Files
multica/server/internal/daemon/execenv/runtime_config_test.go
Naiyuan Qing b9334dd59f fix: anchor comment triggers to thread roots (#3746)
Co-authored-by: multica-agent <github@multica.ai>
2026-06-04 13:47:05 +08:00

1230 lines
42 KiB
Go

package execenv
import (
"fmt"
"os"
"path/filepath"
"strings"
"testing"
)
// Sub-issue Creation section — after MUL-2538 the platform posts the
// child-done parent notification itself, so the brief no longer carries
// any parent-notification rule (per Bohan's call on PR #3055: delete the
// guidance entirely, do not replace it with a "do not post one" sentence
// — the agent should not be thinking about parent comments at all). All
// that remains is the `--status todo` vs `--status backlog` rule for
// creating sub-issues, which is unrelated to the notification path.
func TestSubIssueCreationSectionPresentForIssueRuns(t *testing.T) {
t.Parallel()
cases := []struct {
name string
ctx TaskContextForEnv
}{
{
name: "assignment-triggered",
ctx: TaskContextForEnv{IssueID: "11111111-2222-3333-4444-555555555555"},
},
{
name: "comment-triggered",
ctx: TaskContextForEnv{
IssueID: "22222222-3333-4444-5555-666666666666",
TriggerCommentID: "33333333-4444-5555-6666-777777777777",
},
},
}
for _, tc := range cases {
tc := tc
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
out := buildMetaSkillContent("claude", tc.ctx)
if !strings.Contains(out, "## Sub-issue Creation") {
t.Fatalf("expected Sub-issue Creation section in %s brief", tc.name)
}
for _, want := range []string{
"**Choosing `--status` when creating sub-issues.**",
"`--status todo` = **start now**",
"`--status backlog` = **wait**",
"`multica issue status <child-id> todo`",
"all `--status todo`",
"`--status backlog` from the start",
} {
if !strings.Contains(out, want) {
t.Errorf("[%s] section missing %q", tc.name, want)
}
}
})
}
}
// The brief must no longer carry any parent-notification guidance. PR
// #2918 added a "Tell the parent when you finish a child" rule that
// turned into noise (self-mention loops, planner ack ping-pong,
// hardcoded `MUL-` prefix). PR #3055 first downgraded it to a "do NOT
// post one" guardrail, but Bohan's product call was to remove the
// guidance entirely rather than substitute a new prohibition. These
// canaries lock that in: any wording that re-introduces the
// parent-comment concept — positive, negative, or descriptive — must
// not come back through future edits.
func TestBriefHasNoParentNotificationGuidance(t *testing.T) {
t.Parallel()
cases := []TaskContextForEnv{
{IssueID: "11111111-2222-3333-4444-555555555555"},
{
IssueID: "22222222-3333-4444-5555-666666666666",
TriggerCommentID: "33333333-4444-5555-6666-777777777777",
},
}
for _, ctx := range cases {
ctx := ctx
out := buildMetaSkillContent("claude", ctx)
// The pre-MUL-2538 phrasing instructed the agent to compose a
// parent comment by hand — including a hardcoded `MUL-` prefix
// and an assignee mention. The intermediate revision (PR #3055
// before Bohan's call) instead told the agent NOT to post one.
// Both framings must stay out.
for _, banned := range []string{
// Old "do it yourself" framing (PR #2918).
"## Parent / Sub-issue Protocol",
"**Tell the parent when you finish a child.**",
"multica issue comment add <parent-id>",
"with NO `--parent`",
"link the child as `[MUL-",
"`@mention` the parent's assignee",
"`mention://agent/<id>`",
"`mention://member/<id>`",
"`mention://squad/<id>`",
// Intermediate "do NOT do it yourself" framing (PR #3055
// before Bohan's call) — also out per product direction.
"**Do NOT post your own parent-notification comment.**",
"Do NOT post your own parent-notification comment",
"parent-notification comment",
"system comment on the parent fires from the status transition",
"re-trigger the parent's assignee for nothing",
"platform posts a top-level system comment on the parent",
// Earlier revisions split rules by trigger type or used
// table/subsection layouts. None of those structures should
// come back either.
"| Parent assignee | Parent status |",
"The same agent as yourself",
"| Member or squad |",
"### A. Notify the parent",
"### B. Choose",
"When this issue has `parent_issue_id`:",
"**Closing out child work** (only if this issue has `parent_issue_id`)",
"**Notify the parent** (only if this issue has `parent_issue_id`",
"**Creating sub-issues** (applies to any issue-bound run)",
"For parent/child work, use these best-effort rules",
// The protocol must no longer emit a placeholder
// `<this-issue-id>` status flip — the workflow above owns
// that command with the real issue id substituted.
"`multica issue status <this-issue-id> in_review`",
// Non-existent CLI form Elon's earlier review flagged.
