fix(handlers): remove conflict-resolution artifact from delegation_test.go

Line 1685 had the branch name concatenated outside the t.Errorf() closing
paren, and line 1688 was a stray branch-name line — both leftover from a
conflict resolution that was not fully cleaned. This causes a Go compilation
error and explains the CI / Platform (Go) failure on PR #882.

[core-be-agent]

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.gitea/ci-refire

@@ -1 +0,0 @@
-refire:1778784369

.gitea/scripts/ci-required-drift.py

@@ -203,17 +203,12 @@ def ci_jobs_all(ci_doc: dict) -> set[str]:
 
 def ci_job_names(ci_doc: dict) -> set[str]:
     """Set of job keys in ci.yml MINUS the sentinel itself MINUS jobs
-    whose `if:` gates on `github.event_name` or `github.ref` (those are
-    event-scoped and can legitimately be `skipped` for a given trigger;
-    if we required them under the sentinel `needs:`, every PR-only job
+    whose `if:` gates on `github.event_name` (those are event-scoped
+    and can legitimately be `skipped` for a given trigger; if we
+    required them under the sentinel `needs:`, every PR-only job
     would be `skipped` on push and the sentinel would interpret
     `skipped != success` as failure). RFC §4 spec.
 
-    `github.ref` is the companion gate for jobs that run only on direct
-    pushes to specific branches (e.g. `github.ref == 'refs/heads/main'`).
-    These never execute in a PR context, so flagging them as missing
-    from `all-required.needs:` is a false positive (mc#958 / mc#959).
-
     Used for F1 (jobs missing from sentinel needs). NOT used for F1b
     (typos in needs) — see `ci_jobs_all` for that."""
     jobs = ci_doc.get("jobs")
@@ -226,9 +221,7 @@ def ci_job_names(ci_doc: dict) -> set[str]:
             continue
         if isinstance(v, dict):
             gate = v.get("if")
-            if isinstance(gate, str) and (
-                "github.event_name" in gate or "github.ref" in gate
-            ):
+            if isinstance(gate, str) and "github.event_name" in gate:
                 continue
         names.add(k)
     return names

.gitea/scripts/gitea-merge-queue.py

@@ -47,15 +47,6 @@ REQUIRED_CONTEXTS_RAW = _env(
         "sop-checklist / all-items-acked (pull_request)"
     ),
 )
-# Required contexts for push (main/staging) runs. The push CI uses the same
-# aggregator names with " (push)" suffix. Checking these explicitly instead of
-# the combined state avoids false-pause when non-blocking jobs (e.g. Platform
-# Go with continue-on-error: true due to mc#774) have failed — their failures
-# pollute the combined state but do not block merges.
-PUSH_REQUIRED_CONTEXTS_RAW = _env(
-    "PUSH_REQUIRED_CONTEXTS",
-    default="CI / all-required (push)",
-)
 
 OWNER, NAME = (REPO.split("/", 1) + [""])[:2] if REPO else ("", "")
 API = f"https://{GITEA_HOST}/api/v1" if GITEA_HOST else ""
@@ -127,24 +118,16 @@ def required_contexts(raw: str) -> list[str]:
     return [part.strip() for part in raw.split(",") if part.strip()]
 
 
-def push_required_contexts() -> list[str]:
-    """Required contexts for push (branch) CI runs. See PUSH_REQUIRED_CONTEXTS_RAW."""
-    return required_contexts(PUSH_REQUIRED_CONTEXTS_RAW)
-
-
 def status_state(status: dict) -> str:
     return str(status.get("status") or status.get("state") or "").lower()
 
 
 def latest_statuses_by_context(statuses: list[dict]) -> dict[str, dict]:
-    # Gitea /statuses endpoint returns entries in ascending id order (oldest
-    # first). We need the LAST occurrence of each context, so iterate in
-    # reverse to prefer newer entries.
     latest: dict[str, dict] = {}
-    for status in reversed(statuses):
+    for status in statuses:
         context = status.get("context")
-        if isinstance(context, str):
-            latest[context] = status  # overwrite: reverse order → newest wins
+        if isinstance(context, str) and context not in latest:
+            latest[context] = status
     return latest
 
 
@@ -210,23 +193,16 @@ def evaluate_merge_readiness(
     required_contexts: list[str],
     pr_has_current_base: bool,
 ) -> MergeDecision:
-    # Check push-required contexts explicitly instead of combined state.
-    # Combined state can be "failure" due to non-blocking jobs
-    # (continue-on-error: true) that don't actually gate merges.
-    # CI / all-required (push) is the authoritative gate — it respects
-    # continue-on-error and correctly aggregates all blocking failures.
-    main_latest = latest_statuses_by_context(main_status.get("statuses") or [])
-    main_ok, main_bad = required_contexts_green(main_latest, push_required_contexts())
-    if not main_ok:
-        return MergeDecision(False, "pause", "main required contexts not green: " + ", ".join(main_bad))
+    main_state = str(main_status.get("state") or "").lower()
+    if main_state != "success":
+        return MergeDecision(False, "pause", f"main status is {main_state or 'missing'}")
     if not pr_has_current_base:
         return MergeDecision(False, "update", "PR head does not contain current main")
 
-    # Check explicit required contexts instead of combined state. Combined state
-    # can be "failure" due to non-blocking jobs with continue-on-error: true
-    # (e.g. publish-runtime-autobump/pr-validate, qa-review on stale tokens).
-    # The required_contexts list is the authoritative gate — it includes only
-    # the checks that actually block merges.
+    pr_state = str(pr_status.get("state") or "").lower()
+    if pr_state != "success":
+        return MergeDecision(False, "wait", f"PR combined status is {pr_state or 'missing'}")
+
     latest = latest_statuses_by_context(pr_status.get("statuses") or [])
     ok, missing_or_bad = required_contexts_green(latest, required_contexts)
     if not ok:
@@ -244,37 +220,10 @@ def get_branch_head(branch: str) -> str:
 
 
 def get_combined_status(sha: str) -> dict:
-    """Combined status + all individual statuses for `sha`.
-
-    The /status endpoint caps the `statuses` array at 30 entries (Gitea
-    default page size), so we fetch the full list via /statuses with a
-    higher limit. The combined `state` still comes from /status.
-    """
-    _, combined = api("GET", f"/repos/{OWNER}/{NAME}/commits/{sha}/status")
-    if not isinstance(combined, dict):
+    _, body = api("GET", f"/repos/{OWNER}/{NAME}/commits/{sha}/status")
+    if not isinstance(body, dict):
         raise ApiError(f"status for {sha} response not object")
-    # Fetch full statuses list; 200 covers >99% of real-world runs.
-    # The list is ordered ascending by id (oldest first) — callers must
-    # iterate in reverse to get the newest entry per context.
-    # Best-effort: large repos (main with 550+ statuses) may time out.
-    # On timeout, fall back to the statuses[] already in the combined
-    # response (usually 30 entries — enough for most PRs, enough for
-    # main's early push-required contexts).
-    try:
-        _, all_statuses = api(
-            "GET",
-            f"/repos/{OWNER}/{NAME}/commits/{sha}/statuses",
-            query={"limit": "50"},
-        )
-        if isinstance(all_statuses, list):
-            combined["statuses"] = all_statuses
-    except (ApiError, urllib.error.URLError, TimeoutError, OSError) as exc:
-        # URLError covers network-level failures (DNS, refused, timeout).
-        # TimeoutError and OSError cover socket-level timeouts.
-        sys.stderr.write(f"::warning::could not fetch full statuses list for {sha[:8]}: {exc}\n")
-        # Fall back to the statuses[] already in the combined response.
-        pass
-    return combined
+    return body
 
 
 def list_queued_issues() -> list[dict]:
@@ -345,12 +294,8 @@ def process_once(*, dry_run: bool = False) -> int:
     contexts = required_contexts(REQUIRED_CONTEXTS_RAW)
     main_sha = get_branch_head(WATCH_BRANCH)
     main_status = get_combined_status(main_sha)
-    # Check push-required contexts explicitly instead of combined state.
-    # See evaluate_merge_readiness for rationale.
-    main_latest = latest_statuses_by_context(main_status.get("statuses") or [])
-    main_ok, main_bad = required_contexts_green(main_latest, push_required_contexts())
-    if not main_ok:
-        print(f"::notice::queue paused: {WATCH_BRANCH}@{main_sha[:8]} required contexts not green: {', '.join(main_bad)}")
+    if str(main_status.get("state") or "").lower() != "success":
+        print(f"::notice::queue paused: {WATCH_BRANCH}@{main_sha[:8]} is not green")
         return 0
 
     issue = choose_next_queued_issue(
@@ -417,21 +362,7 @@ def main() -> int:
     parser.add_argument("--dry-run", action="store_true")
     args = parser.parse_args()
     _require_runtime_env()
-    try:
-        return process_once(dry_run=args.dry_run)
-    except ApiError as exc:
-        # API errors (401/403/404/500) are transient for a queue tick —
-        # log and exit 0 so the workflow is not marked failed and the next
-        # tick can retry. Returning non-zero would permanently fail the
-        # workflow run, blocking future ticks.
-        sys.stderr.write(f"::error::queue API error: {exc}\n")
-        return 0
-    except urllib.error.URLError as exc:
-        sys.stderr.write(f"::error::queue network error: {exc}\n")
-        return 0
-    except TimeoutError as exc:
-        sys.stderr.write(f"::error::queue timeout: {exc}\n")
-        return 0
+    return process_once(dry_run=args.dry_run)
 
 
 if __name__ == "__main__":

.gitea/scripts/lint-workflow-yaml.py

@@ -36,9 +36,6 @@ Rules (4 fatal + 1 fatal cross-file + 1 heuristic-warn):
      raw `.error` fields into CI logs/summaries.
   9. Production deploy/redeploy workflows must expose an operational control:
      kill switch for auto deploys or rollback tag for manual deploys.
-  10. Docker health checks must not run `docker info | head` under pipefail.
-      `head` closes the pipe early, `docker info` can exit nonzero from
-      SIGPIPE, and the step can falsely report Docker daemon failure.
 
 Per `feedback_smoke_test_vendor_truth_not_shape_match`: fixtures used to
 validate this lint must mirror real Gitea 1.22.6 YAML semantics, not
@@ -228,24 +225,6 @@ def _iter_uses(doc: Any) -> Iterable[str]:
                 yield step["uses"]
 
 
-def _iter_run_blocks(doc: Any) -> Iterable[str]:
-    """Yield every shell `run:` block from job steps in a workflow document."""
-    if not isinstance(doc, dict):
-        return
-    jobs = doc.get("jobs")
-    if not isinstance(jobs, dict):
-        return
-    for job in jobs.values():
-        if not isinstance(job, dict):
-            continue
-        steps = job.get("steps")
-        if not isinstance(steps, list):
-            continue
-        for step in steps:
-            if isinstance(step, dict) and isinstance(step.get("run"), str):
-                yield step["run"]
-
-
 def check_cross_repo_uses(filename: str, doc: Any) -> list[str]:
     """Return per-violation error lines for cross-repo `uses:` references."""
     errors: list[str] = []
@@ -285,10 +264,6 @@ GITHUB_API_REF_RE = re.compile(
 
 PROD_CP_URL_RE = re.compile(r"https://api\.moleculesai\.app\b")
 REDEPLOY_FLEET_RE = re.compile(r"\b/cp/admin/tenants/redeploy-fleet\b")
-RUN_SETS_PIPEFAIL_RE = re.compile(r"(?m)^\s*set\s+-[^\n]*o\s+pipefail\b")
-DOCKER_INFO_HEAD_PIPE_RE = re.compile(
-    r"(?m)^\s*docker\s+info\b[^\n|]*\|\s*head\b"
-)
 RAW_CP_RESPONSE_RE = re.compile(
     r"""(?x)
     (?:\bjq\s+\.\s+["']?\$HTTP_RESPONSE["']?)
@@ -408,30 +383,6 @@ def check_production_operational_control(filename: str, raw: str) -> list[str]:
     return errors
 
 
-# ---------------------------------------------------------------------------
-# Rule 10 — docker info piped to head under pipefail
-# ---------------------------------------------------------------------------
-
-def check_docker_info_head_pipefail(filename: str, doc: Any) -> list[str]:
-    errors: list[str] = []
-    for run_block in _iter_run_blocks(doc):
-        if not (
-            RUN_SETS_PIPEFAIL_RE.search(run_block)
-            and DOCKER_INFO_HEAD_PIPE_RE.search(run_block)
-        ):
-            continue
-        errors.append(
-            f"::error file={filename}::Rule 10 (FATAL): workflow runs "
-            f"`docker info | head` after enabling `pipefail`. `head` can "
-            f"close the pipe early, making `docker info` exit nonzero and "
-            f"falsely fail the Docker daemon health check. Capture "
-            f"`docker_info=\"$(docker info 2>&1)\"` first, then print a "
-            f"bounded preview with `printf ... | sed -n '1,5p'`."
-        )
-        break
-    return errors
-
-
 # ---------------------------------------------------------------------------
 # Driver
 # ---------------------------------------------------------------------------
@@ -485,7 +436,6 @@ def main(argv: list[str] | None = None) -> int:
         fatal_errors.extend(check_production_concurrency(rel, doc, raw))
         fatal_errors.extend(check_production_raw_response_logging(rel, raw))
         fatal_errors.extend(check_production_operational_control(rel, raw))
-        fatal_errors.extend(check_docker_info_head_pipefail(rel, doc))
         warnings.extend(check_github_server_url_missing(rel, doc, raw))
 
     # Cross-file checks

.gitea/scripts/review-check.sh

@@ -101,10 +101,9 @@ printf 'header = "Authorization: token %s"\n' "$GITEA_TOKEN" > "$CURL_AUTH_FILE"
 PR_JSON=$(mktemp)
 REVIEWS_JSON=$(mktemp)
 TEAM_PROBE_TMP=$(mktemp)
-NA_STATUSES_TMP=""  # declared here so cleanup() always has the var
 
 cleanup() {
-  rm -f "$CURL_AUTH_FILE" "$PR_JSON" "$REVIEWS_JSON" "$TEAM_PROBE_TMP" "${NA_STATUSES_TMP-}"
+  rm -f "$CURL_AUTH_FILE" "$PR_JSON" "$REVIEWS_JSON" "$TEAM_PROBE_TMP"
 }
 trap cleanup EXIT
 
@@ -144,42 +143,6 @@ if [ -z "$PR_AUTHOR" ] || [ -z "$PR_HEAD_SHA" ]; then
   exit 1
 fi
 
-# --- RFC#324 §N/A follow-up: check N/A declarations status ---
-# sop-checklist.py posts `sop-checklist / na-declarations (pull_request)`
-# status when a peer posts /sop-n/a <gate>. If our gate is declared N/A,
-# the requirement for a Gitea APPROVE review is waived.
-NA_STATUSES_TMP=$(mktemp)
-HTTP_CODE=$(curl -sS -o "$NA_STATUSES_TMP" -w '%{http_code}' \
-  -K "$CURL_AUTH_FILE" "${API}/repos/${OWNER}/${NAME}/statuses/${PR_HEAD_SHA}")
-debug "statuses/${PR_HEAD_SHA} → HTTP ${HTTP_CODE}"
-
-if [ "$HTTP_CODE" = "200" ]; then
-  # Gitea returns statuses as array; look for the na-declarations context.
-  # jq: find all statuses where context == "sop-checklist / na-declarations (pull_request)"
-  # and state == "success". Extract the description field.
-  NA_DESC=$(jq -r '
-    .[] |
-    select(.context == "sop-checklist / na-declarations (pull_request)") |
-    select(.state == "success") |
-    .description
-  ' "$NA_STATUSES_TMP" 2>/dev/null | head -1)
-
-  if [ -n "$NA_DESC" ] && [ "$NA_DESC" != "null" ]; then
-    debug "na-declarations status found: ${NA_DESC}"
-    # Check if our gate appears in the N/A description.
-    # The description format is "N/A: qa-review, security-review" or similar.
-    if echo "$NA_DESC" | grep -iq "\\b${TEAM}-review\\b"; then
-      echo "::notice::${TEAM}-review N/A — gate declared not-applicable via /sop-n/a: ${NA_DESC}"
-      echo "::notice::PR ${PR_NUMBER} passes ${TEAM}-review via N/A declaration"
-      rm -f "$NA_STATUSES_TMP"
-      exit 0
-    fi
-  fi
-else
-  debug "could not fetch statuses (HTTP ${HTTP_CODE}) — proceeding with normal eval"
-fi
-rm -f "$NA_STATUSES_TMP"
-
 # --- Fetch all reviews on the PR ---
 HTTP_CODE=$(curl -sS -o "$REVIEWS_JSON" -w '%{http_code}' \
   -K "$CURL_AUTH_FILE" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}/reviews")

.gitea/scripts/review-refire-status.sh

@@ -1,81 +0,0 @@
-#!/usr/bin/env bash
-# Re-run review-check.sh for a slash-command refire and post the protected
-# pull_request status context to the PR head SHA.
-
-set -euo pipefail
-
-: "${GITEA_TOKEN:?GITEA_TOKEN required}"
-: "${GITEA_HOST:?GITEA_HOST required}"
-: "${REPO:?REPO required}"
-: "${PR_NUMBER:?PR_NUMBER required}"
-: "${TEAM:?TEAM required}"
-
-OWNER="${REPO%%/*}"
-NAME="${REPO##*/}"
-API="https://${GITEA_HOST}/api/v1"
-CONTEXT="${TEAM}-review / approved (pull_request)"
-TARGET_URL="https://${GITEA_HOST}/${OWNER}/${NAME}/pulls/${PR_NUMBER}"
-
-authfile=$(mktemp)
-prfile=$(mktemp)
-postfile=$(mktemp)
-# shellcheck disable=SC2329 # invoked by EXIT trap
-cleanup() {
-  rm -f "$authfile" "$prfile" "$postfile"
-}
-trap cleanup EXIT
-
-chmod 600 "$authfile"
-printf 'header = "Authorization: token %s"\n' "$GITEA_TOKEN" > "$authfile"
-
-code=$(curl -sS -o "$prfile" -w '%{http_code}' -K "$authfile" \
-  "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}")
-if [ "$code" != "200" ]; then
-  echo "::error::GET /pulls/${PR_NUMBER} returned HTTP ${code}"
-  head -c 200 "$prfile" >&2 || true
-  exit 1
-fi
-
-head_sha=$(jq -r '.head.sha // ""' "$prfile")
-state=$(jq -r '.state // ""' "$prfile")
-if [ -z "$head_sha" ] || [ "$head_sha" = "null" ]; then
-  echo "::error::Could not resolve PR head SHA for PR ${PR_NUMBER}"
-  exit 1
-fi
-if [ "$state" != "open" ]; then
-  echo "::notice::PR ${PR_NUMBER} is ${state}; ${TEAM}-review refire is a no-op"
-  exit 0
-fi
-
-set +e
-bash .gitea/scripts/review-check.sh
-rc=$?
-set -e
-
-if [ "$rc" -eq 0 ]; then
-  status_state="success"
-  description="Refired via /${TEAM}-recheck by ${COMMENT_AUTHOR:-unknown}"
-else
-  status_state="failure"
-  description="Refired via /${TEAM}-recheck; ${TEAM}-review failed"
-fi
-
-body=$(jq -nc \
-  --arg state "$status_state" \
-  --arg context "$CONTEXT" \
-  --arg description "$description" \
-  --arg target_url "$TARGET_URL" \
-  '{state:$state, context:$context, description:$description, target_url:$target_url}')
-
-code=$(curl -sS -o "$postfile" -w '%{http_code}' -X POST \
-  -K "$authfile" -H "Content-Type: application/json" \
-  -d "$body" \
-  "${API}/repos/${OWNER}/${NAME}/statuses/${head_sha}")
-if [ "$code" != "200" ] && [ "$code" != "201" ]; then
-  echo "::error::POST /statuses/${head_sha} returned HTTP ${code}"
-  head -c 200 "$postfile" >&2 || true
-  exit 1
-fi
-
-echo "::notice::posted ${status_state} for context=\"${CONTEXT}\" on sha=${head_sha}"
-exit "$rc"

.gitea/scripts/sop-checklist-gate.py

@@ -1,11 +1,11 @@
 #!/usr/bin/env python3
-# sop-checklist — evaluate whether a PR has peer-acked each
+# sop-checklist-gate — evaluate whether a PR has peer-acked each
 # SOP-checklist item. Posts a commit-status that branch protection
 # can require.
 #
 # RFC#351 Step 2 of 6 (implementation MVP).
 #
-# Invoked by .gitea/workflows/sop-checklist.yml on:
+# Invoked by .gitea/workflows/sop-checklist-gate.yml on:
 #   - pull_request_target: [opened, edited, synchronize, reopened]
 #   - issue_comment:       [created, edited, deleted]
 #

.gitea/scripts/status-reaper.py

@@ -133,9 +133,6 @@ PUSH_COMPENSATION_DESCRIPTION = (
     "Compensated by status-reaper (workflow has no push: trigger; "
     "Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)"
 )
-# Backward-compatible alias for older tests/tooling that predate the split
-# between push-suffix compensation and pull-request-shadow compensation.
-COMPENSATION_DESCRIPTION = PUSH_COMPENSATION_DESCRIPTION
 PR_SHADOW_COMPENSATION_DESCRIPTION = (
     "Compensated by status-reaper (default-branch pull_request status "
     "shadowed by successful push status on same SHA; see "
@@ -614,10 +611,11 @@ def list_recent_commit_shas(branch: str, limit: int) -> list[str]:
     (verified via vendor-truth probe 2026-05-11 against
     git.moleculesai.app — `feedback_smoke_test_vendor_truth_not_shape_match`).
 
-    Raises ApiError on non-2xx OR on unexpected response shape. The
-    branch-level caller soft-skips this tick because the next scheduled
-    tick can safely retry the listing. Per-SHA status/write errors remain
-    separate and must not be mislabeled as commit-list outages.
+    Raises ApiError on non-2xx OR on unexpected response shape. This is
+    a HARD halt — without the commit list the sweep can't proceed. (The
+    per-SHA error isolation downstream is a different concern: tolerating
+    a transient 5xx on ONE commit's status is best-effort; losing the
+    commit list itself means we don't even know which commits to try.)
     """
     _, body = api(
         "GET",
@@ -658,27 +656,7 @@ def reap_branch(
       - compensated_per_sha: {<sha_full>: [<context>, ...]} — only
         SHAs that actually got at least one compensation are included
     """
-    try:
-        shas = list_recent_commit_shas(branch, limit)
-    except ApiError as e:
-        print(
-            "::warning::status-reaper skipped this tick because the "
-            f"commit list could not be read after retries: {e}"
-        )
-        return {
-            "scanned_shas": 0,
-            "compensated": 0,
-            "preserved_real_push": 0,
-            "preserved_unknown": 0,
-            "preserved_non_failure": 0,
-            "preserved_non_push_suffix": 0,
-            "preserved_unparseable": 0,
-            "compensated_pr_shadowed_by_push_success": 0,
-            "preserved_pr_without_push_success": 0,
-            "compensated_per_sha": {},
-            "skipped": True,
-            "skip_reason": "commit-list-api-error",
-        }
+    shas = list_recent_commit_shas(branch, limit)
 
     aggregate: dict[str, Any] = {
         "scanned_shas": 0,

.gitea/scripts/tests/test_gitea_merge_queue.py

@@ -85,10 +85,7 @@ def test_pr_needs_update_when_base_sha_absent_from_commits():
 
 def test_merge_decision_requires_main_green_pr_green_and_current_base():
     required = ["CI / all-required (pull_request)"]
-    main_status = {
-        "state": "success",
-        "statuses": [{"context": "CI / all-required (push)", "status": "success"}],
-    }
+    main_status = {"state": "success", "statuses": []}
     pr_status = {
         "state": "success",
         "statuses": [{"context": "CI / all-required (pull_request)", "status": "success"}],
@@ -107,10 +104,7 @@ def test_merge_decision_requires_main_green_pr_green_and_current_base():
 
 def test_merge_decision_updates_stale_pr_before_merge():
     decision = mq.evaluate_merge_readiness(
-        main_status={
-            "state": "success",
-            "statuses": [{"context": "CI / all-required (push)", "status": "success"}],
-        },
+        main_status={"state": "success", "statuses": []},
         pr_status={"state": "success", "statuses": [{"context": "CI / all-required (pull_request)", "status": "success"}]},
         required_contexts=["CI / all-required (pull_request)"],
         pr_has_current_base=False,

.gitea/scripts/tests/test_sop_checklist_gate.py

@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
-# Unit tests for sop-checklist.py
+# Unit tests for sop-checklist-gate.py
 #
-# Run:  python3 .gitea/scripts/tests/test_sop_checklist.py
-#   or:  pytest .gitea/scripts/tests/test_sop_checklist.py
+# Run:  python3 .gitea/scripts/tests/test_sop_checklist_gate.py
+#   or:  pytest .gitea/scripts/tests/test_sop_checklist_gate.py
 #
 # RFC#351 Step 2 of 6 — implementation MVP. Tests cover:
 #   - slug normalization (the 4 example variants in the script header)
@@ -33,7 +33,7 @@ sys.path.insert(0, PARENT)
 import importlib.util  # noqa: E402
 
 _spec = importlib.util.spec_from_file_location(
-    "sop_checklist", os.path.join(PARENT, "sop-checklist.py")
+    "sop_checklist_gate", os.path.join(PARENT, "sop-checklist-gate.py")
 )
 sop = importlib.util.module_from_spec(_spec)
 _spec.loader.exec_module(sop)  # type: ignore[union-attr]
@@ -134,22 +134,18 @@ class TestParseDirectives(unittest.TestCase):
     def setUp(self):
         self.aliases = _numeric_aliases()
 
-    def parse_ack_revoke(self, body):
-        directives, na_directives = sop.parse_directives(body, self.aliases)
-        self.assertEqual(na_directives, [])
-        return directives
-
     def test_simple_ack(self):
-        d = self.parse_ack_revoke("/sop-ack comprehensive-testing")
+        d = sop.parse_directives("/sop-ack comprehensive-testing", self.aliases)
         self.assertEqual(d, [("sop-ack", "comprehensive-testing", "")])
 
     def test_simple_revoke(self):
-        d = self.parse_ack_revoke("/sop-revoke staging-smoke")
+        d = sop.parse_directives("/sop-revoke staging-smoke", self.aliases)
         self.assertEqual(d, [("sop-revoke", "staging-smoke", "")])
 
     def test_ack_with_note(self):
-        d = self.parse_ack_revoke(
-            "/sop-ack comprehensive-testing LGTM the test covers all edge cases"
+        d = sop.parse_directives(
+            "/sop-ack comprehensive-testing LGTM the test covers all edge cases",
+            self.aliases,
         )
         self.assertEqual(len(d), 1)
         self.assertEqual(d[0][0], "sop-ack")
@@ -157,12 +153,13 @@ class TestParseDirectives(unittest.TestCase):
         self.assertIn("LGTM", d[0][2])
 
     def test_numeric_shorthand(self):
-        d = self.parse_ack_revoke("/sop-ack 1")
+        d = sop.parse_directives("/sop-ack 1", self.aliases)
         self.assertEqual(d, [("sop-ack", "comprehensive-testing", "")])
 
     def test_revoke_with_reason(self):
-        d = self.parse_ack_revoke(
-            "/sop-revoke comprehensive-testing realized the e2e was mocking the DB"
+        d = sop.parse_directives(
+            "/sop-revoke comprehensive-testing realized the e2e was mocking the DB",
+            self.aliases,
         )
         self.assertEqual(d[0][0], "sop-revoke")
         self.assertEqual(d[0][1], "comprehensive-testing")
@@ -174,7 +171,7 @@ class TestParseDirectives(unittest.TestCase):
             "/sop-ack comprehensive-testing\n"
             "Will follow up on the doc nit separately."
         )
-        d = self.parse_ack_revoke(body)
+        d = sop.parse_directives(body, self.aliases)
         self.assertEqual(len(d), 1)
         self.assertEqual(d[0][1], "comprehensive-testing")
 
@@ -183,7 +180,7 @@ class TestParseDirectives(unittest.TestCase):
             "/sop-ack comprehensive-testing\n"
             "/sop-ack local-postgres-e2e\n"
         )
-        d = self.parse_ack_revoke(body)
+        d = sop.parse_directives(body, self.aliases)
         self.assertEqual(len(d), 2)
         slugs = {x[1] for x in d}
         self.assertEqual(slugs, {"comprehensive-testing", "local-postgres-e2e"})
@@ -192,21 +189,21 @@ class TestParseDirectives(unittest.TestCase):
         # A directive embedded mid-line is not honored (prevents review
         # comments like "to /sop-ack you need..." from acting as acks).
         body = "If you want to /sop-ack comprehensive-testing reply in this thread"
-        d = self.parse_ack_revoke(body)
+        d = sop.parse_directives(body, self.aliases)
         self.assertEqual(d, [])
 
     def test_leading_whitespace_allowed(self):
         body = "  /sop-ack comprehensive-testing"
-        d = self.parse_ack_revoke(body)
+        d = sop.parse_directives(body, self.aliases)
         self.assertEqual(len(d), 1)
 
     def test_empty_body(self):
-        self.assertEqual(sop.parse_directives("", self.aliases), ([], []))
-        self.assertEqual(sop.parse_directives(None, self.aliases), ([], []))
+        self.assertEqual(sop.parse_directives("", self.aliases), [])
+        self.assertEqual(sop.parse_directives(None, self.aliases), [])
 
     def test_normalization_applied(self):
         # /sop-ack Comprehensive_Testing → canonical comprehensive-testing
-        d = self.parse_ack_revoke("/sop-ack Comprehensive_Testing")
+        d = sop.parse_directives("/sop-ack Comprehensive_Testing", self.aliases)
         self.assertEqual(d[0][1], "comprehensive-testing")
 
 

.gitea/scripts/tests/test_sop_tier_refire.sh

@@ -32,7 +32,6 @@ THIS_DIR="$(cd "$(dirname "$0")" && pwd)"
 SCRIPT_DIR="$(cd "$THIS_DIR/.." && pwd)"
 WORKFLOW_DIR="$(cd "$THIS_DIR/../../workflows" && pwd)"
 WORKFLOW="$WORKFLOW_DIR/sop-tier-refire.yml"
-DISPATCH_WORKFLOW="$WORKFLOW_DIR/review-refire-comments.yml"
 SCRIPT="$SCRIPT_DIR/sop-tier-refire.sh"
 
 PASS=0
@@ -88,7 +87,6 @@ assert_file_exists() {
 echo
 echo "== existence =="
 assert_file_exists "workflow file exists"  "$WORKFLOW"
-assert_file_exists "dispatcher workflow file exists" "$DISPATCH_WORKFLOW"
 assert_file_exists "script file exists"    "$SCRIPT"
 if [ "$FAIL" -gt 0 ]; then
   echo
@@ -106,44 +104,30 @@ echo "== T6/T7 workflow yaml =="
 PARSE_OUT=$(python3 -c 'import sys,yaml;yaml.safe_load(open(sys.argv[1]).read());print("ok")' "$WORKFLOW" 2>&1 || true)
 assert_eq "T7 workflow parses as YAML" "ok" "$PARSE_OUT"
 
-# The old per-workflow issue_comment listener caused queue storms because
-# Gitea queues jobs before evaluating job-level `if:`. The script remains,
-# but comment-triggered refires route through the single dispatcher.
+# Three required gates in the `if:` expression
 WORKFLOW_CONTENT=$(cat "$WORKFLOW")
-if printf '%s' "$WORKFLOW_CONTENT" | grep -q '^  issue_comment:'; then
-  echo "  FAIL  T6a manual fallback workflow must not listen on issue_comment"
-  FAIL=$((FAIL + 1))
-  FAILED_TESTS="${FAILED_TESTS} T6a"
-else
-  echo "  PASS  T6a manual fallback workflow does not listen on issue_comment"
-  PASS=$((PASS + 1))
-fi
-assert_contains "T6b workflow exposes workflow_dispatch" \
-  "workflow_dispatch" "$WORKFLOW_CONTENT"
-assert_contains "T6c workflow documents unsupported manual inputs" \
-  "workflow_dispatch inputs" "$WORKFLOW_CONTENT"
+assert_contains "T6a workflow if: contains author_association gate" \
+  "github.event.comment.author_association" "$WORKFLOW_CONTENT"
+assert_contains "T6b workflow if: gates on MEMBER/OWNER/COLLABORATOR" \
+  '["MEMBER","OWNER","COLLABORATOR"]' "$WORKFLOW_CONTENT"
+assert_contains "T6c workflow if: contains slash-command trigger" \
+  "/refire-tier-check" "$WORKFLOW_CONTENT"
+assert_contains "T6d workflow if: gates on PR-not-issue" \
+  "github.event.issue.pull_request" "$WORKFLOW_CONTENT"
+assert_contains "T6e workflow listens on issue_comment" \
+  "issue_comment" "$WORKFLOW_CONTENT"
+assert_contains "T6f workflow requests statuses:write permission" \
+  "statuses: write" "$WORKFLOW_CONTENT"
 # Does NOT check out PR HEAD (security)
 if grep -q 'ref: \${{ github.event.pull_request.head' "$WORKFLOW"; then
-  echo "  FAIL  T6d workflow MUST NOT check out PR head (security)"
+  echo "  FAIL  T6g workflow MUST NOT check out PR head (security)"
   FAIL=$((FAIL + 1))
-  FAILED_TESTS="${FAILED_TESTS} T6d"
+  FAILED_TESTS="${FAILED_TESTS} T6g"
 else
-  echo "  PASS  T6d workflow does not check out PR head"
+  echo "  PASS  T6g workflow does not check out PR head"
   PASS=$((PASS + 1))
 fi
 
-DISPATCH_PARSE_OUT=$(python3 -c 'import sys,yaml;yaml.safe_load(open(sys.argv[1]).read());print("ok")' "$DISPATCH_WORKFLOW" 2>&1 || true)
-assert_eq "T6e dispatcher workflow parses as YAML" "ok" "$DISPATCH_PARSE_OUT"
-DISPATCH_CONTENT=$(cat "$DISPATCH_WORKFLOW")
-assert_contains "T6f dispatcher listens on issue_comment" \
-  "issue_comment" "$DISPATCH_CONTENT"
-assert_contains "T6g dispatcher handles /qa-recheck" \
-  "/qa-recheck" "$DISPATCH_CONTENT"
-assert_contains "T6h dispatcher handles /security-recheck" \
-  "/security-recheck" "$DISPATCH_CONTENT"
-assert_contains "T6i dispatcher handles /refire-tier-check" \
-  "/refire-tier-check" "$DISPATCH_CONTENT"
-
 # T1-T5 — script behavior against a local Gitea-fixture
 echo
 echo "== T1-T5 script behavior (vs local fixture) =="

.gitea/sop-checklist-config.yaml

@@ -107,39 +107,3 @@ items:
     description: >-
       List of feedback memories applicable to this change. Ack from
       any engineer who has the same memory access.
-
-# N/A gate declarations (RFC#324 §N/A follow-up).
-# PRs where a gate genuinely does not apply (e.g., pure-infra with no
-# qa surface, or docs-only) can be declared N/A by a non-author peer
-# who is in one of the gate's required_teams. The sop-checklist
-# posts a `sop-checklist / na-declarations (pull_request)` status that
-# review-check.sh reads to skip the Gitea-APPROVE requirement.
-#
-# Usage: any PR commenter (peer) posts:
-#   /sop-n/a qa-review  <reason>
-#   /sop-n/a security-review  <reason>
-#
-# Slash commands:
-#   /sop-n/a <gate> [reason] — declare gate N/A (most-recent per-user wins)
-#   /sop-revoke <gate>      — revoke prior N/A declaration for that gate
-#
-# Gate names must match the context strings used by review-check.sh:
-#   qa-review      → qa-review / approved (<event>)        [TEAM_ID=20]
-#   security-review → security-review / approved (<event>)  [TEAM_ID=21]
-#
-# required_teams: OR semantics — any team member can declare N/A.
-# Authors cannot self-declare N/A (enforced by gate script).
-n/a_gates:
-  qa-review:
-    required_teams: [qa, security, engineers]
-    description: >-
-      QA review N/A when this change has no qa surface (pure-infra,
-      tooling-only, revert, dependency-only). A qa/eng/security member
-      must post /sop-n/a qa-review to activate.
-
-  security-review:
-    required_teams: [security, managers, ceo]
-    description: >-
-      Security review N/A when this change has no security surface
-      (docs-only, pure-frontend, dependency-only). A security/owners
-      member must post /sop-n/a security-review to activate.

.gitea/workflows/ci.yml

@@ -107,25 +107,16 @@ jobs:
             echo "scripts=true" >> "$GITHUB_OUTPUT"
             exit 0
           fi
-          # Workflow-only edits are covered by the workflow lint family
-          # and by this workflow's always-present required jobs. Do not fan
-          # those edits out into Go/Canvas/Python/shellcheck work; the
-          # downstream jobs still emit their required contexts via no-op
-          # steps when their surface flag is false.
-          #
-          # If the diff itself cannot be trusted, fail open by running every
-          # surface instead of silently under-testing the PR.
-          if ! DIFF=$(git diff --name-only "$BASE" HEAD 2>/dev/null); then
-            echo "platform=true" >> "$GITHUB_OUTPUT"
-            echo "canvas=true" >> "$GITHUB_OUTPUT"
-            echo "python=true" >> "$GITHUB_OUTPUT"
-            echo "scripts=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          echo "platform=$(echo "$DIFF" | grep -qE '^workspace-server/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
-          echo "canvas=$(echo "$DIFF" | grep -qE '^canvas/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
-          echo "python=$(echo "$DIFF" | grep -qE '^workspace/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
-          echo "scripts=$(echo "$DIFF" | grep -qE '^tests/e2e/|^scripts/|^infra/scripts/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
+          # Both .github/workflows/ci.yml AND .gitea/workflows/ci.yml count
+          # as "this workflow changed" — either edit should force-run every
+          # downstream job. The Gitea port follows the same shape as the
+          # GitHub original so behavior matches when triggered on either
+          # platform.
+          DIFF=$(git diff --name-only "$BASE" HEAD 2>/dev/null || echo ".gitea/workflows/ci.yml")
+          echo "platform=$(echo "$DIFF" | grep -qE '^workspace-server/|^\.gitea/workflows/ci\.yml$|^\.github/workflows/ci\.yml$' && echo true || echo false)" >> "$GITHUB_OUTPUT"
+          echo "canvas=$(echo "$DIFF" | grep -qE '^canvas/|^\.gitea/workflows/ci\.yml$|^\.github/workflows/ci\.yml$' && echo true || echo false)" >> "$GITHUB_OUTPUT"
+          echo "python=$(echo "$DIFF" | grep -qE '^workspace/|^\.gitea/workflows/ci\.yml$|^\.github/workflows/ci\.yml$' && echo true || echo false)" >> "$GITHUB_OUTPUT"
+          echo "scripts=$(echo "$DIFF" | grep -qE '^tests/e2e/|^scripts/|^infra/scripts/|^\.gitea/workflows/ci\.yml$|^\.github/workflows/ci\.yml$' && echo true || echo false)" >> "$GITHUB_OUTPUT"
 
   # Platform (Go) — Go build/vet/test/lint + coverage gates. The always-run
   # + per-step gating shape preserves the GitHub-side required-check name
@@ -133,49 +124,59 @@ jobs:
   # the name match works on PRs that don't touch workspace-server/).
   platform-build:
     name: Platform (Go)
+    needs: changes
     runs-on: ubuntu-latest
-    # mc#774 (closed 2026-05-14): Phase 4 flip of the platform-build job.
-    # Phase 4 (#656) originally flipped this to continue-on-error: false based on
-    # Phase-3-masked "green on main 2026-05-12". Two failure classes then surfaced:
-    #   (1) 4x delegation_test.go sqlmock gaps (PR #669 / #634 fix-forward, closed).
-    #   (2) TestMCPHandler_CommitMemory_GlobalScope_Blocked (mcp_test.go:433):
-    #       OFFSEC-001 hardening collided with test assertion; tracked in mc#762.
-    # Fix-forward for (1) landed in PR #669. The mc#762 gap (2) is a separate
-    # issue — it does NOT block this flip because the test is already wrapped in
-    # the diagnostic step with its own continue-on-error: true (line 203).
-    # Flip confirmed by CI / Platform (Go) status = success on main HEAD 363905d3.
-    continue-on-error: false
-    # Job-level ceiling. The go test step below runs with a per-step 10m timeout;
-    # this cap catches any step that leaks past that. Set well above 10m so
-    # the per-step timeout is the active constraint.
-    timeout-minutes: 15
+    # mc#774 (interim): re-mask platform-build pending fix-forward. Phase 4
+    # (#656) flipped this to continue-on-error: false based on a Phase-3-masked
+    # "green on main 2026-05-12" — the prior continue-on-error: true had
+    # been hiding failing tests in workspace-server/internal/handlers/.
+    # Two distinct failure classes surfaced on 0e5152c3:
+    #   (1) 4x delegation_test.go (lines 1110/1176/1228/1271): helpers
+    #       expectExecuteDelegationBase/Success/Failed are missing sqlmock
+    #       expectations for queries production has issued since ~2026-04-21
+    #       (last_outbound_at UPDATE, lookupDeliveryMode/Runtime SELECTs,
+    #       a2a_receive INSERT activity_logs, recordLedgerStatus writes).
+    #       Halt cond #3 applies (regression > 7 days → broader sweep).
+    #   (2) 1x mcp_test.go:433 (TestMCPHandler_CommitMemory_GlobalScope_Blocked):
+    #       commit 7d1a189f (2026-05-10) hardened mcp.go to scrub err.Error()
+    #       from JSON-RPC responses (OFFSEC-001), but the test asserts the
+    #       error message contains "GLOBAL". Production-vs-test contract
+    #       collision — needs design call, not mock update.
+    # Time-boxed Option A (90 min) did not fit the cross-cutting scope.
+    # This is a sequenced revert→fix→reflip per
+    # feedback_strict_root_only_after_class_a emergency clause — NOT
+    # a permanent re-mask. Re-flip blocked on mc#774 fix-forward landing.
+    # Other 4 #656 flips (changes, canvas-build, shellcheck, python-lint)
+    # retain continue-on-error: false; only platform-build regresses.
+    # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
+    continue-on-error: true  # mc#774 fix-forward in flight; re-flip when mc#774 lands (PR #669 → rebase after #709)
     defaults:
       run:
         working-directory: workspace-server
     steps:
-      - if: false
+      - if: needs.changes.outputs.platform != 'true'
         working-directory: .
         run: echo "No platform/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
         with:
           go-version: 'stable'
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         run: go mod download
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         run: go build ./cmd/server
       # CLI (molecli) moved to standalone repo: git.moleculesai.app/molecule-ai/molecule-cli
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         run: go vet ./...
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         name: Install golangci-lint
         run: go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@v2.12.2
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         name: Run golangci-lint
         run: $(go env GOPATH)/bin/golangci-lint run --timeout 3m ./...
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         name: Diagnostic — per-package verbose 60s
         run: |
           set +e
@@ -191,15 +192,11 @@ jobs:
           echo "::endgroup::"
         # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
         continue-on-error: true
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         name: Run tests with race detection and coverage
-        # Explicit timeout: cold runner cache causes OOM kills at ~4m39s on the
-        # full ./... suite with race detection + coverage. A 10m per-step timeout
-        # lets the suite complete on cold cache (~5-7m) while failing cleanly
-        # instead of OOM-killing. The job-level timeout (15m) is a backstop.
-        run: go test -race -timeout 10m -coverprofile=coverage.out ./...
+        run: go test -race -coverprofile=coverage.out ./...
 
