context (light framework §6.1). - Repo-local focus: optional .pr-review.json at repo root ({focus,exclude_paths,languages,instructions}), fetched at head ref. - Inline comments + apply-able suggestions: model emits JSON findings {severity,path,line,problem,fix,suggestion}; diff hunks parsed into valid (path,new_line) RIGHT-side anchors; anchored findings become positional review comments with a ```suggestion fence (Gitea apply-button); unanchored findings fold into the summary body. - Tests: parse_diff_anchors, parse_findings (tolerant JSON), split_findings, inline_comment_body, summary_bullets, parse_repo_config, reviewed_shas, prior_review_bodies, sha-marker. 35 pass. - Bump OLLAMA_MAX_TOKENS default 6000 -> 8000 (suggestions add length). Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-17 19:59:36 +00:00
parent 789fb38bae
commit 90cea84f6f
4 changed files with 734 additions and 45 deletions
@@ -10,7 +10,15 @@ sys.path.insert(0, os.path.join(ROOT, "pilot"))
 from ai_review import (  # noqa: E402
    build_user_prompt,
    format_review_body,
+    inline_comment_body,
+    parse_diff_anchors,
+    parse_findings,
+    parse_repo_config,
    parse_text_blocks,
+    prior_review_bodies,
+    reviewed_shas,
+    split_findings,
+    summary_bullets,
    truncate_diff,
 )

@@ -130,4 +138,206 @@ def test_build_user_prompt_truncates_long_body():

 def test_build_user_prompt_no_body():
    p = build_user_prompt("t", "", "d")
-    assert "Description:" not in p
+    assert "Description:" not in p
+
+
+def test_build_user_prompt_with_config_and_prior():
+    cfg = {"focus": ["security"], "instructions": "Use Result<T,E>."}
+    prior = ["🤖 **AI Review** …\n- [high] x:1 — old."]
+    p = build_user_prompt("t", "b", "diff --git a/x b/x", config=cfg, prior_reviews=prior)
+    assert "## Repo review config" in p
+    assert "security" in p
+    assert "Result<T,E>" in p
+    assert "## PREVIOUS REVIEWS" in p
+    assert "old." in p
+
+
+# ---------------------------------------------------------------------------
+# parse_diff_anchors
+# ---------------------------------------------------------------------------
+
+
+_DIFF = """\
+diff --git a/src/a.py b/src/a.py
+index 1..2 100644
+--- a/src/a.py
+++ b/src/a.py
+@@ -1,4 +1,5 @@
+ context
+-removed
+added
+ context2
+@@ -10,3 +10,4 @@
+ keep
+new
+ last
+diff --git a/binary.bin b/binary.bin
+new file mode 100644
+index 0..1
+Binary files differ
+"""
+
+
+def test_parse_diff_anchors_context_and_added():
+    a = parse_diff_anchors(_DIFF)
+    # context(1), +added(2), context2(3) | keep(10), +new(11), last(12)
+    assert a["src/a.py"] == {1, 2, 3, 10, 11, 12}
+    # removed line (-removed, old line 2) has no new-line anchor
+    assert 2 in a["src/a.py"]  # 2 here is the +added line, not the removed one
+
+
+def test_parse_diff_anchors_binary_file_present_no_lines():
+    a = parse_diff_anchors(_DIFF)
+    assert "binary.bin" in a
+    assert a["binary.bin"] == set()
+
+
+def test_parse_diff_anchors_empty():
+    assert parse_diff_anchors("") == {}
+    assert parse_diff_anchors(None) == {}  # type: ignore[arg-type]
+
+
+def test_parse_diff_anchors_new_file():
+    diff = "diff --git a/new.ts b/new.ts\nnew file mode 100644\n--- /dev/null\n+++ b/new.ts\n@@ -0,0 +1,3 @@\n+a\n+b\n+c\n"
+    a = parse_diff_anchors(diff)
+    assert a["new.ts"] == {1, 2, 3}
+
+
+# ---------------------------------------------------------------------------
+# parse_findings
+# ---------------------------------------------------------------------------
+
+
+def test_parse_findings_clean_json():
+    txt = '{"findings":[{"severity":"high","path":"a.py","line":3,"problem":"x","fix":"y","suggestion":"z"}]}'
+    fs = parse_findings(txt)
+    assert len(fs) == 1
+    assert fs[0]["severity"] == "high"
+    assert fs[0]["path"] == "a.py"
+    assert fs[0]["line"] == 3
+
+
+def test_parse_findings_fenced_json():
+    txt = '```json\n{"findings":[{"severity":"low","path":"b.go","line":1,"problem":"p","fix":"","suggestion":""}]}\n```'
+    fs = parse_findings(txt)
+    assert len(fs) == 1
+    assert fs[0]["path"] == "b.go"
+
+
+def test_parse_findings_json_in_prose():
+    txt = 'Here is my review: {"findings":[{"severity":"critical","path":"c","line":9,"problem":"q"}]} thanks!'