"issue list --parent",
} {
if strings.Contains(out, banned) {
t.Errorf("expected %q to be removed from the brief", banned)
}
}
}
}
// Comment-triggered briefs must NOT carry any unconditional status-flip
// command targeting the current issue. Previous revisions had a
// dedicated protocol step that wrote `multica issue status <this-issue-id> in_review`;
// the comment-triggered workflow rule "Do NOT change the issue status
// unless the comment explicitly asks for it" must remain the source of
// truth (Elon's blocking review on PR #2918).
func TestCommentTriggeredProtocolDoesNotForceInReview(t *testing.T) {
t.Parallel()
ctx := TaskContextForEnv{
IssueID: "55555555-6666-7777-8888-999999999999",
TriggerCommentID: "66666666-7777-8888-9999-aaaaaaaaaaaa",
}
out := buildMetaSkillContent("claude", ctx)
if strings.Contains(out, "`multica issue status <this-issue-id> in_review`") {
t.Errorf("comment-triggered brief must not contain a placeholder `<this-issue-id> in_review` flip — that conflicts with the comment-triggered \"do not change status unless asked\" rule")
}
const guardrail = "Do NOT change the issue status unless the comment explicitly asks for it"
if !strings.Contains(out, guardrail) {
t.Errorf("expected the comment-triggered workflow guardrail %q to be present", guardrail)
}
}
// The CLAUDE.md workflow surface must carry the same issue-wide since-delta
// new-comment hint as the per-turn prompt. PR #2816 requires the two surfaces
// stay in sync.
func TestCommentTriggeredBriefCarriesNewCommentsHint(t *testing.T) {
t.Parallel()
const (
issueID = "55555555-6666-7777-8888-999999999999"
since = "2026-05-28T11:00:00Z"
)
ctx := TaskContextForEnv{
IssueID: issueID,
TriggerCommentID: "reply-abc",
NewCommentCount: 4,
NewCommentsSince: since,
}
out := buildMetaSkillContent("claude", ctx)
// Issue-wide count.
if !strings.Contains(out, "4 new comment(s) on this issue since your last run") {
t.Errorf("comment brief must report the issue-wide new-comment count, got:\n%s", out)
}
if !strings.Contains(out, "blindly") {
t.Errorf("comment brief must discourage blindly reading every new comment, got:\n%s", out)
}
// Parent thread first.
if !strings.Contains(out, "--thread reply-abc --since "+since+" --output json") {
t.Errorf("comment brief must point at the triggering (parent) thread --since read first, got:\n%s", out)
}
if !strings.Contains(out, "--tail 30") {
t.Errorf("comment brief must offer the full-thread (--tail 30) option, got:\n%s", out)
}
// Issue-wide catch-up demoted to an only-if-needed fallback.
if !strings.Contains(out, "multica issue comment list "+issueID+" --since "+since+" --output json") {
t.Errorf("comment brief must keep the issue-wide --since catch-up fallback, got:\n%s", out)
}
// The removed resolve step must not reappear.
if strings.Contains(out, "multica comment resolve") {
t.Errorf("comment brief must not carry the dropped resolve step, got:\n%s", out)
}
}
// Cold start (no prior run → no since anchor) must point the agent at the
// triggering CONVERSATION (--thread <trigger> --tail 30) instead of the flat
// timeline dump or the since-delta hint.
func TestCommentTriggeredBriefColdStartThreadRead(t *testing.T) {
t.Parallel()
const issueID = "55555555-6666-7777-8888-999999999999"
ctx := TaskContextForEnv{
IssueID: issueID,
TriggerCommentID: "trigger-1",
TriggerThreadID: "thread-root-1",
NewCommentCount: 0,
NewCommentsSince: "",
}
out := buildMetaSkillContent("claude", ctx)
if strings.Contains(out, "new comment(s) since your last run") {
t.Errorf("no since-delta hint should render on cold start, got:\n%s", out)
}
if !strings.Contains(out, "multica issue comment list "+issueID+" --thread thread-root-1 --tail 30 --output json") {
t.Errorf("cold start must point at the triggering thread read, got:\n%s", out)
}
}
// A resumed comment session with no since-delta should not fall back to the
// cold-start "read the triggering conversation first" instruction. The trigger
// body is already embedded in the per-turn prompt and the resumed session should
// carry prior thread context, so the thread read is only a fallback.
func TestCommentTriggeredBriefResumedNoDeltaSkipsDefaultThreadRead(t *testing.T) {
t.Parallel()
const issueID = "55555555-6666-7777-8888-999999999999"
ctx := TaskContextForEnv{
IssueID: issueID,
TriggerCommentID: "trigger-1",
TriggerThreadID: "thread-root-1",
PriorSessionResumed: true,
NewCommentCount: 0,
NewCommentsSince: "",
}
out := buildMetaSkillContent("claude", ctx)
for _, want := range []string{
"triggering comment is already included above",
"No other new comments on this issue since your last run",
"active thread anchor `thread-root-1` and triggering comment ID `trigger-1`",
"If your reply depends on thread context",
"do not rely only on resumed session memory",
"multica issue comment list " + issueID + " --thread thread-root-1 --tail 30 --output json",
} {
if !strings.Contains(out, want) {
t.Errorf("resumed/no-delta brief missing %q\n--- output ---\n%s", want, out)
}
}
if strings.Contains(out, "scoped to the triggering thread") {
t.Errorf("resumed/no-delta brief must not claim the delta is thread-scoped, got:\n%s", out)
}
if strings.Contains(out, "Read the triggering conversation first") {
t.Errorf("resumed/no-delta brief must not use the cold-start forced-read wording, got:\n%s", out)
}
}
// Assignment-triggered briefs are the inverse boundary: when the agent
// owns the issue lifecycle, the brief AS A WHOLE must still tell it to
// flip to in_review on completion. The flip lives in the
// assignment-triggered workflow above (with the real id substituted).