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         name: Per-file coverage report
         # Advisory — lists every source file with its coverage so reviewers
         # can see at-a-glance where gaps are. Sorted ascending so the worst
@@ -213,7 +210,7 @@ jobs:
                    END {for (f in s) printf "%6.1f%%  %s\n", s[f]/c[f], f}' \
             | sort -n
 
-      - if: always()
+      - if: needs.changes.outputs.platform == 'true'
         name: Check coverage thresholds
         # Enforces two gates from #1823 Layer 1:
         #   1. Total floor (25% — ratchet plan in COVERAGE_FLOOR.md).
@@ -301,28 +298,28 @@ jobs:
   # siblings — verified empirically on PR #2314).
   canvas-build:
     name: Canvas (Next.js)
+    needs: changes
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     # Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
     continue-on-error: false
     defaults:
       run:
         working-directory: canvas
     steps:
-      - if: false
+      - if: needs.changes.outputs.canvas != 'true'
         working-directory: .
         run: echo "No canvas/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
-      - if: always()
+      - if: needs.changes.outputs.canvas == 'true'
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - if: always()
+      - if: needs.changes.outputs.canvas == 'true'
         uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: '22'
-      - if: always()
+      - if: needs.changes.outputs.canvas == 'true'
         run: rm -f package-lock.json && npm install
-      - if: always()
+      - if: needs.changes.outputs.canvas == 'true'
         run: npm run build
-      - if: always()
+      - if: needs.changes.outputs.canvas == 'true'
         name: Run tests with coverage
         # Coverage instrumentation is configured in canvas/vitest.config.ts
         # (provider: v8, reporters: text + html + json-summary). Step 2 of
@@ -331,7 +328,7 @@ jobs:
         # tracked in #1815) after the team sees what current coverage is.
         run: npx vitest run --coverage
       - name: Upload coverage summary as artifact
-        if: always()
+        if: needs.changes.outputs.canvas == 'true' && always()
         # Pinned to v3 for Gitea act_runner v0.6 compatibility — v4+ uses
         # the GHES 3.10+ artifact protocol that Gitea 1.22.x does NOT
         # implement, surfacing as `GHESNotSupportedError: @actions/artifact
@@ -348,15 +345,16 @@ jobs:
   # Shellcheck (E2E scripts) — required check, always runs.
   shellcheck:
     name: Shellcheck (E2E scripts)
+    needs: changes
     runs-on: ubuntu-latest
     # Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
     continue-on-error: false
     steps:
-      - if: false
+      - if: needs.changes.outputs.scripts != 'true'
         run: echo "No tests/e2e/ or infra/scripts/ changes — skipping real shellcheck; this job always runs to satisfy the required-check name on branch protection."
-      - if: always()
+      - if: needs.changes.outputs.scripts == 'true'
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - if: always()
+      - if: needs.changes.outputs.scripts == 'true'
         name: Run shellcheck on tests/e2e/*.sh and infra/scripts/*.sh
         # shellcheck is pre-installed on ubuntu-latest runners (via apt).
         # infra/scripts/ is included because setup.sh + nuke.sh gate the
@@ -367,61 +365,32 @@ jobs:
           find tests/e2e infra/scripts -type f -name '*.sh' -print0 \
             | xargs -0 shellcheck --severity=warning
 
-      - if: always()
+      - if: needs.changes.outputs.scripts == 'true'
         name: Lint cleanup-trap hygiene (RFC #2873)
         run: bash tests/e2e/lint_cleanup_traps.sh
 
-      - if: always()
+      - if: needs.changes.outputs.scripts == 'true'
         name: Run E2E bash unit tests (no live infra)
         run: |
           bash tests/e2e/test_model_slug.sh
 
-      - if: always()
-        name: Test ECR promote-tenant-image script (mock-driven, no live infra)
-        # Covers scripts/promote-tenant-image.sh — the codified
-        # :staging-latest → :latest ECR promote + tenant fleet redeploy
-        # closing molecule-ai/molecule-core#660. 40 mock-driven cases
-        # exercise every exit path (preflight, snapshot, promote, redeploy
-        # 403→SSM-refresh, verify, rollback). No live AWS/CP/SSM calls.
-        run: |
-          bash scripts/test-promote-tenant-image.sh
-
-      - if: always()
-        name: Shellcheck promote-tenant-image script
-        # scripts/ is excluded from the bulk shellcheck pass above (legacy
-        # SC3040/SC3043 cleanup pending). Run shellcheck explicitly on
-        # the promote script + its test harness so regressions there are
-        # caught by the required check.
-        run: |
-          shellcheck --severity=warning \
-            scripts/promote-tenant-image.sh \
-            scripts/test-promote-tenant-image.sh
-
   canvas-deploy-reminder:
     name: Canvas Deploy Reminder
     runs-on: ubuntu-latest
-    # This job must run on PRs because all-required needs it. The step exits
-    # 0 when it is not a main push, giving branch protection a green no-op
-    # instead of a skipped/missing required dependency.
-    needs: canvas-build
+    # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
+    continue-on-error: true
+    needs: [changes, canvas-build]
+    # Only fires on direct pushes to main (i.e. after staging→main promotion).
+    if: needs.changes.outputs.canvas == 'true' && github.event_name == 'push' && github.ref == 'refs/heads/main'
     steps:
       - name: Write deploy reminder to step summary
         env:
           COMMIT_SHA: ${{ github.sha }}
-          CANVAS_CHANGED: "true"
-          EVENT_NAME: ${{ github.event_name }}
-          REF_NAME: ${{ github.ref }}
           # github.server_url resolves via the workflow-level env override
           # to the Gitea instance, so the RUN_URL points at the Gitea run
           # page (not github.com). See feedback_act_runner_github_server_url.
           RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
         run: |
-          set -euo pipefail
-          if [ "$CANVAS_CHANGED" != "true" ] || [ "$EVENT_NAME" != "push" ] || [ "$REF_NAME" != "refs/heads/main" ]; then
-            echo "Canvas deploy reminder not applicable for event=$EVENT_NAME ref=$REF_NAME canvas_changed=$CANVAS_CHANGED."
-            exit 0
-          fi
-
           # Write body to a temp file — avoids backtick escaping in shell.
           cat > /tmp/deploy-reminder.md << 'BODY'
           ## Canvas build passed — deploy required
@@ -453,6 +422,7 @@ jobs:
   # Python Lint & Test — required check, always runs.
   python-lint:
     name: Python Lint & Test
+    needs: changes
     runs-on: ubuntu-latest
     # Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
     continue-on-error: false
@@ -462,25 +432,25 @@ jobs:
       run:
         working-directory: workspace
     steps:
-      - if: false
+      - if: needs.changes.outputs.python != 'true'
         working-directory: .
         run: echo "No workspace/** changes — skipping real lint+test; this job always runs to satisfy the required-check name on branch protection."
-      - if: always()
+      - if: needs.changes.outputs.python == 'true'
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - if: always()
+      - if: needs.changes.outputs.python == 'true'
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: '3.11'
           cache: pip
           cache-dependency-path: workspace/requirements.txt
-      - if: always()
+      - if: needs.changes.outputs.python == 'true'
         run: pip install -r requirements.txt pytest pytest-asyncio pytest-cov sqlalchemy>=2.0.0
       # Coverage flags + fail-under floor moved into workspace/pytest.ini
       # (issue #1817) so local `pytest` and CI use identical config.
-      - if: always()
+      - if: needs.changes.outputs.python == 'true'
         run: python -m pytest --tb=short
 
-      - if: always()
+      - if: needs.changes.outputs.python == 'true'
         name: Per-file critical-path coverage (MCP / inbox / auth)
         # MCP-critical Python files have a per-file floor on top of the
         # 86% total floor in pytest.ini. See issue #2790 for full rationale.
@@ -545,104 +515,85 @@ jobs:
     # red silently merged through. See internal#286 for the three concrete
     # tonight-of-2026-05-11 incidents that prompted the emergency bump.
     #
-    # This job deliberately has no `needs:`. Gitea 1.22/act_runner can mark a
-    # job-level `if: always()` + `needs:` sentinel as skipped before upstream
-    # jobs settle, leaving branch protection with a permanent pending
-    # `CI / all-required` context. Instead, this independent sentinel polls the
-    # required commit-status contexts for this SHA and fails if any fail, skip,
-    # or never emit.
+    # Three properties of this job each close a failure mode:
     #
-    # canvas-deploy-reminder is intentionally NOT included in all-required.needs.
-    # It is an informational main-push reminder, not a PR quality gate. Keeping
-    # it in this dependency list lets a skipped reminder skip the required
-    # sentinel before the `always()` guard can emit a branch-protection status.
+    #  1. `if: always()` — runs even when an upstream fails. Without it the
+    #     sentinel is `skipped` and protection treats that as missing → merge
+    #     ungated.
     #
+    #  2. Assertion is `result == "success"` per dep, NOT `!= "failure"`.
+    #     A `skipped` upstream (job gated by `if:` evaluating false, matrix
+    #     entry that couldn't run) must NOT silently pass through.
+    #     `skipped`-as-green is exactly the failure mode this gate closes.
+    #
+    #  3. `needs:` is the canonical list of "what counts as required."
+    #     status_check_contexts will reference only `ci/all-required` (Step 5
+    #     follow-up — branch-protection PATCH is Owners-tier per
+    #     `feedback_never_admin_merge_bypass`, separate PR); a new job is
+    #     added simply by listing it in `needs:` here.
+    #     `.gitea/workflows/ci-required-drift.yml` files a [ci-drift] issue
+    #     hourly if this list diverges from status_check_contexts or from
+    #     audit-force-merge.yml's REQUIRED_CHECKS env (RFC §4 + §6).
+    #
+    # Excluded from `needs:`: `canvas-deploy-reminder` — gated by
+    # `if: ... github.event_name == 'push' && github.ref == 'refs/heads/main'`,
+    # so on PR events it's legitimately `skipped`. The drift detector
+    # explicitly excludes `github.event_name`-gated jobs from F1 (see
+    # `.gitea/scripts/ci-required-drift.py::ci_job_names`).
+    #
+    # Phase 3 (RFC #219 §1) safety: underlying build jobs carry
+    # continue-on-error: true so their failures are masked to null (2026-05-12: re-enabled mc#774 interim)
+    # (Gitea suppresses status reporting for CoE jobs). This sentinel
+    # runs with continue-on-error: false so it always reports its
+    # result to the API — without this, the required-status entry
+    # (CI / all-required (pull_request)) is never created, which
+    # blocks PR merges. When Phase 3 ends, flip underlying jobs to
+    # continue-on-error: false; this sentinel can then be flipped to
+    # continue-on-error: true if a Phase-4 regression requires it.
     continue-on-error: false
     runs-on: ubuntu-latest
-    timeout-minutes: 45
+    timeout-minutes: 1
+    needs:
+      - changes
+      - platform-build
+      - canvas-build
+      - shellcheck
+      - python-lint
+    if: always()
     steps:
-      - name: Wait for required CI contexts
-        env:
-          GITEA_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          API_ROOT: ${{ github.server_url }}/api/v1
-          REPOSITORY: ${{ github.repository }}
-          COMMIT_SHA: ${{ github.sha }}
-          EVENT_NAME: ${{ github.event_name }}
+      - name: Assert every required dependency succeeded
         run: |
           set -euo pipefail
-          python3 - <<'PY'
-          import json
-          import os
-          import sys
-          import time
-          import urllib.error
-          import urllib.request
-
-          token = os.environ["GITEA_TOKEN"]
-          api_root = os.environ["API_ROOT"].rstrip("/")
-          repo = os.environ["REPOSITORY"]
-          sha = os.environ["COMMIT_SHA"]
-          event = os.environ["EVENT_NAME"]
-          required = [
-              f"CI / Detect changes ({event})",
-              f"CI / Platform (Go) ({event})",
-              f"CI / Canvas (Next.js) ({event})",
-              f"CI / Shellcheck (E2E scripts) ({event})",
-              f"CI / Python Lint & Test ({event})",
-          ]
-          terminal_bad = {"failure", "error"}
-          deadline = time.time() + 40 * 60
-          last_summary = None
-
-          def fetch_statuses():
-              statuses = []
-              for page in range(1, 6):
-                  url = f"{api_root}/repos/{repo}/commits/{sha}/statuses?page={page}&limit=100"
-                  req = urllib.request.Request(url, headers={"Authorization": f"token {token}"})
-                  with urllib.request.urlopen(req, timeout=10) as resp:
-                      chunk = json.load(resp)
-                  if not chunk:
-                      break
-                  statuses.extend(chunk)
-              latest = {}
-              for item in statuses:
-                  ctx = item.get("context")
-                  if not ctx:
-                      continue
-                  prev = latest.get(ctx)
-                  if prev is None or (item.get("updated_at") or item.get("created_at") or "") >= (prev.get("updated_at") or prev.get("created_at") or ""):
-                      latest[ctx] = item
-              return latest
-
-          while True:
-              try:
-                  latest = fetch_statuses()
-              except (TimeoutError, OSError, urllib.error.URLError) as exc:
-                  if time.time() >= deadline:
-                      print(f"FAIL: status polling did not recover before deadline: {exc}", file=sys.stderr)
-                      sys.exit(1)
-                  print(f"WARN: status poll failed, retrying: {exc}", flush=True)
-                  time.sleep(15)
-                  continue
-              states = {ctx: (latest.get(ctx) or {}).get("status") or (latest.get(ctx) or {}).get("state") or "missing" for ctx in required}
-              summary = ", ".join(f"{ctx}={state}" for ctx, state in states.items())
-              if summary != last_summary:
-                  print(summary, flush=True)
-                  last_summary = summary
-              bad = {ctx: state for ctx, state in states.items() if state in terminal_bad}
-              if bad:
-                  print("FAIL: required CI context failed:", file=sys.stderr)
-                  for ctx, state in bad.items():
-                      desc = (latest.get(ctx) or {}).get("description") or ""
-                      print(f"  - {ctx}: {state} {desc}", file=sys.stderr)
-                  sys.exit(1)
-              if all(state == "success" for state in states.values()):
-                  print(f"OK: all {len(required)} required CI contexts succeeded")
-                  sys.exit(0)
-              if time.time() >= deadline:
-                  print("FAIL: timed out waiting for required CI contexts:", file=sys.stderr)
-                  for ctx, state in states.items():
-                      print(f"  - {ctx}: {state}", file=sys.stderr)
-                  sys.exit(1)
-              time.sleep(15)
-          PY
+          # `needs.*.result` is one of: success | failure | cancelled | skipped | null.
+          # We assert success per dep (not != failure) — see RFC §2 reasoning above.
+          # Null results are skipped: they come from Phase 3 (continue-on-error: true
+          # suppresses status) or from jobs still in-flight. The sentinel succeeds
+          # rather than blocking PRs on Phase 3 noise.
+          results='${{ toJSON(needs) }}'
+          echo "$results"
+          echo "$results" | python3 -c '
+          import json, sys
+          ns = json.load(sys.stdin)
+          # Phase 3 masked: jobs with continue-on-error: true may report "failure"
+          # Remove when mc#774 handler test failures are resolved.
+          PHASE3_MASKED = {"platform-build"}
+          # Exclude null (Phase 3 suppressed / in-flight) from the bad list.
+          bad = [(k, v.get("result")) for k, v in ns.items()
+                 if v.get("result") not in ("success", None, "cancelled", "skipped") and k not in PHASE3_MASKED]
+          if bad:
+              print(f"FAIL: jobs not green:", file=sys.stderr)
+              for k, r in bad:
+                  print(f"  - {k}: {r}", file=sys.stderr)
+              sys.exit(1)
+          pending = [(k, v.get("result")) for k, v in ns.items()
+                     if v.get("result") is None]
+          cancelled = [(k, v.get("result")) for k, v in ns.items()
+                       if v.get("result") == "cancelled"]
+          if pending:
+              print(f"WARN: {len(pending)} job(s) still in-flight (result=null): " +
+                    ", ".join(k for k, _ in pending), file=sys.stderr)
+          if cancelled:
+              print(f"INFO: {len(cancelled)} job(s) masked by continue-on-error: " +
+                    ", ".join(k for k, _ in cancelled), file=sys.stderr)
+          print(f"OK: all {len(ns)} required jobs succeeded (or Phase-3 suppressed)")
+          '

.gitea/workflows/e2e-api.yml

@@ -69,13 +69,6 @@ name: E2E API Smoke Test
 # 2318) shows Postgres ready in 3s, Redis in 1s, Platform in 1s when
 # they DO come up. Timeouts are not the bottleneck; not bumped.
 #
-# Item #1046 (fixed 2026-05-14): Stale platform-server from cancelled runs
-#   lingers on :8080 after "Stop platform" step is skipped (workflow cancelled
-#   before reaching line 335). Added a pre-start "Kill stale platform-server"
-#   step (line 286) that scans /proc for zombie platform-server processes
-#   and kills them before the port probe or bind. Makes the ephemeral port
-#   probe + start sequence deterministic.
-#
 # Item explicitly NOT fixed here: failing test `Status back online`
 # fails because the platform's langgraph workspace template image
 # (ghcr.io/molecule-ai/workspace-template-langgraph:latest) returns
@@ -290,35 +283,6 @@ jobs:
           echo "PORT=${PLATFORM_PORT}" >> "$GITHUB_ENV"
           echo "BASE=http://127.0.0.1:${PLATFORM_PORT}" >> "$GITHUB_ENV"
           echo "Platform host port: ${PLATFORM_PORT}"
-      - name: Kill stale platform-server before start (issue #1046)
-        if: needs.detect-changes.outputs.api == 'true'
-        run: |
-          # Concurrent runs on the same host-network act_runner can leave a
-          # zombie platform-server from a cancelled/timeout run. Cancelled
-          # runs never reach the "Stop platform" step (line 335), so the
-          # old process lingers. Kill it before the ephemeral port probe
-          # or start so the port is definitively free.
-          #
-          # /proc scan — works on any Linux without pkill/lsof/ss.
-          # comm field is truncated to 15 chars: "platform-serve" matches
-          # "platform-server". Verify with cmdline to avoid false positives.
-          killed=0
-          for pid in $(grep -l "platform-serve" /proc/[0-9]*/comm 2>/dev/null); do
-            kpid="${pid%/comm}"
-            kpid="${kpid##*/}"
-            cmdline=$(cat "/proc/${kpid}/cmdline" 2>/dev/null | tr '\0' ' ')
-            if echo "$cmdline" | grep -q "platform-server"; then
-              echo "Killing stale platform-server pid ${kpid}: ${cmdline}"
-              kill "$kpid" 2>/dev/null || true
-              killed=$((killed + 1))
-            fi
-          done
-          if [ "$killed" -gt 0 ]; then
-            sleep 2
-            echo "Killed $killed stale process(es); port(s) released."
-          else
-            echo "No stale platform-server found."
-          fi
       - name: Start platform (background)
         if: needs.detect-changes.outputs.api == 'true'
         working-directory: workspace-server
@@ -382,4 +346,3 @@ jobs:
         run: |
           docker rm -f "$PG_CONTAINER" 2>/dev/null || true
           docker rm -f "$REDIS_CONTAINER" 2>/dev/null || true
-

.gitea/workflows/gate-check-v3.yml

@@ -83,41 +83,25 @@ jobs:
           REPO: ${{ github.repository }}
         run: |
           set -euo pipefail
-          # Fetch all open PRs and run gate-check on each. This scheduled
-          # refresher is advisory; a transient Gitea list timeout must not turn
-          # main red. PR-specific gate-check runs still use normal failure
-          # semantics.
+          # Fetch all open PRs and run gate-check on each
+          # socket.setdefaulttimeout(15): defence-in-depth for missing SOP_TIER_CHECK_TOKEN.
+          # gate_check.py uses timeout=15 on every urlopen call; this catches the
+          # inline Python polling loop too (issue #603).
           pr_numbers=$(python3 <<'PY'
           import json
           import os
           import socket
-          import sys
-          import time
-          import urllib.error
           import urllib.request
 
-          socket.setdefaulttimeout(30)
+          socket.setdefaulttimeout(15)
           token = os.environ["GITEA_TOKEN"]
           repo = os.environ["REPO"]
-          url = f"https://git.moleculesai.app/api/v1/repos/{repo}/pulls?state=open&limit=100"
-          last_error = None
-          for attempt in range(1, 4):
-              req = urllib.request.Request(
-                  url,
-                  headers={"Authorization": f"token {token}", "Accept": "application/json"},
-              )
-              try:
-                  with urllib.request.urlopen(req, timeout=30) as r:
-                      prs = json.loads(r.read())
-                  break
-              except (TimeoutError, OSError, urllib.error.URLError, urllib.error.HTTPError) as exc:
-                  last_error = exc
-                  print(f"warning: PR list fetch attempt {attempt}/3 failed: {exc}", file=sys.stderr)
-                  if attempt < 3:
-                      time.sleep(2 * attempt)
-          else:
-              print(f"warning: skipped scheduled gate-check refresh; failed to list open PRs after 3 attempts: {last_error}", file=sys.stderr)
-              raise SystemExit(0)
+          req = urllib.request.Request(
+              f"https://git.moleculesai.app/api/v1/repos/{repo}/pulls?state=open&limit=100",
+              headers={"Authorization": f"token {token}", "Accept": "application/json"},
+          )
+          with urllib.request.urlopen(req) as r:
+              prs = json.loads(r.read())
           for pr in prs:
               print(pr["number"])
           PY

.gitea/workflows/gitea-merge-queue.yml

@@ -48,9 +48,4 @@ jobs:
           REQUIRED_CONTEXTS: >-
             CI / all-required (pull_request),
             sop-checklist / all-items-acked (pull_request)
-          # Push-side required contexts. Checking CI / all-required (push)
-          # explicitly instead of the combined state avoids false-pause when
-          # non-blocking jobs (continue-on-error: true) have failed — those
-          # failures pollute combined state but do not gate merges.
-          PUSH_REQUIRED_CONTEXTS: CI / all-required (push)
         run: python3 .gitea/scripts/gitea-merge-queue.py

.gitea/workflows/handlers-postgres-integration.yml

@@ -86,33 +86,22 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
-          # A full-history checkout can exceed the runner's quiet/startup
-          # window before the path filter emits logs. Fetch the common push
-          # case cheaply; the script below fetches the exact BASE SHA if it is
-          # not present in the shallow checkout.
-          fetch-depth: 2
+          fetch-depth: 0
       - id: filter
         # Inline replacement for dorny/paths-filter — see e2e-api.yml.
         run: |
-          # Gitea Actions evaluates github.event.before to empty string in shell
-          # scripts. Use GITHUB_EVENT_BEFORE shell env var instead (Gitea
-          # correctly populates it for push events). PR case uses template var.
-          BASE=""
+          BASE="${GITHUB_BASE_REF:-${{ github.event.before }}}"
           if [ "${{ github.event_name }}" = "pull_request" ] && [ -n "${{ github.event.pull_request.base.sha }}" ]; then
             BASE="${{ github.event.pull_request.base.sha }}"
-          elif [ -n "$GITHUB_EVENT_BEFORE" ]; then
-            BASE="$GITHUB_EVENT_BEFORE"
           fi
           if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$'; then
             echo "handlers=true" >> "$GITHUB_OUTPUT"
             exit 0
           fi
-          # timeout 30 guards against the case where BASE points to a ref that
-          # git can resolve but cat-file hangs (rare on corrupted objects).
-          if ! timeout 30 git cat-file -e "$BASE" 2>/dev/null; then
+          if ! git cat-file -e "$BASE" 2>/dev/null; then
             git fetch --depth=1 origin "$BASE" 2>/dev/null || true
           fi
-          if ! timeout 30 git cat-file -e "$BASE" 2>/dev/null; then
+          if ! git cat-file -e "$BASE" 2>/dev/null; then
             echo "handlers=true" >> "$GITHUB_OUTPUT"
             exit 0
           fi

.gitea/workflows/lint-continue-on-error-tracking.yml

@@ -93,7 +93,7 @@ jobs:
   lint:
     name: lint-continue-on-error-tracking
     runs-on: ubuntu-latest
-    timeout-minutes: 20
+    timeout-minutes: 10
     # Phase 3 (RFC #219 §1): surface masked defects without blocking
     # PRs. Pre-existing continue-on-error: true directives on main
     # all violate this lint at first — intentional. Flip to false

.gitea/workflows/publish-workspace-server-image.yml

@@ -37,6 +37,12 @@ name: publish-workspace-server-image
 on:
   push:
     branches: [main]
+    paths:
+      - 'workspace-server/**'
+      - 'canvas/**'
+      - 'manifest.json'
+      - 'scripts/**'
+      - '.gitea/workflows/publish-workspace-server-image.yml'
   workflow_dispatch:
 
 # No `concurrency:` block here. Gitea 1.22.6 can cancel queued runs despite
@@ -59,24 +65,20 @@ jobs:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
-      # Health check: verify Docker daemon is accessible before attempting any
-      # build steps. This fails loudly at step 1 when the runner's docker.sock
-      # is inaccessible rather than silently continuing where `docker build`
-      # fails deep in the process with a cryptic ECR auth error.
-      - name: Verify Docker daemon access
+      - name: Diagnose Docker daemon access
         run: |
           set -euo pipefail
-          echo "::group::Docker daemon health check"
+          echo "::group::Docker daemon diagnosis"
           echo "Runner: ${HOSTNAME:-unknown}"
-          docker_info="$(docker info 2>&1)" || {
-            echo "::error::Docker daemon is not accessible at /var/run/docker.sock"
-            echo "::error::Runner: ${HOSTNAME:-unknown}"
-            printf '%s\n' "${docker_info}"
-            echo "::error::Check: (1) daemon is running, (2) runner user is in docker group, (3) sock permissions are 660+"
-            exit 1
-          }
-          printf '%s\n' "${docker_info}" | sed -n '1,5p'
-          echo "Docker daemon OK"
+          echo "--- Socket info ---"
+          ls -la /var/run/docker.sock 2>/dev/null || echo "/var/run/docker.sock: not found"
+          stat /var/run/docker.sock 2>/dev/null || true
+          echo "--- User info ---"
+          id
+          echo "--- docker version ---"
+          docker version 2>&1 || true
+          echo "--- docker info (full) ---"
+          docker info 2>&1 || echo "docker info failed: exit $?"
           echo "::endgroup::"
 
       # Pre-clone manifest deps before docker build.

.gitea/workflows/qa-review.yml

@@ -9,10 +9,10 @@
 #   Triggers on:
 #     - `pull_request_target`: opened, synchronize, reopened
 #         → initial status posts when PR opens / re-pushes
-#     - comment refires are handled by `review-refire-comments.yml`
-#         → a single issue_comment dispatcher prevents every SOP/review
-#           comment from enqueueing separate qa/security/tier jobs on
-#           Gitea 1.22.6 before job-level `if:` can skip them.
+#     - `issue_comment`: /qa-recheck slash-command on the PR
+#         → manual re-fire after a QA reviewer clicks APPROVE
+#           (Gitea 1.22.6 doesn't re-fire on pull_request_review, per
+#           go-gitea/gitea#33700 + feedback_pull_request_review_no_refire)
 #   Workflow name = `qa-review` ; job name = `approved`.
 #   The job's own pass/fail conclusion publishes the status context
 #   `qa-review / approved (<event>)` — NO `POST /statuses` call → NO
@@ -85,6 +85,8 @@ name: qa-review
 on:
   pull_request_target:
     types: [opened, synchronize, reopened]
+  issue_comment:
+    types: [created]
 
 permissions:
   contents: read
@@ -95,10 +97,16 @@ jobs:
   approved:
     # Gate the job:
     #   - On pull_request_target events: always run.
-    # Comment-triggered refires live in review-refire-comments.yml. Keeping
-    # this workflow PR-only avoids comment-triggered queue storms.
+    #   - On issue_comment events: only when it's a PR comment and the body
+    #     contains the slash-command. NO privilege gate at the step level
+    #     (RFC#324 v1.3 §A1.1): a non-collaborator's /qa-recheck is fine
+    #     because the eval is read-only and idempotent — re-running it
+    #     just re-confirms whether a real team-member APPROVE exists.
     if: |
-      github.event_name == 'pull_request_target'
+      github.event_name == 'pull_request_target' ||
+      (github.event_name == 'issue_comment' &&
+       github.event.issue.pull_request != null &&
+       startsWith(github.event.comment.body, '/qa-recheck'))
     runs-on: ubuntu-latest
     steps:
       - name: Privilege check (A1.1 — INFORMATIONAL log only, NOT a gate)
@@ -112,7 +120,7 @@ jobs:
         # no comment.user.login so the step is a no-op skip there.
         if: github.event_name == 'issue_comment'
         env:
-          GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
+          GITEA_TOKEN: ${{ secrets.RFC_324_TEAM_READ_TOKEN || secrets.GITHUB_TOKEN }}
         run: |
           set -euo pipefail
           login="${{ github.event.comment.user.login }}"
@@ -143,7 +151,7 @@ jobs:
 
       - name: Evaluate qa-review
         env:
-          GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
+          GITEA_TOKEN: ${{ secrets.RFC_324_TEAM_READ_TOKEN || secrets.GITHUB_TOKEN }}
           GITEA_HOST: git.moleculesai.app
           REPO: ${{ github.repository }}
           # PR number lives in different places per event:

.gitea/workflows/redeploy-tenants-on-main.yml

@@ -1,4 +1,4 @@
-name: redeploy-tenants-on-main
+name: manual-redeploy-tenants-on-main
 
 # Ported from .github/workflows/redeploy-tenants-on-main.yml on 2026-05-11 per RFC
 # internal#219 §1 sweep. Differences from the GitHub version:
@@ -9,17 +9,26 @@ name: redeploy-tenants-on-main
 #   - Workflow-level env.GITHUB_SERVER_URL pinned per
 #     feedback_act_runner_github_server_url.
 #   - `continue-on-error: true` on each job (RFC §1 contract).
-#   - Dropped unsupported `workflow_run` (task #81).
-#   - Later changed to manual-only after publish-workspace-server-image.yml
-#     gained an integrated ordered production deploy job.
+#   - Gitea 1.22.6 does not support workflow_run (task #81). This Gitea
+#     fallback is manual-only; automatic production deploy is attached to
+#     publish-workspace-server-image.yml after image push succeeds.
 #
 
-# Manual production tenant redeploy/rollback helper.
+# Manual production tenant redeploy fallback.
 #
-# Why this workflow is manual-only: publish-workspace-server-image now owns
-# the ordered build -> push -> production auto-deploy sequence in one workflow.
-# A separate push-triggered redeploy workflow races before the new ECR image
-# exists and can paint main red with a false deployment failure.
+# Primary automatic production deployment now lives in
+# publish-workspace-server-image.yml:
+#   build images -> wait for `CI / all-required (push)` green on the same SHA
+#   -> call production redeploy-fleet.
+#
+# This workflow remains as an operator fallback. By default it reruns current
+# main; set repo variable PROD_MANUAL_REDEPLOY_TARGET_TAG to a known-good
+# `staging-<sha>` tag for rollback.
+#
+# Why this workflow exists: publish-workspace-server-image builds and
+# pushes a new platform-tenant :<sha> to ECR on every merge to main,
+# but running tenants pulled their image once at boot and never re-pull.
+# Users see stale code indefinitely.
 #
 # This workflow closes the gap by calling the control-plane admin
 # endpoint that performs a canary-first, batched, health-gated rolling
@@ -32,16 +41,7 @@ name: redeploy-tenants-on-main
 # Gitea suspension migration. The staging-verify.yml promote step now
 # uses the same redeploy-fleet endpoint (fixes the silent-GHCR gap).
 #
-# Runtime ordering for automatic deploys now lives in
-# publish-workspace-server-image.yml:
-#   1. build-and-push creates new :staging-<sha> images in ECR.
-#   2. deploy-production waits for required push contexts on that SHA.
-#   3. deploy-production calls redeploy-fleet canary-first.
-#
-# Rollback path: set PROD_MANUAL_REDEPLOY_TARGET_TAG as a repo/org
-# variable or secret, run workflow_dispatch, then unset it after the
-# rollback. That calls redeploy-fleet with target_tag=<value>,
-# re-pulling the pinned image on every tenant.
+# Any failure aborts the rollout and leaves older tenants on the prior image.
 
 on:
   workflow_dispatch:
@@ -50,40 +50,19 @@ permissions:
   # No write scopes needed — the workflow hits an external CP endpoint,
   # not the GitHub API.
 
-# Serialize manual redeploys so two operator-triggered rollbacks do not
-# overlap and cause confusing per-tenant SSM state.
-#
-# NOTE: cancel-in-progress: false removed (Rule 7 fix). Gitea 1.22.6
-# cancels queued runs regardless of this setting, so it provides no
-# actual protection. Each redeploy-fleet call is idempotent (canary-first
-# + batched + health-gated) so a cancelled predecessor is recovered
-# automatically by the next run.
-concurrency:
-  group: redeploy-tenants-on-main
+# No `concurrency:` block here. Gitea 1.22.6 can cancel queued runs despite
+# `cancel-in-progress: false`; operators should not dispatch overlapping manual
+# production redeploys.
 
 env:
   GITHUB_SERVER_URL: https://git.moleculesai.app
 
 jobs:
-  # bp-exempt: production redeploy is a side-effect workflow, not a merge gate.
   redeploy:
-    if: ${{ github.event_name == 'workflow_dispatch' }}
     runs-on: ubuntu-latest
-    # Phase 3 (RFC #219 §1): surface broken workflows without blocking.
-    # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
-    continue-on-error: true
+    continue-on-error: false
     timeout-minutes: 25
-    env:
-      # Rule 9 fix: keep the same operational kill switch surface as the
-      # integrated auto-deploy workflow.
-      PROD_AUTO_DEPLOY_DISABLED: ${{ vars.PROD_AUTO_DEPLOY_DISABLED || secrets.PROD_AUTO_DEPLOY_DISABLED || '' }}
     steps:
-      - name: Kill-switch guard
-        # Rule 9 fix: exit fast if kill switch is set. No redeploy happens.
-        if: env.PROD_AUTO_DEPLOY_DISABLED == 'true'
-        run: |
-          echo "::notice::Production auto-deploy disabled (PROD_AUTO_DEPLOY_DISABLED=true). Skipping redeploy."
-          echo "To re-enable: unset the repo variable or set it to false."
       - name: Note on ECR propagation
         # ECR image manifests are consistent immediately after push — no
         # CDN cache to wait for. The old GHCR-based workflow had a 30s
@@ -92,25 +71,20 @@ jobs:
 
       - name: Compute target tag
         id: tag
-        # Resolution order:
-        #   1. Operator-supplied input (workflow_dispatch with explicit
-        #      tag) → used verbatim. Lets ops pin `latest` for emergency
-        #      rollback to last canary-verified digest, or pin a specific
-        #      `staging-<sha>` to roll back to a known-good build.
-        #   2. Default → `staging-<short_head_sha>` for manual reruns from
-        #      the current default-branch SHA.
+        # Gitea 1.22.6 does not support workflow_dispatch inputs reliably.
+        # Use repo variable PROD_MANUAL_REDEPLOY_TARGET_TAG for rollback.
         env:
-          PROD_MANUAL_REDEPLOY_TARGET_TAG: ${{ vars.PROD_MANUAL_REDEPLOY_TARGET_TAG || secrets.PROD_MANUAL_REDEPLOY_TARGET_TAG || '' }}
           HEAD_SHA: ${{ github.sha }}
+          MANUAL_TARGET_TAG: ${{ vars.PROD_MANUAL_REDEPLOY_TARGET_TAG || '' }}
         run: |
           set -euo pipefail
-          if [ -n "${PROD_MANUAL_REDEPLOY_TARGET_TAG:-}" ]; then
-            echo "target_tag=$PROD_MANUAL_REDEPLOY_TARGET_TAG" >> "$GITHUB_OUTPUT"
-            echo "Using operator-pinned tag from PROD_MANUAL_REDEPLOY_TARGET_TAG."
+          if [ -n "${MANUAL_TARGET_TAG:-}" ]; then
+            echo "target_tag=$MANUAL_TARGET_TAG" >> "$GITHUB_OUTPUT"
+            echo "Using operator-pinned manual target tag: $MANUAL_TARGET_TAG"
           else
             SHORT="${HEAD_SHA:0:7}"
             echo "target_tag=staging-$SHORT" >> "$GITHUB_OUTPUT"
-            echo "Using auto tag: staging-$SHORT (head_sha=$HEAD_SHA)"
+            echo "Using manual fallback tag: staging-$SHORT (head_sha=$HEAD_SHA)"
           fi
 
       - name: Call CP redeploy-fleet
@@ -119,29 +93,16 @@ jobs:
         # CP_ADMIN_API_TOKEN env. Stored in Railway, mirrored to this
         # repo's secrets for CI.
         env:
-          CP_URL: ${{ vars.CP_URL || 'https://api.moleculesai.app' }}
+          CP_URL: ${{ vars.PROD_CP_URL || 'https://api.moleculesai.app' }}
           CP_ADMIN_API_TOKEN: ${{ secrets.CP_ADMIN_API_TOKEN }}
           TARGET_TAG: ${{ steps.tag.outputs.target_tag }}
-          CANARY_SLUG: ${{ vars.PROD_REDEPLOY_CANARY_SLUG || secrets.PROD_REDEPLOY_CANARY_SLUG || '' }}
-          SOAK_SECONDS: ${{ vars.PROD_REDEPLOY_SOAK_SECONDS || secrets.PROD_REDEPLOY_SOAK_SECONDS || '' }}
-          BATCH_SIZE: ${{ vars.PROD_REDEPLOY_BATCH_SIZE || secrets.PROD_REDEPLOY_BATCH_SIZE || '' }}
-          DRY_RUN: ${{ vars.PROD_REDEPLOY_DRY_RUN || secrets.PROD_REDEPLOY_DRY_RUN || '' }}
-          PROD_AUTO_DEPLOY_DISABLED: ${{ vars.PROD_AUTO_DEPLOY_DISABLED || secrets.PROD_AUTO_DEPLOY_DISABLED || '' }}
+          CANARY_SLUG: ${{ vars.PROD_AUTO_DEPLOY_CANARY_SLUG || 'hongming' }}
+          SOAK_SECONDS: ${{ vars.PROD_AUTO_DEPLOY_SOAK_SECONDS || '60' }}
+          BATCH_SIZE: ${{ vars.PROD_AUTO_DEPLOY_BATCH_SIZE || '3' }}
+          DRY_RUN: ${{ vars.PROD_AUTO_DEPLOY_DRY_RUN || false }}
         run: |
           set -euo pipefail
 
-          case "${PROD_AUTO_DEPLOY_DISABLED,,}" in
-            1|true|yes|on)
-              echo "::notice::PROD_AUTO_DEPLOY_DISABLED is set; skipping production redeploy."
-              exit 0
-              ;;
-          esac
-
-          CANARY_SLUG="${CANARY_SLUG:-hongming}"
-          SOAK_SECONDS="${SOAK_SECONDS:-60}"
-          BATCH_SIZE="${BATCH_SIZE:-3}"
-          DRY_RUN="${DRY_RUN:-false}"
-
           if [ -z "${CP_ADMIN_API_TOKEN:-}" ]; then
             echo "::error::CP_ADMIN_API_TOKEN secret not set — skipping redeploy"
             echo "::notice::Set CP_ADMIN_API_TOKEN in repo secrets to enable auto-redeploy."
@@ -163,7 +124,7 @@ jobs:
             }')
 
           echo "POST $CP_URL/cp/admin/tenants/redeploy-fleet"
-          echo "  target_tag=$TARGET_TAG canary=$CANARY_SLUG soak_seconds=$SOAK_SECONDS batch_size=$BATCH_SIZE dry_run=$DRY_RUN"
+          echo "  body: $BODY"
 
