Merge pull request 'watchpr: fix watch mode never detecting changes' (#5) from benvin/watchpr-watchloop-fix into main

Reviewed-on: #5

internal/agent/client_test.go

@@ -163,6 +163,59 @@ func TestFetchState(t *testing.T) {
 	}
 }
 
+// A merged PR whose branch was deleted leaves its head commit unreachable, so
+// the commit-status endpoint 404s. FetchState must still return the (merged)
+// state rather than failing, otherwise the watch loop never sees the merge.
+func TestFetchStateToleratesMissingCommit(t *testing.T) {
+	mux := http.NewServeMux()
+	mux.HandleFunc("/api/v1/repos/unkin/repo/pulls/7", func(w http.ResponseWriter, r *http.Request) {
+		_, _ = io.WriteString(w, `{"number":7,"state":"closed","merged":true,"mergeable":true,"title":"feat","html_url":"u","head":{"sha":"cafebabecafebabe"}}`)
+	})
+	mux.HandleFunc("/api/v1/repos/unkin/repo/commits/cafebabecafebabe/status", func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusNotFound)
+		_, _ = io.WriteString(w, `{"message":"not found"}`)
+	})
+	mux.HandleFunc("/api/v1/repos/unkin/repo/issues/7/comments", func(w http.ResponseWriter, r *http.Request) {
+		_, _ = io.WriteString(w, `[]`)
+	})
+	srv := httptest.NewServer(mux)
+	defer srv.Close()
+
+	c := &GiteaClient{BaseURL: srv.URL, Token: "t", HTTP: srv.Client()}
+	ref := PRRef{Owner: "unkin", Repo: "repo", Number: 7}
+	st, err := FetchState(c, ref, "unkin-agent")
+	if err != nil {
+		t.Fatalf("FetchState must tolerate a 404 status for a gone commit: %v", err)
+	}
+	if !st.Merged || st.State != "closed" {
+		t.Errorf("merged/state = %t/%q, want true/closed", st.Merged, st.State)
+	}
+	if st.CIStatus != "" {
+		t.Errorf("CIStatus = %q, want empty (no status for a gone commit)", st.CIStatus)
+	}
+}
+
+// A non-404 error from the status endpoint is still fatal: only "commit gone" is
+// tolerated, not, say, an auth or server failure.
+func TestFetchStateFailsOnNon404StatusError(t *testing.T) {
+	mux := http.NewServeMux()
+	mux.HandleFunc("/api/v1/repos/unkin/repo/pulls/7", func(w http.ResponseWriter, r *http.Request) {
+		_, _ = io.WriteString(w, `{"number":7,"state":"open","merged":false,"mergeable":true,"head":{"sha":"cafebabecafebabe"}}`)
+	})
+	mux.HandleFunc("/api/v1/repos/unkin/repo/commits/cafebabecafebabe/status", func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusInternalServerError)
+		_, _ = io.WriteString(w, `{"message":"boom"}`)
+	})
+	srv := httptest.NewServer(mux)
+	defer srv.Close()
+
+	c := &GiteaClient{BaseURL: srv.URL, Token: "t", HTTP: srv.Client()}
+	ref := PRRef{Owner: "unkin", Repo: "repo", Number: 7}
+	if _, err := FetchState(c, ref, "unkin-agent"); err == nil {
+		t.Fatal("FetchState should surface a 500 from the status endpoint")
+	}
+}
+
 func TestGiteaAPIError(t *testing.T) {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/api/v1/repos/unkin/repo/pulls", func(w http.ResponseWriter, r *http.Request) {

internal/agent/gitea.go

@@ -3,12 +3,33 @@ package agent
 import (
 	"bytes"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
 	"strings"
 )
 
+// APIError is a non-2xx response from the Gitea API. It carries the status code
+// so callers can react to specific failures (e.g. tolerate a 404 for a commit
+// whose branch was deleted after a merge) instead of parsing error strings.
+type APIError struct {
+	Method     string
+	Path       string
+	StatusCode int
+	Body       string
+}
+
+func (e *APIError) Error() string {
+	return fmt.Sprintf("gitea %s %s: HTTP %d: %s", e.Method, e.Path, e.StatusCode, e.Body)
+}
+
+// isNotFound reports whether err is a Gitea 404.
+func isNotFound(err error) bool {
+	var apiErr *APIError
+	return errors.As(err, &apiErr) && apiErr.StatusCode == http.StatusNotFound
+}
+
 // GiteaClient talks to the Gitea REST API as the agent user.
 type GiteaClient struct {
 	BaseURL string
@@ -49,7 +70,7 @@ func (c *GiteaClient) do(method, path string, body any, out any) error {
 	defer func() { _ = resp.Body.Close() }()
 	data, _ := io.ReadAll(resp.Body)
 	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
-		return fmt.Errorf("gitea %s %s: HTTP %d: %s", method, path, resp.StatusCode, strings.TrimSpace(string(data)))
+		return &APIError{Method: method, Path: path, StatusCode: resp.StatusCode, Body: strings.TrimSpace(string(data))}
 	}
 	if out != nil && len(data) > 0 {
 		if err := json.Unmarshal(data, out); err != nil {