func TestAssignmentTriggeredProtocolStillFlipsInReview(t *testing.T) {
t.Parallel()
const issueID = "77777777-8888-9999-aaaa-bbbbbbbbbbbb"
ctx := TaskContextForEnv{IssueID: issueID}
out := buildMetaSkillContent("claude", ctx)
want := "`multica issue status " + issueID + " in_review`"
if !strings.Contains(out, want) {
t.Errorf("assignment-triggered brief must still flip to in_review on completion (expected %q in the workflow above)", want)
}
}
// The sub-issue creation rule must reach top-level parents that have no
// `parent_issue_id` of their own — that is where the `todo` vs `backlog`
// decision matters most. The section must not gate on this issue being
// a child, and must not even mention `parent_issue_id`.
func TestSubIssueCreationSectionIsUnconditional(t *testing.T) {
t.Parallel()
ctx := TaskContextForEnv{
IssueID: "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
}
out := buildMetaSkillContent("claude", ctx)
const header = "## Sub-issue Creation"
start := strings.Index(out, header)
if start == -1 {
t.Fatalf("sub-issue creation section missing")
}
rest := out[start:]
end := strings.Index(rest[len(header):], "\n## ")
var section string
if end == -1 {
section = rest
} else {
section = rest[:len(header)+end]
}
if strings.Contains(section, "parent_issue_id") {
t.Errorf("Sub-issue Creation section must not reference `parent_issue_id` — it applies to any issue-bound run, including top-level parents:\n%s", section)
}
}
// Workspace Context block: workspace.context (the per-workspace system prompt
// owners set in Settings → General) must reach the brief as `## Workspace
// Context` for every task kind so agents see a consistent shared system prompt
// regardless of how they were triggered. Empty content must skip the heading
// entirely — bare headings would just add noise.
func TestWorkspaceContextRenderedAcrossTaskKinds(t *testing.T) {
t.Parallel()
const wsContext = "All comments must be in English. Prefer concise PR descriptions."
cases := []struct {
name string
ctx TaskContextForEnv
}{
{
name: "assignment-triggered",
ctx: TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
WorkspaceContext: wsContext,
},
},
{
name: "comment-triggered",
ctx: TaskContextForEnv{
IssueID: "22222222-3333-4444-5555-666666666666",
TriggerCommentID: "33333333-4444-5555-6666-777777777777",
WorkspaceContext: wsContext,
},
},
{
name: "chat",
ctx: TaskContextForEnv{
ChatSessionID: "chat-1",
WorkspaceContext: wsContext,
},
},
{
name: "quick-create",
ctx: TaskContextForEnv{
QuickCreatePrompt: "create me an issue",
WorkspaceContext: wsContext,
},
},
{
name: "autopilot run-only",
ctx: TaskContextForEnv{
AutopilotRunID: "run-1",
WorkspaceContext: wsContext,
},
},
}
for _, tc := range cases {
tc := tc
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
out := buildMetaSkillContent("claude", tc.ctx)
if !strings.Contains(out, "## Workspace Context") {
t.Fatalf("[%s] expected `## Workspace Context` heading", tc.name)
}
if !strings.Contains(out, wsContext) {
t.Errorf("[%s] brief missing workspace context body %q", tc.name, wsContext)
}
// The block must precede Available Commands so it acts as
// background framing, not a footer hidden below CLI usage.
ctxIdx := strings.Index(out, "## Workspace Context")
cmdsIdx := strings.Index(out, "## Available Commands")
if ctxIdx == -1 || cmdsIdx == -1 || ctxIdx > cmdsIdx {
t.Errorf("[%s] `## Workspace Context` must appear above `## Available Commands` (ctx=%d, cmds=%d)", tc.name, ctxIdx, cmdsIdx)
}
})
}
}
func TestWorkspaceContextHeadingSkippedWhenEmpty(t *testing.T) {
t.Parallel()
cases := []struct {
name string
ctx TaskContextForEnv
}{
{
name: "empty string",
ctx: TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
WorkspaceContext: "",
},
},
{
name: "whitespace only",
ctx: TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
WorkspaceContext: " \n\t \r\n",
},
},
}
for _, tc := range cases {
tc := tc
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
out := buildMetaSkillContent("claude", tc.ctx)
if strings.Contains(out, "## Workspace Context") {
t.Errorf("[%s] empty workspace context must NOT emit the heading", tc.name)
}
})
}
}
func TestSubIssueCreationSectionSkippedForNonIssueModes(t *testing.T) {
t.Parallel()
cases := []struct {
name string
ctx TaskContextForEnv
}{
{
name: "chat",
ctx: TaskContextForEnv{ChatSessionID: "chat-1"},
},
{
name: "quick-create",
ctx: TaskContextForEnv{QuickCreatePrompt: "create me an issue"},
},
{
name: "autopilot run-only",
ctx: TaskContextForEnv{AutopilotRunID: "run-1"},
},
}
for _, tc := range cases {
tc := tc
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
out := buildMetaSkillContent("claude", tc.ctx)
if strings.Contains(out, "## Sub-issue Creation") {
t.Errorf("%s mode must NOT emit the Sub-issue Creation section", tc.name)
}
})
}
}
// writeRuntimeConfigFile is the safe replacement for the previous
// unconditional os.WriteFile of CLAUDE.md / AGENTS.md / GEMINI.md. The three
// states it must handle correctly are: file missing, file present without
// markers (user-authored content already there — the regression case from
// MUL-2753), and file present with markers (idempotent second-run replace).