+    fs = parse_findings(txt)
+    assert len(fs) == 1
+    assert fs[0]["severity"] == "critical"
+
+
+def test_parse_findings_empty():
+    assert parse_findings('{"findings":[]}') == []
+    assert parse_findings("") == []
+    assert parse_findings("not json at all") == []
+
+
+def test_parse_findings_drops_bad_entries():
+    # missing path, bad line, unknown severity (normalised)
+    txt = '{"findings":[{"line":1},{"path":"x","line":-1},{"path":"x","line":2,"severity":"bogus","problem":"p"}]}'
+    fs = parse_findings(txt)
+    assert len(fs) == 1
+    assert fs[0]["severity"] == "medium"
+
+
+# ---------------------------------------------------------------------------
+# split_findings + inline_comment_body + summary_bullets
+# ---------------------------------------------------------------------------
+
+
+def test_split_findings_by_anchor():
+    anchors = {"a.py": {1, 3, 4}}
+    fs = [
+        {"severity": "high", "path": "a.py", "line": 3, "problem": "p", "fix": "f", "suggestion": ""},
+        {"severity": "low", "path": "a.py", "line": 99, "problem": "off", "fix": "", "suggestion": ""},
+        {"severity": "medium", "path": "other.go", "line": 1, "problem": "x", "fix": "", "suggestion": ""},
+    ]
+    anchored, unanchored = split_findings(fs, anchors)
+    assert [f["line"] for f in anchored] == [3]
+    assert len(unanchored) == 2
+
+
+def test_inline_comment_body_with_suggestion():
+    f = {"severity": "high", "path": "a", "line": 1, "problem": "bad", "fix": "swap", "suggestion": "good()"}
+    body = inline_comment_body(f)
+    assert "**[HIGH]**" in body
+    assert "bad" in body
+    assert "```suggestion\n" in body
+    assert "good()" in body
+
+
+def test_inline_comment_body_no_suggestion():
+    f = {"severity": "low", "path": "a", "line": 1, "problem": "p", "fix": "f", "suggestion": ""}
+    body = inline_comment_body(f)
+    assert "```suggestion" not in body
+    assert "Fix: f" in body
+
+
+def test_summary_bullets_format():
+    fs = [{"severity": "high", "path": "a.py", "line": 7, "problem": "p", "fix": "f", "suggestion": ""}]
+    b = summary_bullets(fs)
+    assert "- **[HIGH]**" in b
+    assert "`a.py:7`" in b
+
+
+# ---------------------------------------------------------------------------
+# repo config parsing
+# ---------------------------------------------------------------------------
+
+
+def test_parse_repo_config_full():
+    raw = '{"focus":["security","perf"],"exclude_paths":["vendor/**"],"languages":["go"],"instructions":"be strict"}'
+    c = parse_repo_config(raw)
+    assert c["focus"] == ["security", "perf"]
+    assert c["exclude_paths"] == ["vendor/**"]
+    assert c["instructions"] == "be strict"
+
+
+def test_parse_repo_config_partial_and_bad():
+    assert parse_repo_config('{"focus":"not-a-list"}') == {}
+    assert parse_repo_config('{"focus":["ok"]}') == {"focus": ["ok"]}
+    assert parse_repo_config("") == {}
+    assert parse_repo_config("not json") == {}
+    assert parse_repo_config('{"instructions":"   "}') == {}
+
+
+# ---------------------------------------------------------------------------
+# dedupe / prior-context parsing
+# ---------------------------------------------------------------------------
+
+
+def test_reviewed_shas_extracts_marker():
+    reviews = [
+        {"body": "🤖 AI Review · glm · `abcdef12`\n\n<!-- pragent:sha=abcdef1234567890 -->"},
+        {"body": "human comment, no marker"},
+        {"body": "<!-- pragent:sha=0987654 -->"},
+    ]
+    shas = reviewed_shas(reviews)
+    assert "abcdef1234567890" in shas
+    assert "0987654" in shas
+
+
+def test_reviewed_shas_empty():
+    assert reviewed_shas([]) == set()
+    assert reviewed_shas([{"body": "no marker"}]) == set()
+
+
+def test_prior_review_bodies_skips_current_sha():
+    reviews = [
+        {"body": "r1\n<!-- pragent:sha=1111111 -->"},
+        {"body": "r2\n<!-- pragent:sha=2222222 -->"},
+        {"body": "no marker here"},
+    ]
+    prior = prior_review_bodies(reviews, current_sha="2222222")
+    assert len(prior) == 1
+    assert "r1" in prior[0]
+
+
+def test_format_review_body_has_sha_marker():
+    body = format_review_body("- [high] x:1 — b", "glm-5.2:cloud", "abcdef1234567890")
+    assert "<!-- pragent:sha=abcdef1234567890 -->" in body