fix(gate): pin primary diff evidence to PR head #281
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,96 @@ | ||
| package evidence | ||
|
|
||
| import ( | ||
| "encoding/json" | ||
| "strings" | ||
| "testing" | ||
| ) | ||
|
|
||
| func TestFetchPrimaryDiffPinsViewedHead(t *testing.T) { | ||
| const ( | ||
| base = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" | ||
| head = "1111111111111111111111111111111111111111" | ||
| ) | ||
| result, err := fetchPrimaryDiff(PRRef{Repo: "o/r", Number: 7}, head, primaryDiffFetchers{ | ||
| pull: func(PRRef) (json.RawMessage, error) { | ||
| return pullHeads(base, head), nil | ||
| }, | ||
| compare: func(_ PRRef, gotBase, gotHead string) (json.RawMessage, error) { | ||
| if gotBase != base || gotHead != head { | ||
| t.Fatalf("compare pair = %s...%s, want %s...%s", gotBase, gotHead, base, head) | ||
| } | ||
| return []byte("the diff"), nil | ||
| }, | ||
| }) | ||
| if err != nil { | ||
| t.Fatalf("fetchPrimaryDiff: %v", err) | ||
| } | ||
| if result.Diff != "the diff" || result.Head != head { | ||
| t.Fatalf("result = %+v, want diff and exact viewed head", result) | ||
| } | ||
| } | ||
|
|
||
| // This is the moved-head mutant: the pull read reports a different head than | ||
| // the view. No diff fetch may run and no bytes may escape as evidence. | ||
| func TestFetchPrimaryDiffRefusesMovedHead(t *testing.T) { | ||
| const ( | ||
| viewed = "1111111111111111111111111111111111111111" | ||
| moved = "2222222222222222222222222222222222222222" | ||
| ) | ||
| compareCalled := false | ||
| result, err := fetchPrimaryDiff(PRRef{Repo: "o/r", Number: 7}, viewed, primaryDiffFetchers{ | ||
| pull: func(PRRef) (json.RawMessage, error) { | ||
| return pullHeads("aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa", moved), nil | ||
| }, | ||
| compare: func(PRRef, string, string) (json.RawMessage, error) { | ||
| compareCalled = true | ||
| return []byte("diff for the moved head"), nil | ||
| }, | ||
| }) | ||
| if err == nil { | ||
| t.Fatalf("moved head returned recordable evidence: %+v", result) | ||
| } | ||
| if !strings.Contains(err.Error(), "pr head moved during gather") || | ||
| !strings.Contains(err.Error(), viewed) || !strings.Contains(err.Error(), moved) { | ||
| t.Fatalf("moved-head refusal lost its evidence: %v", err) | ||
| } | ||
| if result != (diffResult{}) { | ||
| t.Fatalf("moved head returned partial evidence: %+v", result) | ||
| } | ||
| if compareCalled { | ||
| t.Fatal("moved head reached the compare diff fetch") | ||
| } | ||
| } | ||
|
|
||
| // This is the double-force-push mutant from review: the PR begins at A, moves | ||
| // to B during the diff read, then returns to A. The compare fetch can still | ||
| // receive only A's immutable commit pair. | ||
| func TestFetchPrimaryDiffPinsABARaceToCommitPair(t *testing.T) { | ||
| const ( | ||
| base = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" | ||
| viewed = "1111111111111111111111111111111111111111" | ||
| moved = "2222222222222222222222222222222222222222" | ||
| ) | ||
| liveHead := viewed | ||
| result, err := fetchPrimaryDiff(PRRef{Repo: "o/r", Number: 7}, viewed, primaryDiffFetchers{ | ||
| pull: func(PRRef) (json.RawMessage, error) { return pullHeads(base, liveHead), nil }, | ||
| compare: func(_ PRRef, gotBase, gotHead string) (json.RawMessage, error) { | ||
| liveHead = moved | ||
| defer func() { liveHead = viewed }() | ||
| if gotBase != base || gotHead != viewed { | ||
| t.Fatalf("mutable pair reached compare: %s...%s", gotBase, gotHead) | ||
| } | ||
| return []byte("diff for immutable A"), nil | ||
| }, | ||
| }) | ||
| if err != nil { | ||
| t.Fatalf("fetchPrimaryDiff under A-B-A race: %v", err) | ||
| } | ||
| if liveHead != viewed || result.Head != viewed || result.Diff != "diff for immutable A" { | ||
| t.Fatalf("A-B-A result = %+v, live head %s", result, liveHead) | ||
| } | ||
| } | ||
|
|
||
| func pullHeads(base, head string) json.RawMessage { | ||
| return []byte(`{"base":{"sha":"` + base + `"},"head":{"sha":"` + head + `"}}`) | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -40,7 +40,7 @@ type diffBody struct { | |
| PR PRRef `json:"pr"` | ||
| Diff string `json:"diff"` | ||
| // Provenance — reconstructable from state alone which path produced the | ||
| // diff and which commits it spans. "api" = GitHub's SHA-pinned compare diff; | ||
| // "local-merge-base" = the oversized-PR fallback. | ||
| Method string `json:"method,omitempty"` | ||
| Head string `json:"head,omitempty"` | ||
|
|
@@ -115,6 +115,11 @@ type reviewFetchers struct { | |
| panel func(PRRef, string, []rawComment, []Comment) reviewpanel.Evidence | ||
| } | ||
|
|
||
| type primaryDiffFetchers struct { | ||
| pull func(PRRef) (json.RawMessage, error) | ||
| compare func(PRRef, string, string) (json.RawMessage, error) | ||
| } | ||
|
|
||
| // Gather records view, diff, and comments evidence for a PR and returns their ids. | ||