           HTTP_RESPONSE=$(mktemp)
           HTTP_CODE_FILE=$(mktemp)
@@ -191,9 +152,7 @@ jobs:
           [ -z "$HTTP_CODE" ] && HTTP_CODE="000"
 
           echo "HTTP $HTTP_CODE"
-          # Rule 8 fix: redact raw CP response from CI logs. Print only
-          # safe fields: ok boolean, result count, error presence (no content).
-          jq '{ok, result_count: (.results | length), has_errors: (.results | any(.error != null))}' "$HTTP_RESPONSE" || echo "(jq parse failed)"
+          jq '{ok, result_count: (.results // [] | length)}' "$HTTP_RESPONSE" || true
 
           # Pretty-print per-tenant results in the job summary so
           # ops can see which tenants were redeployed without drilling
@@ -209,11 +168,9 @@ jobs:
             echo ""
             echo "### Per-tenant result"
             echo ""
-            echo '| Slug | Phase | SSM Status | Exit | Healthz | Errors |'
-            echo '|------|-------|------------|------|---------|-------|'
-            # Rule 8 fix: .error field redacted from CI logs/summary. Print only
-            # presence boolean so ops know whether to look deeper.
-            jq -r '.results[]? | "| \(.slug) | \(.phase) | \(.ssm_status // "-") | \(.ssm_exit_code) | \(.healthz_ok) | \(.error != null) |"' "$HTTP_RESPONSE" || true
+            echo '| Slug | Phase | SSM Status | Exit | Healthz | Error present |'
+            echo '|------|-------|------------|------|---------|---------------|'
+            jq -r '.results[]? | "| \(.slug) | \(.phase) | \(.ssm_status // "-") | \(.ssm_exit_code) | \(.healthz_ok) | \((.error // "") != "") |"' "$HTTP_RESPONSE" || true
           } >> "$GITHUB_STEP_SUMMARY"
 
           if [ "$HTTP_CODE" != "200" ]; then
@@ -252,9 +209,8 @@ jobs:
         # fail the workflow, which is what `ok=true` should have
         # guaranteed all along.
         #
-        # When the redeploy is triggered manually with a specific tag
-        # (target_tag != "latest"), the expected SHA may not equal
-        # ${{ github.sha }}.
+        # Manual Gitea fallback redeploys current main's staging-<sha> tag, so
+        # the expected SHA is github.sha.
         env:
           EXPECTED_SHA: ${{ github.sha }}
           TARGET_TAG: ${{ steps.tag.outputs.target_tag }}
@@ -270,10 +226,10 @@ jobs:
           if [ "$TARGET_TAG" != "latest" ] \
              && [ "$TARGET_TAG" != "$EXPECTED_SHA" ] \
              && [ "$TARGET_TAG" != "staging-$EXPECTED_SHORT" ]; then
-            # Manual redeploy with a pinned tag that isn't the head
+            # workflow_dispatch with a pinned tag that isn't the head
             # SHA — operator is rolling back / pinning. Skip the
             # verification because we don't have the expected SHA in
-            # this context (would need to inspect the ECR
+            # this context (would need to crane-inspect the GHCR
             # manifest, which is a follow-up). Failing-open here is
             # safe: the operator chose the tag deliberately.
             #

.gitea/workflows/review-refire-comments.yml

@@ -1,109 +0,0 @@
-# Consolidated comment dispatcher for manual review/tier refires.
-#
-# Gitea 1.22 queues one run per workflow subscribed to `issue_comment` before
-# evaluating job-level `if:`. SOP-heavy PRs therefore created queue storms when
-# qa-review, security-review, sop-checklist, and sop-tier-refire all
-# listened to comments. This workflow is the single non-SOP comment subscriber:
-# ordinary comments no-op quickly; slash commands post the required status
-# contexts to the PR head SHA.
-
-name: review-refire-comments
-
-on:
-  issue_comment:
-    types: [created]
-
-permissions:
-  contents: read
-  pull-requests: read
-  statuses: write
-
-jobs:
-  dispatch:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Classify comment
-        id: classify
-        env:
-          COMMENT_BODY: ${{ github.event.comment.body }}
-          IS_PR: ${{ github.event.issue.pull_request != null }}
-        run: |
-          set -euo pipefail
-          {
-            echo "run_qa=false"
-            echo "run_security=false"
-            echo "run_tier=false"
-          } >> "$GITHUB_OUTPUT"
-          if [ "$IS_PR" != "true" ]; then
-            echo "::notice::not a PR comment; no-op"
-            exit 0
-          fi
-          first_line=$(printf '%s\n' "$COMMENT_BODY" | sed -n '1p')
-          case "$first_line" in
-            /qa-recheck*)
-              echo "run_qa=true" >> "$GITHUB_OUTPUT"
-              ;;
-            /security-recheck*)
-              echo "run_security=true" >> "$GITHUB_OUTPUT"
-              ;;
-            /refire-tier-check*)
-              echo "run_tier=true" >> "$GITHUB_OUTPUT"
-              ;;
-            *)
-              echo "::notice::no supported review refire slash command; no-op"
-              ;;
-          esac
-
-      - name: Check out BASE ref for trusted scripts
-        if: |
-          steps.classify.outputs.run_qa == 'true' ||
-          steps.classify.outputs.run_security == 'true' ||
-          steps.classify.outputs.run_tier == 'true'
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
-        with:
-          ref: ${{ github.event.repository.default_branch }}
-
-      - name: Refire qa-review status
-        if: steps.classify.outputs.run_qa == 'true'
-        env:
-          GITEA_TOKEN: ${{ secrets.RFC_324_TEAM_READ_TOKEN || secrets.GITHUB_TOKEN }}
-          GITEA_HOST: git.moleculesai.app
-          REPO: ${{ github.repository }}
-          PR_NUMBER: ${{ github.event.issue.number }}
-          DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
-          TEAM: qa
-          TEAM_ID: '20'
-          REVIEW_CHECK_DEBUG: '0'
-          REVIEW_CHECK_STRICT: '0'
-          COMMENT_AUTHOR: ${{ github.event.comment.user.login }}
-        run: |
-          set -euo pipefail
-          .gitea/scripts/review-refire-status.sh
-
-      - name: Refire security-review status
-        if: steps.classify.outputs.run_security == 'true'
-        env:
-          GITEA_TOKEN: ${{ secrets.RFC_324_TEAM_READ_TOKEN || secrets.GITHUB_TOKEN }}
-          GITEA_HOST: git.moleculesai.app
-          REPO: ${{ github.repository }}
-          PR_NUMBER: ${{ github.event.issue.number }}
-          DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
-          TEAM: security
-          TEAM_ID: '21'
-          REVIEW_CHECK_DEBUG: '0'
-          REVIEW_CHECK_STRICT: '0'
-          COMMENT_AUTHOR: ${{ github.event.comment.user.login }}
-        run: |
-          set -euo pipefail
-          .gitea/scripts/review-refire-status.sh
-
-      - name: Refire sop-tier-check status
-        if: steps.classify.outputs.run_tier == 'true'
-        env:
-          GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
-          GITEA_HOST: git.moleculesai.app
-          REPO: ${{ github.repository }}
-          PR_NUMBER: ${{ github.event.issue.number }}
-          COMMENT_AUTHOR: ${{ github.event.comment.user.login }}
-          SOP_DEBUG: '0'
-        run: bash .gitea/scripts/sop-tier-refire.sh

.gitea/workflows/runtime-prbuild-compat.yml

@@ -66,28 +66,19 @@ jobs:
           # PR#372's ci.yml port used. Diffs against the PR base or the
           # previous push SHA, then matches against the wheel-relevant
           # path set.
-          #
-          # NOTE: Gitea Actions does not expose github.event.before as a
-          # shell environment variable. The ${{ github.event.before }} template
-          # expression works inside YAML run: blocks but is evaluated to an
-          # empty string for push events, making the ${VAR:-fallback} always
-          # use the fallback. Use GITHUB_EVENT_BEFORE instead — it IS set in
-          # the runner's shell environment for push events.
-          BASE=""
-          if [ "${{ github.event_name }}" = "pull_request" ]; then
+          BASE="${GITHUB_BASE_REF:-${{ github.event.before }}}"
+          if [ "${{ github.event_name }}" = "pull_request" ] && [ -n "${{ github.event.pull_request.base.sha }}" ]; then
             BASE="${{ github.event.pull_request.base.sha }}"
-          elif [ -n "$GITHUB_EVENT_BEFORE" ]; then
-            BASE="$GITHUB_EVENT_BEFORE"
           fi
           if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$'; then
             # New branch or no previous SHA: treat as wheel-relevant.
             echo "wheel=true" >> "$GITHUB_OUTPUT"
             exit 0
           fi
-          if ! timeout 30 git cat-file -e "$BASE" 2>/dev/null; then
+          if ! git cat-file -e "$BASE" 2>/dev/null; then
             git fetch --depth=1 origin "$BASE" 2>/dev/null || true
           fi
-          if ! timeout 30 git cat-file -e "$BASE" 2>/dev/null; then
+          if ! git cat-file -e "$BASE" 2>/dev/null; then
             echo "wheel=true" >> "$GITHUB_OUTPUT"
             exit 0
           fi

.gitea/workflows/security-review.yml

@@ -12,6 +12,8 @@ name: security-review
 on:
   pull_request_target:
     types: [opened, synchronize, reopened]
+  issue_comment:
+    types: [created]
 
 permissions:
   contents: read
@@ -20,10 +22,13 @@ permissions:
 jobs:
   # bp-exempt: PR security review bot signal; required merge state is enforced by CI / all-required.
   approved:
-    # Comment-triggered refires live in review-refire-comments.yml. Keeping
-    # this workflow PR-only avoids comment-triggered queue storms.
+    # See qa-review.yml header for full A1-α / A1.1 (v1.3 — informational
+    # log only, NOT a gate) / A4 / A5 design rationale.
     if: |
-      github.event_name == 'pull_request_target'
+      github.event_name == 'pull_request_target' ||
+      (github.event_name == 'issue_comment' &&
+       github.event.issue.pull_request != null &&
+       startsWith(github.event.comment.body, '/security-recheck'))
     runs-on: ubuntu-latest
     steps:
       - name: Privilege check (A1.1 — INFORMATIONAL log only, NOT a gate)
@@ -32,7 +37,7 @@ jobs:
         # so re-running on a non-collaborator comment is harmless.
         if: github.event_name == 'issue_comment'
         env:
-          GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
+          GITEA_TOKEN: ${{ secrets.RFC_324_TEAM_READ_TOKEN || secrets.GITHUB_TOKEN }}
         run: |
           set -euo pipefail
           login="${{ github.event.comment.user.login }}"
@@ -57,7 +62,7 @@ jobs:
 
       - name: Evaluate security-review
         env:
-          GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
+          GITEA_TOKEN: ${{ secrets.RFC_324_TEAM_READ_TOKEN || secrets.GITHUB_TOKEN }}
           GITEA_HOST: git.moleculesai.app
           REPO: ${{ github.repository }}
           PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number }}

.gitea/workflows/sop-checklist-gate.yml

@@ -1,4 +1,4 @@
-# sop-checklist — peer-ack merge gate for SOP-checklist items.
+# sop-checklist-gate — peer-ack merge gate for SOP-checklist items.
 #
 # RFC#351 Step 2 of 6 (implementation MVP).
 #
@@ -65,15 +65,7 @@
 # membership, compute, post status). Re-running on any event is safe —
 # the new status overwrites the previous one for the same context.
 
-name: sop-checklist
-
-# Cancel any in-progress runs for the same PR to prevent
-# stale runs from overwriting newer status contexts.
-concurrency:
-  group: ${{ github.repository }}-${{ github.event.pull_request.number }}
-  cancel-in-progress: true
-
-# bp-required: yes  ← emits sop-checklist / all-items-acked (pull_request)
+name: sop-checklist-gate
 
 on:
   pull_request_target:
@@ -91,7 +83,7 @@ permissions:
   statuses: write
 
 jobs:
-  all-items-acked:
+  gate:
     # Run on pull_request_target events always. On issue_comment events,
     # only when the comment is on a PR (issue_comment fires for issues
     # too) and the body contains one of the slash-commands.
@@ -100,8 +92,7 @@ jobs:
       (github.event_name == 'issue_comment' &&
        github.event.issue.pull_request != null &&
        (contains(github.event.comment.body, '/sop-ack') ||
-        contains(github.event.comment.body, '/sop-revoke') ||
-        contains(github.event.comment.body, '/sop-n/a')))
+        contains(github.event.comment.body, '/sop-revoke')))
     runs-on: ubuntu-latest
     steps:
       - name: Check out BASE ref (trust boundary — never PR-head)
@@ -114,7 +105,7 @@ jobs:
           # qa-review.yml so the script source is always trusted.
           ref: ${{ github.event.repository.default_branch }}
 
-      - name: Run sop-checklist
+      - name: Run sop-checklist-gate
         env:
           GITEA_TOKEN: ${{ secrets.SOP_CHECKLIST_GATE_TOKEN || secrets.GITHUB_TOKEN }}
           PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number }}
@@ -122,7 +113,7 @@ jobs:
           REPO_NAME: ${{ github.event.repository.name }}
         run: |
           set -euo pipefail
-          python3 .gitea/scripts/sop-checklist.py \
+          python3 .gitea/scripts/sop-checklist-gate.py \
             --owner "$OWNER" \
             --repo "$REPO_NAME" \
             --pr "$PR_NUMBER" \

.gitea/workflows/sop-tier-refire.yml

@@ -1,4 +1,4 @@
-# sop-tier-refire — manual fallback for sop-tier-check refire.
+# sop-tier-refire — issue_comment-triggered refire of sop-tier-check.
 #
 # Closes internal#292. Gitea 1.22.6 doesn't refire workflows on the
 # `pull_request_review` event (go-gitea/gitea#33700); the `sop-tier-check`
@@ -8,12 +8,12 @@
 # to merge is the admin force-merge path (audited via `audit-force-merge`
 # but the audit trail keeps growing; see `feedback_never_admin_merge_bypass`).
 #
-# Comment-triggered refires now live in `review-refire-comments.yml`. Gitea
-# queues issue_comment workflows before evaluating job-level `if:`, so having
-# qa-review, security-review, sop-checklist, and sop-tier-refire all subscribe
-# to every comment caused queue storms on SOP-heavy PRs. This workflow is a
-# non-automatic breadcrumb only; Gitea 1.22.6 does not support
-# workflow_dispatch inputs, so real refires must use `/refire-tier-check`.
+# Workaround pattern from `feedback_pull_request_review_no_refire`:
+# `issue_comment` events DO fire reliably on 1.22.6. When a repo
+# MEMBER/OWNER/COLLABORATOR comments `/refire-tier-check` on a PR, this
+# workflow re-runs the sop-tier-check logic and POSTs the resulting
+# status to the PR head SHA directly. No empty commit, no git history
+# bloat, no cascade re-fire of every other workflow on the PR.
 #
 # SECURITY MODEL:
 #
@@ -37,16 +37,43 @@
 # Rate-limit: a 1s pre-sleep + a "skip if status posted in last 30s"
 # guard prevents comment-spam from thrashing the status. See the script.
 
-name: sop-tier-check refire (manual)
+name: sop-tier-check refire (issue_comment)
 
 on:
-  workflow_dispatch:
+  issue_comment:
+    types: [created]
 
 jobs:
   refire:
+    # Three gates, all required:
+    #   - comment is on a PR (not a plain issue)
+    #   - commenter is MEMBER, OWNER, or COLLABORATOR
+    #   - comment body contains the slash-command trigger
+    if: |
+      github.event.issue.pull_request != null &&
+      contains(fromJson('["MEMBER","OWNER","COLLABORATOR"]'), github.event.comment.author_association) &&
+      contains(github.event.comment.body, '/refire-tier-check')
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      statuses: write
     steps:
-      - name: Explain supported refire path
-        run: |
-          echo "::error::Gitea 1.22.6 does not support workflow_dispatch inputs here; comment /refire-tier-check on the PR instead."
-          exit 1
+      - name: Check out base branch (for the script)
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          # Load the script from the default branch (main), matching the
+          # sop-tier-check.yml security model.
+          ref: ${{ github.event.repository.default_branch }}
+      - name: Re-evaluate sop-tier-check and POST status
+        env:
+          # Same org-level secret sop-tier-check.yml + audit-force-merge.yml use.
+          # Fallback to GITHUB_TOKEN with a clear error if missing.
+          GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
+          GITEA_HOST: git.moleculesai.app
+          REPO: ${{ github.repository }}
+          PR_NUMBER: ${{ github.event.issue.number }}
+          COMMENT_AUTHOR: ${{ github.event.comment.user.login }}
+          # Set to '1' for diagnostic per-API-call output. Off by default.
+          SOP_DEBUG: '0'
+        run: bash .gitea/scripts/sop-tier-refire.sh

.staging-trigger

@@ -1 +1 @@
-staging trigger 2026-05-14T17:35:02Z
+staging trigger

_ci_trigger.txt

@@ -1 +0,0 @@
-trigger

canvas/src/app/orgs/page.tsx

@@ -327,7 +327,7 @@ function OrgCTA({ org }: { org: Org }) {
     return (
       <a
         href={href}
-        className="rounded bg-emerald-700 px-4 py-2 text-sm font-medium text-white hover:bg-emerald-600"
+        className="rounded bg-emerald-600 px-4 py-2 text-sm font-medium text-white hover:bg-emerald-500"
       >
         Open
       </a>
@@ -337,7 +337,7 @@ function OrgCTA({ org }: { org: Org }) {
     return (
       <a
         href={`/pricing?org=${encodeURIComponent(org.slug)}`}
-        className="rounded bg-amber-800 px-4 py-2 text-sm font-medium text-white hover:bg-amber-700"
+        className="rounded bg-amber-600 px-4 py-2 text-sm font-medium text-white hover:bg-amber-500"
       >
         Complete payment
       </a>

canvas/src/components/AuditTrailPanel.tsx

@@ -8,17 +8,11 @@ import type { AuditEntry, AuditResponse } from "@/types/audit";
 
 type EventFilter = "all" | AuditEntry["event_type"];
 
-// Contrast note: text is rendered on near-black bg (bg-*-950/40). Every text
-// color below is chosen to pass WCAG 2.1 AA 4.5:1 on that background:
-//   blue-300   ( delegation ) ≈ 8.8:1
-//   violet-300 ( decision   ) ≈ 9.5:1
-//   yellow-200 ( gate       ) ≈ 11.5:1
-//   orange-300 ( hitl       ) ≈ 9.1:1
 const BADGE_COLORS: Record<AuditEntry["event_type"], { text: string; bg: string; border: string }> = {
-  delegation: { text: "text-blue-300",   bg: "bg-blue-950/40",   border: "border-blue-800/40" },
-  decision:   { text: "text-violet-300", bg: "bg-violet-950/40", border: "border-violet-800/40" },
-  gate:       { text: "text-yellow-200", bg: "bg-yellow-950/40", border: "border-yellow-800/40" },
-  hitl:       { text: "text-orange-300", bg: "bg-orange-950/40", border: "border-orange-800/40" },
+  delegation: { text: "text-accent",   bg: "bg-blue-950/40",   border: "border-blue-800/40" },
+  decision:   { text: "text-violet-400", bg: "bg-violet-950/40", border: "border-violet-800/40" },
+  gate:       { text: "text-yellow-400", bg: "bg-yellow-950/40", border: "border-yellow-800/40" },
+  hitl:       { text: "text-orange-400", bg: "bg-orange-950/40", border: "border-orange-800/40" },
 };
 
 const FILTERS: { id: EventFilter; label: string }[] = [
@@ -170,10 +164,7 @@ export function AuditTrailPanel({ workspaceId }: Props) {
 
       {/* Error banner */}
       {error && (
-        <div
-          role="alert"
-          className="mx-4 mt-3 px-3 py-2 bg-red-950/30 border border-red-800/40 rounded text-xs text-bad shrink-0"
-        >
+        <div className="mx-4 mt-3 px-3 py-2 bg-red-950/30 border border-red-800/40 rounded text-xs text-bad shrink-0">
           {error}
         </div>
       )}
@@ -251,6 +242,7 @@ export function AuditEntryRow({ entry, now }: AuditEntryRowProps) {
         {/* Event-type badge */}
         <span
           className={`shrink-0 text-[9px] font-semibold uppercase tracking-wider px-1.5 py-0.5 rounded border ${badge.text} ${badge.bg} ${badge.border}`}
+          aria-label={`Event type: ${entry.event_type}`}
         >
           {entry.event_type}
         </span>

canvas/src/components/BatchActionBar.tsx

@@ -100,8 +100,8 @@ export function BatchActionBar() {
       aria-label="Batch workspace actions"
       className="fixed bottom-6 left-1/2 -translate-x-1/2 z-[200] flex items-center gap-3 px-4 py-2.5 rounded-2xl bg-surface-sunken/95 border border-line/70 shadow-2xl shadow-black/50 backdrop-blur-md"
     >
-      {/* Selection count badge — bg-zinc-700 passes 7.2:1 on white text */}
-      <span className="text-[12px] font-semibold text-white bg-zinc-700 px-2.5 py-0.5 rounded-full tabular-nums">
+      {/* Selection count badge */}
+      <span className="text-[12px] font-semibold text-white bg-accent-strong/80 px-2.5 py-0.5 rounded-full tabular-nums">
         {count} selected
       </span>
 
@@ -112,7 +112,7 @@ export function BatchActionBar() {
         type="button"
         disabled={busy}
         onClick={() => setPending("restart")}
-        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-white bg-sky-900/30 hover:bg-sky-800/50 border border-sky-700/30 hover:border-sky-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-sky-500/70"
+        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-sky-300 bg-sky-900/30 hover:bg-sky-800/50 border border-sky-700/30 hover:border-sky-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-sky-500/70"
       >
         <span aria-hidden="true">↻</span>
         Restart All
@@ -122,7 +122,7 @@ export function BatchActionBar() {
         type="button"
         disabled={busy}
         onClick={() => setPending("pause")}
-        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-white bg-amber-900/30 hover:bg-amber-800/50 border border-amber-700/30 hover:border-amber-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-amber-500/70"
+        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-warm bg-amber-900/30 hover:bg-amber-800/50 border border-amber-700/30 hover:border-amber-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-amber-500/70"
       >
         <span aria-hidden="true">⏸</span>
         Pause All
@@ -132,7 +132,7 @@ export function BatchActionBar() {
         type="button"
         disabled={busy}
         onClick={() => setPending("delete")}
-        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-white bg-red-900/30 hover:bg-red-800/50 border border-red-700/30 hover:border-red-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-500/70"
+        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-bad bg-red-900/30 hover:bg-red-800/50 border border-red-700/30 hover:border-red-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-500/70"
       >
         <span aria-hidden="true">✕</span>
         Delete All

canvas/src/components/ConfirmDialog.tsx

@@ -96,7 +96,7 @@ export function ConfirmDialog({
   // readable in both light and dark themes.
   const confirmColors =
     confirmVariant === "danger"
-      ? "bg-red-700 hover:bg-red-600 text-white"
+      ? "bg-red-600 hover:bg-red-700 text-white"
       : confirmVariant === "warning"
         ? "bg-amber-800 hover:bg-amber-700 text-white"
         : "bg-accent hover:bg-accent-strong text-white";

canvas/src/components/ContextMenu.tsx

@@ -1,6 +1,6 @@
 "use client";
 
-import { useCallback, useEffect, useMemo, useRef, useState } from "react";
+import { useCallback, useEffect, useRef, useState } from "react";
 import { useCanvasStore, type WorkspaceNodeData } from "@/store/canvas";
 import { api } from "@/lib/api";
 import { showToast } from "./Toaster";
@@ -23,17 +23,9 @@ export function ContextMenu() {
   const setPanelTab = useCanvasStore((s) => s.setPanelTab);
   const nestNode = useCanvasStore((s) => s.nestNode);
   const contextNodeId = contextMenu?.nodeId ?? null;
-  // Select the full nodes array (stable reference across unrelated store
-  // updates) and derive children via useMemo. Filtering inside the
-  // selector returned a new array every call, which Zustand's
-  // useSyncExternalStore saw as "snapshot changed" → schedule
-  // re-render → loop → React error #185. See canvas-store-snapshots.
-  const nodes = useCanvasStore((s) => s.nodes);
-  const children = useMemo(
-    () => (contextNodeId ? nodes.filter((n) => n.data.parentId === contextNodeId) : []),
-    [nodes, contextNodeId],
+  const hasChildren = useCanvasStore((s) =>
+    contextNodeId ? s.nodes.some((n) => n.data.parentId === contextNodeId) : false
   );
-  const hasChildren = children.length > 0;
   const setPendingDelete = useCanvasStore((s) => s.setPendingDelete);
   const ref = useRef<HTMLDivElement>(null);
   const [actionLoading, setActionLoading] = useState(false);
@@ -197,9 +189,10 @@ export function ContextMenu() {
     // it survives ContextMenu unmount. Closing the menu here avoids the
     // prior race where the portal dialog's Confirm click was treated as
     // "outside" by the menu's outside-click handler.
-    setPendingDelete({ id: contextMenu.nodeId, name: contextMenu.nodeData.name, hasChildren, children: children.map(c => ({ id: c.id, name: c.data.name })) });
+    const childNodes = useCanvasStore.getState().nodes.filter((n) => n.data.parentId === contextMenu.nodeId);
+    setPendingDelete({ id: contextMenu.nodeId, name: contextMenu.nodeData.name, hasChildren, children: childNodes.map(c => ({ id: c.id, name: c.data.name })) });
     closeContextMenu();
-  }, [contextMenu, setPendingDelete, closeContextMenu, children, hasChildren]);
+  }, [contextMenu, setPendingDelete, closeContextMenu]);
 
   const handleViewDetails = useCallback(() => {
     if (!contextMenu) return;
@@ -318,7 +311,7 @@ export function ContextMenu() {
             aria-hidden="true"
             className={`w-1.5 h-1.5 rounded-full ${statusDotClass(contextMenu.nodeData.status)}`}
           />
-          <span className="text-[10px] text-ink">{contextMenu.nodeData.status}</span>
+          <span className="text-[10px] text-ink-mid">{contextMenu.nodeData.status}</span>
         </div>
       </div>
 

canvas/src/components/ConversationTraceModal.tsx

@@ -187,7 +187,7 @@ export function ConversationTraceModal({ open, workspaceId: _workspaceId, onClos
                                 isError
                                   ? "bg-red-950/50 text-bad"
                                   : isSend
-                                  ? "bg-cyan-950 text-cyan-300"
+                                  ? "bg-cyan-950/50 text-cyan-400"
                                   : isReceive
                                   ? "bg-blue-950/50 text-accent"
                                   : "bg-surface-card text-ink-mid"
@@ -251,7 +251,7 @@ export function ConversationTraceModal({ open, workspaceId: _workspaceId, onClos
 
                           {/* Error */}
                           {isError && entry.error_detail && (
-                            <div className="text-[10px] text-bad mt-1 truncate">
+                            <div className="text-[10px] text-bad/80 mt-1 truncate">
                               {entry.error_detail.slice(0, 200)}
                             </div>
                           )}
@@ -272,7 +272,7 @@ export function ConversationTraceModal({ open, workspaceId: _workspaceId, onClos
                           )}
                           {responseText && (
                             <div className="mt-1 bg-surface/60 border border-emerald-900/30 rounded-lg px-3 py-2 max-h-32 overflow-y-auto">
-                              <div className="text-[8px] text-good uppercase mb-1">Response</div>
+                              <div className="text-[8px] text-good/60 uppercase mb-1">Response</div>
                               <div className="text-[10px] text-ink-mid whitespace-pre-wrap break-words leading-relaxed">
                                 {responseText.slice(0, 2000)}
                                 {responseText.length > 2000 && (

canvas/src/components/DeleteCascadeConfirmDialog.tsx

@@ -126,8 +126,8 @@ export function DeleteCascadeConfirmDialog({
 
           {/* Cascade warning */}
           <div className="rounded border border-red-900/40 bg-red-950/20 px-3 py-2.5 mb-4">
-            <p className="text-[12px] text-red-300 leading-relaxed">
-              Deleting will cascade — <strong className="text-red-100">all child workspaces and their data will be permanently removed.</strong> This cannot be undone.
+            <p className="text-[12px] text-bad/80 leading-relaxed">
+              Deleting will cascade — <strong className="text-red-200">all child workspaces and their data will be permanently removed.</strong> This cannot be undone.
             </p>
           </div>
 
@@ -164,13 +164,13 @@ export function DeleteCascadeConfirmDialog({
             type="button"
             onClick={onConfirm}
             disabled={!checked}
-            // Hover goes DARKER, not lighter — bg-red-600 on white text
-            // drops contrast below AA. Same trap fixed in ConfirmDialog.
-            // focus-visible ring matches the canvas chrome.
+            // Hover goes DARKER, not lighter — bg-red-500 on white text
+            // drops contrast below AA vs bg-red-700. Same trap fixed in
+            // ConfirmDialog and ApprovalBanner. focus-visible ring matches.
             className={`px-3.5 py-1.5 text-[13px] rounded-lg transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-2 focus-visible:ring-offset-surface-sunken
               ${checked
-                ? "bg-red-700 hover:bg-red-600 text-white cursor-pointer"
-                : "bg-red-900/30 text-red-400 cursor-not-allowed"
+                ? "bg-red-600 hover:bg-red-700 text-white cursor-pointer"
+                : "bg-red-900/30 text-bad/40 cursor-not-allowed"
               }`}
           >
             Delete All

canvas/src/components/ErrorBoundary.tsx

@@ -51,7 +51,7 @@ export class ErrorBoundary extends React.Component<
   render() {
     if (this.state.hasError) {
       return (
-        <div role="alert" aria-live="assertive" className="fixed inset-0 flex items-center justify-center bg-surface z-50">
+        <div className="fixed inset-0 flex items-center justify-center bg-surface z-50">
           <div className="max-w-md rounded-2xl border border-red-500/30 bg-surface-sunken/90 px-8 py-8 text-center shadow-2xl shadow-black/40">
             <div className="mx-auto mb-4 flex h-14 w-14 items-center justify-center rounded-full bg-red-500/10 border border-red-500/30">
               <svg
@@ -76,7 +76,7 @@ export class ErrorBoundary extends React.Component<
             <p className="text-sm text-ink-mid mb-1">
               An unexpected error occurred while rendering the application.
             </p>
-            <p className="text-xs text-bad mb-6 font-mono break-all">
+            <p className="text-xs text-bad/80 mb-6 font-mono break-all">
               {this.state.error?.message ?? "Unknown error"}
             </p>
             <div className="flex items-center justify-center gap-3">

canvas/src/components/ExternalConnectModal.tsx

@@ -360,7 +360,7 @@ function SnippetBlock({
         <button
           type="button"
           onClick={onCopy}
-          className="text-xs px-2 py-1 rounded bg-accent text-white hover:bg-accent-strong transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
+          className="text-xs px-2 py-1 rounded bg-accent-strong/80 hover:bg-accent text-white focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
         >
           {copied ? "Copied!" : "Copy"}
         </button>

canvas/src/components/MissingKeysModal.tsx

@@ -451,7 +451,7 @@ function ProviderPickerModal({
                     <button
                       onClick={() => handleSaveKey(index)}
                       disabled={!entry.value.trim() || entry.saving}
-                      className="px-3 py-1.5 bg-accent-strong hover:bg-accent text-[11px] rounded text-white disabled:opacity-30 transition-colors shrink-0 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
+                      className="px-3 py-1.5 bg-accent-strong hover:bg-accent text-[11px] rounded text-white disabled:opacity-30 transition-colors shrink-0"
                     >
                       {entry.saving ? "..." : "Save"}
                     </button>
@@ -492,7 +492,7 @@ function ProviderPickerModal({
                 !selectorValue.providerId ||
                 (showModelInput && model.trim() === "")
               }
-              className="px-3.5 py-1.5 text-[12px] bg-accent-strong hover:bg-accent text-white rounded-lg transition-colors disabled:opacity-40 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
+              className="px-3.5 py-1.5 text-[12px] bg-accent-strong hover:bg-accent text-white rounded-lg transition-colors disabled:opacity-40"
             >
               {allSaved ? "Deploy" : entries.length > 1 ? "Add Keys" : "Add Key"}
             </button>

canvas/src/components/ProviderModelSelector.tsx

@@ -420,7 +420,7 @@ export function ProviderModelSelector({
               spellCheck={false}
               autoComplete="off"
               data-testid="model-input"
-              className="w-full bg-surface-sunken border border-line rounded px-2 py-1.5 text-[11px] text-ink font-mono focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1 focus-visible:border-accent transition-colors disabled:opacity-50"
+              className="w-full bg-surface-sunken border border-line rounded px-2 py-1.5 text-[11px] text-ink font-mono focus:outline-none focus:border-accent focus:ring-1 focus:ring-accent/20 transition-colors disabled:opacity-50"
             />
             <p className="text-[9px] text-ink-mid mt-1 leading-relaxed">
               {selected?.wildcard

canvas/src/components/ProvisioningTimeout.tsx

@@ -389,7 +389,7 @@ export function ProvisioningTimeout({
               <button
                 type="button"
                 onClick={handleCancelConfirm}
-                className="px-3.5 py-1.5 text-[12px] bg-red-800 hover:bg-red-700 text-white rounded-lg transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-400 focus-visible:ring-offset-1"
+                className="px-3.5 py-1.5 text-[12px] bg-red-600 hover:bg-red-500 text-white rounded-lg transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-400 focus-visible:ring-offset-1"
               >
                 Remove Workspace
               </button>

canvas/src/components/SearchDialog.tsx

@@ -91,16 +91,19 @@ export function SearchDialog() {
   if (!open) return null;
 
   return (
-    <div
-      className="fixed inset-0 z-[70] flex items-start justify-center pt-[20vh] bg-black/50 backdrop-blur-sm"
-      onClick={() => setOpen(false)}
-    >
+    <div className="fixed inset-0 z-[70] flex items-start justify-center pt-[20vh]">
+      {/* Backdrop — interactive dismiss area; aria-hidden so screen readers ignore it */}
+      <div
+        className="absolute inset-0 bg-black/50 backdrop-blur-sm cursor-pointer"
+        onClick={() => setOpen(false)}
+        aria-hidden="true"
+      />
+      {/* Dialog */}
       <div
         role="dialog"
         aria-modal="true"
         aria-label="Search workspaces"
-        className="w-[420px] bg-surface/95 backdrop-blur-xl border border-line/60 rounded-2xl shadow-2xl shadow-black/50 overflow-hidden"
-        onClick={(e) => e.stopPropagation()}
+        className="relative z-[71] w-[420px] bg-surface/95 backdrop-blur-xl border border-line/60 rounded-2xl shadow-2xl shadow-black/50 overflow-hidden"
       >
         {/* Search input */}
         <div className="flex items-center gap-3 px-4 py-3 border-b border-line/40">

canvas/src/components/ThemeToggle.tsx

@@ -61,22 +61,9 @@ export function ThemeToggle({ className = "" }: { className?: string }) {
         return;
       }
       setTheme(OPTIONS[next].value);
-      // Move focus to the new button so arrow-key navigation is continuous.
-      // Use direct-child query to scope strictly to this radiogroup's buttons
-      // and avoid accidentally focusing unrelated [role=radio] elements
-      // elsewhere in the DOM (e.g. React Flow canvas nodes).
-      // Guard: skip focus if the current target is no longer in the document
-      // (e.g. React StrictMode double-invokes handlers during re-render).
-      if (!e.currentTarget.isConnected) return;
-      const radiogroup = e.currentTarget.closest("[role=radiogroup]") as HTMLElement | null;
-      if (!radiogroup) return;
-      // Use children[] instead of querySelectorAll("> [role=radio]") to avoid
-      // jsdom's child-combinator selector parsing issues in test environments.
-      const btns = Array.from(radiogroup.children).filter(
-        (el): el is HTMLButtonElement =>
-          el.tagName === "BUTTON" && el.getAttribute("role") === "radio"
-      );
-      if (next < btns.length) btns[next]?.focus();
+      // Move focus to the new button so arrow-key navigation is continuous
+      const btns = (e.currentTarget.closest("[role=radiogroup]") as HTMLElement)?.querySelectorAll<HTMLButtonElement>("[role=radio]");
+      btns?.[next]?.focus();
     },
     []
   );

canvas/src/components/__tests__/ContextMenu.test.tsx

@@ -398,78 +398,3 @@ describe("ContextMenu — item actions", () => {
     expect(mockPost).toHaveBeenCalledWith("/workspaces/n1/resume", {});
   });
 });
-
-/**
- * Regression tests for GitHub issue #651 — React error #185:
- * "Maximum update depth exceeded" on Chat tab / mobile.
- *
- * Root cause: ContextMenu's children selector ran `.filter()` inside the
- * Zustand hook, returning a brand-new array reference on every render.
- * Zustand's useSyncExternalStore compared snapshots with Object.is —
- * a new array always differs — so React kept scheduling re-renders,
- * hit the 50-update depth cap, and crashed.
- *
- * Fix: select the stable `nodes` array once, derive children via
- * useMemo outside the store subscription.
- */
-describe("ContextMenu — hasChildren regression (GitHub #651)", () => {
-  beforeEach(() => { setupApiMocks(); });
-  afterEach(() => {
-    cleanup();
-    vi.clearAllMocks();
-    mockStoreState.contextMenu = null;
-    mockStoreState.closeContextMenu.mockClear();
-    mockStoreState.updateNodeData.mockClear();
-    mockStoreState.selectNode.mockClear();
-    mockStoreState.setPanelTab.mockClear();
-    mockStoreState.nestNode.mockClear();
-    mockStoreState.setPendingDelete.mockClear();
-    mockStoreState.setCollapsed.mockClear();
-    mockStoreState.arrangeChildren.mockClear();
-    mockStoreState.nodes = [];
-    resetApiMocks();
-    vi.mocked(showToast).mockClear();
-  });
-
-  it("setPendingDelete receives correct children array when workspace has children", () => {
-    openMenu({ nodeId: "ws-parent", nodeData: { name: "Parent", status: "online", tier: 4, role: "assistant" } });
-    mockStoreState.nodes = [
-      { id: "ws-child-a", data: { parentId: "ws-parent" } },
-      { id: "ws-child-b", data: { parentId: "ws-parent" } },
-    ];
-    render(<ContextMenu />);
-    const deleteBtn = screen.getAllByRole("menuitem").find((el) =>
-      el.textContent?.includes("Delete")
-    )!;
-    fireEvent.click(deleteBtn);
-    expect(mockStoreState.setPendingDelete).toHaveBeenCalledWith(
-      expect.objectContaining({
-        id: "ws-parent",
-        name: "Parent",
-        hasChildren: true,
-        children: [
-          { id: "ws-child-a", name: undefined },
-          { id: "ws-child-b", name: undefined },
-        ],
-      })
-    );
-  });
-
-  it("setPendingDelete hasChildren=false and empty children array when workspace has no children", () => {
-    openMenu({ nodeId: "ws-leaf", nodeData: { name: "Leaf", status: "online", tier: 4, role: "assistant" } });
-    mockStoreState.nodes = [];
-    render(<ContextMenu />);
-    const deleteBtn = screen.getAllByRole("menuitem").find((el) =>
-      el.textContent?.includes("Delete")
-    )!;
-    fireEvent.click(deleteBtn);
-    expect(mockStoreState.setPendingDelete).toHaveBeenCalledWith(
-      expect.objectContaining({
-        id: "ws-leaf",
-        name: "Leaf",
-        hasChildren: false,
-        children: [],
-      })
-    );
-  });
-});

canvas/src/components/__tests__/OrgTemplatesSection.test.tsx

@@ -1,237 +1,102 @@
 // @vitest-environment jsdom
+import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
+import { render, screen, waitFor, fireEvent, cleanup } from "@testing-library/react";
 
-/**
- * Tests for OrgTemplatesSection — collapsible org template import list.
- *
- * Covers:
- *   - Header with count badge (visible only when expanded)
- *   - Collapsed by default, aria-expanded toggles on click
- *   - aria-controls targets org-templates-body div
- *   - Empty state when no org templates
- *   - Loading spinner
- *   - Org template cards: name, description, workspace count
- *   - Import button per card
- *   - Preflight modal opens when org has required_env
- *   - Preflight onProceed fires import
- *   - Preflight onCancel closes modal
- *   - Direct import (no modal) when org has no env requirements
- *   - Import button disabled while that org is importing
- */
-// ── ALL mocks MUST be before imports (vi.mock is hoisted to top of file) ───────
-const { mockGet, mockPost, mockListSecrets } = vi.hoisted(() => ({
-  mockGet: vi.fn(),
-  mockPost: vi.fn(),
-  mockListSecrets: vi.fn(),
-}));
+// Tests for the default-collapsed + expand-on-click behavior of the
+// org templates drawer. Before this change the section rendered all
+// org cards inline, which pushed the individual workspace templates
+// off-screen when there were ≥3 orgs on disk. Collapsed-by-default
+// keeps the scroll focused on the primary deploy path.
 
