fix(review): correct diff-compression line numbers, prior-review dedupe, triage skip
Four defects, all found reviewing PR #9 (two of them by pragent-bot's own review of that PR, which the anchoring bug then misplaced): * compress_diff dropped context lines but copied the original `@@` hunk header verbatim, so the header no longer described the lines beneath it. parse_diff_anchors then walked stale headers and produced anchor sets shifted by the number of elided lines, misplacing inline comments or demoting them to bullets. Each surviving run of lines is now re-emitted as its own hunk with a recomputed `@@ -a,b +c,d @@`, so the output stays a valid unified diff whose numbers describe the real post-change file. The pseudo-marker `@@ … N context line(s) omitted … @@` is gone; it parsed as a hunk header and reset the anchor counter to 0. Anchoring additionally runs on the raw diff now, so the prompt window can never shrink the anchorable set. * compress_diff's `_FILE_HEADER` regex matched diff *body* lines: a removed YAML `---` separator or an added `++` line was read as a file header, truncating the hunk and dropping its `@@` header with it. Body detection is now prefix-based, with a full-shape hunk-header regex. * extract_finding_bullets could not match the bullets pragent itself posts: summary_bullets renders an emoji severity badge between the `-` and the `[SEV]` tag, which the regex rejected, so compact_prior_reviews always returned [] and every re-review repeated its previous findings. * triage returning `{"lenses":[]}` — documented in .opencode/agents/triage.md as "no lens has surface, skip the fan-out" — ran every lens instead, since _intersect_with_triage mapped an empty selection to "all" and the call site had a second `or reviewers` fallback. `[]` and None are now distinct outcomes: `[]` skips, None fails open. A roster naming only unknown lens ids now fails open rather than silencing the review. The skip path returns a well-formed empty-findings response instead of "", which had landed in ai_review's unparseable-output branch and posted "AI review produced no parseable output" — a malfunction message for a normal verdict. Also: non-URL references (a CVE id, a doc title) rendered as `[CVE-2024-1234](CVE-2024-1234)`, a broken relative link in Gitea — now plain text. PRAGENT_DIFF_CONTEXT and friends parse through _int_env, so a typo logs and falls back instead of killing a review mid-flight. Removed format_usage_section, dead since the collapsible usage block replaced it and carrying a duplicate copy of the price-target logic. Tests: 290 -> 301. New coverage for hunk-header fidelity before/after compression, header-shaped content lines, the bullet round-trip against the real renderer, and triage's three outcomes (previously untested). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01B11e8TZZxJyzHW7jj7KWUN
This commit is contained in:
Marcos
@@ -19,7 +19,6 @@ from ai_review import ( # noqa: E402
|
||||
compute_attribution,
|
||||
findings_table,
|
||||
format_review_body,
|
||||
format_usage_section,
|
||||
inline_comment_body,
|
||||
parse_diff_anchors,
|
||||
parse_findings,
|
||||
@@ -604,6 +603,31 @@ def test_inline_comment_body_renders_reference():
|
||||
assert "🔗 **Reference:** [cve.example/X](https://cve.example/X)" in body
|
||||
|
||||
|
||||
def test_reference_non_url_renders_as_plain_text():