func TestWriteRuntimeConfigFileCreatesMissingFile(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
const brief = "# Multica Agent Runtime\n\nbrief body line"
if err := writeRuntimeConfigFile(path, brief); err != nil {
t.Fatalf("writeRuntimeConfigFile returned error: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back file: %v", err)
}
s := string(got)
if !strings.HasPrefix(s, runtimeMarkerBegin+"\n") {
t.Errorf("output should start with begin marker, got:\n%s", s)
}
if !strings.Contains(s, brief) {
t.Errorf("output should contain brief body, got:\n%s", s)
}
if !strings.Contains(s, "\n"+runtimeMarkerEnd+"\n") {
t.Errorf("output should contain end marker followed by newline, got:\n%s", s)
}
}
func TestWriteRuntimeConfigFilePreservesUserContent(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
const userContent = "# User repo CLAUDE.md\n\n- rule one\n- rule two\n"
if err := os.WriteFile(path, []byte(userContent), 0o644); err != nil {
t.Fatalf("seed user file: %v", err)
}
const brief = "## Multica brief\n\ninjected body"
if err := writeRuntimeConfigFile(path, brief); err != nil {
t.Fatalf("writeRuntimeConfigFile returned error: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back file: %v", err)
}
s := string(got)
// The user's original content must be untouched and appear before the
// injected marker block; this is the core regression case from MUL-2753.
if !strings.HasPrefix(s, userContent) {
t.Errorf("user content must be preserved verbatim at the top of the file, got:\n%s", s)
}
beginIdx := strings.Index(s, runtimeMarkerBegin)
endIdx := strings.Index(s, runtimeMarkerEnd)
if beginIdx < 0 || endIdx <= beginIdx {
t.Fatalf("expected a well-formed marker block in:\n%s", s)
}
if beginIdx < len(userContent) {
t.Errorf("begin marker must appear after user content, beginIdx=%d userLen=%d", beginIdx, len(userContent))
}
if !strings.Contains(s, brief) {
t.Errorf("brief body missing from output:\n%s", s)
}
}
func TestWriteRuntimeConfigFileReplacesExistingBlock(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "AGENTS.md")
const userBefore = "# User AGENTS.md\n\nuser line above\n"
const userAfter = "\nuser line below the block\n"
original := userBefore +
runtimeMarkerBegin + "\n" +
"OLD BRIEF CONTENT THAT MUST GO AWAY\n" +
runtimeMarkerEnd + "\n" +
userAfter
if err := os.WriteFile(path, []byte(original), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
const newBrief = "## New Multica brief\n\nfresh body"
if err := writeRuntimeConfigFile(path, newBrief); err != nil {
t.Fatalf("writeRuntimeConfigFile returned error: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back file: %v", err)
}
s := string(got)
if !strings.HasPrefix(s, userBefore) {
t.Errorf("content above the marker block must be preserved, got:\n%s", s)
}
if !strings.HasSuffix(s, userAfter) {
t.Errorf("content below the marker block must be preserved, got:\n%s", s)
}
if strings.Contains(s, "OLD BRIEF CONTENT THAT MUST GO AWAY") {
t.Errorf("previous block body must be replaced, got:\n%s", s)
}
if !strings.Contains(s, newBrief) {
t.Errorf("new brief body missing from output:\n%s", s)
}
if strings.Count(s, runtimeMarkerBegin) != 1 || strings.Count(s, runtimeMarkerEnd) != 1 {
t.Errorf("there must be exactly one begin/end marker pair, got:\n%s", s)
}
}
func TestWriteRuntimeConfigFileIsIdempotent(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
const userContent = "# User CLAUDE.md\n\nimportant rules\n"
if err := os.WriteFile(path, []byte(userContent), 0o644); err != nil {
t.Fatalf("seed user file: %v", err)
}
const brief = "## Multica brief\n\nbody"
for i := 0; i < 5; i++ {
if err := writeRuntimeConfigFile(path, brief); err != nil {
t.Fatalf("iteration %d: %v", i, err)
}
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back file: %v", err)
}
s := string(got)
if strings.Count(s, runtimeMarkerBegin) != 1 {
t.Errorf("repeated runs must not duplicate the begin marker, count=%d, file:\n%s", strings.Count(s, runtimeMarkerBegin), s)
}
if strings.Count(s, runtimeMarkerEnd) != 1 {
t.Errorf("repeated runs must not duplicate the end marker, count=%d, file:\n%s", strings.Count(s, runtimeMarkerEnd), s)
}
if strings.Count(s, brief) != 1 {
t.Errorf("repeated runs must not duplicate the brief body, count=%d, file:\n%s", strings.Count(s, brief), s)
}
if !strings.HasPrefix(s, userContent) {
t.Errorf("user content must remain intact at the top of the file, got:\n%s", s)
}
}
// InjectRuntimeConfig is the production entry point — verify the marker
// semantics propagate through it for each provider's target filename.