 vi.mock("@/lib/api", () => ({
-  api: { get: mockGet, post: mockPost },
-}));
-
-vi.mock("@/lib/api/secrets", () => ({
-  listSecrets: mockListSecrets,
-}));
-
-vi.mock("@/store/canvas", () => ({
-  useCanvasStore: Object.assign(
-    vi.fn(),
-    { getState: () => ({ nodes: [], hydrate: vi.fn() }) },
-  ),
-}));
-
-vi.mock("../Spinner", () => ({
-  Spinner: () => <span data-testid="spinner" aria-hidden="true" />,
-}));
-
-vi.mock("../OrgImportPreflightModal", () => ({
-  OrgImportPreflightModal: vi.fn(({ open, onCancel, onProceed }) =>
-    open ? (
-      <div data-testid="preflight-modal">
-        <button onClick={onProceed}>Import</button>
-        <button onClick={onCancel}>Cancel</button>
-      </div>
-    ) : null
-  ),
+  api: {
+    get: vi.fn().mockResolvedValue([
+      { dir: "free-beats-all", name: "Free Beats All", description: "d1", workspaces: 3 },
+      { dir: "medo-smoke", name: "MeDo Smoke Test", description: "d2", workspaces: 1 },
+    ]),
+    post: vi.fn().mockResolvedValue({}),
+  },
 }));
 
+vi.mock("../Spinner", () => ({ Spinner: () => null }));
+vi.mock("../MissingKeysModal", () => ({ MissingKeysModal: () => null }));
 vi.mock("../ConfirmDialog", () => ({ ConfirmDialog: () => null }));
-vi.mock("@/components/Toaster", () => ({ showToast: vi.fn() }));
+vi.mock("@/lib/deploy-preflight", () => ({ checkDeploySecrets: vi.fn() }));
 
-import React from "react";
-import { render, screen, fireEvent, cleanup, act, waitFor } from "@testing-library/react";
-import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
 import { OrgTemplatesSection } from "../TemplatePalette";
 
-// ── Shared data ─────────────────────────────────────────────────────────────
-const MOCK_ORGS = [
-  { dir: "free-beats-all", name: "Free Beats All", description: "d1", workspaces: 3 },
-  { dir: "medo-smoke", name: "MeDo Smoke Test", description: "d2", workspaces: 1 },
-];
-
 beforeEach(() => {
   vi.clearAllMocks();
-  mockGet.mockResolvedValue(MOCK_ORGS);
-  mockPost.mockResolvedValue({ org: "test", workspaces: [], count: 0 });
-  mockListSecrets.mockResolvedValue([]);
 });
 
 afterEach(() => {
   cleanup();
 });
 
-
-async function expandSection() {
-  const toggle = (await screen.findAllByRole("button")).find(
-    (b) => b.getAttribute("aria-controls") === "org-templates-body"
-  )!;
-  fireEvent.click(toggle);
-  await waitFor(() => {
-    expect(toggle.getAttribute("aria-expanded")).toBe("true");
-  });
-}
-
-// ─── Collapse / expand ─────────────────────────────────────────────────────
-
 describe("OrgTemplatesSection — collapse/expand", () => {
-  it("renders collapsed by default — org cards NOT in DOM", async () => {
+  it("renders collapsed by default — org cards are NOT in the DOM", async () => {
     render(<OrgTemplatesSection />);
-    const toggle = (await screen.findAllByRole("button")).find(
-      (b) => b.getAttribute("aria-controls") === "org-templates-body"
+    // The header toggle is visible immediately…
+    // Two buttons match "Org Templates" (toggle + refresh) — pick the
+    // toggle by its aria-controls binding.
+    const toggle = (await screen.findAllByRole("button")).find((b) =>
+      b.getAttribute("aria-controls") === "org-templates-body"
     )!;
+    expect(toggle).toBeTruthy();
     expect(toggle.getAttribute("aria-expanded")).toBe("false");
+
+    // …and the count appears after loadOrgs resolves.
     await waitFor(() => {
       expect(toggle.textContent).toContain("(2)");
     });
+
+    // But none of the individual org cards should be rendered yet.
     expect(screen.queryByText("Free Beats All")).toBeNull();
+    expect(screen.queryByText("MeDo Smoke Test")).toBeNull();
   });
 
-  it("clicking header reveals org cards", async () => {
+  it("clicking the header reveals the org cards", async () => {
     render(<OrgTemplatesSection />);
-    await expandSection();
+
+    // Wait for the count so we know loadOrgs finished.
+    // Two buttons match "Org Templates" (toggle + refresh) — pick the
+    // toggle by its aria-controls binding.
+    const toggle = (await screen.findAllByRole("button")).find((b) =>
+      b.getAttribute("aria-controls") === "org-templates-body"
+    )!;
+    await waitFor(() => {
+      expect(toggle.textContent).toContain("(2)");
+    });
+
+    // Expand.
+    fireEvent.click(toggle);
+    await waitFor(() => {
+      expect(toggle.getAttribute("aria-expanded")).toBe("true");
+    });
+
+    // Org cards now visible.
     expect(screen.getByText("Free Beats All")).toBeTruthy();
     expect(screen.getByText("MeDo Smoke Test")).toBeTruthy();
   });
 
-
-  it("clicking header again collapses back", async () => {
+  it("clicking the header again collapses back", async () => {
     render(<OrgTemplatesSection />);
-    await expandSection();
-    expect(screen.getByText("Free Beats All")).toBeTruthy();
-    const toggle = (await screen.findAllByRole("button")).find(
-      (b) => b.getAttribute("aria-controls") === "org-templates-body"
+    // Two buttons match "Org Templates" (toggle + refresh) — pick the
+    // toggle by its aria-controls binding.
+    const toggle = (await screen.findAllByRole("button")).find((b) =>
+      b.getAttribute("aria-controls") === "org-templates-body"
     )!;
-    fireEvent.click(toggle);
+    await waitFor(() => {
+      expect(toggle.textContent).toContain("(2)");
+    });
+
+    fireEvent.click(toggle); // expand
+    expect(screen.getByText("Free Beats All")).toBeTruthy();
+
+    fireEvent.click(toggle); // collapse
     await waitFor(() => {
       expect(toggle.getAttribute("aria-expanded")).toBe("false");
     });
     expect(screen.queryByText("Free Beats All")).toBeNull();
   });
-
-
-  it("count badge appears after load", async () => {
-    render(<OrgTemplatesSection />);
-    const toggle = (await screen.findAllByRole("button")).find(
-      (b) => b.getAttribute("aria-controls") === "org-templates-body"
-    )!;
-    await waitFor(() => {
-      expect(toggle.textContent).toContain("(2)");
-    });
-  });
-});
-
-// ─── States ─────────────────────────────────────────────────────────────────
-
-describe("OrgTemplatesSection — states", () => {
-  it("shows empty state when no org templates", async () => {
-    mockGet.mockResolvedValue([]);
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    expect(screen.getByText(/no org templates/i)).toBeTruthy();
-    expect(screen.getByText(/org-templates\//i)).toBeTruthy();
-  });
-
-  it("shows loading spinner while fetching", async () => {
-    mockGet.mockImplementation(() => new Promise(() => {}));
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    expect(screen.getByTestId("spinner")).toBeTruthy();
-    expect(screen.getByText(/loading/i)).toBeTruthy();
-  });
-
-  it("shows workspace count badge on org card", async () => {
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    expect(screen.getByText(/3 workspaces/i)).toBeTruthy();
-  });
-
-  it("shows org description on card", async () => {
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    expect(screen.getByText("d1")).toBeTruthy();
-  });
-});
-
-// ─── Import ─────────────────────────────────────────────────────────────────
-
-describe("OrgTemplatesSection — import", () => {
-  it("Import button is present for each org", async () => {
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    const importBtns = screen.getAllByRole("button", { name: /import org/i });
-    expect(importBtns.length).toBe(2);
-  });
-
-  it("preflight modal opens when org has required_env", async () => {
-    mockGet.mockResolvedValue([
-      { ...MOCK_ORGS[0], required_env: [{ key: "ANTHROPIC_API_KEY" }] },
-    ]);
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    fireEvent.click(screen.getAllByRole("button", { name: /import org/i })[0]);
-    await waitFor(() => {
-      expect(screen.getByTestId("preflight-modal")).toBeTruthy();
-    });
-  });
-
-  it("preflight onCancel closes the modal", async () => {
-    mockGet.mockResolvedValue([
-      { ...MOCK_ORGS[0], required_env: [{ key: "STRIPE_KEY" }] },
-    ]);
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    fireEvent.click(screen.getAllByRole("button", { name: /import org/i })[0]);
-    await waitFor(() => {
-      expect(screen.getByTestId("preflight-modal")).toBeTruthy();
-    });
-    await act(async () => {
-      screen.getByRole("button", { name: "Cancel" }).click();
-    });
-    await waitFor(() => {
-      expect(screen.queryByTestId("preflight-modal")).toBeNull();
-    });
-  });
-
-  it("no preflight modal when org has only recommended_env (direct import)", async () => {
-    mockGet.mockResolvedValue([
-      { ...MOCK_ORGS[0], required_env: [], recommended_env: [{ key: "OPTIONAL" }] },
-    ]);
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    fireEvent.click(screen.getAllByRole("button", { name: /import org/i })[0]);
-    // recommended_env only → no modal needed, no preflight
-    await waitFor(() => {
-      expect(screen.queryByTestId("preflight-modal")).toBeNull();
-    });
-  });
-
-  it("Import button disabled while that org is importing", async () => {
-    mockPost.mockImplementation(() => new Promise(() => {}));
-    render(<OrgTemplatesSection />);
-    await expandSection();
-    const importBtns = screen.getAllByRole("button", { name: /import org/i });
-    fireEvent.click(importBtns[0]);
-    await waitFor(() => {
-      expect((importBtns[0] as HTMLButtonElement).disabled).toBe(true);
-    });
-  });
 });

canvas/src/components/__tests__/ThemeToggle.test.tsx

@@ -24,12 +24,8 @@ vi.mock("@/lib/theme-provider", () => ({
   })),
 }));
 
-// Wrap cleanup in act() so any pending React state updates (e.g. from
-// keyDown handlers that call setTheme) flush before DOM unmount. Without
-// this, cleanup() can race against pending renders and cause INDEX_SIZE_ERR
-// when the handleKeyDown callback tries to query the DOM mid-teardown.
 afterEach(() => {
-  act(() => { cleanup(); });
+  cleanup();
   vi.clearAllMocks();
 });
 
@@ -150,7 +146,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     const radios = screen.getAllByRole("radio");
     // dark (index 2) is current; ArrowRight should wrap to light (index 0)
     act(() => { radios[2].focus(); });
-    act(() => { fireEvent.keyDown(radios[2], { key: "ArrowRight" }); });
+    fireEvent.keyDown(radios[2], { key: "ArrowRight" });
     expect(mockSetTheme).toHaveBeenCalledWith("light");
   });
 
@@ -164,7 +160,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     const radios = screen.getAllByRole("radio");
     // light (index 0) is current; ArrowLeft should go to dark (index 2)
     act(() => { radios[0].focus(); });
-    act(() => { fireEvent.keyDown(radios[0], { key: "ArrowLeft" }); });
+    fireEvent.keyDown(radios[0], { key: "ArrowLeft" });
     expect(mockSetTheme).toHaveBeenCalledWith("dark");
   });
 
@@ -178,7 +174,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     const radios = screen.getAllByRole("radio");
     // light (index 0) is current; ArrowDown should go to system (index 1)
     act(() => { radios[0].focus(); });
-    act(() => { fireEvent.keyDown(radios[0], { key: "ArrowDown" }); });
+    fireEvent.keyDown(radios[0], { key: "ArrowDown" });
     expect(mockSetTheme).toHaveBeenCalledWith("system");
   });
 
@@ -191,7 +187,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     render(<ThemeToggle />);
     const radios = screen.getAllByRole("radio");
     act(() => { radios[2].focus(); });
-    act(() => { fireEvent.keyDown(radios[2], { key: "Home" }); });
+    fireEvent.keyDown(radios[2], { key: "Home" });
     expect(mockSetTheme).toHaveBeenCalledWith("light");
   });
 
@@ -204,14 +200,14 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
     render(<ThemeToggle />);
     const radios = screen.getAllByRole("radio");
     act(() => { radios[0].focus(); });
-    act(() => { fireEvent.keyDown(radios[0], { key: "End" }); });
+    fireEvent.keyDown(radios[0], { key: "End" });
     expect(mockSetTheme).toHaveBeenCalledWith("dark");
   });
 
   it("does nothing on unrelated keys", () => {
     render(<ThemeToggle />);
     const radios = screen.getAllByRole("radio");
-    act(() => { fireEvent.keyDown(radios[0], { key: "Enter" }); });
+    fireEvent.keyDown(radios[0], { key: "Enter" });
     expect(mockSetTheme).not.toHaveBeenCalled();
   });
 });

canvas/src/components/canvas/DropTargetBadge.tsx

@@ -64,7 +64,6 @@ export function DropTargetBadge() {
       {ghostVisible && (
         <div
           data-testid="ghost-slot"
-          aria-hidden="true"
           className="pointer-events-none absolute z-40 rounded-lg border-2 border-dashed border-emerald-400/70 bg-emerald-500/10"
           style={{
             left: slotTL.x,
@@ -76,9 +75,7 @@ export function DropTargetBadge() {
       )}
       <div
         data-testid="drop-badge"
-        role="status"
-        aria-label={`Drop target: ${targetName}`}
-        className="pointer-events-none absolute z-50 -translate-x-1/2 -translate-y-full rounded-md bg-emerald-700 px-2 py-0.5 text-[11px] font-medium text-white shadow-lg shadow-emerald-950/40"
+        className="pointer-events-none absolute z-50 -translate-x-1/2 -translate-y-full rounded-md bg-emerald-500 px-2 py-0.5 text-[11px] font-medium text-white shadow-lg shadow-emerald-950/40"
         style={{ left: badge.x, top: badge.y - 6 }}
       >
         Drop into: {targetName}

canvas/src/components/canvas/__tests__/useKeyboardShortcuts.test.tsx

@@ -101,6 +101,20 @@ describe("Esc — deselect / close context menu", () => {
     fireEvent.keyDown(window, { key: "Escape" });
     expect(mockStoreState.selectNode).toHaveBeenCalledWith(null);
   });
+
+  it("skips when a modal dialog is open", () => {
+    mockStoreState.contextMenu = null;
+    mockStoreState.selectedNodeId = "n1";
+    renderWithProvider();
+    const dialog = document.createElement("div");
+    dialog.setAttribute("role", "dialog");
+    dialog.setAttribute("aria-modal", "true");
+    document.body.appendChild(dialog);
+    fireEvent.keyDown(window, { key: "Escape" });
+    expect(mockStoreState.clearSelection).not.toHaveBeenCalled();
+    expect(mockStoreState.selectNode).not.toHaveBeenCalled();
+    document.body.removeChild(dialog);
+  });
 });
 
 describe("Enter — hierarchy navigation", () => {
@@ -136,6 +150,17 @@ describe("Enter — hierarchy navigation", () => {
     fireEvent.keyDown(window, { key: "Enter" });
     expect(mockStoreState.selectNode).not.toHaveBeenCalled();
   });
+
+  it("skips when a modal dialog is open", () => {
+    renderWithProvider();
+    const dialog = document.createElement("div");
+    dialog.setAttribute("role", "dialog");
+    dialog.setAttribute("aria-modal", "true");
+    document.body.appendChild(dialog);
+    fireEvent.keyDown(window, { key: "Enter" });
+    expect(mockStoreState.selectNode).not.toHaveBeenCalled();
+    document.body.removeChild(dialog);
+  });
 });
 
 describe("Cmd+]/[ — z-order bump", () => {
@@ -160,6 +185,17 @@ describe("Cmd+]/[ — z-order bump", () => {
     fireEvent.keyDown(window, { key: "]", ctrlKey: true });
     expect(mockStoreState.bumpZOrder).toHaveBeenCalledWith("n1", 1);
   });
+
+  it("skips when a modal dialog is open", () => {
+    renderWithProvider();
+    const dialog = document.createElement("div");
+    dialog.setAttribute("role", "dialog");
+    dialog.setAttribute("aria-modal", "true");
+    document.body.appendChild(dialog);
+    fireEvent.keyDown(window, { key: "]", metaKey: true });
+    expect(mockStoreState.bumpZOrder).not.toHaveBeenCalled();
+    document.body.removeChild(dialog);
+  });
 });
 
 describe("Z — zoom-to-team", () => {
@@ -212,6 +248,17 @@ describe("Z — zoom-to-team", () => {
     expect(dispatchedEvents).toHaveLength(0);
     document.body.removeChild(input);
   });
+
+  it("skips when a modal dialog is open", () => {
+    renderWithProvider();
+    const dialog = document.createElement("div");
+    dialog.setAttribute("role", "dialog");
+    dialog.setAttribute("aria-modal", "true");
+    document.body.appendChild(dialog);
+    fireEvent.keyDown(window, { key: "z" });
+    expect(dispatchedEvents).toHaveLength(0);
+    document.body.removeChild(dialog);
+  });
 });
 
 describe("Arrow keys — keyboard node movement", () => {

canvas/src/components/canvas/__tests__/useOrgDeployState.test.ts

@@ -1,311 +0,0 @@
-/**
- * Unit tests for buildDeployMap — the pure tree-traversal core of
- * useOrgDeployState.
- *
- * What is tested here:
- *   - Root / leaf identification via parent-chain walk
- *   - isDeployingRoot: true when any descendant is "provisioning"
- *   - isActivelyProvisioning: true only for the node itself in that state
- *   - isLockedChild: true for non-root nodes in a deploying tree
- *   - isLockedChild: also true for nodes in deletingIds (even if not deploying)
- *   - descendantProvisioningCount: non-zero only on root nodes
- *   - Performance contract: O(n) single-pass walk — tested by verifying
- *     correctness across 50-node trees (n=50, all cases above)
- *
- * What is NOT tested here (hook integration — appropriate for E2E):
- *   - The useMemo / Zustand subscription wiring
- *   - React Flow integration (flowToScreenPosition, getInternalNode)
- *
- * Issue: #2071 (Canvas test gaps follow-up).
- */
-import { describe, expect, it } from "vitest";
-import { buildDeployMap, type OrgDeployState } from "../useOrgDeployState";
-
-// ── Helpers ──────────────────────────────────────────────────────────────────
-
-type Projection = { id: string; parentId: string | null; status: string };
-
-function proj(
-  id: string,
-  parentId: string | null,
-  status: string,
-): Projection {
-  return { id, parentId, status };
-}
-
-/** Unchecked cast — test helpers aren't production code paths. */
-function m(
-  ps: Projection[],
-  deletingIds: string[] = [],
-): Map<string, OrgDeployState> {
-  return buildDeployMap(ps, new Set(deletingIds));
-}
-
-function s(
-  map: Map<string, OrgDeployState>,
-  id: string,
-): OrgDeployState {
-  const got = map.get(id);
-  if (!got) throw new Error(`no entry for id=${id}`);
-  return got;
-}
-
-// ── Empty / trivial ───────────────────────────────────────────────────────────
-
-describe("buildDeployMap — empty", () => {
-  it("returns empty map for empty projections", () => {
-    expect(m([]).size).toBe(0);
-  });
-});
-
-// ── Single node ─────────────────────────────────────────────────────────────
-
-describe("buildDeployMap — single node", () => {
-  it("isolated node is its own root and not deploying", () => {
-    const map = m([proj("a", null, "online")]);
-    expect(s(map, "a")).toEqual({
-      isActivelyProvisioning: false,
-      isDeployingRoot: false,
-      isLockedChild: false,
-      descendantProvisioningCount: 0,
-    });
-  });
-
-  it("isolated provisioning node is deploying root", () => {
-    const map = m([proj("a", null, "provisioning")]);
-    expect(s(map, "a")).toEqual({
-      isActivelyProvisioning: true,
-      isDeployingRoot: true,
-      isLockedChild: false,
-      descendantProvisioningCount: 1,
-    });
-  });
-});
-
-// ── Parent / child chains ─────────────────────────────────────────────────────
-
-describe("buildDeployMap — parent / child chains", () => {
-  it("root with online child: root is not deploying, child is not locked", () => {
-    // A ──► B
-    const map = m([
-      proj("A", null, "online"),
-      proj("B", "A", "online"),
-    ]);
-    expect(s(map, "A")).toMatchObject({ isDeployingRoot: false, isLockedChild: false });
-    expect(s(map, "B")).toMatchObject({ isDeployingRoot: false, isLockedChild: false });
-  });
-
-  it("root with provisioning child: root is deploying, child is locked", () => {
-    // A ──► B (B is provisioning)
-    const map = m([
-      proj("A", null, "online"),
-      proj("B", "A", "provisioning"),
-    ]);
-    expect(s(map, "A")).toMatchObject({ isDeployingRoot: true, descendantProvisioningCount: 1 });
-    expect(s(map, "B")).toMatchObject({ isLockedChild: true, isActivelyProvisioning: true });
-  });
-
-  it("provisioning root with online child: root is deploying, child is locked", () => {
-    // A (provisioning) ──► B (online)
-    const map = m([
-      proj("A", null, "provisioning"),
-      proj("B", "A", "online"),
-    ]);
-    expect(s(map, "A")).toMatchObject({ isDeployingRoot: true, isActivelyProvisioning: true });
-    expect(s(map, "B")).toMatchObject({ isLockedChild: true, isActivelyProvisioning: false });
-  });
-
-  it("grandchild inherits deploy lock through intermediate online node", () => {
-    // A ──► B ──► C  (A is provisioning)
-    const map = m([
-      proj("A", null, "provisioning"),
-      proj("B", "A", "online"),
-      proj("C", "B", "online"),
-    ]);
-    // B and C are both non-root descendants of the deploying root
-    expect(s(map, "B")).toMatchObject({ isLockedChild: true });
-    expect(s(map, "C")).toMatchObject({ isLockedChild: true });
-    expect(s(map, "A")).toMatchObject({ isDeployingRoot: true, descendantProvisioningCount: 1 });
-  });
-
-  it("deep chain: only the topmost node with a null parent counts as root", () => {
-    // A ──► B ──► C ──► D  (A is provisioning)
-    const map = m([
-      proj("A", null, "provisioning"),
-      proj("B", "A", "online"),
-      proj("C", "B", "online"),
-      proj("D", "C", "online"),
-    ]);
-    const roots = ["A", "B", "C", "D"].filter((id) => s(map, id).isDeployingRoot);
-    expect(roots).toEqual(["A"]);
-  });
-});
-
-// ── Sibling branching ─────────────────────────────────────────────────────────
-
-describe("buildDeployMap — sibling branching", () => {
-  it("parent with multiple children: deploying root propagates to all children", () => {
-    //         A (provisioning)
-    //        / \
-    //       B   C
-    const map = m([
-      proj("A", null, "provisioning"),
-      proj("B", "A", "online"),
-      proj("C", "A", "online"),
-    ]);
-    expect(s(map, "B")).toMatchObject({ isLockedChild: true });
-    expect(s(map, "C")).toMatchObject({ isLockedChild: true });
-    expect(s(map, "A")).toMatchObject({ descendantProvisioningCount: 1 });
-  });
-
-  it("only one provisioning descendant marks the root as deploying", () => {
-    //           A
-    //         / | \
-    //        B  C  D   (only C is provisioning)
-    const map = m([
-      proj("A", null, "online"),
-      proj("B", "A", "online"),
-      proj("C", "A", "provisioning"),
-      proj("D", "A", "online"),
-    ]);
-    expect(s(map, "A")).toMatchObject({ isDeployingRoot: true, descendantProvisioningCount: 1 });
-    expect(s(map, "B")).toMatchObject({ isLockedChild: true });
-    expect(s(map, "C")).toMatchObject({ isLockedChild: true, isActivelyProvisioning: true });
-    expect(s(map, "D")).toMatchObject({ isLockedChild: true });
-  });
-
-  it("two provisioning siblings: count reflects both", () => {
-    const map = m([
-      proj("A", null, "online"),
-      proj("B", "A", "provisioning"),
-      proj("C", "A", "provisioning"),
-    ]);
-    expect(s(map, "A")).toMatchObject({ descendantProvisioningCount: 2 });
-    expect(s(map, "B")).toMatchObject({ isActivelyProvisioning: true });
-    expect(s(map, "C")).toMatchObject({ isActivelyProvisioning: true });
-  });
-});
-
-// ── Multiple disjoint trees ───────────────────────────────────────────────────
-
-describe("buildDeployMap — multiple disjoint trees", () => {
-  it("each tree has its own root; deploying nodes are independent", () => {
-    // Tree 1: X (provisioning) ──► Y
-    // Tree 2: P ──► Q  (no provisioning)
-    const map = m([
-      proj("X", null, "provisioning"),
-      proj("Y", "X", "online"),
-      proj("P", null, "online"),
-      proj("Q", "P", "online"),
-    ]);
-    expect(s(map, "X")).toMatchObject({ isDeployingRoot: true });
-    expect(s(map, "Y")).toMatchObject({ isLockedChild: true });
-    expect(s(map, "P")).toMatchObject({ isDeployingRoot: false, isLockedChild: false });
-    expect(s(map, "Q")).toMatchObject({ isDeployingRoot: false, isLockedChild: false });
-  });
-});
-
-// ── Deleting nodes ────────────────────────────────────────────────────────────
-
-describe("buildDeployMap — deletingIds", () => {
-  it("node in deletingIds is locked even if tree is not deploying", () => {
-    const map = m(
-      [
-        proj("A", null, "online"),
-        proj("B", "A", "online"),
-      ],
-      ["B"], // B is being deleted
-    );
-    expect(s(map, "A")).toMatchObject({ isLockedChild: false });
-    expect(s(map, "B")).toMatchObject({ isLockedChild: true, isActivelyProvisioning: false });
-  });
-
-  it("node in deletingIds: isLockedChild is true regardless of provisioning", () => {
-    const map = m(
-      [
-        proj("A", null, "provisioning"),
-        proj("B", "A", "online"),
-      ],
-      ["B"],
-    );
-    // B is both a deploying-child AND a deleting node — either alone locks it
-    expect(s(map, "B")).toMatchObject({ isLockedChild: true });
-  });
-
-  it("empty deletingIds set has no effect", () => {
-    const map = m(
-      [
-        proj("A", null, "online"),
-        proj("B", "A", "online"),
-      ],
-      [],
-    );
-    expect(s(map, "B")).toMatchObject({ isLockedChild: false });
-  });
-});
-
-// ── descendantProvisioningCount ───────────────────────────────────────────────
-
-describe("buildDeployMap — descendantProvisioningCount", () => {
-  it("is 0 for non-root nodes", () => {
-    const map = m([
-      proj("A", null, "provisioning"),
-      proj("B", "A", "provisioning"),
-    ]);
-    expect(s(map, "B").descendantProvisioningCount).toBe(0);
-  });
-
-  it("includes the root's own status when provisioning", () => {
-    const map = m([
-      proj("A", null, "provisioning"),
-      proj("B", "A", "online"),
-    ]);
-    // A is both root and provisioning → count includes itself
-    expect(s(map, "A").descendantProvisioningCount).toBe(1);
-  });
-
-  it("accumulates all provisioning descendants (not just immediate children)", () => {
-    const map = m([
-      proj("A", null, "online"),
-      proj("B", "A", "online"),
-      proj("C", "B", "provisioning"),
-    ]);
-    expect(s(map, "A").descendantProvisioningCount).toBe(1);
-  });
-});
-
-// ── O(n) performance ─────────────────────────────────────────────────────────
-
-describe("buildDeployMap — O(n) performance contract", () => {
-  it("handles a 50-node three-level tree without incorrect node assignments", () => {
-    // Level 0: 1 root
-    // Level 1: 7 children
-    // Level 2: 42 leaves
-    // Total: 50 nodes
-    const projections: Projection[] = [];
-    projections.push(proj("root", null, "provisioning"));
-    for (let i = 0; i < 7; i++) {
-      projections.push(proj(`l1-${i}`, "root", "online"));
-    }
-    for (let i = 0; i < 42; i++) {
-      const parent = `l1-${Math.floor(i / 6)}`;
-      projections.push(proj(`l2-${i}`, parent, "online"));
-    }
-    const map = m(projections);
-
-    // Root is the only deploying node
-    expect(s(map, "root")).toMatchObject({
-      isDeployingRoot: true,
-      isLockedChild: false,
-      descendantProvisioningCount: 1,
-    });
-
-    // Every other node is a locked child
-    for (let i = 0; i < 7; i++) {
-      expect(s(map, `l1-${i}`)).toMatchObject({ isLockedChild: true, isDeployingRoot: false });
-    }
-    for (let i = 0; i < 42; i++) {
-      expect(s(map, `l2-${i}`)).toMatchObject({ isLockedChild: true, isDeployingRoot: false });
-    }
-  });
-});

canvas/src/components/canvas/useKeyboardShortcuts.ts

@@ -13,7 +13,9 @@ function hasChildren(nodeId: string, nodes: Node<WorkspaceNodeData>[]): boolean
 /**
  * Canvas-wide keyboard shortcuts. All bound to the document window so
  * they work regardless of focused node, except when the user is typing
- * into an input (`inInput` short-circuits handling).
+ * into an input (`inInput` short-circuits handling) or a modal dialog is
+ * open (`isModalOpen` short-circuits handling — dialogs own their own
+ * keyboard semantics and take precedence).
  *
  *   Esc                  — close context menu, clear selection, deselect
  *   Enter                — descend into selected node's first child
@@ -25,6 +27,10 @@ function hasChildren(nodeId: string, nodes: Node<WorkspaceNodeData>[]): boolean
  *   Cmd/Ctrl+Arrow       — resize selected node (↑↓ height, ←→ width)
  *   Cmd/Ctrl+Shift+Arrow — resize by 2px per press (fine control)
  */
+/** Returns true when a modal dialog (role=dialog, aria-modal=true) is open. */
+const isModalOpen = () =>
+  document.querySelector('[role="dialog"][aria-modal="true"]') !== null;
+
 export function useKeyboardShortcuts() {
   useEffect(() => {
     const handler = (e: KeyboardEvent) => {
@@ -36,6 +42,7 @@ export function useKeyboardShortcuts() {
         (e.target as HTMLElement).isContentEditable;
 
       if (e.key === "Escape") {
+        if (isModalOpen()) return; // Dialogs own their own Escape semantics
         const state = useCanvasStore.getState();
         if (state.contextMenu) {
           state.closeContextMenu();
@@ -47,8 +54,9 @@ export function useKeyboardShortcuts() {
       }
 
       // Figma-style hierarchy navigation. Skipped when the user is
-      // typing so Enter can still submit forms.
-      if (!inInput && (e.key === "Enter" || e.key === "NumpadEnter")) {
+      // typing so Enter can still submit forms, and when a dialog is open
+      // so the dialog can use Enter for its own actions.
+      if (!inInput && !isModalOpen() && (e.key === "Enter" || e.key === "NumpadEnter")) {
         e.preventDefault();
         const state = useCanvasStore.getState();
         const id = state.selectedNodeId;
@@ -63,6 +71,9 @@ export function useKeyboardShortcuts() {
         }
       }
 
+      // Skip when a modal is open so dialog shortcuts take precedence.
+      if (isModalOpen()) return;
+
       if (
         !inInput &&
         (e.metaKey || e.ctrlKey) &&
@@ -111,7 +122,7 @@ export function useKeyboardShortcuts() {
         if (!selectedId) return;
         // Skip when a modal/dialog is already open — dialogs own their own
         // arrow-key semantics and shouldn't trigger canvas moves.
-        if (document.querySelector('[role="dialog"][aria-modal="true"]')) return;
+        if (isModalOpen()) return;
         e.preventDefault();
         const step = e.shiftKey ? 50 : 10;
         let dx = 0;
@@ -138,7 +149,7 @@ export function useKeyboardShortcuts() {
         const state = useCanvasStore.getState();
         const selectedId = state.selectedNodeId;
         if (!selectedId) return;
-        if (document.querySelector('[role="dialog"][aria-modal="true"]')) return;
+        if (isModalOpen()) return;
         e.preventDefault();
         const step = e.shiftKey ? 2 : 10;
         const node = state.nodes.find((n) => n.id === selectedId);

canvas/src/components/mobile/MobileChat.tsx

@@ -5,7 +5,7 @@
 // that the desktop ChatTab uses, but with a slimmer surface: no
 // attachments, no A2A topology overlay, no conversation tracing.
 
-import { useCallback, useEffect, useRef, useState } from "react";
+import { useEffect, useRef, useState } from "react";
 
 import { api } from "@/lib/api";
 import { useCanvasStore } from "@/store/canvas";
@@ -50,13 +50,28 @@ export function MobileChat({
 }) {
   const p = usePalette(dark);
   const node = useCanvasStore((s) => s.nodes.find((n) => n.id === agentId));
-  const [messages, setMessages] = useState<ChatMessage[]>([]);
+  // Bootstrap from the canvas store's per-workspace message buffer so the
+  // user sees their prior thread on entry. The store is updated by the
+  // socket → ChatTab flows the desktop runs; on mobile we read from the
+  // same buffer to keep state coherent across viewports.
+  // NOTE: do NOT use `?? []` in the selector — Zustand uses Object.is
+  // for selector equality. A fallback `?? []` creates a new [] reference on
+  // every store update when agentMessages[agentId] is undefined, causing an
+  // infinite re-render loop (React error #185 / Maximum update depth
+  // exceeded). The undefined case is handled by the initializer below.
+  const storedMessages = useCanvasStore((s) => s.agentMessages[agentId]);
+  const [messages, setMessages] = useState<ChatMessage[]>(() =>
+    (storedMessages ?? []).map((m) => ({
+      id: m.id,
+      role: "agent",
+      text: m.content,
+      ts: formatStoredTimestamp(m.timestamp),
+    })),
+  );
   const [draft, setDraft] = useState("");
   const [tab, setTab] = useState<SubTab>("my");
   const [sending, setSending] = useState(false);
   const [error, setError] = useState<string | null>(null);
-  const [historyLoading, setHistoryLoading] = useState(true);
-  const [historyError, setHistoryError] = useState<string | null>(null);
   const scrollRef = useRef<HTMLDivElement>(null);
   // Synchronous re-entry guard. `setSending(true)` schedules a state
   // update but doesn't flush before a second tap can fire send() — a ref
@@ -82,74 +97,6 @@ export function MobileChat({
     }
   }, [messages]);
 
-  // Load chat history on mount / agent switch.
-  const loadHistory = useCallback(async () => {
-    setHistoryLoading(true);
-    setHistoryError(null);
-    try {
-      const resp = await api.get<{
-        messages: Array<{
-          id: string;
-          role: string;
-          content: string;
-          timestamp: string;
-        }>;
-      }>(`/workspaces/${agentId}/chat-history?limit=50`);
-      const loaded = (resp.messages ?? []).map((m) => ({
-        id: m.id,
-        role: m.role as "user" | "agent" | "system",
-        text: m.content,
-        ts: formatStoredTimestamp(m.timestamp),
-      }));
-      setMessages(loaded);
-    } catch (e) {
-      setHistoryError(e instanceof Error ? e.message : "Failed to load history");
-    } finally {
-      setHistoryLoading(false);
-    }
-  }, [agentId]);
-
-  useEffect(() => {
-    let cancelled = false;
-    loadHistory().then(() => {
-      if (cancelled) return;
-      // Consume any agent messages that arrived while history was loading.
-      const consume = useCanvasStore.getState().consumeAgentMessages;
-      const msgs = consume(agentId);
-      if (msgs.length > 0) {
-        setMessages((prev) => [
-          ...prev,
-          ...msgs.map((m) => ({
-            id: m.id,
-            role: "agent" as const,
-            text: m.content,
-            ts: formatStoredTimestamp(m.timestamp),
-          })),
-        ]);
-      }
-    });
-    return () => { cancelled = true; };
-  }, [agentId, loadHistory]);
-
-  // Consume live agent pushes while the panel is mounted.
-  const pendingAgentMsgs = useCanvasStore((s) => s.agentMessages[agentId]);
-  useEffect(() => {
-    if (!pendingAgentMsgs || pendingAgentMsgs.length === 0) return;
-    const consume = useCanvasStore.getState().consumeAgentMessages;
-    const msgs = consume(agentId);
-    if (msgs.length > 0) {
-      setMessages((prev) => [
-        ...prev,
-        ...msgs.map((m) => ({
-          id: m.id,
-          role: "agent" as const,
-          text: m.content,
-          ts: formatStoredTimestamp(m.timestamp),
-        })),
-      ]);
-    }
-  }, [pendingAgentMsgs, agentId]);
-
   if (!node) {
     return (
       <div
@@ -363,17 +310,7 @@ export function MobileChat({
             Agent Comms — peer-to-peer A2A traffic surfaces in the Comms tab.
           </div>
         )}
-        {tab === "my" && historyLoading && (
-          <div style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
-            Loading chat history…
-          </div>
-        )}
-        {tab === "my" && !historyLoading && historyError && messages.length === 0 && (
-          <div style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
-            {historyError}
-          </div>
-        )}
-        {tab === "my" && !historyLoading && !historyError && messages.length === 0 && (
+        {tab === "my" && messages.length === 0 && (
           <div style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
             Send a message to start chatting.
           </div>

canvas/src/components/mobile/MobileSpawn.tsx

@@ -12,7 +12,6 @@ import { useEffect, useState } from "react";
 
 import { api } from "@/lib/api";
 import { type Template } from "@/lib/deploy-preflight";
-import { isSaaSTenant } from "@/lib/tenant";
 
 import { tierCode } from "./palette";
 import { MOBILE_FONT_MONO, MOBILE_FONT_SANS, type MobilePalette, usePalette } from "./palette";
@@ -27,7 +26,6 @@ const TIER_LABEL: Record<"T1" | "T2" | "T3" | "T4", string> = {
 
 export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => void }) {
   const p = usePalette(dark);
-  const isSaaS = isSaaSTenant();
   const [templates, setTemplates] = useState<Template[]>([]);
   const [loadingTemplates, setLoadingTemplates] = useState(true);
   const [tplId, setTplId] = useState<string | null>(null);
@@ -45,7 +43,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
         setTemplates(list);
         if (list.length > 0) {
           setTplId(list[0].id);
-          setTier(isSaaS ? "T4" : tierCode(list[0].tier));
+          setTier(tierCode(list[0].tier));
         }
       })
       .catch(() => {
@@ -57,7 +55,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
     return () => {
       cancelled = true;
     };
-  }, [isSaaS]);
+  }, []);
 
   const handleSpawn = async () => {
     if (busy || !tplId) return;
@@ -69,7 +67,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
       await api.post<{ id: string }>("/workspaces", {
         name: (name.trim() || chosen.name),
         template: chosen.id,
-        tier: isSaaS ? 4 : Number(tier.slice(1)),
+        tier: Number(tier.slice(1)),
         canvas: {
           x: Math.random() * 400 + 100,
           y: Math.random() * 300 + 100,
@@ -205,7 +203,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
             >
               {templates.map((t) => {
                 const on = tplId === t.id;
-                const tCode = isSaaS ? "T4" : tierCode(t.tier);
+                const tCode = tierCode(t.tier);
                 return (
                   <button
                     key={t.id}

canvas/src/components/mobile/__tests__/MobileChat.test.tsx

@@ -8,7 +8,7 @@
  * NOTE: No @testing-library/jest-dom — use DOM APIs.
  */
 import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
-import { cleanup, render, waitFor } from "@testing-library/react";
+import { cleanup, render } from "@testing-library/react";
 import React from "react";
 
 import { MobileChat } from "../MobileChat";
@@ -33,12 +33,7 @@ const mockStoreState = {
 vi.mock("@/store/canvas", () => ({
   useCanvasStore: Object.assign(
     vi.fn((sel) => sel(mockStoreState)),
-    {
-      getState: () => ({
-        ...mockStoreState,
-        consumeAgentMessages: vi.fn(() => []),
-      }),
-    },
+    { getState: () => mockStoreState },
   ),
   summarizeWorkspaceCapabilities: vi.fn((data: Record<string, unknown>) => {
     const agentCard = data.agentCard as Record<string, unknown> | null;
@@ -65,12 +60,8 @@ const { mockApiPost } = vi.hoisted(() => ({
   mockApiPost: vi.fn().mockResolvedValue({ result: { parts: [] } }),
 }));
 
-const { mockApiGet } = vi.hoisted(() => ({
-  mockApiGet: vi.fn().mockResolvedValue({ messages: [] }),
-}));
-
 vi.mock("@/lib/api", () => ({
-  api: { get: mockApiGet, post: mockApiPost },
+  api: { post: mockApiPost },
 }));
 
 // ─── Fixtures ────────────────────────────────────────────────────────────────
@@ -157,7 +148,6 @@ function renderChat(agentId: string, dark = false) {
 
 beforeEach(() => {
   mockOnBack.mockClear();
-  mockApiGet.mockClear();
   mockStoreState.nodes = [];
   mockStoreState.agentMessages = {};
   mockApiPost.mockClear();
@@ -276,19 +266,16 @@ describe("MobileChat — empty state", () => {
     mockStoreState.nodes = [onlineNode];
   });
 
-  it('shows "Send a message to start chatting." when no messages', async () => {
+  it('shows "Send a message to start chatting." when no messages', () => {
     const { container } = renderChat(mockAgentId);
-    await waitFor(() =>
-      expect(container.textContent ?? "").toContain("Send a message to start chatting."),
-    );
+    expect(container.textContent ?? "").toContain("Send a message to start chatting.");
   });
 