|
||||
# A CVE id or doc title is not a URL. `[CVE-2024-1](CVE-2024-1)` renders as
|
||||
# a broken *relative* link in Gitea, so bare text is the correct fallback.
|
||||
assert ai_review._format_reference("CVE-2024-1234") == "CVE-2024-1234"
|
||||
assert ai_review._format_reference("see OWASP A03") == "see OWASP A03"
|
||||
assert ai_review._format_reference("") == ""
|
||||
f = {"severity": "high", "path": "a", "line": 1, "problem": "p", "fix": "",
|
||||
"suggestion": "", "reference": "CVE-2024-1234"}
|
||||
body = inline_comment_body(f)
|
||||
assert "🔗 **Reference:** CVE-2024-1234" in body
|
||||
assert "](CVE-" not in body
|
||||
|
||||
|
||||
def test_int_env_falls_back_on_garbage(monkeypatch, capsys):
|
||||
monkeypatch.setenv("PRAGENT_DIFF_CONTEXT", "two")
|
||||
assert ai_review._int_env("PRAGENT_DIFF_CONTEXT", 1) == 1
|
||||
assert "ignoring PRAGENT_DIFF_CONTEXT" in capsys.readouterr().err
|
||||
monkeypatch.setenv("PRAGENT_DIFF_CONTEXT", " 3 ")
|
||||
assert ai_review._int_env("PRAGENT_DIFF_CONTEXT", 1) == 3
|
||||
monkeypatch.setenv("PRAGENT_DIFF_CONTEXT", "")
|
||||
assert ai_review._int_env("PRAGENT_DIFF_CONTEXT", 1) == 1
|
||||
monkeypatch.delenv("PRAGENT_DIFF_CONTEXT")
|
||||
assert ai_review._int_env("PRAGENT_DIFF_CONTEXT", -1) == -1
|
||||
|
||||
|
||||
def test_inline_comment_body_no_reference_no_ref_line():
|
||||
f = {"severity": "low", "path": "a", "line": 1, "problem": "p", "fix": "",
|
||||
"suggestion": "", "reference": ""}
|
||||
@@ -641,7 +665,7 @@ def test_format_review_body_with_summary_section():
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# AI-USAGE: compute_attribution + format_usage_section + inline 🪙 line
|
||||
# AI-USAGE: compute_attribution + usage block + inline 🪙 line
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@@ -695,47 +719,30 @@ def test_inline_comment_body_no_attribution_no_coin_line():
|
||||
assert "🪙" not in inline_comment_body(f)
|
||||
|
||||
|
||||
def test_format_usage_section_renders_totals_and_table():
|
||||
fs = [
|
||||
{"severity": "critical", "path": "src/Foo.java", "line": 98,
|
||||
"problem": "p"*10, "fix": "f", "suggestion": "", "_tok_attrib": 180, "_tok_pct": 0.29},
|
||||
]
|
||||
def test_render_collapsible_usage_renders_totals():
|
||||
usage = {"input": 18420, "output": 612, "reasoning": 0, "cache_read": 15210,
|
||||
"cache_write": 0, "total": 19032, "cost": 0.0, "steps": 7, "duration_s": 142.0}
|
||||
sec = format_usage_section(usage, fs, "glm-5.2:cloud")
|
||||
assert "## 🔋 AI usage" in sec
|
||||
sec = _render_collapsible_usage(usage, "glm-5.2:cloud", config=None)
|
||||
assert "🔋 AI Usage & Run Details" in sec
|
||||
assert "`glm-5.2:cloud`" in sec
|
||||
assert "agent steps: 7" in sec
|
||||
assert "duration: 142.0s" in sec
|
||||
assert "18420 in" in sec and "612 out" in sec and "19032 total" in sec
|
||||
assert "7 steps" in sec
|
||||
assert "142.0s" in sec
|
||||
assert "18420 in / 612 out" in sec and "19032 total" in sec
|
||||
assert "$0.00" in sec
|
||||
assert "whole-repo checkout" in sec
|
||||
assert "Whole-repo checkout" in sec
|
||||
assert "attributed" in sec
|
||||
# table
|
||||
assert "| severity | location | ≈out tok | % |" in sec
|
||||
assert "CRITICAL" in sec
|
||||
assert "`src/Foo.java:98`" in sec
|
||||
assert "180" in sec and "29%" in sec
|
||||
|
||||
|
||||
def test_format_usage_section_omits_table_when_no_attributed_rows():
|
||||
usage = {"input": 10, "output": 0, "reasoning": 0, "cache_read": 0,
|
||||
"cache_write": 0, "total": 10, "cost": 0.0, "steps": 1, "duration_s": 1.0}
|
||||
sec = format_usage_section(usage, [], "glm-5.2:cloud")
|
||||
assert "## 🔋 AI usage" in sec
|
||||
assert "severity | location" not in sec # no rows → no table
|
||||
def test_render_collapsible_usage_none_returns_empty():
|
||||
assert _render_collapsible_usage(None, "m", config=None) == ""
|
||||
|
||||
|
||||
def test_format_usage_section_none_returns_empty():
|
||||
assert format_usage_section(None, [], "m") == ""
|
||||
|
||||
|
||||
def test_format_usage_section_cost_nonzero():
|
||||
def test_render_collapsible_usage_cost_nonzero_drops_free_tier_note():
|
||||
usage = {"input": 10, "output": 0, "reasoning": 0, "cache_read": 0,
|
||||
"cache_write": 0, "total": 10, "cost": 0.0123, "steps": 1, "duration_s": 1.0}
|
||||
sec = format_usage_section(usage, [], "m")
|
||||
sec = _render_collapsible_usage(usage, "m", config=None)
|
||||
assert "$0.0123" in sec
|
||||
assert "billed by provider" in sec
|
||||
assert "free tier" not in sec
|
||||
|
||||
|
||||
def test_format_review_body_usage_section_below_findings():
|
||||
@@ -1022,7 +1029,7 @@ def test_salvage_summary_empty_when_nothing_to_salvage():
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# equivalent_cost + format_usage_section equivalent-provider line
|
||||
# equivalent_cost + usage-block equivalent-provider line
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@@ -1037,15 +1044,15 @@ def test_equivalent_cost_unknown_key_returns_zero():
|
||||
assert ai_review.equivalent_cost({"input": 100}, "bogus") == 0.0
|
||||
|
||||
|
||||
def test_format_usage_section_shows_equivalent_provider_cost():
|
||||
def test_usage_block_shows_equivalent_provider_cost():
|
||||
usage = {"input": 200000, "output": 4000, "reasoning": 0,
|
||||
"cache_read": 0, "cache_write": 0, "total": 204000,
|
||||
"cost": 0.0, "steps": 6, "duration_s": 100.0}
|
||||
sec = ai_review.format_usage_section(usage, [], "glm-5.2:cloud")
|
||||
sec = ai_review._render_collapsible_usage(usage, "glm-5.2:cloud", config=None)