func TestInjectRuntimeConfigPreservesUserContent(t *testing.T) {
t.Parallel()
cases := []struct {
provider string
filename string
}{
{"claude", "CLAUDE.md"},
{"codex", "AGENTS.md"},
{"copilot", "AGENTS.md"},
{"opencode", "AGENTS.md"},
{"openclaw", "AGENTS.md"},
{"hermes", "AGENTS.md"},
{"pi", "AGENTS.md"},
{"cursor", "AGENTS.md"},
{"kimi", "AGENTS.md"},
{"kiro", "AGENTS.md"},
{"antigravity", "AGENTS.md"},
{"gemini", "GEMINI.md"},
}
for _, tc := range cases {
tc := tc
t.Run(tc.provider, func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, tc.filename)
const userContent = "# User-authored file\n\ndon't touch this\n"
if err := os.WriteFile(path, []byte(userContent), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
content, err := InjectRuntimeConfig(dir, tc.provider, TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
})
if err != nil {
t.Fatalf("InjectRuntimeConfig: %v", err)
}
if content == "" {
t.Fatalf("returned brief content must be non-empty")
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
s := string(got)
if !strings.HasPrefix(s, userContent) {
t.Errorf("[%s] user content must be preserved verbatim at the top of %s, got:\n%s", tc.provider, tc.filename, s)
}
if !strings.Contains(s, runtimeMarkerBegin) || !strings.Contains(s, runtimeMarkerEnd) {
t.Errorf("[%s] %s must contain the runtime marker block, got:\n%s", tc.provider, tc.filename, s)
}
})
}
}
func TestInjectRuntimeConfigUnknownProviderSkipsWrite(t *testing.T) {
t.Parallel()
dir := t.TempDir()
// Seed all three candidate filenames so we can verify none of them get
// written when the provider is unknown.
for _, name := range []string{"CLAUDE.md", "AGENTS.md", "GEMINI.md"} {
if err := os.WriteFile(filepath.Join(dir, name), []byte("untouched\n"), 0o644); err != nil {
t.Fatalf("seed %s: %v", name, err)
}
}
if _, err := InjectRuntimeConfig(dir, "totally-unknown-provider", TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
}); err != nil {
t.Fatalf("InjectRuntimeConfig: %v", err)
}
for _, name := range []string{"CLAUDE.md", "AGENTS.md", "GEMINI.md"} {
got, err := os.ReadFile(filepath.Join(dir, name))
if err != nil {
t.Fatalf("read %s: %v", name, err)
}
if string(got) != "untouched\n" {
t.Errorf("unknown provider must not write %s; got:\n%s", name, string(got))
}
}
}
// Parser hardening: the end marker must be found strictly after the begin
// marker so a stray end marker that appears earlier in user content (e.g.
// a documentation snippet showing what the wire format looks like) doesn't
// trick writeRuntimeConfigFile into thinking the file is malformed and
// appending another block on every run.
func TestWriteRuntimeConfigFileIgnoresStrayEndMarkerBeforeBegin(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
// Seed a file whose user-authored portion documents the marker format
// (so the *end* marker appears before any *begin* marker), then has a
// real block authored by an earlier Multica run below.
const userDoc = "# Repo CLAUDE.md\n\nExample of what Multica writes:\n" +
runtimeMarkerEnd + "\n\n# Real config below\n"
original := userDoc +
runtimeMarkerBegin + "\nFIRST BRIEF\n" + runtimeMarkerEnd + "\n"
if err := os.WriteFile(path, []byte(original), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
const newBrief = "SECOND BRIEF"
if err := writeRuntimeConfigFile(path, newBrief); err != nil {
t.Fatalf("writeRuntimeConfigFile: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
s := string(got)
// The user's stray end marker line plus surrounding doc text must still
// be present, and the file must contain exactly one begin marker and
// one *additional* end marker (so two end markers total — the stray
// one and the one closing our block).
if !strings.Contains(s, userDoc) {
t.Errorf("user doc with stray end marker must be preserved verbatim, got:\n%s", s)
}
if got, want := strings.Count(s, runtimeMarkerBegin), 1; got != want {
t.Errorf("expected exactly %d begin markers, got %d:\n%s", want, got, s)
}
if got, want := strings.Count(s, runtimeMarkerEnd), 2; got != want {
t.Errorf("expected exactly %d end markers (1 user stray + 1 closing our block), got %d:\n%s", want, got, s)
}
if strings.Contains(s, "FIRST BRIEF") {
t.Errorf("previous brief body must be replaced, got:\n%s", s)
}
if !strings.Contains(s, newBrief) {
t.Errorf("new brief body missing from output:\n%s", s)
}
// Idempotency under the stray-end pattern: a second write must not
// stack another block.
if err := writeRuntimeConfigFile(path, newBrief); err != nil {
t.Fatalf("second writeRuntimeConfigFile: %v", err)
}
got2, _ := os.ReadFile(path)
s2 := string(got2)
if got, want := strings.Count(s2, runtimeMarkerBegin), 1; got != want {
t.Errorf("repeat write must not grow begin markers, got %d, want %d:\n%s", got, want, s2)
}
}
// Parser hardening: a file containing only a begin marker (e.g. a previous
// run that crashed mid-write) must not cause every subsequent run to stack
// another block beneath the half-block.
