From 6988be9ff3fbc846b72d1bd071aa6c0d6e8cc511 Mon Sep 17 00:00:00 2001 From: unkin-agent Date: Sat, 26 Sep 2026 18:45:48 +1000 Subject: [PATCH 1/6] watchpr: only alert on mergeability lost after the baseline Track mergeability across the whole run and decode it as a tri-state, so a PR already conflicted when watching starts is polled on instead of reported. --- AGENTS.md | 6 ++ README.md | 5 +- cmd/watchpr/main.go | 2 +- internal/agent/gitea.go | 12 +-- internal/agent/watch.go | 131 +++++++++++++++++++----- internal/agent/watch_test.go | 193 +++++++++++++++++++++++++++++++---- 6 files changed, 298 insertions(+), 51 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 2ef6715..68433d2 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -220,6 +220,12 @@ wrapped per stage (login / read denied / write denied) via `ErrVaultDenied`. half-finished (`rebase-merge`, `MERGE_HEAD`, `CHERRY_PICK_HEAD`, …). A directory whose backing repo is gone is deleted outright, but only ever inside the worktree root. +- `watchpr` alerts on changes, not on conditions: the baseline snapshot is a real + read, so a PR that is already conflicted or already CI-failing when watching + starts is polled on rather than reported. Mergeability is the one rule needing + a run of observations (`prWatch`), because a conflict must both persist for two + polls and follow a mergeable one; Gitea's `mergeable` is tri-state (absent/null + = not yet computed) and unknown counts as neither answer. - CI "combined status" comes from `/commits/{sha}/status`; an empty head SHA yields an empty state without an API call. - Gitea backs every PR with an issue of the same number and serves comments from diff --git a/README.md b/README.md index a09ac35..e09979c 100644 --- a/README.md +++ b/README.md @@ -85,7 +85,10 @@ Non-zero exit on any API error. Poll PRs and exit (reporting what changed) when a tracked PR **merges/closes**, gets a **new comment from someone other than the agent**, its **CI fails** (failure/error), or it **loses mergeability** (a conflict appears). Benign -transitions — CI `pending`→`success`, the agent's own comments — are ignored. +transitions — CI `pending`→`success`, the agent's own comments and pushes — are +ignored, and so is any condition the PR was already in at the baseline: a PR +that is already conflicted or already failing when watching starts keeps being +watched. ```bash # Watch until something meaningful happens (default interval 60s) diff --git a/cmd/watchpr/main.go b/cmd/watchpr/main.go index 3efcee5..5a9d505 100644 --- a/cmd/watchpr/main.go +++ b/cmd/watchpr/main.go @@ -176,7 +176,7 @@ func report(key, reason string, st agent.PRState, jsonMode bool) { } func printState(st agent.PRState) { - fmt.Printf("%s state=%s merged=%t mergeable=%t ci=%s head=%s comments(non-agent)=%d\n", + fmt.Printf("%s state=%s merged=%t mergeable=%s ci=%s head=%s comments(non-agent)=%d\n", st.Ref.String(), st.State, st.Merged, st.Mergeable, ciOrNone(st.CIStatus), shortSHA(st.HeadSHA), st.NonAgentComments) } diff --git a/internal/agent/gitea.go b/internal/agent/gitea.go index 6cc8d73..6f84f75 100644 --- a/internal/agent/gitea.go +++ b/internal/agent/gitea.go @@ -189,12 +189,12 @@ func (c *GiteaClient) Whoami() (User, error) { // PullRequest is the subset of Gitea's PR object we track. type PullRequest struct { - Number int `json:"number"` - State string `json:"state"` - Title string `json:"title"` - Merged bool `json:"merged"` - Mergeable bool `json:"mergeable"` - HTMLURL string `json:"html_url"` + Number int `json:"number"` + State string `json:"state"` + Title string `json:"title"` + Merged bool `json:"merged"` + Mergeable Mergeability `json:"mergeable"` + HTMLURL string `json:"html_url"` Head struct { Sha string `json:"sha"` Ref string `json:"ref"` diff --git a/internal/agent/watch.go b/internal/agent/watch.go index 385fa8c..4719e3a 100644 --- a/internal/agent/watch.go +++ b/internal/agent/watch.go @@ -3,6 +3,7 @@ package agent import ( "errors" "fmt" + "strings" "time" ) @@ -16,17 +17,62 @@ func IsPRGone(err error) bool { return errors.Is(err, errPRGone) } +// Mergeability is Gitea's mergeable flag as a tri-state. The flag is null or +// absent while Gitea recomputes the merge base, and an unknown value must not be +// read as either answer. +type Mergeability int + +const ( + MergeUnknown Mergeability = iota + MergeYes + MergeNo +) + +func (m Mergeability) String() string { + switch m { + case MergeYes: + return "true" + case MergeNo: + return "false" + } + return "unknown" +} + +func (m Mergeability) MarshalJSON() ([]byte, error) { + switch m { + case MergeYes: + return []byte("true"), nil + case MergeNo: + return []byte("false"), nil + } + return []byte("null"), nil +} + +func (m *Mergeability) UnmarshalJSON(b []byte) error { + switch strings.TrimSpace(string(b)) { + case "true": + *m = MergeYes + case "false": + *m = MergeNo + case "null": + *m = MergeUnknown + default: + return fmt.Errorf("mergeable: unexpected value %s", b) + } + return nil +} + // PRState is a point-in-time snapshot of the PR attributes watchpr tracks. type PRState struct { - Ref PRRef `json:"ref"` - State string `json:"state"` // open / closed - Merged bool `json:"merged"` - HeadSHA string `json:"head_sha"` - Mergeable bool `json:"mergeable"` - CIStatus string `json:"ci_status"` // success / pending / failure / error / "" - NonAgentComments int `json:"non_agent_comments"` - Title string `json:"title"` - URL string `json:"url"` + Ref PRRef `json:"ref"` + State string `json:"state"` // open / closed + Merged bool `json:"merged"` + HeadSHA string `json:"head_sha"` + Mergeable Mergeability `json:"mergeable"` + CIStatus string `json:"ci_status"` // success / pending / failure / error / "" + NonAgentComments int `json:"non_agent_comments"` + Title string `json:"title"` + URL string `json:"url"` } // FetchState builds a PRState for the given ref. agentLogin's comments are @@ -95,6 +141,53 @@ func terminalState(st PRState) (bool, string) { return false, "" } +// conflictPolls is how many consecutive non-mergeable polls confirm a real +// conflict. Gitea reports mergeable=false while it recomputes the merge base +// after a push, so a single poll is debounced. +const conflictPolls = 2 + +// prWatch tracks one PR across polls. Mergeability needs more memory than the +// previous snapshot: losing it only counts as a change if the PR was mergeable +// at some point after watching began, since a conflict that predates the +// baseline is the state the operator is already waiting on. +type prWatch struct { + prev PRState + everMergeable bool + conflicts int +} + +func newPRWatch(baseline PRState) *prWatch { + w := &prWatch{prev: baseline} + w.track(baseline) + return w +} + +// track folds one snapshot's mergeability into the run of observations. Unknown +// neither confirms a conflict nor clears one. +func (w *prWatch) track(st PRState) { + switch st.Mergeable { + case MergeYes: + w.everMergeable = true + w.conflicts = 0 + case MergeNo: + w.conflicts++ + } +} + +// observe folds in the newest snapshot and reports whether the watch should end. +func (w *prWatch) observe(cur PRState) (bool, string) { + changed, reason := MeaningfulChange(w.prev, cur) + w.prev = cur + w.track(cur) + if changed { + return true, reason + } + if w.everMergeable && w.conflicts >= conflictPolls && cur.State == "open" { + return true, "PR lost mergeability (conflict)" + } + return false, "" +} + // MaxPollFailures is how many consecutive failed polls of the same PR are // tolerated before Watch gives up. The abort fires on the 20th failed tick, so // at watchpr's default 60s interval a watch rides out ~19 minutes of failure. @@ -112,7 +205,7 @@ const MaxPollFailures = 20 // onBaseline, if set, fires once after all baselines are captured and before the // first tick. func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Time, onBaseline func(), onError func(PRRef, error)) (WatchResult, error) { - prev := make(map[string]PRState, len(refs)) + watches := make(map[string]*prWatch, len(refs)) for _, ref := range refs { st, err := f.FetchState(ref, agentLogin) if err != nil { @@ -121,7 +214,7 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti if terminal, reason := terminalState(st); terminal { return WatchResult{Ref: ref, Reason: reason, State: st}, nil } - prev[ref.String()] = st + watches[ref.String()] = newPRWatch(st) } if onBaseline != nil { onBaseline() @@ -145,10 +238,9 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti continue } fails[key] = 0 - if changed, reason := MeaningfulChange(prev[key], cur); changed { + if changed, reason := watches[key].observe(cur); changed { return WatchResult{Ref: ref, Reason: reason, State: cur}, nil } - prev[key] = cur } } return WatchResult{}, nil @@ -172,15 +264,15 @@ func isFailedCI(state string) bool { // MeaningfulChange compares a previous state to the current one and reports // whether a change warrants alerting the operator, with a human-readable -// reason. Benign transitions (CI pending→success, the agent's own comments, an -// unchanged snapshot) return false. +// reason. Benign transitions (CI pending→success, the agent's own comments, a +// new head commit, an unchanged snapshot) return false. Mergeability is not +// decided here: it takes a whole run of observations, which prWatch keeps. // // Alerting conditions: // - the PR merged // - the PR closed without merging // - a new comment from someone other than the agent // - CI transitioned into failure/error -// - the PR lost mergeability (a conflict appeared) for two consecutive polls func MeaningfulChange(prev, cur PRState) (bool, string) { if !prev.Merged && cur.Merged { return true, "PR merged" @@ -195,12 +287,5 @@ func MeaningfulChange(prev, cur PRState) (bool, string) { if isFailedCI(cur.CIStatus) && !isFailedCI(prev.CIStatus) { return true, "CI failed (" + cur.CIStatus + ")" } - // Gitea computes mergeability asynchronously, so a PR can briefly report - // mergeable=false right after a push. Require the loss to persist across two - // consecutive polls (both prev and cur false, still open) before treating it - // as a real conflict; a single false poll is debounced. - if !prev.Mergeable && !cur.Mergeable && cur.State == "open" { - return true, "PR lost mergeability (conflict)" - } return false, "" } diff --git a/internal/agent/watch_test.go b/internal/agent/watch_test.go index 101ecff..66a702b 100644 --- a/internal/agent/watch_test.go +++ b/internal/agent/watch_test.go @@ -1,6 +1,7 @@ package agent import ( + "encoding/json" "errors" "fmt" "net/http" @@ -17,7 +18,7 @@ func base() PRState { State: "open", Merged: false, HeadSHA: "abc123", - Mergeable: true, + Mergeable: MergeYes, CIStatus: "pending", NonAgentComments: 0, } @@ -66,25 +67,11 @@ func TestMeaningfulChange(t *testing.T) { wantChange: true, }, { - // A single mergeable=false poll is debounced: Gitea often reports - // this transiently right after a push. - name: "mergeable true to false for one poll is benign", - mutate: func(s *PRState) { s.Mergeable = false }, - wantChange: false, - }, - { - // mergeable=false persisting into a second consecutive poll is a - // real conflict and alerts. - name: "mergeable false persisting a second poll alerts", - mutatePrev: func(s *PRState) { s.Mergeable = false }, - mutate: func(s *PRState) { s.Mergeable = false }, - wantChange: true, - }, - { - // mergeable recovered (false then true) must not alert. - name: "mergeable recovered false to true is benign", - mutatePrev: func(s *PRState) { s.Mergeable = false }, - mutate: func(s *PRState) {}, + // Mergeability takes a run of observations, so no pair of snapshots + // decides it here; prWatch owns that rule. + name: "mergeable false pair alone is not a pairwise change", + mutatePrev: func(s *PRState) { s.Mergeable = MergeNo }, + mutate: func(s *PRState) { s.Mergeable = MergeNo }, wantChange: false, }, { @@ -801,3 +788,169 @@ func TestWatchAnonymousKeepsPolling(t *testing.T) { t.Errorf("fetch calls = %d, want 3 (baseline + two polls)", f.calls) } } + +// drainableTicks returns a channel holding n ticks and already closed, so Watch +// polls exactly n times and then returns instead of blocking. +func drainableTicks(n int) <-chan time.Time { + ticks := make(chan time.Time, n) + for i := 0; i < n; i++ { + ticks <- time.Now() + } + close(ticks) + return ticks +} + +// The production bug: a PR that was already conflicted (and already CI-failing) +// when watching began must not be reported as having just changed. That state is +// what the watcher is waiting to see resolved, so the loop keeps polling. +func TestWatchIgnoresBaselineConflictAndFailure(t *testing.T) { + stuck := base() + stuck.Mergeable = MergeNo + stuck.CIStatus = "failure" + f := &fakeFetcher{states: []PRState{stuck}} + + res, err := Watch(f, []PRRef{stuck.Ref}, "unkin-agent", drainableTicks(5), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "" { + t.Fatalf("Watch ended with %q; a conflict/failure predating the watch is not a change", res.Reason) + } + if f.calls != 6 { + t.Errorf("fetch calls = %d, want 6 (baseline + 5 polls)", f.calls) + } +} + +// Mergeability lost after the baseline still alerts, on the second consecutive +// conflicted poll. +func TestWatchDetectsConflictAfterBaseline(t *testing.T) { + ok := base() + conflicted := base() + conflicted.Mergeable = MergeNo + f := &fakeFetcher{states: []PRState{ok, conflicted, conflicted}} + + res, err := Watch(f, []PRRef{ok.Ref}, "unkin-agent", drainableTicks(3), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "PR lost mergeability (conflict)" { + t.Errorf("reason = %q, want the mergeability loss", res.Reason) + } + if f.calls != 3 { + t.Errorf("fetch calls = %d, want 3 (baseline + the two conflicted polls)", f.calls) + } +} + +// CI that goes green→red during the watch alerts. +func TestWatchDetectsCIFailureAfterBaseline(t *testing.T) { + ok := base() + ok.CIStatus = "pending" + green := base() + green.CIStatus = "success" + red := base() + red.CIStatus = "failure" + f := &fakeFetcher{states: []PRState{ok, green, red}} + + res, err := Watch(f, []PRRef{ok.Ref}, "unkin-agent", drainableTicks(3), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "CI failed (failure)" { + t.Errorf("reason = %q, want the CI failure (pending→success must pass silently)", res.Reason) + } + if f.calls != 3 { + t.Errorf("fetch calls = %d, want 3 (the success poll must not end the watch)", f.calls) + } +} + +// The agent's own pushes and comments must not end a watch; a comment from +// anyone else must. +func TestWatchIgnoresAgentActivity(t *testing.T) { + start := base() + pushed := base() + pushed.HeadSHA = "def456" // the agent pushed a fix; non-agent comments unchanged + commented := pushed + commented.NonAgentComments = 1 + f := &fakeFetcher{states: []PRState{start, pushed, pushed, commented}} + + res, err := Watch(f, []PRRef{start.Ref}, "unkin-agent", drainableTicks(3), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "new comment from a non-agent user" { + t.Errorf("reason = %q, want the non-agent comment", res.Reason) + } + if f.calls != 4 { + t.Errorf("fetch calls = %d, want 4 (the agent's push and comment must not end the watch)", f.calls) + } +} + +func TestPRWatchMergeability(t *testing.T) { + snap := func(m Mergeability) PRState { + s := base() + s.Mergeable = m + return s + } + tests := []struct { + name string + baseline Mergeability + polls []Mergeability + wantPoll int // 1-based poll that ends the watch; 0 for none + }{ + {"conflicted before the watch never alerts", MergeNo, []Mergeability{MergeNo, MergeNo, MergeNo}, 0}, + {"loss after a mergeable baseline alerts on the second poll", MergeYes, []Mergeability{MergeNo, MergeNo}, 2}, + {"a lone conflicted poll is debounced", MergeYes, []Mergeability{MergeNo, MergeYes, MergeNo}, 0}, + {"unknown at baseline does not arm the rule", MergeUnknown, []Mergeability{MergeNo, MergeNo, MergeNo}, 0}, + {"unknown at baseline then a real loss alerts", MergeUnknown, []Mergeability{MergeYes, MergeNo, MergeNo}, 3}, + {"a baseline conflict resolved then lost again alerts", MergeNo, []Mergeability{MergeYes, MergeNo, MergeNo}, 3}, + {"unknown between conflicted polls does not clear them", MergeYes, []Mergeability{MergeNo, MergeUnknown, MergeNo}, 3}, + {"unknown alone is never a conflict", MergeYes, []Mergeability{MergeUnknown, MergeUnknown, MergeUnknown}, 0}, + } + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + w := newPRWatch(snap(tt.baseline)) + got := 0 + for i, m := range tt.polls { + changed, reason := w.observe(snap(m)) + if !changed { + continue + } + if reason != "PR lost mergeability (conflict)" { + t.Fatalf("poll %d ended the watch with %q, want a mergeability loss", i+1, reason) + } + got = i + 1 + break + } + if got != tt.wantPoll { + t.Errorf("alerted on poll %d, want %d", got, tt.wantPoll) + } + }) + } +} + +// An absent or null mergeable flag means Gitea has not computed it yet, and must +// decode as unknown rather than as a conflict. +func TestMergeabilityDecoding(t *testing.T) { + tests := map[string]Mergeability{ + `{"number":7}`: MergeUnknown, + `{"number":7,"mergeable":null}`: MergeUnknown, + `{"number":7,"mergeable":true}`: MergeYes, + `{"number":7,"mergeable":false}`: MergeNo, + } + for body, want := range tests { + var pr PullRequest + if err := json.Unmarshal([]byte(body), &pr); err != nil { + t.Fatalf("Unmarshal(%s): %v", body, err) + } + if pr.Mergeable != want { + t.Errorf("Unmarshal(%s) mergeable = %v, want %v", body, pr.Mergeable, want) + } + } + out, err := json.Marshal(PRState{Mergeable: MergeUnknown}) + if err != nil { + t.Fatalf("Marshal: %v", err) + } + if !strings.Contains(string(out), `"mergeable":null`) { + t.Errorf("unknown mergeability encoded as %s, want null", out) + } +} -- 2.47.3 From 54c1d868d3e5bcf8b1bed8f9f592d577608a7fe4 Mon Sep 17 00:00:00 2001 From: unkin-agent Date: Sat, 26 Sep 2026 20:48:31 +1000 Subject: [PATCH 2/6] watchpr: arm the conflict rule on a new merge computation A mergeable=false baseline meant a conflict could never be reported, since Gitea sends false while it recomputes after a push. Arm on a head or base SHA change as well as on a mergeable poll, break the conflict run on unknown and failed polls, and print the baseline with the conditions it suppresses. --- cmd/watchpr/main.go | 52 +++++++-- cmd/watchpr/main_test.go | 30 +++++ internal/agent/gitea.go | 5 + internal/agent/watch.go | 82 ++++++++----- internal/agent/watch_test.go | 220 +++++++++++++++++++++++++++++++++-- 5 files changed, 346 insertions(+), 43 deletions(-) diff --git a/cmd/watchpr/main.go b/cmd/watchpr/main.go index 5a9d505..6861e87 100644 --- a/cmd/watchpr/main.go +++ b/cmd/watchpr/main.go @@ -1,8 +1,10 @@ // Command watchpr polls one or more Gitea pull requests and exits when a // tracked PR changes in a way worth alerting on: it merges or closes, gets a // new comment from someone other than the agent, its CI fails, or it loses -// mergeability. Benign transitions (CI pending→success, the agent's own -// comments) are ignored. +// mergeability after the baseline. Benign transitions (CI pending→success, the +// agent's own pushes and comments) are ignored, and so is any condition that was +// already true at the baseline -- which watchpr prints, so a run started against +// a conflicted or CI-red PR says so. // // watchpr owner/repo#12 owner/repo:15 // watchpr --once --json owner/repo#12 @@ -14,6 +16,7 @@ import ( "encoding/json" "fmt" "os" + "strings" "time" "git.unkin.net/unkin/agent-tools/internal/agent" @@ -43,7 +46,8 @@ func newRootCmd() *cobra.Command { Short: "Poll Gitea PRs and exit when one changes meaningfully.", Long: "watchpr polls each PR every --interval and exits (reporting what changed)\n" + "when a PR merges/closes, gets a new non-agent comment, its CI fails, or it\n" + - "loses mergeability. Accepts refs as owner/repo#N or owner/repo:N.", + "loses mergeability after the baseline. Conditions already true at the\n" + + "baseline are printed, not alerted on. Refs take owner/repo#N or owner/repo:N.", Version: version, Args: cobra.ArbitraryArgs, SilenceUsage: true, @@ -126,9 +130,13 @@ func runWatch(c *agent.GiteaClient, refs []agent.PRRef, interval time.Duration, ticker := time.NewTicker(interval) defer ticker.Stop() - onBaseline := func() { - if !jsonMode { - fmt.Fprintf(os.Stderr, "watching %d PR(s) every %s; baseline established\n", len(refs), interval) + onBaseline := func(states []agent.PRState) { + if jsonMode { + return + } + fmt.Fprintf(os.Stderr, "watching %d PR(s) every %s; baseline established\n", len(refs), interval) + for _, st := range states { + fmt.Fprintln(os.Stderr, baselineLine(st)) } } onError := func(ref agent.PRRef, err error) { @@ -176,8 +184,36 @@ func report(key, reason string, st agent.PRState, jsonMode bool) { } func printState(st agent.PRState) { - fmt.Printf("%s state=%s merged=%t mergeable=%s ci=%s head=%s comments(non-agent)=%d\n", - st.Ref.String(), st.State, st.Merged, st.Mergeable, ciOrNone(st.CIStatus), shortSHA(st.HeadSHA), st.NonAgentComments) + fmt.Println(stateLine(st)) +} + +func stateLine(st agent.PRState) string { + return fmt.Sprintf("%s state=%s merged=%t mergeable=%s ci=%s head=%s base=%s comments(non-agent)=%d", + st.Ref.String(), st.State, st.Merged, st.Mergeable, ciOrNone(st.CIStatus), + shortSHA(st.HeadSHA), shortSHA(st.BaseSHA), st.NonAgentComments) +} + +// baselineLine describes the state a watch started from, naming the conditions +// it will deliberately stay silent about: watchpr alerts on changes, so a PR +// that is already conflicted or already CI-red produces no alert for either, and +// that suppression has to be visible to whoever started the watch. +func baselineLine(st agent.PRState) string { + line := " baseline " + stateLine(st) + if s := suppressedAtBaseline(st); s != "" { + return line + " -- " + s + "; not alerting on a pre-existing condition" + } + return line +} + +func suppressedAtBaseline(st agent.PRState) string { + var conds []string + if st.Mergeable == agent.MergeNo { + conds = append(conds, "already non-mergeable (a real conflict, or Gitea still recomputing)") + } + if st.CIStatus == "failure" || st.CIStatus == "error" { + conds = append(conds, "CI already "+st.CIStatus) + } + return strings.Join(conds, ", ") } func ciOrNone(s string) string { diff --git a/cmd/watchpr/main_test.go b/cmd/watchpr/main_test.go index 4932472..f009fbf 100644 --- a/cmd/watchpr/main_test.go +++ b/cmd/watchpr/main_test.go @@ -182,3 +182,33 @@ func TestDescribeFailureNamesTheCause(t *testing.T) { }) } } + +// A watch started against an already conflicted or CI-red PR sends no alert for +// either, so the baseline line has to say that is what it is doing: before this, +// such a run printed nothing in either direction. +func TestBaselineLineNamesSuppressedConditions(t *testing.T) { + st := agent.PRState{ + Ref: agent.PRRef{Owner: "unkin", Repo: "repo", Number: 7}, + State: "open", + Mergeable: agent.MergeNo, + CIStatus: "failure", + HeadSHA: "cafebabecafebabe", + BaseSHA: "deadbeefdeadbeef", + } + got := baselineLine(st) + for _, want := range []string{ + "unkin/repo#7", "mergeable=false", "ci=failure", "head=cafebabe", "base=deadbeef", + "already non-mergeable", "CI already failure", "not alerting", + } { + if !strings.Contains(got, want) { + t.Errorf("baselineLine = %q, want it to mention %q", got, want) + } + } + + clean := st + clean.Mergeable = agent.MergeYes + clean.CIStatus = "success" + if got := baselineLine(clean); strings.Contains(got, "not alerting") { + t.Errorf("baselineLine = %q, want no suppression note for a clean baseline", got) + } +} diff --git a/internal/agent/gitea.go b/internal/agent/gitea.go index 6f84f75..46a7dd6 100644 --- a/internal/agent/gitea.go +++ b/internal/agent/gitea.go @@ -200,6 +200,11 @@ type PullRequest struct { Ref string `json:"ref"` Label string `json:"label"` } `json:"head"` + // Base.Sha is the base branch tip as of this response, not the merge base + // recorded when the PR was opened. + Base struct { + Sha string `json:"sha"` + } `json:"base"` } // prPageSize is the per-page limit for the pulls listing; maxPRPages caps how diff --git a/internal/agent/watch.go b/internal/agent/watch.go index 4719e3a..b5e5282 100644 --- a/internal/agent/watch.go +++ b/internal/agent/watch.go @@ -17,9 +17,11 @@ func IsPRGone(err error) bool { return errors.Is(err, errPRGone) } -// Mergeability is Gitea's mergeable flag as a tri-state. The flag is null or -// absent while Gitea recomputes the merge base, and an unknown value must not be -// read as either answer. +// Mergeability is Gitea's mergeable flag. Gitea 1.26 always sends a plain bool, +// and sends false both for a real conflict and while it recomputes the merge +// base after a push, so false on its own decides nothing (prWatch resolves it). +// Unknown covers what the bool cannot carry: an absent or null flag from another +// Gitea build, and a snapshot no successful poll ever filled in. type Mergeability int const ( @@ -68,6 +70,7 @@ type PRState struct { State string `json:"state"` // open / closed Merged bool `json:"merged"` HeadSHA string `json:"head_sha"` + BaseSHA string `json:"base_sha"` Mergeable Mergeability `json:"mergeable"` CIStatus string `json:"ci_status"` // success / pending / failure / error / "" NonAgentComments int `json:"non_agent_comments"` @@ -101,6 +104,7 @@ func FetchState(c *GiteaClient, ref PRRef, agentLogin string) (PRState, error) { State: pr.State, Merged: pr.Merged, HeadSHA: pr.Head.Sha, + BaseSHA: pr.Base.Sha, Mergeable: pr.Mergeable, CIStatus: ci, NonAgentComments: countNonAgentComments(comments, agentLogin), @@ -141,48 +145,67 @@ func terminalState(st