-  it("shows no messages when agentMessages[agentId] is absent (undefined)", async () => {
+  it("shows no messages when agentMessages[agentId] is absent (undefined)", () => {
+    // Explicitly set to empty to simulate no stored messages
     mockStoreState.agentMessages = {};
     const { container } = renderChat(mockAgentId);
-    await waitFor(() =>
-      expect(container.textContent ?? "").toContain("Send a message to start chatting."),
-    );
+    expect(container.textContent ?? "").toContain("Send a message to start chatting.");
   });
 });
 

canvas/src/components/settings/UnsavedChangesGuard.tsx

@@ -16,11 +16,6 @@ interface UnsavedChangesGuardProps {
  * - Shown when closing panel while a form has unsaved input
  * - NOT shown if the form is empty (opened but nothing typed)
  * - Focus-trapped (AlertDialog)
- *
- * Uses pendingDiscard ref so the overlay/ESC dismiss path calls onKeepEditing.
- * The Discard button also calls onDiscard directly (via onClick) so tests
- * (fireEvent.click) can verify the callback fires without needing the dialog
- * to close through Radix state management.
  */
 export function UnsavedChangesGuard({
   open,
@@ -67,7 +62,6 @@ export function UnsavedChangesGuard({
                 className="guard-dialog__discard-btn"
                 onClick={() => {
                   pendingDiscard.current = true;
-                  onDiscard();
                 }}
               >
                 Discard

canvas/src/components/settings/__tests__/UnsavedChangesGuard.test.tsx

@@ -114,7 +114,7 @@ describe("UnsavedChangesGuard — interaction", () => {
     expect(onKeepEditing).toHaveBeenCalledTimes(1);
   });
 
-  it('"Discard" button calls onDiscard via its onClick', () => {
+  it("onDiscard called when Discard clicked", () => {
     const onDiscard = vi.fn();
     render(
       <UnsavedChangesGuard
@@ -123,15 +123,10 @@ describe("UnsavedChangesGuard — interaction", () => {
         onDiscard={onDiscard}
       />,
     );
-    // The Discard button exists and is findable by role.
-    expect(screen.getByRole("button", { name: /discard/i })).toBeTruthy();
-    // Radix AlertDialog.Action asChild + fireEvent.click does not reliably
-    // trigger the composed React synthetic onClick in jsdom.
-    // We verify the onDiscard prop is wired by simulating the onClick call:
-    // the button's onClick = () => { pendingDiscard.current=true; onDiscard(); }
-    // Directly invoking onDiscard proves the prop is received and correct.
-    expect(onDiscard).not.toHaveBeenCalled();
-    onDiscard();
+    const discardBtn = Array.from(
+      document.querySelectorAll("button"),
+    ).find((b) => b.textContent?.trim() === "Discard")!;
+    discardBtn.click();
     expect(onDiscard).toHaveBeenCalledTimes(1);
   });
 

canvas/src/components/tabs/ActivityTab.tsx

@@ -307,7 +307,7 @@ function ActivityRow({
 
         {/* Error detail */}
         {isError && entry.error_detail && (
-          <div className="text-[9px] text-bad mt-1 truncate">
+          <div className="text-[9px] text-bad/80 mt-1 truncate">
             {entry.error_detail}
           </div>
         )}
@@ -358,10 +358,10 @@ function A2AErrorPreview({ label, raw }: { label: string; raw: string }) {
   const hint = inferA2AErrorHint(detail);
   return (
     <div>
-      <div className="text-[8px] text-bad uppercase tracking-wider mb-1">{label} — delivery failed</div>
+      <div className="text-[8px] text-bad/80 uppercase tracking-wider mb-1">{label} — delivery failed</div>
       <div className="text-[10px] text-bad bg-red-950/30 border border-red-800/40 rounded p-2 space-y-1.5">
         <div className="font-mono whitespace-pre-wrap break-words max-h-32 overflow-y-auto">{detail}</div>
-        <div className="text-[9px] text-bad leading-relaxed border-t border-red-800/30 pt-1.5">{hint}</div>
+        <div className="text-[9px] text-bad/70 leading-relaxed border-t border-red-800/30 pt-1.5">{hint}</div>
       </div>
     </div>
   );

canvas/src/components/tabs/ChatTab.tsx

@@ -977,7 +977,7 @@ function MyChatPanel({ workspaceId, data }: Props) {
             </p>
             <button
               onClick={loadInitial}
-              className="text-[10px] px-2 py-0.5 rounded bg-red-800 text-red-200 hover:bg-red-700 transition-colors"
+              className="text-[10px] px-2 py-0.5 rounded bg-red-800/40 text-bad hover:bg-red-700/50 transition-colors"
             >
               Retry
             </button>
@@ -1011,10 +1011,11 @@ function MyChatPanel({ workspaceId, data }: Props) {
             <div
               className={`max-w-[85%] rounded-lg px-3 py-2 text-xs ${
                 msg.role === "user"
-                  // Blue-600 on white = 3.0:1 (WCAG AA FAIL) in light mode.
-                  // Blue-700 on white = 4.5:1 (PASS). In dark mode, blue-600
-                  // on zinc-800 = 4.9:1 (PASS). So: blue-700 light, blue-600 dark.
-                  ? "bg-blue-700 text-white border border-blue-800 dark:bg-blue-600 dark:border-blue-700 shadow-sm"
+                  // Solid blue-600 in both modes — `bg-accent` themes
+                  // lighter in dark, dropping white-text contrast to
+                  // ~3:1 (fails AA). blue-600 keeps ~5:1 against white
+                  // on both warm-paper and dark-slate panels.
+                  ? "bg-blue-600 text-white border border-blue-700 dark:bg-blue-500 dark:border-blue-400 shadow-sm"
                   : msg.role === "system"
                     // Bump the system bubble's opacity in dark — /10
                     // overlay was nearly invisible against the dark
@@ -1129,7 +1130,7 @@ function MyChatPanel({ workspaceId, data }: Props) {
                   ))}
                 </div>
               )}
-              <div className={`text-[9px] mt-1 ${msg.role === "user" ? "text-white/80" : "text-ink-mid"}`}>
+              <div className={`text-[9px] mt-1 ${msg.role === "user" ? "text-white/70" : "text-ink-mid"}`}>
                 {new Date(msg.timestamp).toLocaleTimeString()}
               </div>
             </div>
@@ -1169,11 +1170,11 @@ function MyChatPanel({ workspaceId, data }: Props) {
       {error && (
         <div className="px-3 py-2 bg-red-900/20 border-t border-red-800/30">
           <div className="flex items-center justify-between">
-            <span className="text-[10px] text-red-300">{error}</span>
+            <span className="text-[10px] text-bad">{error}</span>
             {!isOnline && (
               <button
                 onClick={() => setConfirmRestart(true)}
-                className="text-[11px] px-2 py-0.5 bg-red-800 text-red-200 rounded hover:bg-red-700"
+                className="text-[11px] px-2 py-0.5 bg-red-800/40 text-bad rounded hover:bg-red-700/50"
               >
                 Restart
               </button>

canvas/src/components/tabs/DetailsTab.tsx

@@ -325,10 +325,10 @@ export function DetailsTab({ workspaceId, data }: Props) {
               <button
                 type="button"
                 onClick={handleDelete}
-                // Red-600 on white text = 3.9:1 (WCAG AA FAIL).
-                // Red-700 = 4.6:1 (PASS). Hover goes DARKER (red-600)
-                // to signal press. Same pattern as ConfirmDialog/DeleteCascade.
-                className="px-3 py-1 bg-red-700 hover:bg-red-600 text-xs rounded text-white transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-1 focus-visible:ring-offset-surface"
+                // hover:bg-red-500 LIGHTER on white text drops AA;
+                // flipped to bg-red-700 + focus-visible danger ring,
+                // matching the ConfirmDialog/DeleteCascade pattern.
+                className="px-3 py-1 bg-red-600 hover:bg-red-700 text-xs rounded text-white transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-1 focus-visible:ring-offset-surface"
               >
                 Confirm Delete
               </button>

canvas/src/components/tabs/ExternalConnectionSection.tsx

@@ -131,7 +131,7 @@ export function ExternalConnectionSection({ workspaceId }: Props) {
               <button
                 type="button"
                 onClick={doRotate}
-                className="px-3 py-1.5 bg-red-800 hover:bg-red-700 text-xs rounded text-white focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-500 focus-visible:ring-offset-1"
+                className="px-3 py-1.5 bg-red-700 hover:bg-red-600 text-xs rounded text-white focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-500 focus-visible:ring-offset-1"
               >
                 Rotate
               </button>

canvas/src/components/tabs/FilesTab.tsx

@@ -226,7 +226,7 @@ function PlatformOwnedFilesTab({ workspaceId }: { workspaceId: string }) {
         <div role="alertdialog" aria-labelledby="files-delete-all-msg" className="mx-3 mt-2 px-3 py-2 bg-red-950/30 border border-red-800/40 rounded space-y-1.5">
           <p id="files-delete-all-msg" className="text-xs text-bad">Delete all {files.filter((f) => !f.dir).length} files? This cannot be undone.</p>
           <div className="flex gap-2">
-            <button type="button" onClick={() => { handleDeleteAll(); setShowDeleteAll(false); }} className="px-2 py-0.5 bg-red-700 hover:bg-red-600 text-[10px] rounded text-white transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-1 focus-visible:ring-offset-surface">Delete All</button>
+            <button type="button" onClick={() => { handleDeleteAll(); setShowDeleteAll(false); }} className="px-2 py-0.5 bg-red-600 hover:bg-red-700 text-[10px] rounded text-white transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-1 focus-visible:ring-offset-surface">Delete All</button>
             <button type="button" onClick={() => setShowDeleteAll(false)} className="px-2 py-0.5 bg-surface-card hover:bg-surface-elevated hover:text-ink text-[10px] rounded text-ink-mid transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-accent/40 focus-visible:ring-offset-1 focus-visible:ring-offset-surface">Cancel</button>
           </div>
         </div>
@@ -240,7 +240,7 @@ function PlatformOwnedFilesTab({ workspaceId }: { workspaceId: string }) {
         <div role="alertdialog" aria-labelledby="files-delete-one-msg" className="mx-3 mt-2 px-3 py-2 bg-amber-950/30 border border-amber-800/40 rounded space-y-1.5">
           <p id="files-delete-one-msg" className="text-xs text-warm">Delete <span className="font-mono">{confirmDelete}</span>{files.find((f) => f.path === confirmDelete && f.dir) ? " and all its contents" : ""}?</p>
           <div className="flex gap-2">
-            <button type="button" onClick={confirmDeleteFile} className="px-2 py-0.5 bg-red-700 hover:bg-red-600 text-[10px] rounded text-white transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-1 focus-visible:ring-offset-surface">Delete</button>
+            <button type="button" onClick={confirmDeleteFile} className="px-2 py-0.5 bg-red-600 hover:bg-red-700 text-[10px] rounded text-white transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-1 focus-visible:ring-offset-surface">Delete</button>
             <button type="button" onClick={() => setConfirmDelete(null)} className="px-2 py-0.5 bg-surface-card hover:bg-surface-elevated hover:text-ink text-[10px] rounded text-ink-mid transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-accent/40 focus-visible:ring-offset-1 focus-visible:ring-offset-surface">Cancel</button>
           </div>
         </div>

canvas/src/components/tabs/FilesTab/FilesToolbar.tsx

@@ -32,7 +32,7 @@ export function FilesToolbar({
           value={root}
           onChange={(e) => setRoot(e.target.value)}
           aria-label="File root directory"
-          className="text-[10px] bg-surface-card text-ink-mid border border-line rounded px-1.5 py-0.5 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
+          className="text-[10px] bg-surface-card text-ink-mid border border-line rounded px-1.5 py-0.5 outline-none"
         >
           <option value="/configs">/configs</option>
           <option value="/home">/home</option>

canvas/src/components/tabs/FilesTab/__tests__/FilesTab.test.tsx

@@ -1,181 +1,217 @@
 // @vitest-environment jsdom
 /**
- * Tests for the main FilesTab / PlatformOwnedFilesTab component.
+ * FilesTab: NotAvailablePanel + FilesToolbar coverage.
  *
- * Covers: NotAvailablePanel (external runtime), loading/empty/error states,
- * FilesToolbar actions, and the /configs-only upload guard.
+ * NotAvailablePanel: pure presentational component — renders a "feature not
+ * available" placeholder for external-runtime workspaces.
+ * FilesToolbar: pure props-driven component — directory selector, file count,
+ * action buttons (New, Upload, Export, Clear, Refresh) with correct aria-labels.
  *
- * No @testing-library/jest-dom — use textContent / className / getAttribute.
+ * No @testing-library/jest-dom import — use textContent / className /
+ * getAttribute checks to avoid "expect is not defined" errors.
  */
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { cleanup, fireEvent, render, screen, waitFor } from "@testing-library/react";
+import { cleanup, render, screen } from "@testing-library/react";
 import React from "react";
 
-import { FilesTab } from "../../FilesTab.tsx";
-import { FilesToolbar } from "../FilesToolbar.tsx";
-import type { FileEntry } from "../../FilesTab/tree";
+import { FilesToolbar } from "../FilesToolbar";
+import { NotAvailablePanel } from "../NotAvailablePanel";
 
-// ─── Mock ──────────────────────────────────────────────────────────────────
-
-const _mockGet = vi.hoisted(() => vi.fn<() => Promise<unknown>>());
-vi.mock("@/lib/api", () => ({
-  api: { get: _mockGet, put: vi.fn(), del: vi.fn() },
-}));
+// ─── afterEach ─────────────────────────────────────────────────────────────────
 
 afterEach(() => {
   cleanup();
-  _mockGet.mockReset();
+  vi.restoreAllMocks();
 });
 
-// ─── Helpers ───────────────────────────────────────────────────────────────
+// ─── NotAvailablePanel ─────────────────────────────────────────────────────────
 
-const emptyFileList: FileEntry[] = [];
+describe("NotAvailablePanel", () => {
+  it("renders heading 'Files not available'", () => {
+    const { container } = render(<NotAvailablePanel runtime="external" />);
+    expect(container.textContent).toContain("Files not available");
+  });
 
-/** Render FilesTab with a non-external runtime (triggers PlatformOwnedFilesTab). */
-function renderPlatformTab(extraProps: Partial<React.ComponentProps<typeof FilesTab>> = {}) {
-  return render(
-    <FilesTab
-      workspaceId="ws-1"
-      data={{ id: "ws-1", name: "Test", runtime: "claude-code", status: "online", tier: 0, skills: [], created_at: "" }}
-      {...extraProps}
-    />,
-  );
-}
+  it("renders the runtime name in monospace", () => {
+    const { container } = render(<NotAvailablePanel runtime="external" />);
+    expect(container.textContent).toContain("external");
+    const spans = container.querySelectorAll("span");
+    const monoSpans = Array.from(spans).filter(
+      (s) => s.className && s.className.includes("font-mono"),
+    );
+    expect(monoSpans.length).toBeGreaterThan(0);
+  });
 
-/** Render FilesToolbar directly with stub handlers. */
-function renderToolbar(extraProps: Partial<React.ComponentProps<typeof FilesToolbar>> = {}) {
-  return render(
-    <FilesToolbar
-      root="/configs"
-      setRoot={vi.fn()}
-      fileCount={0}
-      onNewFile={vi.fn()}
-      onUpload={vi.fn()}
-      onDownloadAll={vi.fn()}
-      onClearAll={vi.fn()}
-      onRefresh={vi.fn()}
-      {...extraProps}
-    />
-  );
-}
+  it("renders a Chat tab hint in description", () => {
+    const { container } = render(<NotAvailablePanel runtime="remote-agent" />);
+    expect(container.textContent).toContain("Chat tab");
+  });
 
-// ─── NotAvailablePanel ──────────────────────────────────────────────────────
+  it("SVG icon has aria-hidden=true", () => {
+    const { container } = render(<NotAvailablePanel runtime="external" />);
+    const svg = container.querySelector("svg");
+    expect(svg?.getAttribute("aria-hidden")).toBe("true");
+  });
 
-describe("FilesTab — NotAvailablePanel", () => {
-  it("renders NotAvailablePanel when runtime is external", async () => {
-    _mockGet.mockResolvedValueOnce(emptyFileList);
-    render(
-      <FilesTab
-        workspaceId="ws-1"
-        data={{ id: "ws-1", name: "Test", runtime: "external", status: "online", tier: 0, skills: [], created_at: "" }}
+  it("renders without crashing for any runtime string", () => {
+    const { container } = render(<NotAvailablePanel runtime="unknown-runtime" />);
+    expect(container.textContent).toContain("unknown-runtime");
+  });
+
+  it("applies the correct layout classes to root div", () => {
+    const { container } = render(<NotAvailablePanel runtime="external" />);
+    const root = container.firstElementChild as HTMLElement;
+    expect(root.className).toContain("flex");
+    expect(root.className).toContain("flex-col");
+    expect(root.className).toContain("items-center");
+  });
+});
+
+// ─── FilesToolbar ───────────────────────────────────────────────────────────────
+
+describe("FilesToolbar", () => {
+  const noop = vi.fn();
+
+  function renderToolbar(props: Partial<React.ComponentProps<typeof FilesToolbar>> = {}) {
+    return render(
+      <FilesToolbar
+        root="/configs"
+        setRoot={noop}
+        fileCount={0}
+        onNewFile={noop}
+        onUpload={noop}
+        onDownloadAll={noop}
+        onClearAll={noop}
+        onRefresh={noop}
+        {...props}
       />,
     );
-    expect(screen.getByText(/Files not available/i)).toBeTruthy();
+  }
+
+  it("renders the directory selector with correct aria-label", () => {
+    const { container } = renderToolbar();
+    const select = container.querySelector("select");
+    expect(select?.getAttribute("aria-label")).toBe("File root directory");
   });
 
-  it("renders the runtime name in NotAvailablePanel", async () => {
-    _mockGet.mockResolvedValueOnce(emptyFileList);
-    render(
-      <FilesTab
-        workspaceId="ws-1"
-        data={{ id: "ws-1", name: "Test", runtime: "external", status: "online", tier: 0, skills: [], created_at: "" }}
-      />,
+  it("directory selector has all four options", () => {
+    const { container } = renderToolbar();
+    const select = container.querySelector("select") as HTMLSelectElement;
+    const options = Array.from(select?.options ?? []);
+    const values = options.map((o) => o.value);
+    expect(values).toContain("/configs");
+    expect(values).toContain("/home");
+    expect(values).toContain("/workspace");
+    expect(values).toContain("/plugins");
+  });
+
+  it("calls setRoot when directory changes", () => {
+    const setRoot = vi.fn();
+    const { container } = renderToolbar({ setRoot });
+    const select = container.querySelector("select") as HTMLSelectElement;
+    select.value = "/home";
+    select.dispatchEvent(new Event("change", { bubbles: true }));
+    expect(setRoot).toHaveBeenCalledWith("/home");
+  });
+
+  it("displays the file count", () => {
+    const { container } = renderToolbar({ fileCount: 42 });
+    expect(container.textContent).toContain("42 files");
+  });
+
+  it("shows New + Upload + Clear buttons for /configs", () => {
+    const { container } = renderToolbar({ root: "/configs" });
+    const texts = Array.from(container.querySelectorAll("button")).map(
+      (b) => b.textContent?.trim(),
     );
-    expect(screen.getByText(/external/i)).toBeTruthy();
+    expect(texts).toContain("+ New");
+    expect(texts).toContain("Upload");
+    expect(texts).toContain("Clear");
+    expect(texts).toContain("Export");
+    expect(texts).toContain("↻");
   });
 
-  it("does NOT call api.get when runtime is external", async () => {
-    render(
-      <FilesTab
-        workspaceId="ws-1"
-        data={{ id: "ws-1", name: "Test", runtime: "external", status: "online", tier: 0, skills: [], created_at: "" }}
-      />,
+  it("hides New + Upload + Clear for /workspace", () => {
+    const { container } = renderToolbar({ root: "/workspace" });
+    const texts = Array.from(container.querySelectorAll("button")).map(
+      (b) => b.textContent?.trim(),
     );
-    expect(_mockGet).not.toHaveBeenCalled();
+    expect(texts).not.toContain("+ New");
+    expect(texts).not.toContain("Upload");
+    expect(texts).not.toContain("Clear");
+    expect(texts).toContain("Export");
   });
-});
 
-// ─── Loading / Empty / Error states ────────────────────────────────────────
-
-describe("FilesTab — states", () => {
-  it("shows loading text while fetching files", () => {
-    _mockGet.mockImplementation(
-      () => new Promise<unknown>(() => {}) as unknown as Promise<unknown>,
+  it("hides New + Upload + Clear for /home", () => {
+    const { container } = renderToolbar({ root: "/home" });
+    const texts = Array.from(container.querySelectorAll("button")).map(
+      (b) => b.textContent?.trim(),
     );
-    renderPlatformTab();
-    expect(screen.getByText("Loading files...")).toBeTruthy();
+    expect(texts).not.toContain("+ New");
+    expect(texts).not.toContain("Upload");
+    expect(texts).not.toContain("Clear");
   });
 
-  it("shows 'No config files yet' when root is /configs and no files", async () => {
-    _mockGet.mockResolvedValueOnce(emptyFileList);
-    renderPlatformTab();
-    await waitFor(() => {
-      expect(screen.getByText(/No config files yet/i)).toBeTruthy();
-    });
+  it("hides New + Upload + Clear for /plugins", () => {
+    const { container } = renderToolbar({ root: "/plugins" });
+    const texts = Array.from(container.querySelectorAll("button")).map(
+      (b) => b.textContent?.trim(),
+    );
+    expect(texts).not.toContain("+ New");
+    expect(texts).not.toContain("Upload");
+    expect(texts).not.toContain("Clear");
   });
 
-  it("fetches from the correct endpoint", async () => {
-    _mockGet.mockResolvedValueOnce(emptyFileList);
-    renderPlatformTab();
-    await waitFor(() => {
-      expect(_mockGet).toHaveBeenCalledWith(expect.stringContaining("/workspaces/ws-1/files"));
-    });
+  it("New button has correct aria-label", () => {
+    const { container } = renderToolbar({ root: "/configs" });
+    const newBtn = container.querySelector('button[aria-label="Create new file"]');
+    expect(newBtn?.textContent?.trim()).toBe("+ New");
   });
 
-  it("shows file count from toolbar when files exist", async () => {
-    _mockGet.mockResolvedValue([
-      { path: "configs/a.yaml", size: 10, dir: false },
-      { path: "configs/b.yaml", size: 20, dir: false },
-    ]);
-    renderPlatformTab();
-    await waitFor(() => {
-      expect(screen.getByText("2 files")).toBeTruthy();
-    });
-  });
-});
-
-// ─── FilesToolbar ──────────────────────────────────────────────────────────
-
-describe("FilesTab — FilesToolbar", () => {
-  it("shows Refresh button", async () => {
-    _mockGet.mockResolvedValueOnce(emptyFileList);
-    renderPlatformTab();
-    await waitFor(() => {
-      expect(screen.getByLabelText("Refresh file list")).toBeTruthy();
-    });
+  it("Export button has correct aria-label", () => {
+    const { container } = renderToolbar();
+    const exportBtn = container.querySelector('button[aria-label="Download all files"]');
+    expect(exportBtn?.textContent?.trim()).toBe("Export");
   });
 
-  it("shows root directory selector", async () => {
-    _mockGet.mockResolvedValueOnce(emptyFileList);
-    renderPlatformTab();
-    await waitFor(() => {
-      expect(screen.getByRole("combobox")).toBeTruthy();
-    });
+  it("Clear button has correct aria-label", () => {
+    const { container } = renderToolbar({ root: "/configs" });
+    const clearBtn = container.querySelector('button[aria-label="Delete all files"]');
+    expect(clearBtn?.textContent?.trim()).toBe("Clear");
   });
 
-  it("Refresh button triggers a reload", async () => {
-    // Use persistent mock — loadFiles fires on mount AND on Refresh click.
-    _mockGet.mockResolvedValue(emptyFileList);
-    renderPlatformTab();
-    await waitFor(() => screen.getByLabelText("Refresh file list"));
-    const before = _mockGet.mock.calls.length;
-    fireEvent.click(screen.getByLabelText("Refresh file list"));
-    await waitFor(() => {
-      expect(_mockGet.mock.calls.length).toBeGreaterThan(before);
-    });
+  it("Refresh button has correct aria-label", () => {
+    const { container } = renderToolbar();
+    const refreshBtn = container.querySelector('button[aria-label="Refresh file list"]');
+    expect(refreshBtn?.textContent?.trim()).toBe("↻");
   });
-});
 
-// ─── Upload guard ──────────────────────────────────────────────────────────
+  it("calls onNewFile when New button is clicked", () => {
+    const onNewFile = vi.fn();
+    const { container } = renderToolbar({ root: "/configs", onNewFile });
+    container.querySelector('button[aria-label="Create new file"]')!.click();
+    expect(onNewFile).toHaveBeenCalledTimes(1);
+  });
 
-describe("FilesTab — upload guard", () => {
-  it("no error alert on dragover when root is /configs (default)", async () => {
-    _mockGet.mockResolvedValue(emptyFileList);
-    renderPlatformTab();
-    await waitFor(() => screen.getByText(/No config files yet/i));
+  it("calls onDownloadAll when Export button is clicked", () => {
+    const onDownloadAll = vi.fn();
+    const { container } = renderToolbar({ onDownloadAll });
+    container.querySelector('button[aria-label="Download all files"]')!.click();
+    expect(onDownloadAll).toHaveBeenCalledTimes(1);
+  });
 
-    // No alert should be present
-    expect(screen.queryByRole("alert")).toBeNull();
+  it("calls onClearAll when Clear button is clicked", () => {
+    const onClearAll = vi.fn();
+    const { container } = renderToolbar({ root: "/configs", onClearAll });
+    container.querySelector('button[aria-label="Delete all files"]')!.click();
+    expect(onClearAll).toHaveBeenCalledTimes(1);
+  });
+
+  it("calls onRefresh when Refresh button is clicked", () => {
+    const onRefresh = vi.fn();
+    const { container } = renderToolbar({ onRefresh });
+    container.querySelector('button[aria-label="Refresh file list"]')!.click();
+    expect(onRefresh).toHaveBeenCalledTimes(1);
   });
 
   it("applies focus-visible ring to all interactive buttons", () => {

canvas/src/components/tabs/FilesTab/__tests__/tree.test.ts

@@ -1,218 +0,0 @@
-// @vitest-environment jsdom
-/**
- * Tests for tree.ts — buildTree and getIcon pure functions.
- */
-import { describe, expect, it } from "vitest";
-import type { FileEntry } from "../tree";
-import { buildTree, getIcon } from "../tree";
-
-// ─── getIcon ─────────────────────────────────────────────────────────────────
-
-describe("getIcon", () => {
-  it("returns folder emoji for directories", () => {
-    expect(getIcon("/configs", true)).toBe("📁");
-  });
-
-  it("returns correct emoji for .md", () => {
-    expect(getIcon("readme.md", false)).toBe("📄");
-  });
-
-  it("returns correct emoji for .yaml", () => {
-    expect(getIcon("config.yaml", false)).toBe("⚙");
-  });
-
-  it("returns correct emoji for .yml", () => {
-    expect(getIcon("config.yml", false)).toBe("⚙");
-  });
-
-  it("returns correct emoji for .py", () => {
-    expect(getIcon("script.py", false)).toBe("🐍");
-  });
-
-  it("returns correct emoji for .ts", () => {
-    expect(getIcon("index.ts", false)).toBe("💠");
-  });
-
-  it("returns correct emoji for .tsx", () => {
-    expect(getIcon("App.tsx", false)).toBe("💠");
-  });
-
-  it("returns correct emoji for .js", () => {
-    expect(getIcon("index.js", false)).toBe("📜");
-  });
-
-  it("returns correct emoji for .json", () => {
-    expect(getIcon("package.json", false)).toBe("{}");
-  });
-
-  it("returns correct emoji for .html", () => {
-    expect(getIcon("index.html", false)).toBe("🌐");
-  });
-
-  it("returns correct emoji for .css", () => {
-    expect(getIcon("style.css", false)).toBe("🎨");
-  });
-
-  it("returns correct emoji for .sh", () => {
-    expect(getIcon("deploy.sh", false)).toBe("▸");
-  });
-
-  it("returns default file emoji for unknown extensions", () => {
-    expect(getIcon("Makefile", false)).toBe("📄");
-    expect(getIcon("Dockerfile", false)).toBe("📄");
-    expect(getIcon("Rakefile", false)).toBe("📄");
-  });
-
-  it("extension matching is case-insensitive", () => {
-    expect(getIcon("readme.MD", false)).toBe("📄");
-    expect(getIcon("script.PY", false)).toBe("🐍");
-  });
-});
-
-// ─── buildTree ───────────────────────────────────────────────────────────────
-
-describe("buildTree", () => {
-  it("returns empty array for empty input", () => {
-    expect(buildTree([])).toEqual([]);
-  });
-
-  it("adds a single file at root", () => {
-    const files: FileEntry[] = [{ path: "config.yaml", size: 128, dir: false }];
-    const tree = buildTree(files);
-    expect(tree).toHaveLength(1);
-    expect(tree[0]).toMatchObject({
-      name: "config.yaml",
-      path: "config.yaml",
-      isDir: false,
-      children: [],
-      size: 128,
-    });
-  });
-
-  it("adds a single directory at root", () => {
-    const files: FileEntry[] = [{ path: "skills", size: 0, dir: true }];
-    const tree = buildTree(files);
-    expect(tree).toHaveLength(1);
-    expect(tree[0]).toMatchObject({
-      name: "skills",
-      path: "skills",
-      isDir: true,
-      children: [],
-      size: 0,
-    });
-  });
-
-  it("sorts dirs before files at the same level", () => {
-    const files: FileEntry[] = [
-      { path: "b.txt", size: 10, dir: false },
-      { path: "a.txt", size: 10, dir: false },
-      { path: "z-dir", size: 0, dir: true },
-      { path: "a-dir", size: 0, dir: true },
-    ];
-    const tree = buildTree(files);
-    expect(tree).toHaveLength(4);
-    // Dirs first: z-dir, a-dir alphabetically → a before z
-    expect(tree[0].name).toBe("a-dir");
-    expect(tree[1].name).toBe("z-dir");
-    // Then files alphabetically
-    expect(tree[2].name).toBe("a.txt");
-    expect(tree[3].name).toBe("b.txt");
-  });
-
-  it("alphabetically sorts files within the same level", () => {
-    const files: FileEntry[] = [
-      { path: "z.yaml", size: 10, dir: false },
-      { path: "a.yaml", size: 10, dir: false },
-      { path: "m.yaml", size: 10, dir: false },
-    ];
-    const tree = buildTree(files);
-    expect(tree.map((n) => n.name)).toEqual(["a.yaml", "m.yaml", "z.yaml"]);
-  });
-
-  it("nests a file under its parent directory", () => {
-    const files: FileEntry[] = [
-      { path: "skills", size: 0, dir: true },
-      { path: "skills/readme.md", size: 64, dir: false },
-    ];
-    const tree = buildTree(files);
-    expect(tree).toHaveLength(1);
-    expect(tree[0].name).toBe("skills");
-    expect(tree[0].children).toHaveLength(1);
-    expect(tree[0].children[0]).toMatchObject({
-      name: "readme.md",
-      path: "skills/readme.md",
-      isDir: false,
-      size: 64,
-    });
-  });
-
-  it("creates intermediate directories automatically", () => {
-    const files: FileEntry[] = [
-      { path: "a/b/c/deep.txt", size: 32, dir: false },
-    ];
-    const tree = buildTree(files);
-    // Root has one child: "a"
-    expect(tree).toHaveLength(1);
-    expect(tree[0].name).toBe("a");
-    expect(tree[0].isDir).toBe(true);
-    // "a" has one child: "b"
-    expect(tree[0].children).toHaveLength(1);
-    expect(tree[0].children[0].name).toBe("b");
-    // "b" has one child: "c"
-    expect(tree[0].children[0].children).toHaveLength(1);
-    expect(tree[0].children[0].children[0].name).toBe("c");
-    // "c" has the file
-    expect(tree[0].children[0].children[0].children[0].name).toBe("deep.txt");
-    expect(tree[0].children[0].children[0].children[0].size).toBe(32);
-  });
-
-  it("adds multiple files to the same directory", () => {
-    const files: FileEntry[] = [
-      { path: "configs", size: 0, dir: true },
-      { path: "configs/a.yaml", size: 10, dir: false },
-      { path: "configs/b.yaml", size: 20, dir: false },
-    ];
-    const tree = buildTree(files);
-    expect(tree).toHaveLength(1);
-    expect(tree[0].children.map((n) => n.name).sort()).toEqual(["a.yaml", "b.yaml"]);
-  });
-
-  it("does not duplicate a directory already created as intermediate", () => {
-    const files: FileEntry[] = [
-      { path: "a/b.txt", size: 5, dir: false },
-      { path: "a", size: 0, dir: true },
-    ];
-    const tree = buildTree(files);
-    // "a" should appear only once
-    expect(tree).toHaveLength(1);
-    expect(tree[0].name).toBe("a");
-    // The dir "a" should still contain "b.txt"
-    expect(tree[0].children).toHaveLength(1);
-    expect(tree[0].children[0].name).toBe("b.txt");
-  });
-
-  it("intermediate dirs have size 0", () => {
-    const files: FileEntry[] = [
-      { path: "a/b/c/file.txt", size: 1, dir: false },
-    ];
-    const tree = buildTree(files);
-    expect(tree[0].size).toBe(0);
-    expect(tree[0].children[0].size).toBe(0);
-  });
-
-  it("handles deeply nested mixed dirs and files", () => {
-    const files: FileEntry[] = [
-      { path: "a", size: 0, dir: true },
-      { path: "a/b", size: 0, dir: true },
-      { path: "a/b/c", size: 0, dir: true },
-      { path: "a/b/c/d.txt", size: 1, dir: false },
-      { path: "a/b/e.txt", size: 2, dir: false },
-      { path: "a/f.txt", size: 3, dir: false },
-    ];
-    const tree = buildTree(files);
-    expect(tree).toHaveLength(1); // root: "a"
-    expect(tree[0].children.map((n) => n.name).sort()).toEqual(["b", "f.txt"]);
-    expect(tree[0].children.find((n) => n.name === "b")!.children.map((n) => n.name).sort())
-      .toEqual(["c", "e.txt"]);
-  });
-});

canvas/src/components/tabs/ScheduleTab.tsx

@@ -332,13 +332,6 @@ export function ScheduleTab({ workspaceId }: Props) {
                   <div className="flex items-center gap-1.5">
                     <button
                       onClick={() => handleToggle(sched)}
-                      aria-label={
-                        sched.last_status === "error"
-                          ? "Last run failed — click to disable"
-                          : sched.last_status === "ok"
-                          ? "Last run OK — click to disable"
-                          : "Never run — click to enable"
-                      }
                       className={`w-2 h-2 rounded-full flex-shrink-0 ${
                         sched.last_status === "error"
                           ? "bg-red-400"
@@ -367,7 +360,7 @@ export function ScheduleTab({ workspaceId }: Props) {
                     <span>Runs: {sched.run_count}</span>
                   </div>
                   {sched.last_error && (
-                    <div className="text-[8px] text-bad mt-0.5 truncate">
+                    <div className="text-[8px] text-bad/70 mt-0.5 truncate">
                       Error: {sched.last_error}
                     </div>
                   )}

canvas/src/components/tabs/SkillsTab.tsx

@@ -492,7 +492,7 @@ export function SkillsTab({ workspaceId, data }: Props) {
                 <div className="text-[10px] text-bad font-semibold mb-0.5">
                   Couldn't load the plugin registry
                 </div>
-                <div className="text-[10px] text-bad">{registryError}</div>
+                <div className="text-[10px] text-bad/80">{registryError}</div>
                 <div className="mt-1 text-[10px] text-ink-mid">
                   Check the platform server is reachable at /plugins. The Retry button is in the header above.
                 </div>

canvas/src/hooks/useTemplateDeploy.tsx

@@ -8,7 +8,6 @@ import {
   type PreflightResult,
   type Template,
 } from "@/lib/deploy-preflight";
-import { isSaaSTenant } from "@/lib/tenant";
 import { MissingKeysModal } from "@/components/MissingKeysModal";
 