func TestWriteRuntimeConfigFileReplacesMalformedHalfBlock(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "AGENTS.md")
const userTop = "# Repo AGENTS.md\n\nrules above\n"
const halfBlock = "leftover from crashed write\nsecond line\n"
original := userTop + runtimeMarkerBegin + "\n" + halfBlock
if err := os.WriteFile(path, []byte(original), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
const newBrief = "recovered brief"
if err := writeRuntimeConfigFile(path, newBrief); err != nil {
t.Fatalf("writeRuntimeConfigFile: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
s := string(got)
if !strings.HasPrefix(s, userTop) {
t.Errorf("user content above the half-block must be preserved, got:\n%s", s)
}
if strings.Contains(s, "leftover from crashed write") {
t.Errorf("half-block contents must be replaced, got:\n%s", s)
}
if got, want := strings.Count(s, runtimeMarkerBegin), 1; got != want {
t.Errorf("expected exactly %d begin marker, got %d:\n%s", want, got, s)
}
if got, want := strings.Count(s, runtimeMarkerEnd), 1; got != want {
t.Errorf("expected exactly %d end marker after recovery, got %d:\n%s", want, got, s)
}
if !strings.Contains(s, newBrief) {
t.Errorf("new brief body missing from output:\n%s", s)
}
}
// Cleanup excises the marker block, preserving every byte of surrounding
// user content. This is the local_directory invariant: a `claude` /
// `codex` run started by the user after a Multica task must see the same
// file the user wrote.
func TestCleanupRuntimeConfigPreservesUserContent(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
const userBefore = "# Repo CLAUDE.md\n\nuser line above\n"
const userAfter = "\nuser line below the block\n"
const userExpected = "# Repo CLAUDE.md\n\nuser line above\n\nuser line below the block\n"
// Inject via the production write path so we exercise the actual
// marker block format, not a hand-rolled approximation.
if err := os.WriteFile(path, []byte(userBefore+userAfter), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
if err := writeRuntimeConfigFile(path, "brief body"); err != nil {
t.Fatalf("seed brief: %v", err)
}
if err := CleanupRuntimeConfig(dir, "claude"); err != nil {
t.Fatalf("CleanupRuntimeConfig: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
s := string(got)
if strings.Contains(s, runtimeMarkerBegin) || strings.Contains(s, runtimeMarkerEnd) {
t.Errorf("marker block must be removed, got:\n%s", s)
}
if strings.Contains(s, "brief body") {
t.Errorf("brief body must be removed, got:\n%s", s)
}
if s != userExpected {
t.Errorf("user content must be preserved byte-for-byte\n got:\n%q\nwant:\n%q", s, userExpected)
}
}
// Cleanup removes the file entirely when the marker block was the only
// content — i.e. we created the file from scratch in a directory that had
// no pre-existing CLAUDE.md / AGENTS.md / GEMINI.md.
func TestCleanupRuntimeConfigRemovesFileWhenOnlyBlockRemained(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
// No seed — writeRuntimeConfigFile creates the file with only the
// marker block inside.
if err := writeRuntimeConfigFile(path, "brief body"); err != nil {
t.Fatalf("seed brief: %v", err)
}
if err := CleanupRuntimeConfig(dir, "claude"); err != nil {
t.Fatalf("CleanupRuntimeConfig: %v", err)
}
if _, err := os.Stat(path); !os.IsNotExist(err) {
t.Errorf("expected file to be removed, stat err=%v", err)
}
}
// Cleanup is a no-op when no marker block exists or when the file is
// missing — Cleanup is safe to call defensively from the daemon's defer.
func TestCleanupRuntimeConfigNoOpCases(t *testing.T) {
t.Parallel()
t.Run("missing file", func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
if err := CleanupRuntimeConfig(dir, "claude"); err != nil {
t.Errorf("missing file must be no-op, got: %v", err)
}
// And the directory must remain untouched.
entries, err := os.ReadDir(dir)
if err != nil {
t.Fatalf("readdir: %v", err)
}
if len(entries) != 0 {
t.Errorf("expected dir to remain empty, got: %v", entries)
}
})
t.Run("file without marker block", func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
const userContent = "# Repo CLAUDE.md\n\nrules\n"
if err := os.WriteFile(path, []byte(userContent), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
if err := CleanupRuntimeConfig(dir, "claude"); err != nil {
t.Errorf("no-marker-block file must be no-op, got: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
if string(got) != userContent {
t.Errorf("file must be untouched\n got:\n%q\nwant:\n%q", string(got), userContent)
}
})
t.Run("unknown provider", func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
// Seed every candidate filename to verify none of them get touched.