PRState) (bool, string) { return false, "" } -// conflictPolls is how many consecutive non-mergeable polls confirm a real -// conflict. Gitea reports mergeable=false while it recomputes the merge base -// after a push, so a single poll is debounced. +// conflictPolls is how many consecutive non-mergeable polls of an unchanged +// merge computation confirm a real conflict. const conflictPolls = 2 -// prWatch tracks one PR across polls. Mergeability needs more memory than the -// previous snapshot: losing it only counts as a change if the PR was mergeable -// at some point after watching began, since a conflict that predates the -// baseline is the state the operator is already waiting on. +// prWatch tracks one PR across polls, because mergeability needs more memory +// than the previous snapshot. Gitea reports mergeable=false while it recomputes +// the merge base after a push, so a false is only trusted once this watch has +// seen a merge computation start: the PR was mergeable at some point, or its +// head or base SHA moved. A bare false inherited from the baseline says nothing +// -- it is equally a conflict the operator is already waiting on and a recompute +// in flight -- so it arms nothing. type prWatch struct { - prev PRState - everMergeable bool - conflicts int + prev PRState + armed bool + conflicts int } func newPRWatch(baseline PRState) *prWatch { - w := &prWatch{prev: baseline} - w.track(baseline) - return w + return &prWatch{prev: baseline, armed: baseline.Mergeable == MergeYes} } -// track folds one snapshot's mergeability into the run of observations. Unknown -// neither confirms a conflict nor clears one. +// mergeInputsChanged reports whether the commits Gitea merges have moved, which +// starts a fresh merge computation whose result is attributable to this watch. +func mergeInputsChanged(prev, cur PRState) bool { + return cur.HeadSHA != prev.HeadSHA || cur.BaseSHA != prev.BaseSHA +} + +// track folds one snapshot's mergeability into the run of observations. The +// polls that confirm a conflict must be adjacent, so anything but another +// non-mergeable observation breaks the run. func (w *prWatch) track(st PRState) { switch st.Mergeable { - case MergeYes: - w.everMergeable = true - w.conflicts = 0 case MergeNo: w.conflicts++ + case MergeYes: + w.armed = true + w.conflicts = 0 + default: + w.conflicts = 0 } } +// missed records a poll that never produced a snapshot; the run of adjacent +// non-mergeable observations does not survive the gap. +func (w *prWatch) missed() { + w.conflicts = 0 +} + // observe folds in the newest snapshot and reports whether the watch should end. func (w *prWatch) observe(cur PRState) (bool, string) { changed, reason := MeaningfulChange(w.prev, cur) + if mergeInputsChanged(w.prev, cur) { + w.armed = true + w.conflicts = 0 + } w.prev = cur w.track(cur) if changed { return true, reason } - if w.everMergeable && w.conflicts >= conflictPolls && cur.State == "open" { + if w.armed && w.conflicts >= conflictPolls && cur.State == "open" { return true, "PR lost mergeability (conflict)" } return false, "" @@ -202,10 +225,11 @@ const MaxPollFailures = 20 // is gone, renamed, or no longer visible), and MaxPollFailures consecutive // failures of one PR all abort, because a watcher that sees nothing must not // look healthy. -// onBaseline, if set, fires once after all baselines are captured and before the -// first tick. -func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Time, onBaseline func(), onError func(PRRef, error)) (WatchResult, error) { +// onBaseline, if set, receives every captured baseline once, before the first +// tick, so a caller can show what state the watch started from. +func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Time, onBaseline func([]PRState), onError func(PRRef, error)) (WatchResult, error) { watches := make(map[string]*prWatch, len(refs)) + baselines := make([]PRState, 0, len(refs)) for _, ref := range refs { st, err := f.FetchState(ref, agentLogin) if err != nil { @@ -215,9 +239,10 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti return WatchResult{Ref: ref, Reason: reason, State: st}, nil } watches[ref.String()] = newPRWatch(st) + baselines = append(baselines, st) } if onBaseline != nil { - onBaseline() + onBaseline(baselines) } fails := make(map[string]int, len(refs)) for range ticks { @@ -229,6 +254,7 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti return WatchResult{}, fmt.Errorf("polling %s: %w", key, err) } fails[key]++ + watches[key].missed() if onError != nil { onError(ref, err) } @@ -265,8 +291,8 @@ func isFailedCI(state string) bool { // MeaningfulChange compares a previous state to the current one and reports // whether a change warrants alerting the operator, with a human-readable // reason. Benign transitions (CI pending→success, the agent's own comments, a -// new head commit, an unchanged snapshot) return false. Mergeability is not -// decided here: it takes a whole run of observations, which prWatch keeps. +// new head or base commit, an unchanged snapshot) return false. Mergeability is +// not decided here: it takes a whole run of observations, which prWatch keeps. // // Alerting conditions: // - the PR merged diff --git a/internal/agent/watch_test.go b/internal/agent/watch_test.go index 66a702b..7820072 100644 --- a/internal/agent/watch_test.go +++ b/internal/agent/watch_test.go @@ -18,6 +18,7 @@ func base() PRState { State: "open", Merged: false, HeadSHA: "abc123", + BaseSHA: "base000", Mergeable: MergeYes, CIStatus: "pending", NonAgentComments: 0, @@ -209,16 +210,16 @@ func TestWatchDetectsMergeAfterBaseline(t *testing.T) { merged.Merged = true f := &fakeFetcher{states: []PRState{open, merged}} // baseline open, then merged - baselineFired := false + var baselines []PRState ticks := make(chan time.Time, 1) ticks <- time.Now() res, err := Watch(f, []PRRef{open.Ref}, "unkin-agent", - ticks, func() { baselineFired = true }, nil) + ticks, func(sts []PRState) { baselines = sts }, nil) if err != nil { t.Fatalf("Watch: %v", err) } - if !baselineFired { - t.Errorf("onBaseline should fire for an open baseline") + if len(baselines) != 1 || baselines[0].Ref != open.Ref { + t.Errorf("onBaseline received %v, want the one open baseline", baselines) } if res.Reason != "PR merged" { t.Errorf("reason = %q, want %q", res.Reason, "PR merged") @@ -903,7 +904,8 @@ func TestPRWatchMergeability(t *testing.T) { {"unknown at baseline does not arm the rule", MergeUnknown, []Mergeability{MergeNo, MergeNo, MergeNo}, 0}, {"unknown at baseline then a real loss alerts", MergeUnknown, []Mergeability{MergeYes, MergeNo, MergeNo}, 3}, {"a baseline conflict resolved then lost again alerts", MergeNo, []Mergeability{MergeYes, MergeNo, MergeNo}, 3}, - {"unknown between conflicted polls does not clear them", MergeYes, []Mergeability{MergeNo, MergeUnknown, MergeNo}, 3}, + {"unknown between conflicted polls breaks the run", MergeYes, []Mergeability{MergeNo, MergeUnknown, MergeNo}, 0}, + {"the run restarts after an unknown", MergeYes, []Mergeability{MergeNo, MergeUnknown, MergeNo, MergeNo}, 4}, {"unknown alone is never a conflict", MergeYes, []Mergeability{MergeUnknown, MergeUnknown, MergeUnknown}, 0}, } for _, tt := range tests { @@ -928,8 +930,9 @@ func TestPRWatchMergeability(t *testing.T) { } } -// An absent or null mergeable flag means Gitea has not computed it yet, and must -// decode as unknown rather than as a conflict. +// Gitea 1.26 always sends mergeable as a plain bool, so unknown is reserved for +// what that bool cannot carry: an absent or null flag must decode as unknown +// rather than as a conflict, and unknown must encode back as null. func TestMergeabilityDecoding(t *testing.T) { tests := map[string]Mergeability{ `{"number":7}`: MergeUnknown, @@ -954,3 +957,206 @@ func TestMergeabilityDecoding(t *testing.T) { t.Errorf("unknown mergeability encoded as %s, want null", out) } } + +// The inverse of the bug this PR fixed: Gitea reports mergeable=false while it +// recomputes the merge base after a push, and watchpr is normally started right +// after the agent pushes, so the baseline can land inside that window. Demanding +// a mergeable observation to arm the rule left a genuinely conflicted PR silent +// forever. The new head is a new merge computation, so the conflict it confirms +// belongs to this watch. +func TestWatchAlertsWhenBaselineLandedInTheRecomputeWindow(t *testing.T) { + baseline := base() + baseline.Mergeable = MergeNo // still recomputing; the push is not visible yet + + pushed := base() + pushed.Mergeable = MergeNo + pushed.HeadSHA = "def456" + + f := &fakeFetcher{states: []PRState{baseline, pushed, pushed, pushed}} + res, err := Watch(f, []PRRef{baseline.Ref}, "unkin-agent", drainableTicks(3), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "PR lost mergeability (conflict)" { + t.Fatalf("reason = %q, want the mergeability loss; a conflict must not be unreportable because the baseline caught the recompute", res.Reason) + } + if f.calls != 3 { + t.Errorf("fetch calls = %d, want 3 (baseline + the two conflicted polls on the new head)", f.calls) + } +} + +// A base-branch move restarts the same merge computation, so a conflict that +// only becomes visible once someone merges into main alerts too. +func TestWatchAlertsWhenBaseMovedIntoAConflict(t *testing.T) { + baseline := base() + baseline.Mergeable = MergeNo + + moved := base() + moved.Mergeable = MergeNo + moved.BaseSHA = "base111" + + f := &fakeFetcher{states: []PRState{baseline, moved, moved}} + res, err := Watch(f, []PRRef{baseline.Ref}, "unkin-agent", drainableTicks(3), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "PR lost mergeability (conflict)" { + t.Errorf("reason = %q, want the mergeability loss", res.Reason) + } +} + +// The fix this PR exists for: a conflict predating the watch, on a head and base +// that never move, is the condition the operator is already waiting on and must +// stay silent however long the watch runs. +func TestWatchNeverAlertsOnAStableBaselineConflict(t *testing.T) { + stuck := base() + stuck.Mergeable = MergeNo + f := &fakeFetcher{states: []PRState{stuck}} + + res, err := Watch(f, []PRRef{stuck.Ref}, "unkin-agent", drainableTicks(100), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "" { + t.Fatalf("Watch ended with %q after 100 unchanged polls; a conflict that predates the watch is not a change", res.Reason) + } +} + +// Head and base movement arm the conflict rule but are not themselves alerts: a +// push, or a base that moves under the PR, must not end a watch. +func TestWatchArmingMovementDoesNotAlert(t *testing.T) { + start := base() + pushed := base() + pushed.HeadSHA = "def456" + rebased := base() + rebased.HeadSHA = "789abc" + rebased.BaseSHA = "base111" + f := &fakeFetcher{states: []PRState{start, pushed, rebased}} + + res, err := Watch(f, []PRRef{start.Ref}, "unkin-agent", drainableTicks(5), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "" { + t.Fatalf("Watch ended with %q; a new head or base is not a change worth alerting on", res.Reason) + } +} + +// The polls that confirm a conflict must be adjacent. A failed poll produces no +// snapshot, so the run cannot span it and two non-adjacent falses do not fire. +func TestWatchConflictRunDoesNotSpanAFailedPoll(t *testing.T) { + ok := base() + conflicted := base() + conflicted.Mergeable = MergeNo + f := &fakeFetcher{ + states: []PRState{ok, conflicted, conflicted, conflicted, conflicted}, + errs: []error{nil, nil, errors.New("HTTP 502"), nil, nil}, + } + + res, err := Watch(f, []PRRef{ok.Ref}, "unkin-agent", drainableTicks(4), nil, func(PRRef, error) {}) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "PR lost mergeability (conflict)" { + t.Fatalf("reason = %q, want the mergeability loss on the two adjacent polls", res.Reason) + } + if f.calls != 5 { + t.Errorf("fetch calls = %d, want 5: the falses either side of the failed poll are not a run", f.calls) + } +} + +// perRefFetcher scripts a separate sequence per ref, so a multi-ref watch can be +// driven with each PR doing something different. +type perRefFetcher struct { + states map[string][]PRState + calls map[string]int +} + +func (f *perRefFetcher) FetchState(ref PRRef, _ string) (PRState, error) { + key := ref.String() + seq := f.states[key] + i := f.calls[key] + if i >= len(seq) { + i = len(seq) - 1 + } + f.calls[key]++ + return seq[i], nil +} + +// Each ref keeps its own run of observations: one PR's mergeability, pushes and +// resolutions must neither arm nor disarm another's conflict rule. +func TestWatchTracksRefsIndependently(t *testing.T) { + refA := PRRef{Owner: "unkin", Repo: "repo", Number: 1} + refB := PRRef{Owner: "unkin", Repo: "repo", Number: 2} + snap := func(ref PRRef, m Mergeability, head string) PRState { + s := base() + s.Ref = ref + s.Mergeable = m + s.HeadSHA = head + return s + } + + tests := []struct { + name string + a, b []PRState + want string // reason, "" for no alert + }{ + { + name: "a mergeable neighbour does not arm a baseline conflict", + a: []PRState{snap(refA, MergeYes, "aaa")}, + b: []PRState{snap(refB, MergeNo, "bbb")}, + want: "", + }, + { + name: "a neighbour's push does not arm a baseline conflict", + a: []PRState{snap(refA, MergeYes, "aaa"), snap(refA, MergeYes, "aa2"), snap(refA, MergeYes, "aa3")}, + b: []PRState{snap(refB, MergeNo, "bbb")}, + want: "", + }, + { + name: "a neighbour's mergeable polls do not clear another's run", + a: []PRState{snap(refA, MergeYes, "aaa")}, + b: []PRState{snap(refB, MergeYes, "bbb"), snap(refB, MergeNo, "bbb"), snap(refB, MergeNo, "bbb")}, + want: "PR lost mergeability (conflict)", + }, + } + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + f := &perRefFetcher{ + states: map[string][]PRState{refA.String(): tt.a, refB.String(): tt.b}, + calls: map[string]int{}, + } + res, err := Watch(f, []PRRef{refA, refB}, "unkin-agent", drainableTicks(6), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != tt.want { + t.Fatalf("reason = %q, want %q", res.Reason, tt.want) + } + if tt.want != "" && res.Ref != refB { + t.Errorf("alert names %s, want %s", res.Ref, refB) + } + }) + } +} + +// A watch that will deliberately stay silent about a pre-existing conflict has +// to hand its caller the baseline it is staying silent about. +func TestWatchReportsBaselineStates(t *testing.T) { + stuck := base() + stuck.Mergeable = MergeNo + stuck.CIStatus = "failure" + f := &fakeFetcher{states: []PRState{stuck}} + + var got []PRState + if _, err := Watch(f, []PRRef{stuck.Ref}, "unkin-agent", drainableTicks(1), + func(sts []PRState) { got = sts }, nil); err != nil { + t.Fatalf("Watch: %v", err) + } + if len(got) != 1 { + t.Fatalf("onBaseline received %d state(s), want 1", len(got)) + } + if got[0].Mergeable != MergeNo || got[0].CIStatus != "failure" { + t.Errorf("baseline = %+v, want the conflicted, CI-red snapshot the watch started from", got[0]) + } +} -- 2.47.3 From 7baa194c52f9c587d5434a98f5e70270f5eb8683 Mon Sep 17 00:00:00 2001 From: unkin-agent Date: Sat, 26 Sep 2026 20:48:31 +1000 Subject: [PATCH 3/6] docs: mergeable is a plain bool, not a tri-state on the wire --- AGENTS.md | 18 ++++++++++++++---- README.md | 8 +++++++- 2 files changed, 21 insertions(+), 5 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 68433d2..ff6b99d 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -222,10 +222,20 @@ wrapped per stage (login / read denied / write denied) via `ErrVaultDenied`. worktree root. - `watchpr` alerts on changes, not on conditions: the baseline snapshot is a real read, so a PR that is already conflicted or already CI-failing when watching - starts is polled on rather than reported. Mergeability is the one rule needing - a run of observations (`prWatch`), because a conflict must both persist for two - polls and follow a mergeable one; Gitea's `mergeable` is tri-state (absent/null - = not yet computed) and unknown counts as neither answer. + starts is polled on rather than reported. That suppression is printed with the + baseline, since a silent watcher and a watcher with nothing to say look alike. +- Mergeability is the one `watchpr` rule needing a run of observations + (`prWatch`). Gitea 1.26 sends `mergeable` as a plain bool — always present, + never null — and sends `false` both for a real conflict and while it recomputes + the merge base after a push, which is exactly when an agent starts a watch. So + `false` counts only once this watch has seen a merge computation start (the PR + was mergeable, or `head.sha`/`base.sha` moved), and then only across two + consecutive polls of an unchanged head and base; a mergeable poll, an unknown + one or a failed poll all break the run. `base.sha` is the base branch tip as of + the response, not the merge base at PR creation, so it moves when main does. + `Mergeability` stays tri-state for what the bool cannot carry: an absent/null + flag from some other Gitea, and a state no successful poll ever filled in. + Head and base SHAs are read only to arm this rule — a push never alerts. - CI "combined status" comes from `/commits/{sha}/status`; an empty head SHA yields