| func Gather(st *state.Store, run string, pr PRRef) (Bundle, error) { | ||
| viewID, view, err := View(st, run, pr) | ||
|
|
@@ -160,23 +165,20 @@ func GatherFrom(st *state.Store, run string, pr PRRef, viewID string, view json. | |
| return b, fmt.Errorf("evidence: parse PR head: %w", err) | ||
| } | ||
|
|
||
| // The primary path reads the pull's immutable commit pair, checks that its | ||
| // head matches the view, then asks GitHub for that pair's compare diff. The | ||
| // fallback controls the same exact SHAs locally when GitHub rejects the diff | ||
| // as oversized. | ||
| body := diffBody{PR: pr, Method: "api"} | ||
| r, err := primaryDiff(pr, viewed.HeadRefOid) | ||
| if tooLarge(err) { | ||
| r, err = fallbackDiff(pr, view) | ||
| body.Method = "local-merge-base" | ||
| } | ||
| if err != nil { | ||
| return b, err | ||
| } | ||
| body.Diff, body.MergeBase, body.Head = r.Diff, r.MergeBase, r.Head | ||
| a, err := st.Append(state.KindEvidence, run, nil, body) | ||
| if err != nil { | ||
| return b, err | ||
|
|
@@ -211,6 +213,47 @@ func GatherFrom(st *state.Store, run string, pr PRRef, viewID string, view json. | |
| return b, nil | ||
| } | ||
|
|
||
| func primaryDiff(pr PRRef, viewHead string) (diffResult, error) { | ||
| return fetchPrimaryDiff(pr, viewHead, primaryDiffFetchers{ | ||
| pull: func(pr PRRef) (json.RawMessage, error) { | ||
| return gh("api", fmt.Sprintf("repos/%s/pulls/%d", pr.Repo, pr.Number)) | ||
| }, | ||
| compare: func(pr PRRef, base, head string) (json.RawMessage, error) { | ||
| return gh("api", "-H", "Accept: application/vnd.github.v3.diff", | ||
| fmt.Sprintf("repos/%s/compare/%s...%s", pr.Repo, base, head)) | ||
| }, | ||
| }) | ||
| } | ||
|
|
||
| // fetchPrimaryDiff binds the primary diff to an immutable commit pair. The | ||
| // pull read must still match the view evidence, and the diff is then fetched by | ||
| // those exact base/head SHAs rather than by mutable PR number. An A→B→A | ||
| // force-push during the fetch cannot substitute B's bytes for A's evidence. | ||
| func fetchPrimaryDiff(pr PRRef, viewHead string, fetchers primaryDiffFetchers) (diffResult, error) { | ||
| pull, err := fetchers.pull(pr) | ||
| if err != nil { | ||
| return diffResult{}, err | ||
| } | ||
| base, head, err := parsePullHeads(pull) | ||
| if err != nil { | ||
| return diffResult{}, err | ||
| } | ||
| if !reSHA.MatchString(base) || !reSHA.MatchString(head) { | ||
| return diffResult{}, fmt.Errorf("evidence: non-hex commit id from api (base=%q head=%q)", base, head) | ||
| } | ||
| if head != viewHead { | ||
| return diffResult{}, fmt.Errorf("evidence: pr head moved during gather: view %s, pulls %s", viewHead, head) | ||
| } | ||
| diff, err := fetchers.compare(pr, base, head) | ||
| if err != nil { | ||
| return diffResult{}, err | ||
| } | ||
| if len(diff) == 0 { | ||
| return diffResult{}, fmt.Errorf("evidence: empty diff at head %s", head) | ||
| } | ||
| return diffResult{Diff: string(diff), Head: head}, nil | ||
|
Comment on lines
+244
to
+254
There was a problem hiding this comment.
When a writer can force-push twice during this gather, the post-read still accepts bytes from the wrong head: the view sees A, the writer pushes B, AGENTS.md reference: AGENTS.md:L160-L161 Useful? React with 👍 / 👎.
Owner
Author
There was a problem hiding this comment. Addressed in 9c19941: the primary path now fetches the diff from the SHA-pinned compare/... endpoint after validating the pull pair against the viewed head. Added a deterministic A→B→A mutant and verified the compare bytes match gh pr diff byte-for-byte on this PR. There was a problem hiding this comment.
When the base branch advances after gathering, this result records only AGENTS.md reference: cmd/gate/AGENTS.md:L3-L6 Useful? React with 👍 / 👎. |
||
| } | ||
|
Comment on lines
+251
to
+255
|
||
|
|
||
| // decisiveReviewState reports whether a submission state states a position on | ||
| // whether the PR may merge. APPROVED and CHANGES_REQUESTED do; COMMENTED does | ||
| // NOT — GitHub is unambiguous that commenting after approving does not withdraw | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For a PR changing more than 300 files but remaining below the old 20,000-line limit, this endpoint can return a successful, nonempty response while omitting later files: GitHub's Compare two commits documentation limits the comparison's changed-file output to 300, and the repository's own
cmd/gate/docs/features/evidence-local-diff/spec.md:27-28already notes that truncation. Thelen(diff) != 0check therefore accepts partial evidence, allowing the floor and model verifiers to authorize a head without seeing changes after the cap; use the commit-pinned local diff path or otherwise prove completeness before recording this response.AGENTS.md reference: AGENTS.md:L160-L161
Useful? React with 👍 / 👎.