for _, name := range []string{"CLAUDE.md", "AGENTS.md", "GEMINI.md"} {
if err := os.WriteFile(filepath.Join(dir, name), []byte("untouched\n"), 0o644); err != nil {
t.Fatalf("seed %s: %v", name, err)
}
}
if err := CleanupRuntimeConfig(dir, "totally-unknown-provider"); err != nil {
t.Errorf("unknown provider must be no-op, got: %v", err)
}
for _, name := range []string{"CLAUDE.md", "AGENTS.md", "GEMINI.md"} {
got, err := os.ReadFile(filepath.Join(dir, name))
if err != nil {
t.Fatalf("read %s: %v", name, err)
}
if string(got) != "untouched\n" {
t.Errorf("unknown provider must not touch %s; got:\n%s", name, string(got))
}
}
})
}
// Cleanup must handle a half-block left by a previous crashed run: begin
// marker present but no end. Otherwise the half-block would survive
// cleanup and pollute the next manual CLI invocation in the same dir.
func TestCleanupRuntimeConfigRemovesMalformedHalfBlock(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "AGENTS.md")
const userTop = "# Repo AGENTS.md\n\nrules\n"
original := userTop + runtimeMarkerBegin + "\nhalf-written brief no end\n"
if err := os.WriteFile(path, []byte(original), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
if err := CleanupRuntimeConfig(dir, "codex"); err != nil {
t.Fatalf("CleanupRuntimeConfig: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
s := string(got)
if strings.Contains(s, runtimeMarkerBegin) {
t.Errorf("half-block begin marker must be excised, got:\n%s", s)
}
if strings.Contains(s, "half-written brief no end") {
t.Errorf("half-block body must be excised, got:\n%s", s)
}
if !strings.HasPrefix(s, userTop) {
t.Errorf("user content above the half-block must remain, got:\n%s", s)
}
}
// Cleanup must remove the marker block for every provider's target file,
// using the same provider→filename mapping as InjectRuntimeConfig — so a
// new provider added to one side cannot drift past the other.
func TestCleanupRuntimeConfigByProvider(t *testing.T) {
t.Parallel()
cases := []struct {
provider string
filename string
}{
{"claude", "CLAUDE.md"},
{"codex", "AGENTS.md"},
{"copilot", "AGENTS.md"},
{"opencode", "AGENTS.md"},
{"openclaw", "AGENTS.md"},
{"hermes", "AGENTS.md"},
{"pi", "AGENTS.md"},
{"cursor", "AGENTS.md"},
{"kimi", "AGENTS.md"},
{"kiro", "AGENTS.md"},
{"antigravity", "AGENTS.md"},
{"gemini", "GEMINI.md"},
}
for _, tc := range cases {
tc := tc
t.Run(tc.provider, func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, tc.filename)
const userContent = "# User file\n\ndon't touch this\n"
if err := os.WriteFile(path, []byte(userContent), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
// Inject through the production path so cleanup runs against
// the same wire format the agent saw.
if _, err := InjectRuntimeConfig(dir, tc.provider, TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
}); err != nil {
t.Fatalf("InjectRuntimeConfig: %v", err)
}
if err := CleanupRuntimeConfig(dir, tc.provider); err != nil {
t.Fatalf("CleanupRuntimeConfig: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
s := string(got)
if strings.Contains(s, runtimeMarkerBegin) || strings.Contains(s, runtimeMarkerEnd) {
t.Errorf("[%s] marker block must be removed from %s, got:\n%s", tc.provider, tc.filename, s)
}
if s != userContent {
t.Errorf("[%s] user content in %s must be preserved byte-for-byte\n got:\n%q\nwant:\n%q", tc.provider, tc.filename, s, userContent)
}
})
}
}
// Inject → Cleanup → manual edit → Inject must converge back to the
// pre-injection state on the next Cleanup. This is the end-to-end
// regression that locks in: the user's repo is byte-identical to what
// they had before the task, every task cycle.
func TestInjectThenCleanupRoundTrip(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
const userContent = "# User-authored CLAUDE.md\n\n- rule A\n- rule B\n"
if err := os.WriteFile(path, []byte(userContent), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
// Two full inject→cleanup cycles — covers both the "first task on a
// fresh user file" path and the "subsequent task hits a clean file
// again" path.
for i := 0; i < 2; i++ {
if _, err := InjectRuntimeConfig(dir, "claude", TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
}); err != nil {
t.Fatalf("iter %d inject: %v", i, err)
}
if err := CleanupRuntimeConfig(dir, "claude"); err != nil {
t.Fatalf("iter %d cleanup: %v", i, err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("iter %d read back: %v", i, err)
}
if string(got) != userContent {
t.Errorf("iter %d: user file must be byte-identical to pre-injection state\n got:\n%q\nwant:\n%q", i, string(got), userContent)
}
}
}
// Byte-exact boundary coverage flagged in PR #3438 review (Elon): the
// previous cleanup used TrimRight + "\n" and TrimSpace-based file removal,
// which created a real diff in three boundary cases. The table walks each
// one through a full inject→cleanup cycle and asserts the file ends up
// byte-identical (or, for missing-file, that it stays missing).
func TestInjectThenCleanupRoundTripByteExactBoundaries(t *testing.T) {
t.Parallel()
cases := []struct {
name string
// seed describes the pre-inject filesystem state. When seedExists
// is false the file is absent; when true the file is created with
// seedContent (which may be empty / whitespace-only / arbitrary
// bytes).