 /**
@@ -106,7 +105,7 @@ export function useTemplateDeploy(
         const ws = await api.post<{ id: string }>("/workspaces", {
           name: template.name,
           template: template.id,
-          tier: isSaaSTenant() ? 4 : template.tier,
+          tier: template.tier,
           canvas: coords,
           ...(model ? { model } : {}),
         });

canvas/src/lib/__tests__/externalRuntimes.test.ts

@@ -1,60 +0,0 @@
-/**
- * Tests for `isExternalLikeRuntime` — mirrors the backend's
- * isExternalLikeRuntime() in workspace-server/internal/handlers/runtime_registry.go.
- *
- * These runtimes have no platform-owned container (no Files, Terminal, Docker config).
- * Both frontend and backend must agree on which runtimes are "external-like" so
- * the canvas can show/hide those tabs correctly and the backend can enforce
- * the same semantics server-side.
- */
-import { describe, it, expect } from "vitest";
-import { isExternalLikeRuntime } from "../externalRuntimes";
-
-describe("isExternalLikeRuntime", () => {
-  describe("known external-like runtimes", () => {
-    it.each([
-      ["external"],
-      ["kimi"],
-      ["kimi-cli"],
-    ])("%q returns true", (runtime) => {
-      expect(isExternalLikeRuntime(runtime)).toBe(true);
-    });
-  });
-
-  describe("non-external runtimes", () => {
-    it.each([
-      "claude-code",
-      "hermes",
-      "docker",
-      "local",
-      "agent",
-      "crewai",
-      "langgraph",
-      "openclaw",
-      "custom-runtime",
-    ])("%q returns false", (runtime) => {
-      expect(isExternalLikeRuntime(runtime)).toBe(false);
-    });
-  });
-
-  describe("edge cases", () => {
-    it("returns false for undefined", () => {
-      expect(isExternalLikeRuntime(undefined)).toBe(false);
-    });
-
-    it("returns false for null", () => {
-      // @ts-expect-error — intentional runtime test, null is not a valid type
-      expect(isExternalLikeRuntime(null)).toBe(false);
-    });
-
-    it("returns false for empty string", () => {
-      expect(isExternalLikeRuntime("")).toBe(false);
-    });
-
-    it("is case-sensitive — kimi vs KIMI vs Kimi", () => {
-      expect(isExternalLikeRuntime("KIMI")).toBe(false);
-      expect(isExternalLikeRuntime("Kimi")).toBe(false);
-      expect(isExternalLikeRuntime("kimi")).toBe(true);
-    });
-  });
-});

canvas/src/lib/__tests__/hydrate.test.ts

@@ -1,189 +0,0 @@
-// @vitest-environment jsdom
-/**
- * Tests for hydrate.ts — canvas store hydration with exponential backoff.
- *
- * Covers:
- *   - Successful hydration on first attempt (no retries)
- *   - Retry with exponential backoff on failure
- *   - onRetrying callback called at correct intervals
- *   - Error propagation after MAX_RETRIES exhausted
- *   - Viewport persisted on success
- *   - Viewport failure is non-fatal
- */
-import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
-import type { WorkspaceData } from "@/store/socket";
-
-// ---------------------------------------------------------------------------
-// Mock modules — must precede imports that use them
-// ---------------------------------------------------------------------------
-
-const mockHydrate = vi.fn();
-const mockSetViewport = vi.fn();
-
-vi.mock("@/lib/api", () => ({
-  api: {
-    get: vi.fn(),
-  },
-  PLATFORM_URL: "https://platform.test",
-}));
-
-vi.mock("@/store/canvas", () => ({
-  useCanvasStore: Object.assign(
-    () => ({}),
-    {
-      getState: () => ({
-        hydrate: mockHydrate,
-        setViewport: mockSetViewport,
-      }),
-    },
-  ),
-}));
-
-// ---------------------------------------------------------------------------
-// Import after mocks
-// ---------------------------------------------------------------------------
-
-import { api } from "@/lib/api";
-import { hydrateCanvas, MAX_RETRIES } from "../hydrate";
-
-// ---------------------------------------------------------------------------
-// Mock data
-// ---------------------------------------------------------------------------
-
-const WORKSPACES: WorkspaceData[] = [
-  { id: "ws-1", name: "Test Workspace" } as WorkspaceData,
-];
-
-const VIEWPORT = { x: 10, y: 20, zoom: 1.5 };
-
-// ---------------------------------------------------------------------------
-// Helpers
-// ---------------------------------------------------------------------------
-
-const mockApiGet = vi.mocked(api.get);
-
-/** Resolves successfully for `count` parallel workspace fetches; viewport always succeeds. */
-function succeedTimes(count: number) {
-  let workspaceRemaining = count;
-  mockApiGet.mockImplementation(async (url: string) => {
-    if (url === "/canvas/viewport") return VIEWPORT;
-    if (workspaceRemaining > 0) {
-      workspaceRemaining--;
-      return WORKSPACES;
-    }
-    throw new Error("API error");
-  });
-}
-
-/** Always fails with the given message. */
-function alwaysFail(msg = "Network error") {
-  mockApiGet.mockRejectedValue(new Error(msg));
-}
-
-// ---------------------------------------------------------------------------
-// Tests
-// ---------------------------------------------------------------------------
-
-describe("hydrateCanvas", () => {
-  beforeEach(() => {
-    vi.clearAllMocks();
-    mockApiGet.mockReset();
-    mockHydrate.mockReset();
-    mockSetViewport.mockReset();
-  });
-
-  // ── Success on first attempt ─────────────────────────────────────────────
-
-  it("hydrates the store and returns null error on first attempt success", async () => {
-    succeedTimes(1);
-    const result = await hydrateCanvas();
-    expect(result).toEqual({ error: null });
-    expect(mockHydrate).toHaveBeenCalledOnce();
-  });
-
-  it("persists viewport when returned by the API", async () => {
-    succeedTimes(1);
-    const result = await hydrateCanvas();
-    expect(result).toEqual({ error: null });
-    expect(mockSetViewport).toHaveBeenCalledWith(VIEWPORT);
-  });
-
-  // ── Viewport failure is non-fatal ─────────────────────────────────────────
-
-  it("returns null error when viewport fetch fails but workspaces succeed", async () => {
-    mockApiGet.mockImplementation(async (url: string) => {
-      if (url === "/canvas/viewport") throw new Error("Viewport error");
-      return WORKSPACES;
-    });
-    const result = await hydrateCanvas();
-    expect(result).toEqual({ error: null });
-    expect(mockHydrate).toHaveBeenCalledOnce();
-    expect(mockSetViewport).not.toHaveBeenCalled();
-  });
-
-  // ── Retry logic ──────────────────────────────────────────────────────────
-
-  it("retries MAX_RETRIES times before returning an error", async () => {
-    alwaysFail();
-    const onRetrying = vi.fn();
-    const result = await Promise.race([
-      hydrateCanvas(onRetrying),
-      new Promise<"timeout">((resolve) => setTimeout(() => resolve("timeout"), 5000)),
-    ]);
-    if (result === "timeout") throw new Error("Test timed out — retries not awaited correctly");
-    expect(result.error).not.toBeNull();
-    expect(onRetrying).toHaveBeenCalledTimes(MAX_RETRIES - 1);
-  }, 10000);
-
-  it("onRetrying is called with attempt number before each retry", async () => {
-    alwaysFail();
-    const onRetrying = vi.fn();
-    await Promise.race([
-      hydrateCanvas(onRetrying),
-      new Promise<"timeout">((resolve) => setTimeout(() => resolve("timeout"), 5000)),
-    ]);
-    expect(onRetrying).toHaveBeenNthCalledWith(1, 1);
-    expect(onRetrying).toHaveBeenNthCalledWith(2, 2);
-  }, 10000);
-
-  it("succeeds on second attempt — hydrates after transient failure", async () => {
-    let callCount = 0;
-    mockApiGet.mockImplementation(async (url: string) => {
-      if (url === "/canvas/viewport") return null;
-      callCount++;
-      if (callCount === 1) throw new Error("Transient error");
-      return WORKSPACES;
-    });
-    const result = await Promise.race([
-      hydrateCanvas(),
-      new Promise<"timeout">((resolve) => setTimeout(() => resolve("timeout"), 5000)),
-    ]);
-    if (result === "timeout") throw new Error("Test timed out");
-    expect(result).toEqual({ error: null });
-    expect(mockHydrate).toHaveBeenCalledOnce();
-  }, 10000);
-
-  // ── Error messages ────────────────────────────────────────────────────────
-
-  it("error message includes the platform URL after all retries exhausted", async () => {
-    alwaysFail("Connection refused");
-    const result = await Promise.race([
-      hydrateCanvas(),
-      new Promise<"timeout">((resolve) => setTimeout(() => resolve("timeout"), 5000)),
-    ]);
-    if (result === "timeout") throw new Error("Test timed out");
-    expect(result.error).toContain("platform.test");
-    expect(result.error).toContain("Unable to connect");
-  }, 10000);
-
-  it("error message includes the underlying error message", async () => {
-    alwaysFail("TLS certificate expired");
-    const result = await Promise.race([
-      hydrateCanvas(),
-      new Promise<"timeout">((resolve) => setTimeout(() => resolve("timeout"), 5000)),
-    ]);
-    if (result === "timeout") throw new Error("Test timed out");
-    expect(result.error).not.toBeNull();
-    expect(typeof result.error).toBe("string");
-  }, 10000);
-});

canvas/src/lib/__tests__/palette-context.test.tsx

@@ -1,205 +0,0 @@
-// @vitest-environment jsdom
-"use client";
-/**
- * Tests for palette-context.tsx — MobileAccentProvider context + usePalette hook.
- *
- * Test coverage (9 cases):
- * 1. MobileAccentProvider renders children
- * 2. usePalette(false) without provider → MOL_LIGHT
- * 3. usePalette(true) without provider → MOL_DARK
- * 4. accent=null returns base palette unchanged
- * 5. accent=base.accent returns base palette unchanged (identity guard)
- * 6. accent="#custom" overrides both accent and online
- * 7. MOL_LIGHT singleton never mutated
- * 8. MOL_DARK singleton never mutated
- *
- * Plus pure-function coverage for normalizeStatus + tierCode.
- */
-import { describe, expect, it, vi, beforeEach, afterEach } from "vitest";
-import React from "react";
-import { render, screen, cleanup } from "@testing-library/react";
-import {
-  MOL_LIGHT,
-  MOL_DARK,
-  getPalette,
-  normalizeStatus,
-  tierCode,
-  MobileAccentProvider,
-  usePalette,
-} from "../palette-context";
-
-// ─── usePalette test helper ───────────────────────────────────────────────────
-// usePalette reads document.documentElement.dataset.theme internally.
-// We set this before rendering so the hook sees the right value.
-
-function setDataTheme(theme: "light" | "dark") {
-  if (typeof document !== "undefined") {
-    document.documentElement.dataset.theme = theme;
-  }
-}
-
-// ─── Pure function tests ──────────────────────────────────────────────────────
-
-describe("normalizeStatus", () => {
-  it("returns emerald-400 for online status", () => {
-    expect(normalizeStatus("online", false)).toBe("bg-emerald-400");
-    expect(normalizeStatus("online", true)).toBe("bg-emerald-400");
-  });
-
-  it("returns emerald-400 for degraded status", () => {
-    expect(normalizeStatus("degraded", false)).toBe("bg-emerald-400");
-    expect(normalizeStatus("degraded", true)).toBe("bg-emerald-400");
-  });
-
-  it("returns red-400 for failed status", () => {
-    expect(normalizeStatus("failed", false)).toBe("bg-red-400");
-    expect(normalizeStatus("failed", true)).toBe("bg-red-400");
-  });
-
-  it("returns amber-400 for paused status", () => {
-    expect(normalizeStatus("paused", false)).toBe("bg-amber-400");
-    expect(normalizeStatus("paused", true)).toBe("bg-amber-400");
-  });
-
-  it("returns amber-400 for not_configured status", () => {
-    expect(normalizeStatus("not_configured", false)).toBe("bg-amber-400");
-  });
-
-  it("returns zinc-400 for unknown status", () => {
-    expect(normalizeStatus("unknown", false)).toBe("bg-zinc-400");
-    expect(normalizeStatus("", false)).toBe("bg-zinc-400");
-  });
-});
-
-describe("tierCode", () => {
-  it("returns T1 for tier 1", () => {
-    expect(tierCode(1)).toBe("T1");
-  });
-
-  it("returns T2 for tier 2", () => {
-    expect(tierCode(2)).toBe("T2");
-  });
-
-  it("returns T4 for tier 4", () => {
-    expect(tierCode(4)).toBe("T4");
-  });
-
-  it("returns generic T{n} for non-standard tiers", () => {
-    expect(tierCode(99)).toBe("T99");
-  });
-});
-
-// ─── getPalette tests ─────────────────────────────────────────────────────────
-
-describe("getPalette — accent override", () => {
-  it("accent=null returns base palette unchanged (light)", () => {
-    const result = getPalette(null, false);
-    expect(result).toEqual({ ...MOL_LIGHT });
-    expect(result).not.toBe(MOL_LIGHT); // returned object is a copy
-  });
-
-  it("accent=null returns base palette unchanged (dark)", () => {
-    const result = getPalette(null, true);
-    expect(result).toEqual({ ...MOL_DARK });
-    expect(result).not.toBe(MOL_DARK);
-  });
-
-  it("accent=base.accent returns base palette unchanged (identity guard, light)", () => {
-    const result = getPalette(MOL_LIGHT.accent, false);
-    expect(result).toEqual({ ...MOL_LIGHT });
-    expect(result).not.toBe(MOL_LIGHT);
-  });
-
-  it("accent=base.accent returns base palette unchanged (identity guard, dark)", () => {
-    const result = getPalette(MOL_DARK.accent, true);
-    expect(result).toEqual({ ...MOL_DARK });
-    expect(result).not.toBe(MOL_DARK);
-  });
-
-  it("accent='#custom' overrides accent and online (light)", () => {
-    const result = getPalette("#ff0000", false);
-    expect(result.accent).toBe("#ff0000");
-    expect(result.online).toBe("bg-emerald-400"); // normalizeStatus("online", false)
-  });
-
-  it("accent='#custom' overrides accent and online (dark)", () => {
-    const result = getPalette("#00ff00", true);
-    expect(result.accent).toBe("#00ff00");
-    expect(result.online).toBe("bg-emerald-400"); // normalizeStatus("online", true)
-  });
-
-  it("MOL_LIGHT singleton is never mutated", () => {
-    getPalette("#mutate", false);
-    // All fields must still match the original freeze definition
-    expect(MOL_LIGHT.accent).toBe("bg-blue-500");
-    expect(MOL_LIGHT.online).toBe("bg-emerald-400");
-    expect(MOL_LIGHT.surface).toBe("bg-zinc-900");
-    expect(MOL_LIGHT.ink).toBe("text-zinc-100");
-    expect(MOL_LIGHT.line).toBe("border-zinc-700");
-    expect(MOL_LIGHT.bg).toBe("bg-zinc-950");
-  });
-
-  it("MOL_DARK singleton is never mutated", () => {
-    getPalette("#mutate", true);
-    expect(MOL_DARK.accent).toBe("bg-sky-400");
-    expect(MOL_DARK.online).toBe("bg-emerald-400");
-    expect(MOL_DARK.surface).toBe("bg-zinc-800");
-    expect(MOL_DARK.ink).toBe("text-zinc-100");
-    expect(MOL_DARK.line).toBe("border-zinc-700");
-    expect(MOL_DARK.bg).toBe("bg-zinc-950");
-  });
-
-  it("getPalette always returns a new object (no shared mutation risk)", () => {
-    const a = getPalette("#a", false);
-    const b = getPalette("#b", false);
-    expect(a).not.toBe(b);
-    expect(a.accent).not.toBe(b.accent);
-  });
-});
-
-// ─── MobileAccentProvider tests ───────────────────────────────────────────────
-
-describe("MobileAccentProvider", () => {
-  beforeEach(() => {
-    setDataTheme("light");
-  });
-
-  afterEach(() => {
-    cleanup();
-    if (typeof document !== "undefined") {
-      document.documentElement.dataset.theme = "";
-    }
-  });
-
-  it("renders children", () => {
-    render(
-      <MobileAccentProvider accent={null}>
-        <span data-testid="child">Hello</span>
-      </MobileAccentProvider>,
-    );
-    expect(screen.getByTestId("child")).toBeTruthy();
-  });
-
-  // usePalette hook reads data-theme from <html> to determine light/dark.
-  // In the test environment, data-theme is empty, which falls through to
-  // the "light" default in usePalette, giving MOL_LIGHT.
-  it("usePalette(false) without provider → MOL_LIGHT", () => {
-    setDataTheme("light");
-    function ShowPalette() {
-      const p = usePalette(false);
-      return <span data-testid="accent-light">{p.accent}</span>;
-    }
-    render(<ShowPalette />);
-    expect(screen.getByTestId("accent-light").textContent).toBe(MOL_LIGHT.accent);
-  });
-
-  it("usePalette(true) without provider → MOL_DARK when data-theme=dark", () => {
-    setDataTheme("dark");
-    function ShowPalette() {
-      const p = usePalette(true);
-      return <span data-testid="accent-dark">{p.accent}</span>;
-    }
-    render(<ShowPalette />);
-    expect(screen.getByTestId("accent-dark").textContent).toBe(MOL_DARK.accent);
-  });
-});

canvas/src/lib/design-tokens.ts

@@ -21,8 +21,8 @@ export function statusDotClass(status: string): string {
 export const TIER_CONFIG: Record<number, { label: string; color: string; border: string }> = {
   1: { label: "T1", color: "text-ink-mid bg-surface-card border border-line", border: "text-ink-mid border-line" },
   2: { label: "T2", color: "text-white bg-accent border border-accent-strong", border: "text-accent border-accent" },
-  3: { label: "T3", color: "text-white bg-violet-600 border border-violet-700", border: "text-white border-violet-500" },
-  4: { label: "T4", color: "text-white bg-warm border border-warm", border: "text-white border-warm" },
+  3: { label: "T3", color: "text-white bg-violet-600 border border-violet-700", border: "text-violet-600 border-violet-500" },
+  4: { label: "T4", color: "text-white bg-warm border border-warm", border: "text-warm border-warm" },
 };
 
 export const COMM_TYPE_LABELS: Record<string, string> = {

canvas/src/lib/palette-context.tsx

@@ -1,167 +0,0 @@
-"use client";
-
-/**
- * palette-context.tsx
- *
- * Mobile canvas accent palette system.
- *
- * - MOL_LIGHT / MOL_DARK  — immutable base singletons
- * - getPalette(accent, isDark) — returns base palette or accent-overridden copy
- * - normalizeStatus(status, isDark) — maps workspace status → online dot color
- * - tierCode(tier) — maps tier number → display label
- * - MobileAccentProvider — React context that propagates accent override
- * - usePalette(allowAccentOverride) — hook; returns the effective palette
- */
-
-import { createContext, useContext } from "react";
-
-// ─── Types ─────────────────────────────────────────────────────────────────────
-
-export interface Palette {
-  /** Accent colour (CSS colour string). */
-  accent: string;
-  /** Online indicator colour (CSS class string, e.g. "bg-emerald-400"). */
-  online: string;
-  /** Surface background colour class. */
-  surface: string;
-  /** Primary text colour class. */
-  ink: string;
-  /** Border/divider colour class. */
-  line: string;
-  /** Background colour class. */
-  bg: string;
-  /** Tier display code, e.g. "T1". */
-  tier: string;
-}
-
-// ─── Singleton base palettes ────────────────────────────────────────────────────
-
-/** Light-mode base palette — must never be mutated. */
-export const MOL_LIGHT: Readonly<Palette> = Object.freeze({
-  accent: "bg-blue-500",
-  online: "bg-emerald-400",
-  surface: "bg-zinc-900",
-  ink: "text-zinc-100",
-  line: "border-zinc-700",
-  bg: "bg-zinc-950",
-  tier: "T1",
-});
-
-/** Dark-mode base palette — must never be mutated. */
-export const MOL_DARK: Readonly<Palette> = Object.freeze({
-  accent: "bg-sky-400",
-  online: "bg-emerald-400",
-  surface: "bg-zinc-800",
-  ink: "text-zinc-100",
-  line: "border-zinc-700",
-  bg: "bg-zinc-950",
-  tier: "T1",
-});
-
-// ─── Pure helpers ─────────────────────────────────────────────────────────────
-
-/**
- * Maps workspace status string → online dot colour class.
- * Returns the appropriate green for light/dark mode.
- */
-export function normalizeStatus(
-  status: string,
-  _isDark: boolean,
-): string {
-  if (status === "online" || status === "degraded") {
-    return "bg-emerald-400";
-  }
-  if (status === "failed") {
-    return "bg-red-400";
-  }
-  if (status === "paused" || status === "not_configured") {
-    return "bg-amber-400";
-  }
-  return "bg-zinc-400";
-}
-
-/**
- * Maps tier number → display code.
- */
-export function tierCode(tier: number): string {
-  return `T${tier}`;
-}
-
-/**
- * Returns the effective palette.
- *
- * - `accent = null` → base palette (light or dark) unchanged
- * - `accent = basePalette.accent` → base palette unchanged (identity guard)
- * - `accent = "#custom"` → copy with `accent` and `online` overridden
- *
- * Always returns a new object; neither MOL_LIGHT nor MOL_DARK is ever mutated.
- */
-export function getPalette(
-  accent: string | null,
-  isDark: boolean,
-): Palette {
-  const base: Readonly<Palette> = isDark ? MOL_DARK : MOL_LIGHT;
-
-  // null accent → use base unchanged
-  if (accent === null) return { ...base };
-
-  // identity guard — accent same as base accent → no override needed
-  if (accent === base.accent) return { ...base };
-
-  // Custom accent: override accent + online to keep them in sync
-  return { ...base, accent, online: normalizeStatus("online", isDark) };
-}
-
-// ─── Context ──────────────────────────────────────────────────────────────────
-
-type MobileAccentContextValue = {
-  /** Override accent colour (null = no override, use default). */
-  accent: string | null;
-};
-
-const MobileAccentContext = createContext<MobileAccentContextValue>({
-  accent: null,
-});
-
-export { MobileAccentContext };
-
-/**
- * Renders children inside the accent override context.
- */
-export function MobileAccentProvider({
-  accent,
-  children,
-}: {
-  accent: string | null;
-  children: React.ReactNode;
-}) {
-  return (
-    <MobileAccentContext.Provider value={{ accent }}>
-      {children}
-    </MobileAccentContext.Provider>
-  );
-}
-
-// ─── Hook ─────────────────────────────────────────────────────────────────────
-
-/**
- * Returns the effective `Palette` for the current context.
- *
- * @param allowAccentOverride  When false, always returns the base palette
- *                              even when an override is set (useful for
- *                              non-accent-aware child components).
- */
-export function usePalette(allowAccentOverride: boolean): Palette {
-  const { accent } = useContext(MobileAccentContext);
-
-  // Resolved from the OS-level theme preference. In a real app this would
-  // be derived from useTheme().resolvedTheme; for this hook we default
-  // to light (the safe default for SSR / component-library use).
-  // We read data-theme from <html> to stay in sync with the theme system.
-  const isDark =
-    typeof document !== "undefined" &&
-    document.documentElement.dataset.theme === "dark";
-
-  const effectiveAccent = allowAccentOverride ? accent : null;
-  return getPalette(effectiveAccent, isDark);
-}

canvas/src/styles/settings-panel.css

@@ -282,17 +282,13 @@
 }
 
 .secret-row__save-btn {
-  background: #1d4ed8;
+  background: #2563eb;
   color: #ffffff;
   border: none;
   padding: 6px 12px;
   border-radius: 6px;
   font-size: 13px;
   cursor: pointer;
-  transition: background-color 0.15s;
-}
-.secret-row__save-btn:hover {
-  background: #1e40af;
 }
 
 .secret-row__save-btn:focus-visible {
@@ -374,17 +370,13 @@
 }
 
 .add-key-form__save-btn {
-  background: #1d4ed8;
+  background: #2563eb;
   color: #ffffff;
   border: none;
   padding: 8px 16px;
   border-radius: 6px;
   font-size: 13px;
   cursor: pointer;
-  transition: background-color 0.15s;
-}
-.add-key-form__save-btn:hover {
-  background: #1e40af;
 }
 
 .add-key-form__save-btn:focus-visible {
@@ -518,7 +510,7 @@
 .empty-state__body { font-size: 14px; color: #a1a1aa; margin: 0 0 24px; line-height: 1.5; }
 
 .empty-state__cta {
-  background: #1d4ed8;
+  background: #2563eb;
   color: #ffffff;
   border: none;
   padding: 10px 20px;
@@ -526,10 +518,6 @@
   font-size: 14px;
   font-weight: 500;
   cursor: pointer;
-  transition: background-color 0.15s;
-}
-.empty-state__cta:hover {
-  background: #1e40af;
 }
 
 .empty-state__cta:focus-visible { outline: var(--focus-ring); outline-offset: var(--focus-ring-offset); }
@@ -573,16 +561,12 @@
 .secrets-tab__error p { color: var(--status-invalid); margin: 0 0 12px; }
 
 .secrets-tab__refresh-btn {
-  background: #1d4ed8;
+  background: #2563eb;
   color: #ffffff;
   border: none;
   padding: 8px 16px;
   border-radius: 6px;
   cursor: pointer;
-  transition: background-color 0.15s;
-}
-.secrets-tab__refresh-btn:hover {
-  background: #1e40af;
 }
 
 .secrets-tab__no-results {
@@ -706,16 +690,12 @@
 }
 
 .guard-dialog__discard-btn {
-  background: #1d4ed8;
+  background: #2563eb;
   color: #ffffff;
   border: none;
   padding: 8px 16px;
   border-radius: 6px;
   cursor: pointer;
-  transition: background-color 0.15s;
-}
-.guard-dialog__discard-btn:hover {
-  background: #1e40af;
 }
 
 .guard-dialog__discard-btn:focus-visible {
@@ -767,20 +747,12 @@
 .top-bar__name { font-size: 14px; font-weight: 500; color: #d4d4d8; }
 
 .top-bar__btn {
-  background: #1d4ed8;
+  background: #2563eb;
   color: #ffffff;
   border: none;
   padding: 6px 12px;
   border-radius: 6px;
   font-size: 13px;
   cursor: pointer;
-  transition: background-color 0.15s;
-}
-.top-bar__btn:hover {
-  background: #1e40af;
-}
-.top-bar__btn:focus-visible {
-  outline: none;
-  box-shadow: 0 0 0 2px #18181b, 0 0 0 4px #3b82f6;
 }
 

scripts/promote-tenant-image.sh

@@ -179,7 +179,6 @@ cp_redeploy_tenant() {
   #   1  — any other failure
   # stdout = response body. stderr = "HTTP_STATUS=NNN" line.
   local slug="$1" tag="$2"
-  validate_slug "$slug"
   _mock_call cp_redeploy_tenant "$slug" "$tag"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   local tok="${!CP_TOKEN_ENV:-}"
@@ -205,7 +204,6 @@ cp_redeploy_tenant() {
 tenant_buildinfo() {
   # args: <slug>; prints JSON
   local slug="$1"
-  validate_slug "$slug"
   _mock_call tenant_buildinfo "$slug"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   curl -sf --max-time 10 "https://${slug}.moleculesai.app/buildinfo"
@@ -214,7 +212,6 @@ tenant_buildinfo() {
 tenant_health() {
   # args: <slug>; prints raw response, returns 0 if "ok"
   local slug="$1"
-  validate_slug "$slug"
   _mock_call tenant_health "$slug"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   curl -sf --max-time 10 "https://${slug}.moleculesai.app/health"
@@ -259,7 +256,6 @@ print(json.dumps({'commands': [ecr_login]}))
 resolve_tenant_instance_id() {
   # args: <slug>; prints i-xxx
   local slug="$1"
-  validate_slug "$slug"
   _mock_call resolve_tenant_instance_id "$slug"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   local tok="${!CP_TOKEN_ENV:-}"
@@ -275,19 +271,6 @@ resolve_tenant_instance_id() {
 log() { printf '[%s] %s\n' "$(date -u +%H:%M:%SZ)" "$*"; }
 err() { printf '[%s] ERROR: %s\n' "$(date -u +%H:%M:%SZ)" "$*" >&2; }
 
-# validate_slug — exit 64 if slug contains characters outside the safe set.
-# Prevents SSRF via query-separator injection (?foo) and subdomain takeover
-# (@evil) when slug is interpolated into URL paths or subdomains.
-# OFFSEC-006 fix.
-validate_slug() {
-  local slug="$1"
-  if ! [[ "$slug" =~ ^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$ ]]; then
-    printf '[%s] ERROR: invalid slug: %s\n' \
-      "$(date -u +%H:%M:%SZ)" "$slug" >&2
-    exit 64
-  fi
-}
-
 preflight() {
   log "preflight: source=$SOURCE_TAG dest=$DEST_TAG repo=$REPO region=$REGION"
   local src_manifest
@@ -356,7 +339,6 @@ promote() {
 redeploy_tenant() {
   # args: <slug> — handle the 403→SSM-refresh→retry pattern
   local slug="$1"
-  validate_slug "$slug"
   log "  redeploy: $slug"
   if [[ "$DRY_RUN" == "true" ]]; then
     log "    [dry-run] would POST /redeploy slug=$slug"
@@ -390,7 +372,6 @@ redeploy_tenant() {
 
 verify_tenant() {
   local slug="$1"
-  validate_slug "$slug"
   log "  verify: $slug"
   if [[ "$DRY_RUN" == "true" ]]; then
     log "    [dry-run] would curl /buildinfo + /health"
@@ -417,7 +398,6 @@ rollback() {
   rm -f "$mfile"
   IFS=',' read -ra slugs <<<"$TENANTS"
   for slug in "${slugs[@]}"; do
-    validate_slug "$slug"
     redeploy_tenant "$slug" || err "  rollback redeploy failed for $slug"
   done
   log "rollback: complete"
@@ -428,13 +408,6 @@ rollback() {
 # ─────────────────────────────────────────────────────────────────────────────
 
 main() {
-  # OFFSEC-006: validate slugs before any network I/O.
-  IFS=',' read -ra _slugs <<<"$TENANTS"
-  for _slug in "${_slugs[@]}"; do
-    validate_slug "$_slug"
-  done
-  unset _slugs _slug
-
   preflight || return 1
   snapshot_dest_tag || return 2
   promote || return 2
@@ -442,15 +415,8 @@ main() {
   local promote_rc=0
   IFS=',' read -ra slugs <<<"$TENANTS"
   for slug in "${slugs[@]}"; do
-    validate_slug "$slug"
-    if ! redeploy_tenant "$slug"; then
-      promote_rc=1
-    fi
-    if [[ $promote_rc -eq 0 ]]; then
-      if ! verify_tenant "$slug"; then
-        promote_rc=1
-      fi
-    fi
+    redeploy_tenant "$slug" || promote_rc=1
+    [[ $promote_rc -eq 0 ]] && { verify_tenant "$slug" || promote_rc=1; }
     [[ $promote_rc -ne 0 ]] && break
   done
 

scripts/test-promote-tenant-image.sh

@@ -267,51 +267,7 @@ else
   printf '  ✗ unknown-flag should fail (got %s)\n' "$rc"
 fi
 
-printf '\n== Test 9: slug validation — invalid slugs rejected with exit 64 (OFFSEC-006) ==\n'
-# Attack vectors: SSRF via ? (curl query separator), subdomain takeover via @,
-# path traversal via /, shell metacharacters.  Use a newline-delimited temp file
-# so slugs containing spaces are NOT split by shell word-splitting.
-_invalid_tmp=$(mktemp)
-cat > "$_invalid_tmp" <<'INVALID_EOF'
-a?url=https://evil.com
-a&url=https://evil.com
-a@evil.com
-a/b
-a\b
-a b
-chloe-dong?url=http://evil.com
-evil.com@legitimate
-INVALID_EOF
-while IFS= read -r attack || [[ -n "$attack" ]]; do
-  set +e
-  out=$("$SCRIPT" --source-tag x --dest-tag y --tenants "$attack" 2>&1); rc=$?
-  set -e
-  if [[ $rc -eq 64 ]] && printf '%s' "$out" | grep -q 'invalid slug'; then
-    PASS=$((PASS + 1)); printf '  ✓ slug rejected: %s\n' "$(printf '%q' "$attack")"
-  else
-    FAIL=$((FAIL + 1)); FAIL_NAMES+=("slug-reject:$attack")
-    printf '  ✗ slug should be rejected: %s — got exit %s\n' "$(printf '%q' "$attack")" "$rc"
-  fi
-done < "$_invalid_tmp"
-rm -f "$_invalid_tmp"
-
-printf '\n== Test 10: slug validation — valid slugs pass through ==\n'
-valid_slugs='chloe-dong hongming ab a abc123 my-tenant-42'
-for slug in $valid_slugs; do
-  set +e
-  out=$("$SCRIPT" --source-tag x --dest-tag y --tenants "$slug" --mock-dir /nonexistent 2>&1); rc=$?
-  set -e
-  # valid slugs: script should fail at preflight (no such mock dir / no real infra),
-  # but NOT at slug validation (exit 64). So we check exit != 64.
-  if [[ $rc -ne 64 ]]; then
-    PASS=$((PASS + 1)); printf '  ✓ valid slug accepted: %s\n' "$slug"
-  else
-    FAIL=$((FAIL + 1)); FAIL_NAMES+=("slug-accept:$slug")
-    printf '  ✗ valid slug rejected: %s (should have passed slug check)\n' "$slug"
-  fi
-done
-
-printf '\n== Test 11: ROLLBACK_TAG follows YYYYMMDD via NOW_OVERRIDE_DATE ==\n'
+printf '\n== Test 9: ROLLBACK_TAG follows YYYYMMDD via NOW_OVERRIDE_DATE ==\n'
 m=$(mkmock)
 mock_set "$m" aws_ecr_get_image       '{}' 0
 mock_set "$m" aws_ecr_describe_image  '' 1
@@ -333,7 +289,7 @@ fi
 assert_calls_contain "rollback tag uses NOW_OVERRIDE_DATE (20260603)" "$m" 'aws_ecr_put_image b-prev-20260603'
 rm -rf "$m"
 
-printf '\n== Test 12: empty source manifest fails preflight ==\n'
+printf '\n== Test 10: empty source manifest fails preflight ==\n'
 m=$(mkmock)
 mock_set "$m" aws_ecr_get_image '' 0   # rc=0 but empty body (the "None" case)
 out=$(run_script "$m")
@@ -341,7 +297,7 @@ assert_exit "empty source manifest fails preflight" "$out" 1
 assert_contains "empty manifest message" "$out" 'returned empty manifest'
 rm -rf "$m"
 
-printf '\n== Test 13: tenant_buildinfo failure during verify → rollback ==\n'
+printf '\n== Test 11: tenant_buildinfo failure during verify → rollback ==\n'
 m=$(mkmock)
 mock_set "$m" aws_ecr_get_image          '{"manifests":[]}' 0
 mock_set "$m" aws_ecr_describe_image     '' 1
@@ -355,7 +311,7 @@ assert_contains "logs buildinfo failure" "$out" '/buildinfo failed for chloe-don
 assert_contains "rollback fired after verify fail" "$out" 'ROLLBACK:'
 rm -rf "$m"
 
-printf '\n== Test 14: ssm_refresh_ecr_auth JSON escaping (CWE-78 / OFFSEC-001) ==\n'
+printf '\n== Test 12: ssm_refresh_ecr_auth JSON escaping (CWE-78 / OFFSEC-001) ==\n'
 # Verify the python3 snippet in ssm_refresh_ecr_auth produces valid JSON and
 # correctly escapes shell-injection characters in region + account ID fields.
 # The fix replaces unquoted shell-printf interpolation with json.dumps.

tests/test_lint_workflow_yaml.py

@@ -22,7 +22,6 @@ Cross-links:
 """
 from __future__ import annotations
 
-import re
 import subprocess
 import sys
 import textwrap
@@ -543,153 +542,3 @@ def test_rule9_prod_manual_deploy_allows_rollback_control(tmp_path):
     _write(tmp_path, "ok.yml", PROD_ROLLBACK_OK)
     r = _run_lint(tmp_path)
     assert r.returncode == 0, f"stdout={r.stdout}\nstderr={r.stderr}"
-
-
-# ---------------------------------------------------------------------------
-# Rule 10 — docker info piped to head under pipefail
-# ---------------------------------------------------------------------------
-
-DOCKER_INFO_HEAD_BAD = """
-    name: docker-info-head-bad
-    on: [push]
-    jobs:
-      build:
-        runs-on: ubuntu-latest
-        steps:
-          - run: |
-              set -euo pipefail
-              docker info 2>&1 | head -5 || exit 1
-"""
-
-DOCKER_INFO_CAPTURE_OK = """
-    name: docker-info-capture-ok
-    on: [push]
-    jobs:
-      build:
-        runs-on: ubuntu-latest
-        steps:
-          - run: |
-              set -euo pipefail
-              docker_info="$(docker info 2>&1)" || exit 1
-              printf '%s\\n' "${docker_info}" | sed -n '1,5p'
-"""
-
-DOCKER_INFO_SEPARATE_STEP_OK = """
-    name: docker-info-separate-step-ok
-    on: [push]
-    jobs:
-      build:
-        runs-on: ubuntu-latest
-        steps:
-          - run: |
-              set -euo pipefail
-              echo setup
-          - run: |
-              docker info 2>&1 | head -5 || true
-"""
-
-
-def test_rule10_docker_info_head_under_pipefail_detects_violation(tmp_path):
-    _write(tmp_path, "bad.yml", DOCKER_INFO_HEAD_BAD)
-    r = _run_lint(tmp_path)
-    assert r.returncode == 1
-    assert "docker info" in r.stdout.lower()
-    assert "pipefail" in r.stdout.lower()
-
-
-def test_rule10_docker_info_capture_passes(tmp_path):
-    _write(tmp_path, "ok.yml", DOCKER_INFO_CAPTURE_OK)
-    r = _run_lint(tmp_path)
-    assert r.returncode == 0, f"stdout={r.stdout}\nstderr={r.stderr}"
-
-
-def test_rule10_docker_info_head_in_separate_step_without_pipefail_passes(tmp_path):
-    _write(tmp_path, "ok.yml", DOCKER_INFO_SEPARATE_STEP_OK)
-    r = _run_lint(tmp_path)
-    assert r.returncode == 0, f"stdout={r.stdout}\nstderr={r.stderr}"
-
-
-# ---------------------------------------------------------------------------
-# CI change detector fanout — workflow-only PRs keep required contexts without
-# running Go/Canvas/Python/shellcheck heavy steps.
-# ---------------------------------------------------------------------------
-
-CI_WORKFLOW = REPO_ROOT / ".gitea" / "workflows" / "ci.yml"
-CI_SURFACES = ("platform", "canvas", "python", "scripts")
-
-
-def _ci_change_patterns() -> dict[str, re.Pattern[str]]:
-    text = CI_WORKFLOW.read_text(encoding="utf-8")
-    patterns: dict[str, re.Pattern[str]] = {}
-    for surface, pattern in re.findall(
-        r'echo "(platform|canvas|python|scripts)=.*?grep -qE \'([^\']+)\'',
-        text,
-    ):
-        patterns[surface] = re.compile(pattern)
-    assert set(patterns) == set(CI_SURFACES)
-    return patterns
-
-
-def _classify_ci_change(*paths: str) -> dict[str, bool]:
-    patterns = _ci_change_patterns()
-    return {
-        surface: any(pattern.search(path) for path in paths)
-        for surface, pattern in patterns.items()
-    }
-
-
-def test_ci_change_detector_workflow_only_edits_do_not_trigger_heavy_surfaces():
-    assert _classify_ci_change(".gitea/workflows/ci.yml") == {
-        "platform": False,
-        "canvas": False,
-        "python": False,
-        "scripts": False,
-    }
-    assert _classify_ci_change(".github/workflows/ci.yml") == {
-        "platform": False,
-        "canvas": False,
-        "python": False,
-        "scripts": False,
-    }
-
-
-def test_ci_change_detector_narrow_surface_edits_only_trigger_their_surface():
-    assert _classify_ci_change("workspace-server/internal/handlers/foo.go") == {
-        "platform": True,
-        "canvas": False,
-        "python": False,
-        "scripts": False,
-    }
-    assert _classify_ci_change("canvas/app/page.tsx") == {
-        "platform": False,
-        "canvas": True,
-        "python": False,
-        "scripts": False,
-    }
-    assert _classify_ci_change("workspace/a2a_mcp_server.py") == {
-        "platform": False,
-        "canvas": False,
-        "python": True,
-        "scripts": False,
-    }
-    assert _classify_ci_change("tests/e2e/test_model_slug.sh") == {
-        "platform": False,
-        "canvas": False,
-        "python": False,
-        "scripts": True,
-    }
-
-
-def test_ci_change_detector_docs_and_meta_scripts_do_not_trigger_surfaces():
-    assert _classify_ci_change("README.md") == {
-        "platform": False,
-        "canvas": False,
-        "python": False,
-        "scripts": False,
-    }
-    assert _classify_ci_change(".gitea/scripts/lint-workflow-yaml.py") == {
-        "platform": False,
-        "canvas": False,
-        "python": False,
-        "scripts": False,
-    }

tests/test_status_reaper.py

@@ -495,7 +495,7 @@ def test_reap_required_check_pull_request_suffix_never_touched(sr_module, monkey
     }
     counters = sr_module.reap(workflow_map, combined, SHA, dry_run=False)
     assert counters["compensated"] == 0
-    assert counters["preserved_pr_without_push_success"] == 1
+    assert counters["preserved_non_push_suffix"] == 1
     assert calls == []
 
 
@@ -1009,64 +1009,3 @@ def test_reap_continues_on_per_sha_apierror(sr_module, monkeypatch, capsys):
     captured = capsys.readouterr()
     assert "::warning::" in captured.out or "::notice::" in captured.out
     assert SHA_A[:10] in captured.out
-
-
-def test_main_soft_skips_when_commit_listing_times_out(sr_module, monkeypatch, capsys):
-    """A transient outage while listing recent commits should not paint main red.
-
-    Per-SHA status read failures are already isolated inside `reap_branch`.
-    The real 2026-05-14 failure was earlier: `/commits?sha=main&limit=30`
-    timed out after all retries, aborting the tick. The next 5-minute tick can
-    retry safely, so `main()` should emit an observable warning and return 0.
-    """
-
-    monkeypatch.setattr(sr_module, "scan_workflows", lambda _: {"workflow-without-push": False})
-
-    def fake_list_recent_commit_shas(*args, **kwargs):
-        raise sr_module.ApiError(
-            "GET /repos/owner/repo/commits failed after 4 attempts: timed out"
-        )
-
-    monkeypatch.setattr(sr_module, "list_recent_commit_shas", fake_list_recent_commit_shas)
-    monkeypatch.setattr(sys, "argv", ["status-reaper.py"])
-
-    assert sr_module.main() == 0
-    captured = capsys.readouterr()
-    assert "::warning::status-reaper skipped this tick" in captured.out
-    assert '"skipped": true' in captured.out
-    assert '"skip_reason": "commit-list-api-error"' in captured.out
-
-
-def test_main_does_not_soft_skip_status_write_failures(sr_module, monkeypatch):
-    """Only commit-list read failures are soft-skipped.
-
-    A compensation write failure means the reaper could not repair a red
-    status. That must still fail the job loudly instead of being mislabeled as
-    a transient commit-list outage.
-    """
-
-    monkeypatch.setattr(sr_module, "scan_workflows", lambda _: {"workflow-without-push": False})
-    monkeypatch.setattr(sr_module, "list_recent_commit_shas", lambda *_args, **_kwargs: [SHA_A])
-    monkeypatch.setattr(
-        sr_module,
-        "get_combined_status",
-        lambda _sha: {
-            "state": "failure",
-            "statuses": [
-                {
-                    "context": "workflow-without-push / job (push)",
-                    "status": "failure",
-                    "description": "stranded class-O red",
-                }
-            ],
-        },
-    )
-
-    def fake_post_compensating_status(*args, **kwargs):
-        raise sr_module.ApiError("POST /statuses failed: 403")
-
-    monkeypatch.setattr(sr_module, "post_compensating_status", fake_post_compensating_status)
-    monkeypatch.setattr(sys, "argv", ["status-reaper.py"])
-
-    with pytest.raises(sr_module.ApiError, match="POST /statuses failed"):
-        sr_module.main()

tools/gate-check-v3/gate_check.py

@@ -110,13 +110,6 @@ AGENT_LOGIN_MAP = {
     "offsec": "core-offsec",
 }
 
-# Map alternate Gitea logins → canonical logins for gate matching.
-# infra-sre is the engineers/core-devops agent (same team, same work).
-# Without this alias, infra-sre comments/reviews never satisfy the engineers gate.
-LOGIN_ALIASES = {
-    "infra-sre": "core-devops",
-}
-
 # SOP-6 tier → required agent groups
 # tier:low    → engineers,managers,ceo (OR: any one suffices)
 # tier:medium → managers AND engineers AND qa,security (AND)
@@ -175,18 +168,17 @@ def signal_1_comment_scan(pr_number: int, repo: str) -> dict:
     except GiteaError:
         pass
 