an empty state without an API call. - Gitea backs every PR with an issue of the same number and serves comments from diff --git a/README.md b/README.md index e09979c..f3fef7b 100644 --- a/README.md +++ b/README.md @@ -88,7 +88,13 @@ gets a **new comment from someone other than the agent**, its **CI fails** transitions — CI `pending`→`success`, the agent's own comments and pushes — are ignored, and so is any condition the PR was already in at the baseline: a PR that is already conflicted or already failing when watching starts keeps being -watched. +watched, and the baseline line says which conditions it is staying silent about. + +Gitea reports `mergeable: false` both for a real conflict and while it +recomputes the merge base after a push, so a conflict is only reported once the +watch has seen a merge computation start — the PR was mergeable, or its head or +base commit moved — and then only across two consecutive polls of an unchanged +head and base. ```bash # Watch until something meaningful happens (default interval 60s) -- 2.47.3 From 27e48ac45e8a4b30bae302fbdd437670141284ce Mon Sep 17 00:00:00 2001 From: unkin-agent Date: Sat, 26 Sep 2026 21:14:20 +1000 Subject: [PATCH 4/6] watchpr: debounce conflicts on elapsed time, not poll count Merge-input movement arms the conflict rule and no longer clears the run of non-mergeable observations, so an arming poll's own false cannot be half the evidence and a base branch moving under every poll cannot starve a real conflict. The run must now span conflictWindow, measured on the tick that fired each poll. --- internal/agent/watch.go | 62 +++++++---- internal/agent/watch_test.go | 193 +++++++++++++++++++++++++++++++++-- 2 files changed, 223 insertions(+), 32 deletions(-) diff --git a/internal/agent/watch.go b/internal/agent/watch.go index b5e5282..5cf8488 100644 --- a/internal/agent/watch.go +++ b/internal/agent/watch.go @@ -145,9 +145,14 @@ func terminalState(st PRState) (bool, string) { return false, "" } -// conflictPolls is how many consecutive non-mergeable polls of an unchanged -// merge computation confirm a real conflict. -const conflictPolls = 2 +// conflictWindow is how long an unbroken run of non-mergeable polls must span +// before it is reported as a conflict. What the run has to outlast is Gitea's +// merge recompute, which is a duration, so counting polls cannot express it: +// --interval varies from seconds to hours between callers. Recomputes have been +// observed finishing in ~5-20s with no bound on the tail, so this is set well +// clear of that; the cost of it being too long is only a later conflict alert, +// while too short is a false one. +const conflictWindow = 2 * time.Minute // prWatch tracks one PR across polls, because mergeability needs more memory // than the previous snapshot. Gitea reports mergeable=false while it recomputes @@ -155,11 +160,15 @@ const conflictPolls = 2 // seen a merge computation start: the PR was mergeable at some point, or its // head or base SHA moved. A bare false inherited from the baseline says nothing // -- it is equally a conflict the operator is already waiting on and a recompute -// in flight -- so it arms nothing. +// in flight -- so it arms nothing. Arming and the run of falses are independent: +// movement only arms, because a base branch that moves under the PR on every +// push to main would otherwise restart the run forever. type prWatch struct { - prev PRState - armed bool - conflicts int + prev PRState + armed bool + // conflictSince is when the current unbroken run of non-mergeable polls + // began; zero when no run is in progress. + conflictSince time.Time } func newPRWatch(baseline PRState) *prWatch { @@ -173,39 +182,48 @@ func mergeInputsChanged(prev, cur PRState) bool { } // track folds one snapshot's mergeability into the run of observations. The -// polls that confirm a conflict must be adjacent, so anything but another -// non-mergeable observation breaks the run. -func (w *prWatch) track(st PRState) { +// observations that confirm a conflict must be adjacent, so anything but +// another non-mergeable one breaks the run. +func (w *prWatch) track(st PRState, now time.Time) { switch st.Mergeable { case MergeNo: - w.conflicts++ + if w.conflictSince.IsZero() { + w.conflictSince = now + } case MergeYes: w.armed = true - w.conflicts = 0 + w.conflictSince = time.Time{} default: - w.conflicts = 0 + w.conflictSince = time.Time{} } } // missed records a poll that never produced a snapshot; the run of adjacent // non-mergeable observations does not survive the gap. func (w *prWatch) missed() { - w.conflicts = 0 + w.conflictSince = time.Time{} } -// observe folds in the newest snapshot and reports whether the watch should end. -func (w *prWatch) observe(cur PRState) (bool, string) { +// confirmed reports whether the run of non-mergeable observations has spanned +// the recompute window. The run starts at its first observation, so a lone +// non-mergeable poll never confirms anything whatever the interval. +func (w *prWatch) confirmed(now time.Time) bool { + return !w.conflictSince.IsZero() && now.Sub(w.conflictSince) >= conflictWindow +} + +// observe folds in the newest snapshot, taken at now, and reports whether the +// watch should end. +func (w *prWatch) observe(cur PRState, now time.Time) (bool, string) { changed, reason := MeaningfulChange(w.prev, cur) if mergeInputsChanged(w.prev, cur) { w.armed = true - w.conflicts = 0 } w.prev = cur - w.track(cur) + w.track(cur, now) if changed { return true, reason } - if w.armed && w.conflicts >= conflictPolls && cur.State == "open" { + if w.armed && w.confirmed(now) && cur.State == "open" { return true, "PR lost mergeability (conflict)" } return false, "" @@ -245,7 +263,9 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti onBaseline(baselines) } fails := make(map[string]int, len(refs)) - for range ticks { + // The tick carries the time it fired, which is the clock the conflict + // window is measured on. + for now := range ticks { for _, ref := range refs { key := ref.String() cur, err := f.FetchState(ref, agentLogin) @@ -264,7 +284,7 @@ func Watch(f StateFetcher, refs []PRRef, agentLogin string, ticks <-chan time.Ti continue } fails[key] = 0 - if changed, reason := watches[key].observe(cur); changed { + if changed, reason := watches[key].observe(cur, now); changed { return WatchResult{Ref: ref, Reason: reason, State: cur}, nil } } diff --git a/internal/agent/watch_test.go b/internal/agent/watch_test.go index 7820072..630aa21 100644 --- a/internal/agent/watch_test.go +++ b/internal/agent/watch_test.go @@ -791,11 +791,21 @@ func TestWatchAnonymousKeepsPolling(t *testing.T) { } // drainableTicks returns a channel holding n ticks and already closed, so Watch -// polls exactly n times and then returns instead of blocking. +// polls exactly n times and then returns instead of blocking. The ticks are +// spaced far past conflictWindow, so a run of non-mergeable polls confirms on +// its second observation; spacedTicks drives the intervals where it must not. func drainableTicks(n int) <-chan time.Time { + return spacedTicks(n, 10*time.Minute) +} + +// spacedTicks is drainableTicks with the poll interval named. The tick carries +// the time Watch measures the conflict window on, which makes every wall-clock +// assertion in these tests exact and instant. +func spacedTicks(n int, interval time.Duration) <-chan time.Time { + start := time.Date(2026, 9, 24, 12, 0, 0, 0, time.UTC) ticks := make(chan time.Time, n) - for i := 0; i < n; i++ { - ticks <- time.Now() + for i := 1; i <= n; i++ { + ticks <- start.Add(time.Duration(i) * interval) } close(ticks) return ticks @@ -911,9 +921,10 @@ func TestPRWatchMergeability(t *testing.T) { for _, tt := range tests { t.Run(tt.name, func(t *testing.T) { w := newPRWatch(snap(tt.baseline)) + start := time.Date(2026, 9, 24, 12, 0, 0, 0, time.UTC) got := 0 for i, m := range tt.polls { - changed, reason := w.observe(snap(m)) + changed, reason := w.observe(snap(m), start.Add(time.Duration(i+1)*10*time.Minute)) if !changed { continue } @@ -958,13 +969,12 @@ func TestMergeabilityDecoding(t *testing.T) { } } -// The inverse of the bug this PR fixed: Gitea reports mergeable=false while it -// recomputes the merge base after a push, and watchpr is normally started right -// after the agent pushes, so the baseline can land inside that window. Demanding -// a mergeable observation to arm the rule left a genuinely conflicted PR silent -// forever. The new head is a new merge computation, so the conflict it confirms -// belongs