seedExists bool
seedContent string
}{
{
name: "file missing — Inject creates, Cleanup removes",
seedExists: false,
seedContent: "",
},
{
name: "pre-existing empty file (zero bytes)",
seedExists: true,
seedContent: "",
},
{
name: "pre-existing whitespace-only file",
seedExists: true,
seedContent: " \n",
},
{
name: "no trailing newline",
seedExists: true,
seedContent: "rules",
},
{
name: "one trailing newline (the common markdown shape)",
seedExists: true,
seedContent: "# Rules\n\nbody\n",
},
{
name: "two trailing newlines",
seedExists: true,
seedContent: "rules\n\n",
},
{
name: "many trailing newlines",
seedExists: true,
seedContent: "rules\n\n\n\n",
},
{
name: "CRLF line endings",
seedExists: true,
seedContent: "rule A\r\nrule B\r\n",
},
{
name: "no final newline AND embedded blank lines",
seedExists: true,
seedContent: "para 1\n\npara 2\n\npara 3",
},
}
for _, tc := range cases {
tc := tc
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
if tc.seedExists {
if err := os.WriteFile(path, []byte(tc.seedContent), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
}
// Two cycles to cover both "first inject hits user file" and
// "subsequent inject hits a cleaned file" paths.
for i := 0; i < 2; i++ {
if _, err := InjectRuntimeConfig(dir, "claude", TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
}); err != nil {
t.Fatalf("iter %d inject: %v", i, err)
}
if err := CleanupRuntimeConfig(dir, "claude"); err != nil {
t.Fatalf("iter %d cleanup: %v", i, err)
}
if !tc.seedExists {
// Missing file must remain missing after the cycle so
// the user's directory listing is also byte-identical
// (no zero-byte stub left behind).
if _, err := os.Stat(path); !os.IsNotExist(err) {
t.Errorf("iter %d: file must remain missing, stat err=%v", i, err)
}
continue
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("iter %d read back: %v", i, err)
}
if string(got) != tc.seedContent {
t.Errorf("iter %d: file must be byte-identical to seed\n got: %q\n want: %q", i, string(got), tc.seedContent)
}
}
})
}
}
// Idempotency across the byte-exact boundaries: when a second Inject runs
// against a file that already carries a marker block (the "replace in
// place" branch), the surrounding bytes must stay untouched and the
// subsequent Cleanup must still restore the user's original file
// byte-exactly. This guards against a regression where the replace path
// would re-normalise pre/post bytes the way the old cleanup did.
func TestInjectReplaceThenCleanupRestoresByteExact(t *testing.T) {
t.Parallel()
cases := []struct {
name string
seedContent string
}{
{name: "no trailing newline", seedContent: "rules"},
{name: "two trailing newlines", seedContent: "rules\n\n"},
{name: "empty file", seedContent: ""},
}
for _, tc := range cases {
tc := tc
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
if err := os.WriteFile(path, []byte(tc.seedContent), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
// First inject — append path.
if _, err := InjectRuntimeConfig(dir, "claude", TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
}); err != nil {
t.Fatalf("first inject: %v", err)
}
// Second inject — replace-in-place path.
if _, err := InjectRuntimeConfig(dir, "claude", TaskContextForEnv{
IssueID: "11111111-2222-3333-4444-555555555555",
}); err != nil {
t.Fatalf("second inject: %v", err)
}
if err := CleanupRuntimeConfig(dir, "claude"); err != nil {
t.Fatalf("cleanup: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
if string(got) != tc.seedContent {
t.Errorf("file must be byte-identical to seed after replace+cleanup\n got: %q\n want: %q", string(got), tc.seedContent)
}
})
}
}
// The fixed managed separator is the invariant that makes byte-exact
// cleanup possible. This test pins it: writeRuntimeConfigFile must
// produce exactly `<user-bytes><\n\n><marker-block>` for ANY non-empty
// or empty pre-existing file, with no trailing-newline normalisation.
func TestWriteRuntimeConfigFileAlwaysInsertsFixedManagedSeparator(t *testing.T) {
t.Parallel()
for _, seed := range []string{"", "rules", "rules\n", "rules\n\n", "rules\n\n\n\n"} {
seed := seed
t.Run(fmt.Sprintf("seed=%q", seed), func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, "CLAUDE.md")
if err := os.WriteFile(path, []byte(seed), 0o644); err != nil {
t.Fatalf("seed: %v", err)
}
if err := writeRuntimeConfigFile(path, "brief body"); err != nil {
t.Fatalf("write: %v", err)
}
got, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read back: %v", err)
}
s := string(got)
// The seed must appear verbatim at the start of the file —
// no extra newline appended, no trailing newline trimmed.
if !strings.HasPrefix(s, seed) {
t.Errorf("seed bytes must survive verbatim at the start of the file\n got: %q\n seed: %q", s, seed)
}
// Immediately after the seed we must see the fixed managed
// separator, then the begin marker.
markerStart := len(seed) + len(runtimeManagedSeparator)
if len(s) < markerStart+len(runtimeMarkerBegin) {
t.Fatalf("file shorter than expected layout\n got: %q", s)
}
if got, want := s[len(seed):markerStart], runtimeManagedSeparator; got != want {
t.Errorf("expected managed separator %q immediately after seed, got %q", want, got)
}
if got, want := s[markerStart:markerStart+len(runtimeMarkerBegin)], runtimeMarkerBegin; got != want {
t.Errorf("expected begin marker after managed separator, got %q", got)
}
})
}
}