|
||||
# Two cost lines now: an equivalent (default Sonnet 5) AND the $0 actual.
|
||||
assert "## 🔋 AI usage" in sec
|
||||
assert "est. cost on **Claude Sonnet 5**" in sec
|
||||
assert "actual: $0.00" in sec
|
||||
assert "🔋 AI Usage & Run Details" in sec
|
||||
assert "**Est. cost on Claude Sonnet 5**" in sec
|
||||
assert "**Actual**: $0.00" in sec
|
||||
assert "free tier" in sec
|
||||
# Equivalent should be > 0 for non-trivial token counts.
|
||||
assert "$0.00" in sec # the actual line
|
||||
@@ -1057,36 +1064,36 @@ def test_format_usage_section_shows_equivalent_provider_cost():
|
||||
assert "$0.00" not in cost_lines[0]
|
||||
|
||||
|
||||
def test_format_usage_section_honors_cost_target(monkeypatch):
|
||||
def test_usage_block_honors_cost_target(monkeypatch):
|
||||
monkeypatch.setenv("PRAGENT_PRICE_TARGET", "claude-haiku-4-5")
|
||||
usage = {"input": 1000, "output": 100, "reasoning": 0,
|
||||
"cache_read": 0, "cache_write": 0, "total": 1100,
|
||||
"cost": 0.0, "steps": 1, "duration_s": 5.0}
|
||||
sec = ai_review.format_usage_section(usage, [], "glm-5.2:cloud")
|
||||
sec = ai_review._render_collapsible_usage(usage, "glm-5.2:cloud", config=None)
|
||||
assert "Claude Haiku 4.5" in sec
|
||||
# 1k * $1/MTok + 100 * $5/MTok = 0.001 + 0.0005 = $0.0015
|
||||
assert "$0.0015" in sec
|
||||
|
||||
|
||||
def test_format_usage_section_respects_repo_config_cost_target(monkeypatch):
|
||||
def test_usage_block_respects_repo_config_cost_target(monkeypatch):
|
||||
monkeypatch.delenv("PRAGENT_PRICE_TARGET", raising=False)
|
||||
usage = {"input": 1000, "output": 100, "reasoning": 0,
|
||||
"cache_read": 0, "cache_write": 0, "total": 1100,
|
||||
"cost": 0.0, "steps": 1, "duration_s": 5.0}
|
||||
sec = ai_review.format_usage_section(
|
||||
usage, [], "glm-5.2:cloud", config={"cost_target": "claude-opus-5"}
|
||||
sec = ai_review._render_collapsible_usage(
|
||||
usage, "glm-5.2:cloud", config={"cost_target": "claude-opus-5"}
|
||||
)
|
||||
assert "Claude Opus 5" in sec
|
||||
# Opus 5 = $5/MTok input + $25/MTok output → 1000*5e-6 + 100*25e-6 = 0.0075
|
||||
assert "$0.0075" in sec
|
||||
|
||||
|
||||
def test_format_usage_section_reports_unknown_price_target():
|
||||
def test_usage_block_reports_unknown_price_target():
|
||||
usage = {"input": 100, "output": 100, "reasoning": 0,
|
||||
"cache_read": 0, "cache_write": 0, "total": 200,
|
||||
"cost": 0.0, "steps": 1, "duration_s": 1.0}
|
||||
sec = ai_review.format_usage_section(
|
||||
usage, [], "glm-5.2:cloud", config={"cost_target": "bogus-model"}
|
||||
sec = ai_review._render_collapsible_usage(
|
||||
usage, "glm-5.2:cloud", config={"cost_target": "bogus-model"}
|
||||
)
|
||||
# Falls back to default + surfaces the error in the line.
|
||||
assert "Claude Sonnet 5" in sec
|
||||
|
||||
Reference in New Issue
Block a user