internal/agent/watch.go

@@ -22,8 +22,11 @@ func FetchState(c *GiteaClient, ref PRRef, agentLogin string) (PRState, error) {
 	if err != nil {
 		return PRState{}, err
 	}
+	// A 404 here means the head commit is gone (branch deleted after a squash/
+	// rebase merge); the PR object is still authoritative, so treat CI as absent
+	// rather than discarding the merge signal and hanging the watch loop.
 	ci, err := c.CommitStatus(ref.RepoPath(), pr.Head.Sha)
-	if err != nil {
+	if err != nil && !isNotFound(err) {
 		return PRState{}, err
 	}
 	comments, err := c.ListComments(ref.RepoPath(), ref.Number)

internal/agent/watch_test.go

@@ -2,6 +2,10 @@ package agent
 
 import (
 	"errors"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
 	"testing"
 	"time"
 )
@@ -273,6 +277,78 @@ func TestWatchBaselineErrorAborts(t *testing.T) {
 	}
 }
 
+// The production hang, end to end: a watched PR stays open across several polls,
+// then is squash-merged and its branch deleted, so the commit-status endpoint
+// 404s. Driven through a real *GiteaClient, the watch loop must still detect the
+// merge on the poll it happens. Before the fix, FetchState returned an error on
+// that poll (the 404 masked the merge), so the loop reported only poll errors
+// and never exited -- exactly the 37-minute hang seen in production.
+func TestWatchDetectsMergeWhenCommitGone(t *testing.T) {
+	const sha = "cafebabecafebabe"
+	var polls atomic.Int32 // number of PR fetches so far
+
+	mux := http.NewServeMux()
+	mux.HandleFunc("/api/v1/repos/unkin/repo/pulls/7", func(w http.ResponseWriter, r *http.Request) {
+		n := polls.Add(1)
+		if n >= 4 { // baseline + two unchanged polls, then merged
+			_, _ = fmt.Fprintf(w, `{"number":7,"state":"closed","merged":true,"mergeable":true,"head":{"sha":%q}}`, sha)
+			return
+		}
+		_, _ = fmt.Fprintf(w, `{"number":7,"state":"open","merged":false,"mergeable":true,"head":{"sha":%q}}`, sha)
+	})
+	mux.HandleFunc("/api/v1/repos/unkin/repo/commits/"+sha+"/status", func(w http.ResponseWriter, r *http.Request) {
+		if polls.Load() >= 4 { // branch deleted post-merge: commit is gone
+			w.WriteHeader(http.StatusNotFound)
+			_, _ = fmt.Fprint(w, `{"message":"not found"}`)
+			return
+		}
+		_, _ = fmt.Fprint(w, `{"state":"success"}`)
+	})
+	mux.HandleFunc("/api/v1/repos/unkin/repo/issues/7/comments", func(w http.ResponseWriter, r *http.Request) {
+		_, _ = fmt.Fprint(w, `[]`)
+	})
+	srv := httptest.NewServer(mux)
+	defer srv.Close()
+
+	c := &GiteaClient{BaseURL: srv.URL, Token: "t", HTTP: srv.Client()}
+	ref := PRRef{Owner: "unkin", Repo: "repo", Number: 7}
+
+	// A real ticker so the loop advances on its own; a hang (the bug) is caught
+	// by the timeout below instead of blocking the suite.
+	tk := time.NewTicker(5 * time.Millisecond)
+	defer tk.Stop()
+	var pollErr atomic.Pointer[error]
+	type outcome struct {
+		res WatchResult
+		err error
+	}
+	done := make(chan outcome, 1)
+	go func() {
+		res, err := Watch(c, []PRRef{ref}, "unkin-agent", tk.C, nil,
+			func(_ PRRef, e error) { pollErr.Store(&e) })
+		done <- outcome{res, err}
+	}()
+
+	select {
+	case o := <-done:
+		if o.err != nil {
+			t.Fatalf("Watch: %v", o.err)
+		}
+		if o.res.Reason != "PR merged" {
+			t.Errorf("reason = %q, want %q", o.res.Reason, "PR merged")
+		}
+		if p := pollErr.Load(); p != nil {
+			t.Errorf("no poll error expected once a 404 status is tolerated, got: %v", *p)
+		}
+	case <-time.After(3 * time.Second):
+		var got error
+		if p := pollErr.Load(); p != nil {
+			got = *p
+		}
+		t.Fatalf("Watch hung: a merge with a gone head commit was never detected (last poll error: %v)", got)
+	}
+}
+
 func TestCountNonAgentComments(t *testing.T) {
 	comments := []Comment{
 		{User: User{Login: "unkin-agent"}},