to this watch. -func TestWatchAlertsWhenBaselineLandedInTheRecomputeWindow(t *testing.T) { +// The inverse of the bug this PR fixed: demanding a mergeable observation to arm +// the rule left a PR that was non-mergeable at baseline silent forever, even +// after a push gave Gitea a fresh merge computation to answer for. A head that +// moves during the watch arms the rule, so the conflict the new head keeps +// reporting is attributable to this watch and is reported. +func TestWatchAlertsWhenAPushArmsABaselineConflict(t *testing.T) { baseline := base() baseline.Mergeable = MergeNo // still recomputing; the push is not visible yet @@ -1160,3 +1170,164 @@ func TestWatchReportsBaselineStates(t *testing.T) { t.Errorf("baseline = %+v, want the conflicted, CI-red snapshot the watch started from", got[0]) } } + +// The residual gap, pinned so it is a decision rather than an accident: the +// agent pushes, the push conflicts, watchpr starts inside Gitea's recompute and +// nothing moves again. Every poll answers false and none of them is +// attributable to this watch, so no alert is ever sent -- the baseline line is +// the only notice. Gitea's payload carries no field that separates this from a +// merge check still running. +func TestWatchNeverAlertsOnAConflictLandedByThePushBeforeTheWatch(t *testing.T) { + pushed := base() + pushed.Mergeable = MergeNo + pushed.HeadSHA = "def456" + f := &fakeFetcher{states: []PRState{pushed}} + + res, err := Watch(f, []PRRef{pushed.Ref}, "unkin-agent", drainableTicks(50), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "" { + t.Fatalf("Watch ended with %q; nothing distinguishes this conflict from a merge check in flight, so it must stay silent", res.Reason) + } +} + +// The whole mergeability rule as a sequence table, driven through Watch at the +// intervals that decide it. The debounce is wall-clock, so the same sequence of +// snapshots must alert or stay silent according to how far apart the polls are. +func TestWatchConflictSequences(t *testing.T) { + snap := func(m Mergeability, head, bse string) PRState { + st := base() + st.Mergeable = m + st.HeadSHA = head + st.BaseSHA = bse + return st + } + repeat := func(st PRState, n int) []PRState { + out := make([]PRState, n) + for i := range out { + out[i] = st + } + return out + } + movingBase := func(m Mergeability, n int) []PRState { + out := make([]PRState, n) + for i := range out { + out[i] = snap(m, "h1", fmt.Sprintf("b%d", i)) + } + return out + } + const ( + quick = 5 * time.Second // well inside conflictWindow + normal = 60 * time.Second // watchpr's default + relaxed = 10 * time.Minute // past conflictWindow in a single gap + ) + const conflict = "PR lost mergeability (conflict)" + + yes := snap(MergeYes, "h1", "b1") + no := snap(MergeNo, "h1", "b1") + pushedNo := snap(MergeNo, "h2", "b1") + movedNo := snap(MergeNo, "h1", "b2") + + tests := []struct { + name string + interval time.Duration + baseline PRState + polls []PRState + errs []error + want string + }{ + { + name: "a push then the recompute's falses is not a conflict", + interval: normal, baseline: yes, polls: repeat(pushedNo, 2), want: "", + }, + { + name: "a fast poller rides out the whole recompute after a push", + interval: quick, baseline: yes, polls: repeat(pushedNo, 20), want: "", + }, + { + name: "a base move then the recompute's falses is not a conflict", + interval: normal, baseline: no, polls: repeat(movedNo, 2), want: "", + }, + { + name: "a base moving under every poll still confirms a conflict", + interval: normal, baseline: yes, polls: movingBase(MergeNo, 20), want: conflict, + }, + { + name: "a conflict that predates the watch stays silent forever", + interval: relaxed, baseline: no, polls: repeat(no, 50), want: "", + }, + { + name: "a sustained loss after a mergeable baseline alerts", + interval: normal, baseline: yes, polls: repeat(no, 3), want: conflict, + }, + { + name: "a mergeable poll breaks the run however long it ran", + interval: relaxed, baseline: yes, polls: []PRState{no, yes, no}, want: "", + }, + { + name: "an unknown poll breaks the run however long it ran", + interval: relaxed, baseline: yes, polls: []PRState{no, snap(MergeUnknown, "h1", "b1"), no}, want: "", + }, + { + name: "a baseline conflict that clears and returns alerts", + interval: relaxed, baseline: no, polls: []PRState{yes, no, no}, want: conflict, + }, + { + name: "a failed poll breaks the run", + interval: relaxed, baseline: yes, polls: []PRState{no, no, no}, + errs: []error{nil, nil, errors.New("HTTP 502"), nil}, want: "", + }, + { + name: "the run restarts after a failed poll and still confirms", + interval: relaxed, baseline: yes, polls: []PRState{no, no, no, no}, + errs: []error{nil, nil, errors.New("HTTP 502"), nil, nil}, want: conflict, + }, + } + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + f := &fakeFetcher{states: append([]PRState{tt.baseline}, tt.polls...), errs: tt.errs} + res, err := Watch(f, []PRRef{tt.baseline.Ref}, "unkin-agent", + spacedTicks(len(tt.polls), tt.interval), nil, func(PRRef, error) {}) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != tt.want { + t.Fatalf("reason = %q, want %q", res.Reason, tt.want) + } + }) + } +} + +// Two refs watched together keep separate runs and separate clocks: a PR being +// pushed to must neither delay nor trigger the conflict its neighbour is really +// in, and the alert must name the conflicted one. +func TestWatchConflictIsolatedFromANeighboursPushes(t *testing.T) { + conflicted := PRRef{Owner: "unkin", Repo: "repo", Number: 1} + pushing := PRRef{Owner: "unkin", Repo: "repo", Number: 2} + snap := func(ref PRRef, m Mergeability, head string) PRState { + st := base() + st.Ref = ref + st.Mergeable = m + st.HeadSHA = head + return st + } + f := &perRefFetcher{ + states: map[string][]PRState{ + conflicted.String(): {snap(conflicted, MergeYes, "a1"), snap(conflicted, MergeNo, "a1")}, + pushing.String(): {snap(pushing, MergeYes, "b1"), snap(pushing, MergeYes, "b2"), snap(pushing, MergeYes, "b3")}, + }, + calls: map[string]int{}, + } + + res, err := Watch(f, []PRRef{conflicted, pushing}, "unkin-agent", drainableTicks(4), nil, nil) + if err != nil { + t.Fatalf("Watch: %v", err) + } + if res.Reason != "PR lost mergeability (conflict)" { + t.Fatalf("reason = %q, want the conflict on %s", res.Reason, conflicted) + } + if res.Ref != conflicted { + t.Errorf("alert names %s, want %s", res.Ref, conflicted) + } +} -- 2.47.3 From 15c527ee563d5ea2b3540ff30f46d06a7a514632 Mon Sep 17 00:00:00 2001 From: unkin-agent Date: Sat, 26 Sep 2026 21:14:20 +1000 Subject: [PATCH 5/6] watchpr: emit the baseline under --json The baseline is the only notice that a watch started against an already conflicted PR, and it was missing from the mode automation uses. It goes to stderr as a JSON record, leaving stdout a single result record. --- cmd/watchpr/main.go | 44 ++++++++++++++++++++++++++++++++-------- cmd/watchpr/main_test.go | 44 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+), 9 deletions(-) diff --git a/cmd/watchpr/main.go b/cmd/watchpr/main.go index 6861e87..2f49166 100644 --- a/cmd/watchpr/main.go +++ b/cmd/watchpr/main.go @@ -3,8 +3,13 @@ // new comment from someone other than the agent, its CI fails, or it loses // mergeability after the baseline. Benign transitions (CI pending→success, the // agent's own pushes and comments) are ignored, and so is any condition that was -// already true at the baseline -- which watchpr prints, so a run started against -// a conflicted or CI-red PR says so. +// already true at the baseline -- which watchpr prints on stderr (as a JSON +// record under --json), so a run started against a conflicted or CI-red PR says +// so. One case is never reported at all: a conflict introduced by the push +// immediately before the watch started, on a PR whose head and base then never +// move, stays silent for the whole run, because nothing in Gitea's payload +// separates it from a merge check still in flight. The baseline line is the +// only notice of it. // // watchpr owner/repo#12 owner/repo:15 // watchpr --once --json owner/repo#12 @@ -15,6 +20,7 @@ package main import ( "encoding/json" "fmt" + "io" "os" "strings" "time" @@ -131,13 +137,7 @@ func runWatch(c *agent.GiteaClient, refs []agent.PRRef, interval time.Duration, defer ticker.Stop() onBaseline := func(states []agent.PRState) { - if jsonMode { - return - } - fmt.Fprintf(os.Stderr, "watching %d PR(s) every %s; baseline established\n", len(refs), interval) - for _, st := range states { - fmt.Fprintln(os.Stderr, baselineLine(st)) - } + emitBaselines(os.Stderr, states, interval, jsonMode) } onError := func(ref agent.PRRef, err error) { fmt.Fprintf(os.Stderr, "warning: polling %s: %v\n", ref.String(), err) @@ -151,6 +151,32 @@ func runWatch(c *agent.GiteaClient, refs []agent.PRRef, interval time.Duration, return nil } +// baselineRecord is the --json form of baselineLine. Both go to stderr, leaving +// the stdout contract a single result record: a caller automating watchpr is +// precisely the one who needs to be told the watch started against a PR that is +// already conflicted, since no alert will ever follow for it. +type baselineRecord struct { + Baseline bool `json:"baseline"` + Suppressed string `json:"suppressed,omitempty"` + State agent.PRState `json:"state"` +} + +// emitBaselines writes the state each watch started from, in whichever form the +// caller asked for. +func emitBaselines(w io.Writer, states []agent.PRState, interval time.Duration, jsonMode bool) { + if jsonMode { + enc := json.NewEncoder(w) + for _, st := range states { + _ = enc.Encode(baselineRecord{Baseline: true, Suppressed: suppressedAtBaseline(st), State: st}) + } + return + } + _, _ = fmt.Fprintf(w, "watching %d PR(s) every %s; baseline established\n", len(states), interval) + for _, st := range states { + _, _ = fmt.Fprintln(w, baselineLine(st)) + } +} + // describeFailure names the cause of a terminal failure so a watcher that stops // says why. An anonymous rejection, a permission boundary and a token that // outlived its Vault lease are three different problems and only the last is diff --git a/cmd/watchpr/main_test.go b/cmd/watchpr/main_test.go index f009fbf..f9d2d25 100644 --- a/cmd/watchpr/main_test.go +++ b/cmd/watchpr/main_test.go @@ -1,6 +1,8 @@ package main import ( + "bytes" + "encoding/json" "errors" "fmt" "io" @@ -8,6 +10,7 @@ import ( "net/http/httptest" "strings" "testing" + "time" "git.unkin.net/unkin/agent-tools/internal/agent" ) @@ -212,3 +215,44 @@ func TestBaselineLineNamesSuppressedConditions(t *testing.T) { t.Errorf("baselineLine = %q, want no suppression note for a clean baseline", got) } } + +// --json is the mode automation uses, and automation is exactly who needs to be +// told the watch started against an already-conflicted PR -- the one case that +// will never produce an alert. It must therefore be emitted in JSON mode too, +// on stderr, where it cannot corrupt the result record on stdout. +func TestBaselineIsEmittedInJSONMode(t *testing.T) { + st := agent.PRState{ + Ref: agent.PRRef{Owner: "unkin", Repo: "repo", Number: 7}, + State: "open", + Mergeable: agent.MergeNo, + CIStatus: "failure", + HeadSHA: "cafebabecafebabe", + } + var buf bytes.Buffer + emitBaselines(&buf, []agent.PRState{st}, 30*time.Second, true) + + var got baselineRecord + if err := json.Unmarshal(buf.Bytes(), &got); err != nil { + t.Fatalf("baseline is not a JSON record (%v); got %q", err, buf.String()) + } + if !got.Baseline { + t.Error("record does not mark itself as the baseline") + } + if got.State.Ref != st.Ref || got.State.Mergeable != agent.MergeNo { + t.Errorf("record state = %+v, want the conflicted snapshot the watch started from", got.State) + } + for _, want := range []string{"already non-mergeable", "CI already failure"} { + if !strings.Contains(got.Suppressed, want) { + t.Errorf("suppressed = %q, want it to mention %q", got.Suppressed, want) + } + } + + buf.Reset() + clean := st + clean.Mergeable = agent.MergeYes + clean.CIStatus = "success" + emitBaselines(&buf, []agent.PRState{clean}, 30*time.Second, true) + if strings.Contains(buf.String(), "suppressed") { + t.Errorf("clean baseline = %q, want no suppression field", buf.String()) + } +} -- 2.47.3 From 91509cb9b2ae833b4af79ef1020082b5773fc369 Mon Sep 17 00:00:00 2001 From: unkin-agent Date: Sat, 26 Sep 2026 21:14:20 +1000 Subject: [PATCH 6/6] docs: name the conflict watchpr will never report --- AGENTS.md | 23 ++++++++++++++++------- README.md | 16 ++++++++++++---- 2 files changed, 28 insertions(+), 11 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index ff6b99d..ab4c09e 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -224,18 +224,27 @@ wrapped per stage (login / read denied / write denied) via `ErrVaultDenied`. read, so a PR that is already conflicted or already CI-failing when watching starts is polled on rather than reported. That suppression is printed with the baseline, since a silent watcher and a watcher with nothing to say look alike. + The baseline goes to stderr in both modes — a JSON record under `--json` — + because automation is what most needs it and stdout carries the result. - Mergeability is the one `watchpr` rule needing a run of observations (`prWatch`). Gitea 1.26 sends `mergeable` as a plain bool — always present, never null — and sends `false` both for a real conflict and while it recomputes the merge base after a push, which is exactly when an agent starts a watch. So `false` counts only once this watch has seen a merge computation start (the PR - was mergeable, or `head.sha`/`base.sha` moved), and then only across two - consecutive polls of an unchanged head and base; a mergeable poll, an unknown - one or a failed poll all break the run. `base.sha` is the base branch tip as of - the response, not the merge base at PR creation, so it moves when main does. - `Mergeability` stays tri-state for what the bool cannot carry: an absent/null - flag from some other Gitea, and a state no successful poll ever filled in. - Head and base SHAs are read only to arm this rule — a push never alerts. + was mergeable, or `head.sha`/`base.sha` moved), and then only once the run of + `false`s has spanned `conflictWindow` (2m); a mergeable poll, an unknown one or + a failed poll all break the run. The debounce is wall-clock, measured from the + tick that fired each poll, because what it outlasts is the recompute and + `--interval` spans seconds to hours. Arming and the run are independent: + movement arms and nothing else, since `base.sha` is the base branch tip as of + the response, so it moves for every open PR whenever main does and a run reset + there could never complete on a busy repo. `Mergeability` stays tri-state for + what the bool cannot carry: an absent/null flag from some other Gitea, and a + state no successful poll ever filled in. Head and base SHAs are read only to + arm — a push never alerts. The residue: a conflict landed by the push just + before the watch began, on a head and base that never move again, is never + reported; Gitea's payload has no field separating it from a check in flight + (`merge_base` is the true merge base and does not move on recheck). - CI "combined status" comes from `/commits/{sha}/status`; an empty head SHA yields an empty state without an API call. - Gitea backs every PR with an issue of the same number and serves comments from diff --git a/README.md b/README.md index f3fef7b..3ef3cac 100644 --- a/README.md +++ b/README.md @@ -88,13 +88,21 @@ gets a **new comment from someone other than the agent**, its **CI fails** transitions — CI `pending`→`success`, the agent's own comments and pushes — are ignored, and so is any condition the PR was already in at the baseline: a PR that is already conflicted or already failing when watching starts keeps being -watched, and the baseline line says which conditions it is staying silent about. +watched, and the baseline line — written to stderr, as a JSON record under +`--json` — says which conditions it is staying silent about. Gitea reports `mergeable: false` both for a real conflict and while it recomputes the merge base after a push, so a conflict is only reported once the -watch has seen a merge computation start — the PR was mergeable, or its head or -base commit moved — and then only across two consecutive polls of an unchanged -head and base. +watch has seen a merge computation start (the PR was mergeable, or its head or +base commit moved) **and** the non-mergeable polls have then run unbroken for +two minutes. The debounce is a duration, not a poll count, because what it has +to outlast is Gitea's recompute and `--interval` ranges from seconds to hours. + +One case is therefore never reported: a conflict introduced by the push +immediately before the watch started, on a PR whose head and base never move +again. Nothing in Gitea's payload separates that from a merge check still in +flight, so watchpr stays silent about it for as long as it runs — the baseline +line is how you see it. ```bash # Watch until something meaningful happens (default interval 60s) -- 2.47.3