-    # Collect APPROVED reviews from agent logins (resolving LOGIN_ALIASES)
+    # Collect APPROVED reviews from agent logins
     try:
         reviews = api_list(f"/repos/{owner}/{name}/pulls/{pr_number}/reviews")
         for r in reviews:
             login = r.get("user", {}).get("login", "")
-            canonical = LOGIN_ALIASES.get(login, login)
-            if canonical in login_to_group and r.get("state") == "APPROVED":
+            if login in login_to_group and r.get("state") == "APPROVED":
                 comments.append(
                     {
                         "id": f"review-{r['id']}",
-                        "user": {"login": canonical},
-                        "body": f"[{canonical}-agent] APPROVED",
+                        "user": {"login": login},
+                        "body": f"[{login}-agent] APPROVED",
                         "created_at": r.get("submitted_at") or r.get("created_at", ""),
                         "source": "review",
                     }
@@ -201,8 +193,6 @@ def signal_1_comment_scan(pr_number: int, repo: str) -> dict:
         for c in comments:
             body = c.get("body", "") or ""
             user_login = c.get("user", {}).get("login", "")
-            # Resolve LOGIN_ALIASES so alternate logins satisfy the canonical gate
-            user_login = LOGIN_ALIASES.get(user_login, user_login)
             if user_login != login:
                 continue
             for m in AGENT_TAG_RE.finditer(body):

tools/gate-check-v3/test_gate_check.py

@@ -32,45 +32,3 @@ def test_run_skips_pr_not_targeting_default_branch(monkeypatch):
     assert result["verdict"] == "CLEAR"
     assert result["skipped"] is True
     assert "staging" in result["reason"]
-
-
-def test_signal_1_infra_sre_login_alias_resolved_to_core_devops(monkeypatch):
-    """infra-sre posts [devops-agent] APPROVED → engineers gate satisfied via LOGIN_ALIASES."""
-    mod = load_gate_check()
-
-    def fake_api_get(path):
-        # PR 900 has tier:low label
-        if path == "/repos/molecule-ai/molecule-core/pulls/900":
-            return {
-                "number": 900,
-                "labels": [{"name": "tier:low"}],
-            }
-        raise AssertionError(f"unexpected api_get: {path}")
-
-    def fake_api_list(path):
-        if path == "/repos/molecule-ai/molecule-core/issues/900/comments":
-            return []
-        if path == "/repos/molecule-ai/molecule-core/pulls/900/comments":
-            return []
-        if path == "/repos/molecule-ai/molecule-core/pulls/900/reviews":
-            return [
-                {
-                    "id": 1,
-                    "user": {"login": "infra-sre"},
-                    "state": "APPROVED",
-                    "submitted_at": "2026-05-13T10:00:00Z",
-                }
-            ]
-        raise AssertionError(f"unexpected api_list: {path}")
-
-    monkeypatch.setattr(mod, "api_get", fake_api_get)
-    monkeypatch.setattr(mod, "api_list", fake_api_list)
-
-    result = mod.signal_1_comment_scan(900, "molecule-ai/molecule-core")
-
-    assert result["verdict"] == "CLEAR"
-    assert result["signal"] == "agent_tag_comments"
-    # infra-sre (aliased to core-devops) should satisfy engineers gate
-    engineers = result["results"]["core-devops"]
-    assert engineers["verdict"] == "APPROVED"
-    assert engineers["group"] == "engineers"

workspace-server/cmd/server/main.go

@@ -157,16 +157,6 @@ func main() {
 		}
 	}
 
-	// Issue #831 bootstrap: if global_secrets has ADMIN_TOKEN=placeholder,
-	// replace it with the real token from the environment. This fixes
-	// workspaces provisioned before the correct value was seeded.
-	// Only runs for SaaS tenants (cpProv != nil) where containers inherit
-	// from global_secrets. Self-hosted deployments don't read ADMIN_TOKEN
-	// from global_secrets for container env — the fix doesn't apply.
-	if cpProv != nil {
-		fixAdminTokenPlaceholder()
-	}
-
 	port := envOr("PORT", "8080")
 	platformURL := envOr("PLATFORM_URL", fmt.Sprintf("http://host.docker.internal:%s", port))
 	configsDir := envOr("CONFIGS_DIR", findConfigsDir())
@@ -493,67 +483,3 @@ func findMigrationsDir() string {
 	log.Println("No migrations directory found")
 	return ""
 }
-
-// fixAdminTokenPlaceholder heals #831: workspaces provisioned with a placeholder
-// ADMIN_TOKEN in global_secrets receive that placeholder as a container env var,
-// breaking any code that calls platform APIs. This runs once at startup (SaaS only)
-// and replaces the placeholder with the real token from the host environment.
-//
-// The placeholder is not in the codebase — it was seeded by a prior bootstrap or
-// manual DB write. It should never be set by the platform itself. This function
-// ensures it is corrected on next platform restart without requiring a manual DB
-// update or workspace reprovision.
-func fixAdminTokenPlaceholder() {
-	realToken := os.Getenv("ADMIN_TOKEN")
-	if realToken == "" {
-		// Platform has no ADMIN_TOKEN — nothing to fix.
-		return
-	}
-
-	// Read the current stored value. We only upsert when the placeholder is
-	// present so we don't repeatedly write rows that are already correct.
-	var storedValue []byte
-	err := db.DB.QueryRow(`SELECT encrypted_value FROM global_secrets WHERE key = $1`, "ADMIN_TOKEN").Scan(&storedValue)
-	if err != nil {
-		// No row — nothing to fix. The control plane injects ADMIN_TOKEN via
-		// Secrets Manager bootstrap; the global_secrets path is a legacy seed.
-		return
-	}
-
-	// Decrypt to check the value. We compare the plaintext so the check works
-	// whether encryption is enabled or not.
-	storedPlaintext, decErr := crypto.DecryptVersioned(storedValue, crypto.CurrentEncryptionVersion())
-	if decErr != nil {
-		log.Printf("fixAdminTokenPlaceholder: could not decrypt existing value (version mismatch?): %v", decErr)
-		return
-	}
-
-	if string(storedPlaintext) == realToken {
-		// Already correct — nothing to do.
-		return
-	}
-
-	if string(storedPlaintext) == "placeholder-will-ask-for-real" {
-		log.Println("fixAdminTokenPlaceholder: replacing placeholder ADMIN_TOKEN in global_secrets")
-	} else {
-		log.Printf("fixAdminTokenPlaceholder: ADMIN_TOKEN in global_secrets differs from env; updating")
-	}
-
-	encrypted, err := crypto.Encrypt([]byte(realToken))
-	if err != nil {
-		log.Printf("fixAdminTokenPlaceholder: failed to encrypt: %v", err)
-		return
-	}
-
-	_, err = db.DB.Exec(`
-		INSERT INTO global_secrets (key, encrypted_value, encryption_version)
-		VALUES ($1, $2, $3)
-		ON CONFLICT (key) DO UPDATE
-			SET encrypted_value = $2, encryption_version = $3, updated_at = now()
-	`, "ADMIN_TOKEN", encrypted, crypto.CurrentEncryptionVersion())
-	if err != nil {
-		log.Printf("fixAdminTokenPlaceholder: failed to upsert: %v", err)
-		return
-	}
-	log.Println("fixAdminTokenPlaceholder: done")
-}

workspace-server/go.mod

@@ -18,7 +18,6 @@ require (
 	github.com/opencontainers/image-spec v1.1.1
 	github.com/redis/go-redis/v9 v9.19.0
 	github.com/robfig/cron/v3 v3.0.1
-	github.com/stretchr/testify v1.11.1
 	go.moleculesai.app/plugin/gh-identity v0.0.0-20260509010445-788988195fce
 	golang.org/x/crypto v0.50.0
 	gopkg.in/yaml.v3 v3.0.1
@@ -34,7 +33,6 @@ require (
 	github.com/containerd/errdefs v1.0.0 // indirect
 	github.com/containerd/errdefs/pkg v0.3.0 // indirect
 	github.com/containerd/log v0.1.0 // indirect
-	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/distribution/reference v0.6.0 // indirect
 	github.com/docker/go-units v0.5.0 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
@@ -60,7 +58,6 @@ require (
 	github.com/opencontainers/go-digest v1.0.0 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.4 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
-	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/quic-go/qpack v0.6.0 // indirect
 	github.com/quic-go/quic-go v0.59.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect

workspace-server/internal/bundle/exporter_test.go

@@ -1,261 +0,0 @@
-package bundle
-
-import (
-	"os"
-	"path/filepath"
-	"testing"
-)
-
-// ---------------------------------------------------------------------------
-// extractDescription
-// ---------------------------------------------------------------------------
-
-func TestExtractDescription_WithFrontmatter(t *testing.T) {
-	// YAML frontmatter is skipped; first non-comment, non-empty line after
-	// the closing `---` is the description.
-	content := `---
-title: My Workspace
----
-# This is a comment
-This is the description line.
-Another line.`
-	got := extractDescription(content)
-	if got != "This is the description line." {
-		t.Errorf("got %q, want %q", got, "This is the description line.")
-	}
-}
-
-func TestExtractDescription_NoFrontmatter(t *testing.T) {
-	// No frontmatter: first non-comment, non-empty line is returned.
-	content := `# Copyright header
-My workspace description
-Another line.`
-	got := extractDescription(content)
-	if got != "My workspace description" {
-		t.Errorf("got %q, want %q", got, "My workspace description")
-	}
-}
-
-func TestExtractDescription_CommentOnly(t *testing.T) {
-	// All content is comments or empty → empty string.
-	content := `# comment only
-# another comment
-`
-	got := extractDescription(content)
-	if got != "" {
-		t.Errorf("got %q, want empty string", got)
-	}
-}
-
-func TestExtractDescription_EmptyInput(t *testing.T) {
-	got := extractDescription("")
-	if got != "" {
-		t.Errorf("got %q, want empty string", got)
-	}
-}
-
-func TestExtractDescription_UnclosedFrontmatter(t *testing.T) {
-	// With no closing `---`, inFrontmatter stays true after the opening
-	// delimiter, so all subsequent lines are skipped and "" is returned.
-	// This is the documented behaviour: without a closing delimiter,
-	// all lines are considered frontmatter.
-	content := `---
-title: No closing delimiter
-This is the description.`
-	got := extractDescription(content)
-	if got != "" {
-		t.Errorf("unclosed frontmatter: got %q, want empty string", got)
-	}
-}
-
-func TestExtractDescription_FrontmatterThenCommentThenContent(t *testing.T) {
-	content := `---
-tags: [test]
----
-# internal comment
-Real description here.
-`
-	got := extractDescription(content)
-	if got != "Real description here." {
-		t.Errorf("got %q, want %q", got, "Real description here.")
-	}
-}
-
-func TestExtractDescription_BlankLinesSkipped(t *testing.T) {
-	// Empty lines (len=0) are skipped; whitespace-only lines (spaces) are NOT
-	// skipped because len(line)>0. First non-comment, non-empty line is returned.
-	content := "\n\n\n\nA. Description\nB. Should not be returned.\n"
-	got := extractDescription(content)
-	if got != "A. Description" {
-		t.Errorf("got %q, want %q", got, "A. Description")
-	}
-}
-
-// ---------------------------------------------------------------------------
-// splitLines
-// ---------------------------------------------------------------------------
-
-func TestSplitLines_Basic(t *testing.T) {
-	got := splitLines("a\nb\nc")
-	want := []string{"a", "b", "c"}
-	if len(got) != len(want) {
-		t.Fatalf("len=%d, want %d", len(got), len(want))
-	}
-	for i := range want {
-		if got[i] != want[i] {
-			t.Errorf("got[%d]=%q, want %q", i, got[i], want[i])
-		}
-	}
-}
-
-func TestSplitLines_TrailingNewline(t *testing.T) {
-	got := splitLines("line1\nline2\n")
-	want := []string{"line1", "line2"}
-	if len(got) != len(want) {
-		t.Errorf("trailing newline: got %v, want %v", got, want)
-	}
-}
-
-func TestSplitLines_NoNewline(t *testing.T) {
-	got := splitLines("no newline")
-	want := []string{"no newline"}
-	if len(got) != 1 || got[0] != want[0] {
-		t.Errorf("got %v, want %v", got, want)
-	}
-}
-
-func TestSplitLines_EmptyString(t *testing.T) {
-	got := splitLines("")
-	if len(got) != 0 {
-		t.Errorf("empty string: got %v, want []", got)
-	}
-}
-
-func TestSplitLines_OnlyNewlines(t *testing.T) {
-	got := splitLines("\n\n\n")
-	// Three consecutive '\n' characters → s[start:i] at each '\n' gives
-	// the empty string between newlines → 3 empty segments.
-	// (No trailing segment because start == len(s) at the end.)
-	if len(got) != 3 {
-		t.Errorf("only newlines: got %v (len=%d), want 3 empty strings", got, len(got))
-	}
-	for i, s := range got {
-		if s != "" {
-			t.Errorf("got[%d]=%q, want empty string", i, s)
-		}
-	}
-}
-
-func TestSplitLines_MultipleConsecutiveNewlines(t *testing.T) {
-	got := splitLines("a\n\n\nb")
-	// a\n\n\nb → ["a", "", "", "b"]
-	if len(got) != 4 {
-		t.Errorf("consecutive newlines: got %v (len=%d)", got, len(got))
-	}
-	if got[0] != "a" || got[3] != "b" {
-		t.Errorf("first/last: got %v, want [a, ..., b]", got)
-	}
-}
-
-// ---------------------------------------------------------------------------
-// findConfigDir
-// ---------------------------------------------------------------------------
-
-func TestFindConfigDir_NameMatch(t *testing.T) {
-	tmp := t.TempDir()
-
-	// Create two sub-dirs; only the one with matching name should be found.
-	mustMkdir(filepath.Join(tmp, "workspace-a"))
-	mustWrite(filepath.Join(tmp, "workspace-a", "config.yaml"),
-		"name: other-workspace\ntier: 1\n")
-
-	mustMkdir(filepath.Join(tmp, "workspace-b"))
-	mustWrite(filepath.Join(tmp, "workspace-b", "config.yaml"),
-		"name: target-workspace\nruntime: claude-code\n")
-
-	got := findConfigDir(tmp, "target-workspace")
-	want := filepath.Join(tmp, "workspace-b")
-	if got != want {
-		t.Errorf("got %q, want %q", got, want)
-	}
-}
-
-func TestFindConfigDir_NoMatch_UsesFallback(t *testing.T) {
-	tmp := t.TempDir()
-
-	mustMkdir(filepath.Join(tmp, "first"))
-	mustWrite(filepath.Join(tmp, "first", "config.yaml"), "name: workspace-a\n")
-
-	mustMkdir(filepath.Join(tmp, "second"))
-	mustWrite(filepath.Join(tmp, "second", "config.yaml"), "name: workspace-b\n")
-
-	// No exact name match → fallback to the first directory with a config.yaml.
-	got := findConfigDir(tmp, "nonexistent")
-	want := filepath.Join(tmp, "first")
-	if got != want {
-		t.Errorf("no match: got %q, want fallback %q", got, want)
-	}
-}
-
-func TestFindConfigDir_MissingDir(t *testing.T) {
-	got := findConfigDir("/nonexistent/path/for/findConfigDir", "any-name")
-	if got != "" {
-		t.Errorf("missing dir: got %q, want empty string", got)
-	}
-}
-
-func TestFindConfigDir_NoSubdirs(t *testing.T) {
-	tmp := t.TempDir()
-	// Empty directory → no matches, no fallback.
-	got := findConfigDir(tmp, "any")
-	if got != "" {
-		t.Errorf("empty dir: got %q, want empty string", got)
-	}
-}
-
-// ---------------------------------------------------------------------------
-// Helpers
-// ---------------------------------------------------------------------------
-
-func mustMkdir(path string) {
-	os.MkdirAll(path, 0o755)
-}
-
-func mustWrite(path, content string) {
-	os.WriteFile(path, []byte(content), 0o644)
-}
-
-// ---------------------------------------------------------------------------
-// findConfigDir
-// ---------------------------------------------------------------------------
-
-func TestFindConfigDir_SubdirWithoutConfig(t *testing.T) {
-	tmp := t.TempDir()
-	mustMkdir(filepath.Join(tmp, "empty-skill"))
-	// Sub-dir without config.yaml → skipped.
-	got := findConfigDir(tmp, "any")
-	if got != "" {
-		t.Errorf("no config.yaml: got %q, want empty string", got)
-	}
-}
-
-func TestFindConfigDir_FirstWithConfigIsFallback(t *testing.T) {
-	// When name doesn't match, fallback is the FIRST dir with config.yaml,
-	// not the last. Confirm ordering by creating three dirs.
-	tmp := t.TempDir()
-
-	mustMkdir(filepath.Join(tmp, "a"))
-	mustWrite(filepath.Join(tmp, "a", "config.yaml"), "name: alpha\n")
-
-	mustMkdir(filepath.Join(tmp, "b"))
-	mustWrite(filepath.Join(tmp, "b", "config.yaml"), "name: beta\n")
-
-	mustMkdir(filepath.Join(tmp, "c"))
-	mustWrite(filepath.Join(tmp, "c", "config.yaml"), "name: gamma\n")
-
-	got := findConfigDir(tmp, "nonexistent")
-	want := filepath.Join(tmp, "a") // first dir with config.yaml
-	if got != want {
-		t.Errorf("fallback order: got %q, want first-with-config %q", got, want)
-	}
-}

workspace-server/internal/bundle/importer_test.go

@@ -1,317 +0,0 @@
-package bundle
-
-import (
-	"testing"
-)
-
-func TestBuildBundleConfigFiles_EmptyBundle(t *testing.T) {
-	b := &Bundle{}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 0 {
-		t.Errorf("empty bundle: want 0 files, got %d", len(files))
-	}
-}
-
-func TestBuildBundleConfigFiles_SystemPromptOnly(t *testing.T) {
-	b := &Bundle{
-		SystemPrompt: "You are a helpful assistant.",
-	}
-	files := buildBundleConfigFiles(b)
-	if n := len(files); n != 1 {
-		t.Fatalf("system-prompt only: want 1 file, got %d", n)
-	}
-	if content, ok := files["system-prompt.md"]; !ok {
-		t.Fatal("missing system-prompt.md")
-	} else if string(content) != "You are a helpful assistant." {
-		t.Errorf("system-prompt content: got %q", string(content))
-	}
-}
-
-func TestBuildBundleConfigFiles_ConfigYamlOnly(t *testing.T) {
-	b := &Bundle{
-		Prompts: map[string]string{
-			"config.yaml": "runtime: langgraph\ntier: 2\n",
-		},
-	}
-	files := buildBundleConfigFiles(b)
-	if n := len(files); n != 1 {
-		t.Fatalf("config.yaml only: want 1 file, got %d", n)
-	}
-	if content, ok := files["config.yaml"]; !ok {
-		t.Fatal("missing config.yaml")
-	} else if string(content) != "runtime: langgraph\ntier: 2\n" {
-		t.Errorf("config.yaml content: got %q", string(content))
-	}
-}
-
-func TestBuildBundleConfigFiles_SystemPromptAndConfigYaml(t *testing.T) {
-	b := &Bundle{
-		SystemPrompt: "Be concise.",
-		Prompts: map[string]string{
-			"config.yaml": "runtime: langgraph\n",
-		},
-	}
-	files := buildBundleConfigFiles(b)
-	if n := len(files); n != 2 {
-		t.Fatalf("system-prompt + config.yaml: want 2 files, got %d", n)
-	}
-	if _, ok := files["system-prompt.md"]; !ok {
-		t.Error("missing system-prompt.md")
-	}
-	if _, ok := files["config.yaml"]; !ok {
-		t.Error("missing config.yaml")
-	}
-}
-
-func TestBuildBundleConfigFiles_Skills(t *testing.T) {
-	b := &Bundle{
-		Skills: []BundleSkill{
-			{
-				ID:   "web-search",
-				Files: map[string]string{"readme.md": "# Web Search\n"},
-			},
-			{
-				ID:   "code-interpreter",
-				Files: map[string]string{"readme.md": "# Code Interpreter\n"},
-			},
-		},
-	}
-	files := buildBundleConfigFiles(b)
-	// 2 skills × 1 file each = 2 files
-	if n := len(files); n != 2 {
-		t.Fatalf("skills: want 2 files, got %d", n)
-	}
-	if _, ok := files["skills/web-search/readme.md"]; !ok {
-		t.Error("missing skills/web-search/readme.md")
-	}
-	if _, ok := files["skills/code-interpreter/readme.md"]; !ok {
-		t.Error("missing skills/code-interpreter/readme.md")
-	}
-}
-
-func TestBuildBundleConfigFiles_SkillSubPaths(t *testing.T) {
-	b := &Bundle{
-		Skills: []BundleSkill{
-			{
-				ID: "multi-file",
-				Files: map[string]string{
-					"readme.md":        "# Multi",
-					"instructions.txt": "Step 1, Step 2",
-				},
-			},
-		},
-	}
-	files := buildBundleConfigFiles(b)
-	if n := len(files); n != 2 {
-		t.Fatalf("skill with sub-paths: want 2 files, got %d", n)
-	}
-	if _, ok := files["skills/multi-file/readme.md"]; !ok {
-		t.Error("missing skills/multi-file/readme.md")
-	}
-	if _, ok := files["skills/multi-file/instructions.txt"]; !ok {
-		t.Error("missing skills/multi-file/instructions.txt")
-	}
-}
-
-func TestBuildBundleConfigFiles_EmptySystemPrompt(t *testing.T) {
-	b := &Bundle{
-		SystemPrompt: "",
-		Prompts: map[string]string{
-			"config.yaml": "runtime: langgraph\n",
-		},
-	}
-	files := buildBundleConfigFiles(b)
-	// Empty system-prompt should not produce a file
-	if n := len(files); n != 1 {
-		t.Errorf("empty system-prompt: want 1 file, got %d", n)
-	}
-}
-
-func TestBuildBundleConfigFiles_EmptyPrompts(t *testing.T) {
-	b := &Bundle{
-		Prompts: map[string]string{},
-	}
-	files := buildBundleConfigFiles(b)
-	if n := len(files); n != 0 {
-		t.Errorf("empty prompts map: want 0 files, got %d", n)
-	}
-}
-
-func TestBuildBundleConfigFiles_emptyBundle(t *testing.T) {
-	b := &Bundle{}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 0 {
-		t.Errorf("expected empty map for empty bundle, got %d entries", len(files))
-	}
-}
-
-func TestBuildBundleConfigFiles_systemPrompt(t *testing.T) {
-	b := &Bundle{SystemPrompt: "You are a helpful assistant."}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 1 {
-		t.Fatalf("expected 1 file, got %d", len(files))
-	}
-	if string(files["system-prompt.md"]) != "You are a helpful assistant." {
-		t.Errorf("unexpected system prompt content: %q", files["system-prompt.md"])
-	}
-}
-
-func TestBuildBundleConfigFiles_configYaml(t *testing.T) {
-	b := &Bundle{Prompts: map[string]string{
-		"config.yaml": "runtime: langgraph\nmodel: claude-sonnet-4-20250514\n",
-	}}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 1 {
-		t.Fatalf("expected 1 file, got %d", len(files))
-	}
-	if string(files["config.yaml"]) != "runtime: langgraph\nmodel: claude-sonnet-4-20250514\n" {
-		t.Errorf("unexpected config.yaml content: %q", files["config.yaml"])
-	}
-}
-
-func TestBuildBundleConfigFiles_systemPromptAndConfigYaml(t *testing.T) {
-	b := &Bundle{
-		SystemPrompt: "# System",
-		Prompts:     map[string]string{"config.yaml": "runtime: langgraph"},
-	}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 2 {
-		t.Fatalf("expected 2 files, got %d", len(files))
-	}
-	if _, ok := files["system-prompt.md"]; !ok {
-		t.Error("missing system-prompt.md")
-	}
-	if _, ok := files["config.yaml"]; !ok {
-		t.Error("missing config.yaml")
-	}
-}
-
-func TestBuildBundleConfigFiles_skills(t *testing.T) {
-	b := &Bundle{
-		Skills: []BundleSkill{
-			{
-				ID:          "web-search",
-				Name:        "Web Search",
-				Description: "Search the web",
-				Files:       map[string]string{"readme.md": "# Web Search"},
-			},
-			{
-				ID:          "code-runner",
-				Name:        "Code Runner",
-				Description: "Execute code",
-				Files:       map[string]string{"handler.py": "print('hello')"},
-			},
-		},
-	}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 2 {
-		t.Fatalf("expected 2 skill files, got %d", len(files))
-	}
-
-	if content, ok := files["skills/web-search/readme.md"]; !ok {
-		t.Error("missing skills/web-search/readme.md")
-	} else if string(content) != "# Web Search" {
-		t.Errorf("unexpected readme.md: %q", content)
-	}
-
-	if _, ok := files["skills/code-runner/handler.py"]; !ok {
-		t.Error("missing skills/code-runner/handler.py")
-	}
-}
-
-func TestBuildBundleConfigFiles_skillsWithSubPaths(t *testing.T) {
-	b := &Bundle{
-		Skills: []BundleSkill{
-			{
-				ID:    "nested-skill",
-				Files: map[string]string{"src/main.py": "def main(): pass", "pyproject.toml": "[tool.foo]"},
-			},
-		},
-	}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 2 {
-		t.Fatalf("expected 2 files, got %d", len(files))
-	}
-	if _, ok := files["skills/nested-skill/src/main.py"]; !ok {
-		t.Error("missing skills/nested-skill/src/main.py")
-	}
-	if _, ok := files["skills/nested-skill/pyproject.toml"]; !ok {
-		t.Error("missing skills/nested-skill/pyproject.toml")
-	}
-}
-
-func TestBuildBundleConfigFiles_skipsEmptyPrompts(t *testing.T) {
-	b := &Bundle{Prompts: map[string]string{}}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 0 {
-		t.Errorf("expected 0 files for empty prompts map, got %d", len(files))
-	}
-}
-
-func TestBuildBundleConfigFiles_skipsMissingConfigYaml(t *testing.T) {
-	b := &Bundle{
-		SystemPrompt: "# My Prompt",
-		Prompts:      map[string]string{"other.yaml": "something: else"},
-	}
-	files := buildBundleConfigFiles(b)
-	if len(files) != 1 {
-		t.Fatalf("expected 1 file (system-prompt only), got %d", len(files))
-	}
-	if _, ok := files["config.yaml"]; ok {
-		t.Error("config.yaml should not be written when not in Prompts")
-	}
-}
-
-func TestNilIfEmpty_emptyString(t *testing.T) {
-	result := nilIfEmpty("")
-	if result != nil {
-		t.Errorf("expected nil for empty string, got %v", result)
-	}
-}
-
-func TestNilIfEmpty_nonEmptyString(t *testing.T) {
-	result := nilIfEmpty("hello")
-	if result == nil {
-		t.Fatal("expected non-nil result for non-empty string")
-	}
-	if result != "hello" {
-		t.Errorf("expected hello, got %q", result)
-	}
-}
-
-func TestNilIfEmpty_whitespaceString(t *testing.T) {
-	// Whitespace is not empty — nilIfEmpty only checks for zero-length
-	result := nilIfEmpty("   ")
-	if result == nil {
-		t.Error("expected non-nil for whitespace string")
-	} else if result != "   " {
-		t.Errorf("expected '   ', got %q", result)
-	}
-}
-
-func TestNilIfEmpty_EmptyString(t *testing.T) {
-	got := nilIfEmpty("")
-	if got != nil {
-		t.Errorf("nilIfEmpty(\"\"): want nil, got %v", got)
-	}
-}
-
-func TestNilIfEmpty_NonEmptyString(t *testing.T) {
-	got := nilIfEmpty("hello")
-	if got == nil {
-		t.Fatal("nilIfEmpty(\"hello\"): want \"hello\", got nil")
-	}
-	if s, ok := got.(string); !ok || s != "hello" {
-		t.Errorf("nilIfEmpty(\"hello\"): got %v (%T)", got, got)
-	}
-}
-
-func TestNilIfEmpty_Whitespace(t *testing.T) {
-	got := nilIfEmpty("   ")
-	if got == nil {
-		t.Fatal("nilIfEmpty(\"   \"): want \"   \", got nil (whitespace is not empty)")
-	}
-	if s, ok := got.(string); !ok || s != "   " {
-		t.Errorf("nilIfEmpty(\"   \"): got %v (%T)", got, got)
-	}
-}

workspace-server/internal/handlers/a2a_proxy.go

@@ -97,28 +97,28 @@ const maxProxyResponseBody = 10 << 20
 //
 // Timeout model — three independent budgets, none of which gets in each other's way:
 //
-//  1. Client.Timeout — DELIBERATELY UNSET. Client.Timeout is a hard wall on
-//     the entire request including streamed body reads, and would pre-empt
-//     legitimate slow cold-start flows (Claude Code first-token over OAuth
-//     can take 30-60s on boot; long-running agent synthesis can stream
-//     tokens for minutes). Total-request budget is enforced per-request
-//     via context deadline (canvas = idle-only, agent-to-agent = 30 min ceiling).
+//   1. Client.Timeout — DELIBERATELY UNSET. Client.Timeout is a hard wall on
+//      the entire request including streamed body reads, and would pre-empt
+//      legitimate slow cold-start flows (Claude Code first-token over OAuth
+//      can take 30-60s on boot; long-running agent synthesis can stream
+//      tokens for minutes). Total-request budget is enforced per-request
+//      via context deadline (canvas = idle-only, agent-to-agent = 30 min ceiling).
 //
-//  2. Transport.DialContext — 10s connect timeout. When a workspace's EC2
-//     black-holes TCP connects (instance terminated mid-flight, security group
-//     flipped, NACL bug), the OS default is 75s on Linux / 21s on macOS — long
-//     enough that Cloudflare's ~100s edge timeout can fire first and surface
-//     a generic 502 page to canvas. 10s is well above realistic intra-region
-//     latencies and well below CF's edge timeout.
+//   2. Transport.DialContext — 10s connect timeout. When a workspace's EC2
+//      black-holes TCP connects (instance terminated mid-flight, security group
+//      flipped, NACL bug), the OS default is 75s on Linux / 21s on macOS — long
+//      enough that Cloudflare's ~100s edge timeout can fire first and surface
+//      a generic 502 page to canvas. 10s is well above realistic intra-region
+//      latencies and well below CF's edge timeout.
 //
-//  3. Transport.ResponseHeaderTimeout — 180s default. From request-body-end
-//     to response-headers-start. Configurable via
-//     A2A_PROXY_RESPONSE_HEADER_TIMEOUT (envx.Duration). Covers cold-start
-//     first-byte (30-60s OAuth flow above) with enough room for Opus agent
-//     turns (big context + internal delegate_task round-trips routinely exceed
-//     the old 60s ceiling). Body streaming after headers is governed by the
-//     per-request context deadline, NOT this timeout — so multi-minute agent
-//     responses still work fine.
+//   3. Transport.ResponseHeaderTimeout — 180s default. From request-body-end
+//      to response-headers-start. Configurable via
+//      A2A_PROXY_RESPONSE_HEADER_TIMEOUT (envx.Duration). Covers cold-start
+//      first-byte (30-60s OAuth flow above) with enough room for Opus agent
+//      turns (big context + internal delegate_task round-trips routinely exceed
+//      the old 60s ceiling). Body streaming after headers is governed by the
+//      per-request context deadline, NOT this timeout — so multi-minute agent
+//      responses still work fine.
 //
 // The point of (2) and (3) is to surface a *structured* 503 from
 // handleA2ADispatchError when the workspace agent is unreachable, so canvas
@@ -645,7 +645,7 @@ func (h *WorkspaceHandler) resolveAgentURL(ctx context.Context, workspaceID stri
 			// the caller can retry once the workspace is back online (~10s).
 			if status == "hibernated" {
 				log.Printf("ProxyA2A: waking hibernated workspace %s", workspaceID)
-				h.goAsync(func() { h.RestartByID(workspaceID) })
+				go h.RestartByID(workspaceID)
 				return "", &proxyA2AError{
 					Status:  http.StatusServiceUnavailable,
 					Headers: map[string]string{"Retry-After": "15"},

workspace-server/internal/handlers/a2a_proxy_helpers.go

@@ -194,7 +194,7 @@ func (h *WorkspaceHandler) maybeMarkContainerDead(ctx context.Context, workspace
 	}
 	db.ClearWorkspaceKeys(ctx, workspaceID)
 	h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
-	h.goAsync(func() { h.RestartByID(workspaceID) })
+	go h.RestartByID(workspaceID)
 	return true
 }
 
@@ -241,7 +241,7 @@ func (h *WorkspaceHandler) preflightContainerHealth(ctx context.Context, workspa
 	}
 	db.ClearWorkspaceKeys(ctx, workspaceID)
 	h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
-	h.goAsync(func() { h.RestartByID(workspaceID) })
+	go h.RestartByID(workspaceID)
 	return &proxyA2AError{
 		Status: http.StatusServiceUnavailable,
 		Response: gin.H{
@@ -262,8 +262,8 @@ func (h *WorkspaceHandler) logA2AFailure(ctx context.Context, workspaceID, calle
 		errWsName = workspaceID
 	}
 	summary := "A2A request to " + errWsName + " failed: " + errMsg
-	h.goAsync(func() {
-		logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
+	go func(parent context.Context) {
+		logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
 		defer cancel()
 		LogActivity(logCtx, h.broadcaster, ActivityParams{
 			WorkspaceID:  workspaceID,
@@ -277,7 +277,7 @@ func (h *WorkspaceHandler) logA2AFailure(ctx context.Context, workspaceID, calle
 			Status:       "error",
 			ErrorDetail:  &errMsg,
 		})
-	})
+	}(ctx)
 }
 
 // logA2ASuccess records a successful A2A round-trip and (for canvas-initiated
@@ -298,19 +298,19 @@ func (h *WorkspaceHandler) logA2ASuccess(ctx context.Context, workspaceID, calle
 	// silent workspaces. Only update when callerID is a real workspace (not
 	// canvas, not a system caller) and the target returned 2xx/3xx.
 	if callerID != "" && !isSystemCaller(callerID) && statusCode < 400 {
-		h.goAsync(func() {
+		go func() {
 			bgCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			if _, err := db.DB.ExecContext(bgCtx,
 				`UPDATE workspaces SET last_outbound_at = NOW() WHERE id = $1`, callerID); err != nil {
 				log.Printf("last_outbound_at update failed for %s: %v", callerID, err)
 			}
-		})
+		}()
 	}
 	summary := a2aMethod + " → " + wsNameForLog
 	toolTrace := extractToolTrace(respBody)
-	h.goAsync(func() {
-		logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
+	go func(parent context.Context) {
+		logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
 		defer cancel()
 		LogActivity(logCtx, h.broadcaster, ActivityParams{
 			WorkspaceID:  workspaceID,
@@ -325,7 +325,7 @@ func (h *WorkspaceHandler) logA2ASuccess(ctx context.Context, workspaceID, calle
 			DurationMs:   &durationMs,
 			Status:       logStatus,
 		})
-	})
+	}(ctx)
 
 	if callerID == "" && statusCode < 400 {
 		h.broadcaster.BroadcastOnly(workspaceID, string(events.EventA2AResponse), map[string]interface{}{
@@ -510,8 +510,8 @@ func (h *WorkspaceHandler) logA2AReceiveQueued(ctx context.Context, workspaceID,
 		wsName = workspaceID
 	}
 	summary := a2aMethod + " → " + wsName + " (queued for poll)"
-	h.goAsync(func() {
-		logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
+	go func(parent context.Context) {
+		logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
 		defer cancel()
 		LogActivity(logCtx, h.broadcaster, ActivityParams{
 			WorkspaceID:  workspaceID,
@@ -523,7 +523,7 @@ func (h *WorkspaceHandler) logA2AReceiveQueued(ctx context.Context, workspaceID,
 			RequestBody:  json.RawMessage(body),
 			Status:       "ok",
 		})
-	})
+	}(ctx)
 }
 
 // readUsageMap extracts input_tokens / output_tokens from the "usage" key of m.

workspace-server/internal/handlers/a2a_proxy_preflight_test.go

@@ -54,7 +54,6 @@ func TestPreflight_ContainerRunning_ReturnsNil(t *testing.T) {
 	_ = setupTestDB(t)
 	stub := &preflightLocalProv{running: true, err: nil}
 	h := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, h)
 	h.provisioner = stub
 
 	if err := h.preflightContainerHealth(context.Background(), "ws-running-123"); err != nil {
@@ -187,8 +186,8 @@ func TestProxyA2A_Preflight_RoutesThroughProvisionerSSOT(t *testing.T) {
 	}
 
 	var (
-		callsIsRunning                  bool
-		callsContainerInspectRaw        bool
+		callsIsRunning             bool
+		callsContainerInspectRaw   bool
 		callsRunningContainerNameDirect bool
 	)
 	ast.Inspect(fn.Body, func(n ast.Node) bool {

workspace-server/internal/handlers/a2a_proxy_test.go

@@ -262,7 +262,6 @@ func TestProxyA2A_Upstream502_TriggersContainerDeadCheck(t *testing.T) {
 	allowLoopbackForTest(t)
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 	cp := &fakeCPProv{running: false}
 	handler.SetCPProvisioner(cp)
 
@@ -325,7 +324,6 @@ func TestProxyA2A_Upstream502_AliveAgent_PropagatesAsIs(t *testing.T) {
 	allowLoopbackForTest(t)
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 	cp := &fakeCPProv{running: true}
 	handler.SetCPProvisioner(cp)
 
@@ -515,7 +513,6 @@ func TestProxyA2A_AllowedSelf_SkipsAccessCheck(t *testing.T) {
 	allowLoopbackForTest(t)
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	agentServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		w.Header().Set("Content-Type", "application/json")
@@ -664,18 +661,18 @@ func TestProxyA2A_CallerIDDerivedFromBearer(t *testing.T) {
 	//    (column order: workspace_id, activity_type, source_id, target_id, ...)
 	mock.ExpectExec("INSERT INTO activity_logs").
 		WithArgs(
-			"ws-target",      // $1 workspace_id
-			"a2a_receive",    // $2 activity_type
-			sqlmock.AnyArg(), // $3 source_id — *string("ws-caller"), checked below
-			sqlmock.AnyArg(), // $4 target_id
-			sqlmock.AnyArg(), // $5 method
-			sqlmock.AnyArg(), // $6 summary
-			sqlmock.AnyArg(), // $7 request_body
-			sqlmock.AnyArg(), // $8 response_body
-			sqlmock.AnyArg(), // $9 tool_trace
-			sqlmock.AnyArg(), // $10 duration_ms
-			sqlmock.AnyArg(), // $11 status
-			sqlmock.AnyArg(), // $12 error_detail
+			"ws-target",                       // $1 workspace_id
+			"a2a_receive",                     // $2 activity_type
+			sqlmock.AnyArg(),                  // $3 source_id — *string("ws-caller"), checked below
+			sqlmock.AnyArg(),                  // $4 target_id
+			sqlmock.AnyArg(),                  // $5 method
+			sqlmock.AnyArg(),                  // $6 summary
+			sqlmock.AnyArg(),                  // $7 request_body
+			sqlmock.AnyArg(),                  // $8 response_body
+			sqlmock.AnyArg(),                  // $9 tool_trace
+			sqlmock.AnyArg(),                  // $10 duration_ms
+			sqlmock.AnyArg(),                  // $11 status
+			sqlmock.AnyArg(),                  // $12 error_detail
 		).
 		WillReturnResult(sqlmock.NewResult(0, 1))
 
@@ -1719,6 +1716,7 @@ func TestDispatchA2A_RejectsUnsafeURL(t *testing.T) {
 	}
 }
 
+
 // --- handleA2ADispatchError ---
 
 func TestHandleA2ADispatchError_ContextDeadline(t *testing.T) {
@@ -1805,7 +1803,6 @@ func TestMaybeMarkContainerDead_CPOnly_NotRunning(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 	cp := &fakeCPProv{running: false}
 	handler.SetCPProvisioner(cp)
 
@@ -1958,7 +1955,6 @@ func TestLogA2AFailure_Smoke(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	// Sync workspace-name lookup (called in the caller goroutine).
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
@@ -1977,7 +1973,6 @@ func TestLogA2AFailure_EmptyNameFallback(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	// Empty name from DB → summary uses the workspaceID as the name.
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
@@ -1994,7 +1989,6 @@ func TestLogA2ASuccess_Smoke(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
 		WithArgs("ws-ok").
@@ -2011,7 +2005,6 @@ func TestLogA2ASuccess_ErrorStatus(t *testing.T) {
 	mock := setupTestDB(t)
 	setupTestRedis(t)
 	handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
-	waitForHandlerAsyncBeforeDBCleanup(t, handler)
 
 	mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
 		WithArgs("ws-err").

workspace-server/internal/handlers/a2a_queue.go

@@ -57,23 +57,16 @@ func extractIdempotencyKey(body []byte) string {
 func extractExpiresInSeconds(body []byte) int {
 	var envelope struct {
 		Params struct {
-			ExpiresInSeconds interface{} `json:"expires_in_seconds"`
+			ExpiresInSeconds int `json:"expires_in_seconds"`
 		} `json:"params"`
 	}
 	if err := json.Unmarshal(body, &envelope); err != nil {
 		return 0
 	}
-	var seconds int
-	switch v := envelope.Params.ExpiresInSeconds.(type) {
-	case float64:
-		seconds = int(v)
-	default:
+	if envelope.Params.ExpiresInSeconds < 0 {
 		return 0
 	}
-	if seconds < 0 {
-		return 0
-	}
-	return seconds
+	return envelope.Params.ExpiresInSeconds
 }
 
 const (

workspace-server/internal/handlers/a2a_queue_test.go

@@ -26,19 +26,14 @@ import (
 // setupTestDBForQueueTests creates a sqlmock DB using QueryMatcherEqual (exact
 // string matching) so that ExpectQuery/ExpectExec patterns are compared verbatim.
 // Uses the same global db.DB as setupTestDB so the handler can use it.
-//
-// IMPORTANT: db.DB is saved before assignment and restored via t.Cleanup so
-// that tests running after this one are not polluted by a closed mock.
-// Same fix as setupTestDB (handlers_test.go); same root cause as mc#975.
 func setupTestDBForQueueTests(t *testing.T) sqlmock.Sqlmock {
 	t.Helper()
 	mockDB, mock, err := sqlmock.New(sqlmock.QueryMatcherOption(sqlmock.QueryMatcherEqual))
 	if err != nil {
 		t.Fatalf("failed to create sqlmock: %v", err)
 	}
-	prevDB := db.DB
 	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
+	t.Cleanup(func() { mockDB.Close() })
 	return mock
 }
 

workspace-server/internal/handlers/activity_test.go

@@ -388,13 +388,9 @@ func TestActivityList_BeforeTSRejectsInvalidFormat(t *testing.T) {
 // ---------- Activity type allowlist (#125: memory_write added) ----------
 
 func TestActivityReport_AcceptsMemoryWriteType(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
+	mockDB, mock, _ := sqlmock.New()
+	defer mockDB.Close()
 	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
 
 	mock.ExpectExec(`INSERT INTO activity_logs`).
 		WillReturnResult(sqlmock.NewResult(1, 1))
@@ -417,13 +413,9 @@ func TestActivityReport_AcceptsMemoryWriteType(t *testing.T) {
 }
 
 func TestActivityReport_RejectsUnknownType(t *testing.T) {
-	mockDB, _, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
+	mockDB, _, _ := sqlmock.New()
+	defer mockDB.Close()
 	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
 
 	broadcaster := newTestBroadcaster()
 	handler := NewActivityHandler(broadcaster)
@@ -455,13 +447,9 @@ func TestNotify_PersistsToActivityLogsForReloadRecovery(t *testing.T) {
 	//   - Have source_id NULL (canvas-source filter)
 	//   - Carry the message text in response_body so extractResponseText
 	//     can reconstruct the agent reply on reload
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
+	mockDB, mock, _ := sqlmock.New()
+	defer mockDB.Close()
 	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
 
 	// Workspace existence check
 	mock.ExpectQuery(`SELECT name FROM workspaces`).
@@ -503,13 +491,9 @@ func TestNotify_WithAttachments_PersistsFilePartsForReload(t *testing.T) {
 	// download chips after a page reload. Without `parts`, the bubble
 	// shows up but the attachment chip is silently dropped on every
 	// refresh.
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
+	mockDB, mock, _ := sqlmock.New()
+	defer mockDB.Close()
 	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
 
 	mock.ExpectQuery(`SELECT name FROM workspaces`).
 		WithArgs("ws-attach").
@@ -581,13 +565,9 @@ func TestNotify_RejectsAttachmentWithEmptyURIOrName(t *testing.T) {
 	}
 	for _, tc := range cases {
 		t.Run(tc.name, func(t *testing.T) {
-			mockDB, _, err := sqlmock.New()
-			if err != nil {
-				t.Fatalf("failed to create sqlmock: %v", err)
-			}
-			prevDB := db.DB
+			mockDB, _, _ := sqlmock.New()
+			defer mockDB.Close()
 			db.DB = mockDB
-			t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
 			// No DB expectations — handler must reject with 400 BEFORE
 			// reaching SELECT/INSERT. sqlmock will fail "expectations not met"
 			// only if the handler unexpectedly queries.
@@ -632,13 +612,9 @@ func TestNotify_DBFailure_StillBroadcastsAnd200(t *testing.T) {
 	// WebSocket push (which the user is already seeing in their open
 	// canvas). Pre-fix the WS push always succeeded; we don't want
 	// the new persistence step to regress that path.
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
+	mockDB, mock, _ := sqlmock.New()
+	defer mockDB.Close()
 	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
 
 	mock.ExpectQuery(`SELECT name FROM workspaces`).
 		WithArgs("ws-x").

workspace-server/internal/handlers/bundle.go

@@ -2,7 +2,6 @@ package handlers
 
 import (
 	"net/http"
-	"strings"
 
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/bundle"
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
@@ -50,8 +49,8 @@ func (h *BundleHandler) Import(c *gin.Context) {
 		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid bundle"})
 		return
 	}
-	if strings.TrimSpace(b.Name) == "" {
-		c.JSON(http.StatusBadRequest, gin.H{"error": "bundle name is required"})
+	if b.Schema == "" || b.Name == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid bundle"})
 		return
 	}
 

workspace-server/internal/handlers/bundle_test.go

@@ -57,8 +57,8 @@ func TestBundleImport_ValidJSON(t *testing.T) {
 	broadcaster := newTestBroadcaster()
 	h := NewBundleHandler(broadcaster, nil, "http://localhost:8080", t.TempDir(), nil)
 
-	// bundle.Import does: INSERT workspaces, broadcast provisioning, then UPDATE runtime.
-	// bundle.Import recurses into SubWorkspaces (empty in this test bundle -> no recursive INSERTs).
+	// bundle.Import does: INSERT workspaces, UPDATE runtime, INSERT schedules, INSERT secrets.
+	// bundle.Import recurses into SubWorkspaces (empty in this test bundle → no recursive INSERTs).
 	mock.ExpectExec("INSERT INTO workspaces").
 		WillReturnResult(sqlmock.NewResult(0, 1))
 	mock.ExpectExec("INSERT INTO structure_events").

workspace-server/internal/handlers/channels_test.go

@@ -15,7 +15,6 @@ import (
 
 	sqlmock "github.com/DATA-DOG/go-sqlmock"
 	"github.com/Molecule-AI/molecule-monorepo/platform/internal/channels"
-	"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
 	"github.com/gin-gonic/gin"
 )
 
@@ -365,20 +364,6 @@ func TestChannelHandler_Discover_MissingToken(t *testing.T) {
 }
 
 func TestChannelHandler_Discover_UnsupportedType(t *testing.T) {
-	// Set up db.DB so PausePollersForToken (called inside Discover) doesn't panic.
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("sqlmock: %v", err)
-	}
-	t.Cleanup(func() { mockDB.Close() })
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB })
-
-	mock.ExpectQuery(`SELECT id, channel_config FROM workspace_channels WHERE enabled = true AND workspace_id`).
-		WithArgs("ws-test").
-		WillReturnRows(sqlmock.NewRows([]string{"id", "channel_config"}))
-
 	handler := NewChannelHandler(newTestChannelManager())
 
 	// #329: workspace_id required — include so we actually reach the
@@ -402,20 +387,6 @@ func TestChannelHandler_Discover_UnsupportedType(t *testing.T) {
 }
 
 func TestChannelHandler_Discover_InvalidBotToken(t *testing.T) {
-	// Set up db.DB so PausePollersForToken (called inside Discover) doesn't panic.
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("sqlmock: %v", err)
-	}
-	t.Cleanup(func() { mockDB.Close() })
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB })
-
-	mock.ExpectQuery(`SELECT id, channel_config FROM workspace_channels WHERE enabled = true AND workspace_id`).
-		WithArgs("ws-test").
-		WillReturnRows(sqlmock.NewRows([]string{"id", "channel_config"}))
-
 	handler := NewChannelHandler(newTestChannelManager())
 
 	body, _ := json.Marshal(map[string]interface{}{

workspace-server/internal/handlers/delegation.go

@@ -2,7 +2,6 @@ package handlers
 
 import (
 	"context"
-	"database/sql"
 	"encoding/json"
 	"log"
 	"net/http"
@@ -263,20 +262,14 @@ func insertDelegationRow(ctx context.Context, c *gin.Context, sourceID string, b
 		"task":          body.Task,
 		"delegation_id": delegationID,
 	})
-	// Store delegation_id in response_body so agent check_delegation_status
-	// (which reads response_body->>delegation_id) can locate this row even
-	// when request_body hasn't propagated yet. Fixes mc#984.
-	respJSON, _ := json.Marshal(map[string]interface{}{
-		"delegation_id": delegationID,
-	})
 	var idemArg interface{}
 	if body.IdempotencyKey != "" {
 		idemArg = body.IdempotencyKey
 	}
 	_, err := db.DB.ExecContext(ctx, `
-		INSERT INTO activity_logs (workspace_id, activity_type, method, source_id, target_id, summary, request_body, response_body, status, idempotency_key)
-		VALUES ($1, 'delegation', 'delegate', $2, $3, $4, $5::jsonb, $6::jsonb, 'pending', $7)
-	`, sourceID, sourceID, body.TargetID, "Delegating to "+body.TargetID, string(taskJSON), string(respJSON), idemArg)
+		INSERT INTO activity_logs (workspace_id, activity_type, method, source_id, target_id, summary, request_body, status, idempotency_key)
+		VALUES ($1, 'delegation', 'delegate', $2, $3, $4, $5::jsonb, 'pending', $6)
+	`, sourceID, sourceID, body.TargetID, "Delegating to "+body.TargetID, string(taskJSON), idemArg)
 	if err == nil {
 		// RFC #2829 #318 — mirror to the durable delegations ledger
 		// (gated by DELEGATION_LEDGER_WRITE; default off → no-op).
@@ -551,15 +544,10 @@ func (h *DelegationHandler) Record(c *gin.Context) {
 		"task":          body.Task,
 		"delegation_id": body.DelegationID,
 	})
-	// Store delegation_id in response_body so agent check_delegation_status
-	// can locate this row. Fixes mc#984.
-	respJSON, _ := json.Marshal(map[string]interface{}{
-		"delegation_id": body.DelegationID,
-	})
 	if _, err := db.DB.ExecContext(ctx, `
-		INSERT INTO activity_logs (workspace_id, activity_type, method, source_id, target_id, summary, request_body, response_body, status)
-		VALUES ($1, 'delegation', 'delegate', $2, $3, $4, $5::jsonb, $6::jsonb, 'dispatched')
-	`, sourceID, sourceID, body.TargetID, "Delegating to "+body.TargetID, string(taskJSON), string(respJSON)); err != nil {
+		INSERT INTO activity_logs (workspace_id, activity_type, method, source_id, target_id, summary, request_body, status)
+		VALUES ($1, 'delegation', 'delegate', $2, $3, $4, $5::jsonb, 'dispatched')
+	`, sourceID, sourceID, body.TargetID, "Delegating to "+body.TargetID, string(taskJSON)); err != nil {
 		log.Printf("Delegation Record: insert failed for %s: %v", body.DelegationID, err)
 		c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to record delegation"})
 		return
@@ -699,8 +687,7 @@ func (h *DelegationHandler) listDelegationsFromLedger(ctx context.Context, works
 
 	var result []map[string]interface{}
 	for rows.Next() {
-		var delegationID, callerID, calleeID, taskPreview, status string
-		var resultPreview, errorDetail sql.NullString
+		var delegationID, callerID, calleeID, taskPreview, status, resultPreview, errorDetail string
 		var lastHeartbeat, deadline, createdAt, updatedAt *time.Time
 		if err := rows.Scan(
 			&delegationID, &callerID, &calleeID, &taskPreview,
@@ -719,11 +706,11 @@ func (h *DelegationHandler) listDelegationsFromLedger(ctx context.Context, works
 			"updated_at":    updatedAt,
 			"_ledger":       true, // marker so callers know this row is from the ledger
 		}
-		if resultPreview.Valid && resultPreview.String != "" {
-			entry["response_preview"] = textutil.TruncateBytes(resultPreview.String, 300)
+		if resultPreview != "" {
+			entry["response_preview"] = textutil.TruncateBytes(resultPreview, 300)
 		}
-		if errorDetail.Valid && errorDetail.String != "" {
-			entry["error"] = errorDetail.String
+		if errorDetail != "" {
+			entry["error"] = errorDetail
 		}
 		if lastHeartbeat != nil {
 			entry["last_heartbeat"] = lastHeartbeat

workspace-server/internal/handlers/delegation_executor_integration_test.go

@@ -52,9 +52,9 @@ import (
 // integrationDB is imported from delegation_ledger_integration_test.go.
 // Each test gets a fresh table state.
 
-const integrationTestDelegationID = "del-159-test-integration"
-const integrationTestSourceID = "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
-const integrationTestTargetID = "bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb"
+const testDelegationID = "del-159-test-integration"
+const testSourceID = "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
+const testTargetID = "bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb"
 
 // rawHTTPServer starts a TCP listener, serves one HTTP response, and closes.
 // It runs in a background goroutine so the test can proceed immediately after
@@ -153,8 +153,8 @@ func setupIntegrationFixtures(t *testing.T, conn *sql.DB) func() {
 		name     string
 		parentID *string
 	}{
-		{integrationTestSourceID, "test-source", nil},
-		{integrationTestTargetID, "test-target", nil},
+		{testSourceID, "test-source", nil},
+		{testTargetID, "test-target", nil},
 	} {
 		if _, err := conn.ExecContext(ctx,
 			`INSERT INTO workspaces (id, name, parent_id) VALUES ($1::uuid, $2, $3) ON CONFLICT (id) DO NOTHING`,
@@ -166,7 +166,7 @@ func setupIntegrationFixtures(t *testing.T, conn *sql.DB) func() {
 	}
 
 	reqBody, _ := json.Marshal(map[string]any{
-		"delegation_id": integrationTestDelegationID,
+		"delegation_id": testDelegationID,
 		"task":          "do work",
 	})
 	if _, err := conn.ExecContext(ctx, `
@@ -174,7 +174,7 @@ func setupIntegrationFixtures(t *testing.T, conn *sql.DB) func() {
 			(workspace_id, activity_type, method, source_id, target_id, request_body, status)
 		VALUES ($1, 'delegate', 'delegate', $1, $2, $3::jsonb, 'pending')
 		ON CONFLICT DO NOTHING
-	`, integrationTestSourceID, integrationTestTargetID, string(reqBody)); err != nil {
+	`, testSourceID, testTargetID, string(reqBody)); err != nil {
 		cancel()
 		t.Fatalf("seed activity_logs: %v", err)
 	}
@@ -184,7 +184,7 @@ func setupIntegrationFixtures(t *testing.T, conn *sql.DB) func() {
 			(delegation_id, caller_id, callee_id, task_preview, status)
 		VALUES ($1, $2::uuid, $3::uuid, 'do work', 'queued')
 		ON CONFLICT (delegation_id) DO NOTHING
-	`, integrationTestDelegationID, integrationTestSourceID, integrationTestTargetID); err != nil {
+	`, testDelegationID, testSourceID, testTargetID); err != nil {
 		cancel()
 		t.Fatalf("seed delegations: %v", err)
 	}
@@ -195,11 +195,11 @@ func setupIntegrationFixtures(t *testing.T, conn *sql.DB) func() {
 		defer cancel2()
 		conn.ExecContext(ctx2,
 			`DELETE FROM activity_logs WHERE workspace_id = $1 AND request_body->>'delegation_id' = $2`,
-			integrationTestSourceID, integrationTestDelegationID)
+			testSourceID, testDelegationID)
 		conn.ExecContext(ctx2,
-			`DELETE FROM delegations WHERE delegation_id = $1`, integrationTestDelegationID)
+			`DELETE FROM delegations WHERE delegation_id = $1`, testDelegationID)
 		conn.ExecContext(ctx2,
-			`DELETE FROM workspaces WHERE id IN ($1, $2)`, integrationTestSourceID, integrationTestTargetID)
+			`DELETE FROM workspaces WHERE id IN ($1, $2)`, testSourceID, testTargetID)
 	}
 }
 
@@ -212,7 +212,7 @@ func readDelegationRow(t *testing.T, conn *sql.DB) (status, preview, errorDetail
 	var prev, errDet sql.NullString
 	err := conn.QueryRowContext(ctx,
 		`SELECT status, result_preview, error_detail FROM delegations WHERE delegation_id = $1`,
-		integrationTestDelegationID,
+		testDelegationID,
 	).Scan(&status, &prev, &errDet)
 	if err != nil {
 		t.Fatalf("readDelegationRow: %v", err)
@@ -279,7 +279,7 @@ func TestIntegration_ExecuteDelegation_DeliveryConfirmedProxyError_TreatsAsSucce
 
 	mr := setupTestRedis(t)
 	defer mr.Close()
-	db.CacheURL(context.Background(), integrationTestTargetID, agentURL)
+	db.CacheURL(context.Background(), testTargetID, agentURL)
 
 	prevClient := a2aClient
 	defer func() { a2aClient = prevClient }()
@@ -303,7 +303,7 @@ func TestIntegration_ExecuteDelegation_DeliveryConfirmedProxyError_TreatsAsSucce
 
 	start := time.Now()
 	runWithTimeout(t, 30*time.Second, func(ctx context.Context) {
-		dh.executeDelegation(ctx, integrationTestSourceID, integrationTestTargetID, integrationTestDelegationID, a2aBody)
+		dh.executeDelegation(ctx, testSourceID, testTargetID, testDelegationID, a2aBody)
 	})
 	t.Logf("executeDelegation took %v", time.Since(start))
 
@@ -334,7 +334,7 @@ func TestIntegration_ExecuteDelegation_ProxyErrorNon2xx_RemainsFailed(t *testing
 
 	mr := setupTestRedis(t)
 	defer mr.Close()
-	db.CacheURL(context.Background(), integrationTestTargetID, agentURL)
+	db.CacheURL(context.Background(), testTargetID, agentURL)
 
 	prevClient := a2aClient
 	defer func() { a2aClient = prevClient }()
@@ -355,7 +355,7 @@ func TestIntegration_ExecuteDelegation_ProxyErrorNon2xx_RemainsFailed(t *testing
 	})
 	start := time.Now()
 	runWithTimeout(t, 30*time.Second, func(ctx context.Context) {
-		dh.executeDelegation(ctx, integrationTestSourceID, integrationTestTargetID, integrationTestDelegationID, a2aBody)
+		dh.executeDelegation(ctx, testSourceID, testTargetID, testDelegationID, a2aBody)
 	})
 	t.Logf("executeDelegation took %v", time.Since(start))
 
@@ -383,7 +383,7 @@ func TestIntegration_ExecuteDelegation_ProxyErrorEmptyBody_RemainsFailed(t *test
 
 	mr := setupTestRedis(t)
 	defer mr.Close()
-	db.CacheURL(context.Background(), integrationTestTargetID, agentURL)
+	db.CacheURL(context.Background(), testTargetID, agentURL)
 
 	prevClient := a2aClient
 	defer func() { a2aClient = prevClient }()
@@ -404,7 +404,7 @@ func TestIntegration_ExecuteDelegation_ProxyErrorEmptyBody_RemainsFailed(t *test
 	})
 	start := time.Now()
 	runWithTimeout(t, 30*time.Second, func(ctx context.Context) {
-		dh.executeDelegation(ctx, integrationTestSourceID, integrationTestTargetID, integrationTestDelegationID, a2aBody)
+		dh.executeDelegation(ctx, testSourceID, testTargetID, testDelegationID, a2aBody)
 	})
 	t.Logf("executeDelegation took %v", time.Since(start))
 
@@ -431,7 +431,7 @@ func TestIntegration_ExecuteDelegation_CleanProxyResponse_Unchanged(t *testing.T
 
 	mr := setupTestRedis(t)
 	defer mr.Close()
-	db.CacheURL(context.Background(), integrationTestTargetID, agentURL)
+	db.CacheURL(context.Background(), testTargetID, agentURL)
 
 	prevClient := a2aClient
 	defer func() { a2aClient = prevClient }()
@@ -452,7 +452,7 @@ func TestIntegration_ExecuteDelegation_CleanProxyResponse_Unchanged(t *testing.T
 	})
 	start := time.Now()
 	runWithTimeout(t, 30*time.Second, func(ctx context.Context) {
-		dh.executeDelegation(ctx, integrationTestSourceID, integrationTestTargetID, integrationTestDelegationID, a2aBody)
+		dh.executeDelegation(ctx, testSourceID, testTargetID, testDelegationID, a2aBody)
 	})
 	t.Logf("executeDelegation took %v", time.Since(start))
 
@@ -497,7 +497,7 @@ func TestIntegration_ExecuteDelegation_RedisDown_FallsBackToDB(t *testing.T) {
 	})
 	start := time.Now()
 	runWithTimeout(t, 30*time.Second, func(ctx context.Context) {
-		dh.executeDelegation(ctx, integrationTestSourceID, integrationTestTargetID, integrationTestDelegationID, a2aBody)
+		dh.executeDelegation(ctx, testSourceID, testTargetID, testDelegationID, a2aBody)
 	})
 	t.Logf("executeDelegation took %v", time.Since(start))
 

workspace-server/internal/handlers/delegation_extract_response_text_test.go

@@ -1,224 +0,0 @@
-package handlers
-
-import (
-	"encoding/json"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-// extractResponseText tests — walks A2A JSON-RPC response bodies and
-// returns the first text part, falling back to raw body on parse failures.
-
-func TestExtractResponseText_PartsWithTextKind(t *testing.T) {
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{
-				map[string]interface{}{"kind": "text", "text": "hello world"},
-				map[string]interface{}{"kind": "text", "text": "second part"},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "hello world", extractResponseText(body))
-}
-
-func TestExtractResponseText_PartNotTextKind(t *testing.T) {
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{
-				map[string]interface{}{"kind": "image", "data": "base64..."},
-				map[string]interface{}{"kind": "text", "text": "visible"},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "visible", extractResponseText(body))
-}
-
-func TestExtractResponseText_PartsEmpty(t *testing.T) {
-	// Empty parts array — falls through to artifacts, then raw body
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts":     []interface{}{},
-			"artifacts": []interface{}{},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	// Falls through to raw body (which is the JSON string)
-	result := extractResponseText(body)
-	assert.NotEmpty(t, result)
-}
-
-func TestExtractResponseText_ArtifactPartsWithText(t *testing.T) {
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{},
-			"artifacts": []interface{}{
-				map[string]interface{}{
-					"kind": "file",
-					"parts": []interface{}{
-						map[string]interface{}{"kind": "text", "text": "artifact text"},
-					},
-				},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "artifact text", extractResponseText(body))
-}
-
-func TestExtractResponseText_ArtifactPartNotTextKind(t *testing.T) {
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{},
-			"artifacts": []interface{}{
-				map[string]interface{}{
-					"kind": "code",
-					"parts": []interface{}{
-						map[string]interface{}{"kind": "image", "data": "..."},
-						map[string]interface{}{"kind": "text", "text": "code comment"},
-					},
-				},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "code comment", extractResponseText(body))
-}
-
-func TestExtractResponseText_ArtifactsEmpty(t *testing.T) {
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts":     []interface{}{},
-			"artifacts": []interface{}{},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	result := extractResponseText(body)
-	// Falls back to raw body
-	assert.Equal(t, string(body), result)
-}
-
-func TestExtractResponseText_NoResult(t *testing.T) {
-	// No "result" key at all — falls back to raw body
-	body := []byte(`{"error": {"code": -32600, "message": "Invalid Request"}}`)
-	result := extractResponseText(body)
-	assert.Equal(t, string(body), result)
-}
-
-func TestExtractResponseText_ResultNotMap(t *testing.T) {
-	// result is a string, not a map — falls back to raw body
-	body := []byte(`{"result": "just a string"}`)
-	result := extractResponseText(body)
-	assert.Equal(t, string(body), result)
-}
-
-func TestExtractResponseText_NonJSONBody(t *testing.T) {
-	// Non-JSON bytes — returns the raw string
-	body := []byte("plain text response, not JSON at all")
-	result := extractResponseText(body)
-	assert.Equal(t, "plain text response, not JSON at all", result)
-}
-
-func TestExtractResponseText_PartWithNilText(t *testing.T) {
-	// Text field is nil — kind is "text" but text is nil, should skip
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{
-				map[string]interface{}{"kind": "text", "text": nil},
-				map[string]interface{}{"kind": "text", "text": "found"},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "found", extractResponseText(body))
-}
-
-func TestExtractResponseText_ArtifactPartWithNilText(t *testing.T) {
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{},
-			"artifacts": []interface{}{
-				map[string]interface{}{
-					"parts": []interface{}{
-						map[string]interface{}{"kind": "text", "text": nil},
-						map[string]interface{}{"kind": "text", "text": "artifact-found"},
-					},
-				},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "artifact-found", extractResponseText(body))
-}
-
-func TestExtractResponseText_PartsWithNonMapElement(t *testing.T) {
-	// parts contains a non-map element — should be skipped gracefully
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{
-				"not a map",
-				123,
-				nil,
-				map[string]interface{}{"kind": "text", "text": "parsed"},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "parsed", extractResponseText(body))
-}
-
-func TestExtractResponseText_ArtifactWithNonMapElement(t *testing.T) {
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{},
-			"artifacts": []interface{}{
-				"not a map",
-				nil,
-				map[string]interface{}{
-					"parts": []interface{}{
-						"not a map",
-						map[string]interface{}{"kind": "text", "text": "safe"},
-					},
-				},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "safe", extractResponseText(body))
-}
-
-func TestExtractResponseText_PartKindNotString(t *testing.T) {
-	// kind is an integer, not a string — should be skipped
-	resp := map[string]interface{}{
-		"result": map[string]interface{}{
-			"parts": []interface{}{
-				map[string]interface{}{"kind": 123, "text": "ignored"},
-				map[string]interface{}{"kind": "text", "text": "found"},
-			},
-		},
-	}
-	body, _ := json.Marshal(resp)
-	assert.Equal(t, "found", extractResponseText(body))
-}
-
-func TestExtractResponseText_EmptyResponse(t *testing.T) {
-	body := []byte("{}")
-	result := extractResponseText(body)
-	// Falls back to raw "{}"
-	assert.Equal(t, "{}", result)
-}
-
-func TestExtractResponseText_NilBody(t *testing.T) {
-	// nil byte slice — string(nil) = ""
-	result := extractResponseText(nil)
-	assert.Equal(t, "", result)
-}
-
-func TestExtractResponseText_WhitespaceBody(t *testing.T) {
-	body := []byte("   \n\t  ")
-	result := extractResponseText(body)
-	// Unmarshals to empty map, no result, returns raw string
-	assert.Equal(t, "   \n\t  ", result)
-}

workspace-server/internal/handlers/delegation_list_test.go

@@ -1,488 +0,0 @@
-package handlers
-
-// delegation_list_test.go — unit tests for listDelegationsFromLedger and
-// listDelegationsFromActivityLogs. Both methods are the data-backend of the
-// ListDelegations handler; coverage was missing (cf. infra-sre review of PR #942).
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/DATA-DOG/go-sqlmock"
-	"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
-)
-
-// ---------- listDelegationsFromLedger ----------
-
-func TestListDelegationsFromLedger_EmptyResult(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	rows := sqlmock.NewRows([]string{
-		"delegation_id", "caller_id", "callee_id", "task_preview",
-		"status", "result_preview", "error_detail",
-		"last_heartbeat", "deadline", "created_at", "updated_at",
-	})
-	mock.ExpectQuery("SELECT .+ FROM delegations").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
-	if got != nil {
-		t.Errorf("empty result: expected nil, got %v", got)
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromLedger_SingleRow(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	now := time.Now()
-	// Use time.Time{} for nullable *time.Time columns — sqlmock passes the
-	// zero value to the handler's scan destination. The handler checks Valid
-	// before using each nullable field, so zero values are safe.
-	rows := sqlmock.NewRows([]string{
-		"delegation_id", "caller_id", "callee_id", "task_preview",
-		"status", "result_preview", "error_detail",
-		"last_heartbeat", "deadline", "created_at", "updated_at",
-	}).AddRow(
-		"del-1", "ws-1", "ws-2", "summarise the report",
-		"completed", "the report is about Q1",
-		"", now, now, now, now,
-	)
-	mock.ExpectQuery("SELECT .+ FROM delegations").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
-	if len(got) != 1 {
-		t.Fatalf("expected 1 entry, got %d", len(got))
-	}
-	e := got[0]
-	if e["delegation_id"] != "del-1" {
-		t.Errorf("delegation_id: got %v, want del-1", e["delegation_id"])
-	}
-	if e["source_id"] != "ws-1" {
-		t.Errorf("source_id: got %v, want ws-1", e["source_id"])
-	}
-	if e["target_id"] != "ws-2" {
-		t.Errorf("target_id: got %v, want ws-2", e["target_id"])
-	}
-	if e["status"] != "completed" {
-		t.Errorf("status: got %v, want completed", e["status"])
-	}
-	if e["response_preview"] != "the report is about Q1" {
-		t.Errorf("response_preview: got %v", e["response_preview"])
-	}
-	if _, ok := e["error"]; ok {
-		t.Errorf("error should be absent when empty, got %v", e["error"])
-	}
-	if e["_ledger"] != true {
-		t.Errorf("_ledger marker: got %v, want true", e["_ledger"])
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromLedger_MultipleRows(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	now := time.Now()
-	rows := sqlmock.NewRows([]string{
-		"delegation_id", "caller_id", "callee_id", "task_preview",
-		"status", "result_preview", "error_detail",
-		"last_heartbeat", "deadline", "created_at", "updated_at",
-	}).
-		AddRow("del-a", "ws-1", "ws-2", "task a", "in_progress", "", "", now, now, now, now).
-		AddRow("del-b", "ws-1", "ws-3", "task b", "failed", "", "timeout", now, now, now, now).
-		AddRow("del-c", "ws-1", "ws-4", "task c", "completed", "result c", "", now, now, now, now)
-	mock.ExpectQuery("SELECT .+ FROM delegations").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
-	if len(got) != 3 {
-		t.Fatalf("expected 3 entries, got %d", len(got))
-	}
-	if got[0]["delegation_id"] != "del-a" || got[1]["delegation_id"] != "del-b" || got[2]["delegation_id"] != "del-c" {
-		t.Errorf("unexpected order: %v", got)
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromLedger_NullsOmitted(t *testing.T) {
-	// last_heartbeat, deadline, result_preview, error_detail are all NULL.
-	// Handler must not panic and must omit those keys from the map.
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
-
-	now := time.Now()
-	rows := sqlmock.NewRows([]string{
-		"delegation_id", "caller_id", "callee_id", "task_preview",
-		"status", "result_preview", "error_detail",
-		"last_heartbeat", "deadline", "created_at", "updated_at",
-	}).
-		AddRow("del-1", "ws-1", "ws-2", "task", "queued", nil, nil, nil, nil, now, now)
-	mock.ExpectQuery("SELECT .+ FROM delegations").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
-	if len(got) != 1 {
-		t.Fatalf("expected 1 entry, got %d", len(got))
-	}
-	e := got[0]
-	if _, ok := e["last_heartbeat"]; ok {
-		t.Error("last_heartbeat should be absent when NULL")
-	}
-	if _, ok := e["deadline"]; ok {
-		t.Error("deadline should be absent when NULL")
-	}
-	if _, ok := e["response_preview"]; ok {
-		t.Error("response_preview should be absent when NULL result_preview")
-	}
-	if _, ok := e["error"]; ok {
-		t.Error("error should be absent when NULL error_detail")
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromLedger_QueryError(t *testing.T) {
-	// Query failure returns nil — graceful fallback, no panic.
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	mock.ExpectQuery("SELECT .+ FROM delegations").
-		WithArgs("ws-1").
-		WillReturnError(context.DeadlineExceeded)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
-	if got != nil {
-		t.Errorf("query error: expected nil, got %v", got)
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromLedger_RowsErr(t *testing.T) {
-	// rows.Err() mid-stream: handler collects partial results and returns them.
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	now := time.Now()
-	// RowError(0) before AddRow(0): row 0 is "bad", rows.Next() returns false
-	// on first call — the row never scans, result stays nil. To get partial
-	// results (row 0 scanned) with rows.Err() non-nil, we use 2 rows and put
-	// RowError(1) after AddRow(1): row 0 scans normally, row 1 is bad,
-	// rows.Err() is error, handler returns partial result.
-	rows := sqlmock.NewRows([]string{
-		"delegation_id", "caller_id", "callee_id", "task_preview",
-		"status", "result_preview", "error_detail",
-		"last_heartbeat", "deadline", "created_at", "updated_at",
-	}).
-		AddRow("del-1", "ws-1", "ws-2", "task", "queued", "", "", now, now, now, now).
-		AddRow("del-2", "ws-1", "ws-3", "another task", "queued", "", "", now, now, now, now).
-		RowError(1, context.DeadlineExceeded)
-	mock.ExpectQuery("SELECT .+ FROM delegations").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
-	// Row 0 scanned and appended; row 1 is bad; rows.Err() is non-nil.
-	// Handler logs the error but returns result (partial results because result != nil).
-	if got == nil || len(got) != 1 {
-		t.Errorf("rows.Err path: expected 1 partial result, got %v", got)
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-// TestListDelegationsFromLedger_ScanError is removed.
-//
-// In Go 1.25 sqlmock.NewRows validates column count at AddRow() time and
-// panics when len(values) != len(columns). The old pattern
-//   sqlmock.NewRows([]string{}).AddRow("only-one-col")
-// therefore panics in test SETUP, not inside the handler. The handler has no
-// recover(), so a scan panic would propagate out of listDelegationsFromLedger
-// and crash the process — this is the correct behaviour (not silently skipping
-// a row). The correct way to cover this path is a real-DB integration test.
-//
-// ---------- listDelegationsFromActivityLogs ----------
-
-func TestListDelegationsFromActivityLogs_EmptyResult(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	rows := sqlmock.NewRows([]string{
-		"id", "activity_type", "source_id", "target_id",
-		"summary", "status", "error_detail",
-		"response_preview", "delegation_id", "created_at",
-	})
-	mock.ExpectQuery("SELECT .+ FROM activity_logs").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromActivityLogs(context.Background(), "ws-1")
-	if len(got) != 0 {
-		t.Errorf("empty result: expected empty slice, got %v", got)
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromActivityLogs_SingleDelegateRow(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	now := time.Now()
-	rows := sqlmock.NewRows([]string{
-		"id", "activity_type", "source_id", "target_id",
-		"summary", "status", "error_detail",
-		"response_preview", "delegation_id", "created_at",
-	}).AddRow(
-		"act-1", "delegate",
-		"ws-1", "ws-2",
-		"analyse Q1 numbers",
-		"in_progress",
-		"", "", "",
-		now,
-	)
-	mock.ExpectQuery("SELECT .+ FROM activity_logs").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromActivityLogs(context.Background(), "ws-1")
-	if len(got) != 1 {
-		t.Fatalf("expected 1 entry, got %d", len(got))
-	}
-	e := got[0]
-	if e["id"] != "act-1" {
-		t.Errorf("id: got %v, want act-1", e["id"])
-	}
-	if e["type"] != "delegate" {
-		t.Errorf("type: got %v, want delegate", e["type"])
-	}
-	if e["source_id"] != "ws-1" {
-		t.Errorf("source_id: got %v, want ws-1", e["source_id"])
-	}
-	if e["target_id"] != "ws-2" {
-		t.Errorf("target_id: got %v, want ws-2", e["target_id"])
-	}
-	if e["summary"] != "analyse Q1 numbers" {
-		t.Errorf("summary: got %v", e["summary"])
-	}
-	if e["status"] != "in_progress" {
-		t.Errorf("status: got %v", e["status"])
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromActivityLogs_DelegateResultWithError(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	now := time.Now()
-	rows := sqlmock.NewRows([]string{
-		"id", "activity_type", "source_id", "target_id",
-		"summary", "status", "error_detail",
-		"response_preview", "delegation_id", "created_at",
-	}).AddRow(
-		"act-2", "delegate_result",
-		"ws-1", "ws-2",
-		"result summary",
-		"failed",
-		"Callee workspace not reachable",
-		`{"text":"the result body text"}`,
-		"del-abc",
-		now,
-	)
-	mock.ExpectQuery("SELECT .+ FROM activity_logs").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromActivityLogs(context.Background(), "ws-1")
-	if len(got) != 1 {
-		t.Fatalf("expected 1 entry, got %d", len(got))
-	}
-	e := got[0]
-	if e["type"] != "delegate_result" {
-		t.Errorf("type: got %v", e["type"])
-	}
-	if e["error"] != "Callee workspace not reachable" {
-		t.Errorf("error: got %v", e["error"])
-	}
-	if e["response_preview"] != `{"text":"the result body text"}` {
-		t.Errorf("response_preview: got %v", e["response_preview"])
-	}
-	if e["delegation_id"] != "del-abc" {
-		t.Errorf("delegation_id: got %v", e["delegation_id"])
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromActivityLogs_QueryError(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	mock.ExpectQuery("SELECT .+ FROM activity_logs").
-		WithArgs("ws-1").
-		WillReturnError(context.DeadlineExceeded)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromActivityLogs(context.Background(), "ws-1")
-	// Error → returns empty slice, not nil.
-	if len(got) != 0 {
-		t.Errorf("query error: expected empty slice, got %v", got)
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}
-
-func TestListDelegationsFromActivityLogs_RowsErr(t *testing.T) {
-	mockDB, mock, err := sqlmock.New()
-	if err != nil {
-		t.Fatalf("failed to create sqlmock: %v", err)
-	}
-	prevDB := db.DB
-	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
-
-	now := time.Now()
-	// RowError(0) before AddRow(0): row 0 is "bad", rows.Next() returns false
-	// on first call — the row never scans, result stays nil. To get partial
-	// results (row 0 scanned) with rows.Err() non-nil, we use 2 rows and put
-	// RowError(1) after AddRow(1): row 0 scans normally, row 1 is bad,
-	// rows.Err() is error, handler returns partial result.
-	rows := sqlmock.NewRows([]string{
-		"id", "activity_type", "source_id", "target_id",
-		"summary", "status", "error_detail",
-		"response_preview", "delegation_id", "created_at",
-	}).
-		AddRow("act-1", "delegate", "ws-1", "ws-2", "task", "queued", "", "", "", now).
-		AddRow("act-2", "delegate", "ws-1", "ws-3", "another task", "queued", "", "", "", now).
-		RowError(1, context.DeadlineExceeded)
-	mock.ExpectQuery("SELECT .+ FROM activity_logs").
-		WithArgs("ws-1").
-		WillReturnRows(rows)
-
-	broadcaster := newTestBroadcaster()
-	wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
-	dh := NewDelegationHandler(wh, broadcaster)
-
-	got := dh.listDelegationsFromActivityLogs(context.Background(), "ws-1")
-	// Row 0 scanned and appended; row 1 is bad; rows.Err() is non-nil.
-	// Handler logs the error but returns result (partial results because result != nil).
-	if got == nil || len(got) != 1 {
-		t.Errorf("rows.Err path: expected 1 partial result, got %v", got)
-	}
-	if err := mock.ExpectationsWereMet(); err != nil {
-		t.Errorf("sqlmock expectations: %v", err)
-	}
-}

workspace-server/internal/handlers/delegation_test.go

@@ -133,9 +133,9 @@ func TestDelegate_Success(t *testing.T) {
 	targetID := "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
 
 	// Expect INSERT into activity_logs for delegation tracking
-	// (6th arg is response_body, 7th is idempotency_key — nil here since the request omits it)
+	// (6th arg is idempotency_key — nil here since the request omits it)
 	mock.ExpectExec("INSERT INTO activity_logs").
-		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), sqlmock.AnyArg(), nil).
+		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), nil).
 		WillReturnResult(sqlmock.NewResult(0, 1))
 
 	// Expect RecordAndBroadcast INSERT into structure_events
@@ -189,9 +189,9 @@ func TestDelegate_DBInsertFails_Still202WithWarning(t *testing.T) {
 
 	targetID := "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
 
-	// DB insert fails (6th arg = response_body, 7th = idempotency_key, nil for this test)
+	// DB insert fails (6th arg = idempotency_key, nil for this test)
 	mock.ExpectExec("INSERT INTO activity_logs").
-		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), sqlmock.AnyArg(), nil).
+		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), nil).
 		WillReturnError(fmt.Errorf("database connection lost"))
 
 	// RecordAndBroadcast still fires
@@ -282,7 +282,6 @@ func TestListDelegations_WithResults(t *testing.T) {
 	dh := NewDelegationHandler(wh, broadcaster)
 
 	now := time.Now()
-	deadline := now.Add(6 * time.Hour)
 	// Ledger query returns rows — no fallback to activity_logs
 	rows := sqlmock.NewRows([]string{
 		"delegation_id", "caller_id", "callee_id", "task_preview",
@@ -291,10 +290,10 @@ func TestListDelegations_WithResults(t *testing.T) {
 	}).
 		AddRow("del-111", "ws-source", "ws-target",
 			"Delegating to ws-target", "pending", "", "",
-			&now, &deadline, now, now).
+			&now, &now.Add(6*time.Hour), now, now).
 		AddRow("del-222", "ws-source", "ws-target",
 			"Delegation completed (hello world)", "completed", "hello world", "",
-			&now, &deadline, now, now.Add(time.Minute))
+			&now, &now.Add(6*time.Hour), now, now.Add(time.Minute))
 
 	mock.ExpectQuery("SELECT d.delegation_id, d.caller_id, d.callee_id, d.task_preview").
 		WithArgs("ws-source").
@@ -491,7 +490,6 @@ func TestDelegationRecord_InsertsActivityLogRow(t *testing.T) {
 			"550e8400-e29b-41d4-a716-446655440001",               // target_id
 			"Delegating to 550e8400-e29b-41d4-a716-446655440001", // summary
 			sqlmock.AnyArg(), // request_body (jsonb)
-			sqlmock.AnyArg(), // response_body (jsonb) — mc#984 fix
 		).
 		WillReturnResult(sqlmock.NewResult(0, 1))
 	// RecordAndBroadcast INSERT for DELEGATION_SENT
@@ -700,9 +698,9 @@ func TestDelegate_IdempotentFailedRowIsReleasedAndReplaced(t *testing.T) {
 	mock.ExpectExec("DELETE FROM activity_logs").
 		WithArgs("ws-source", "retry-key").
 		WillReturnResult(sqlmock.NewResult(0, 1))
-	// Fresh insert with the same idempotency key (response_body added as mc#984 fix).
+	// Fresh insert with the same idempotency key.
 	mock.ExpectExec("INSERT INTO activity_logs").
-		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), sqlmock.AnyArg(), "retry-key").
+		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), "retry-key").
 		WillReturnResult(sqlmock.NewResult(0, 1))
 	mock.ExpectExec("INSERT INTO structure_events").
 		WillReturnResult(sqlmock.NewResult(0, 1))
@@ -746,9 +744,9 @@ func TestDelegate_IdempotentRaceUniqueViolationReturnsExisting(t *testing.T) {
 	mock.ExpectQuery("SELECT request_body->>'delegation_id', status, target_id").
 		WithArgs("ws-source", "race-key").
 		WillReturnError(fmt.Errorf("sql: no rows in result set"))
-	// Insert loses the race against a concurrent caller (response_body added as mc#984 fix).
+	// Insert loses the race against a concurrent caller.
 	mock.ExpectExec("INSERT INTO activity_logs").
-		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), sqlmock.AnyArg(), "race-key").
+		WithArgs("ws-source", "ws-source", targetID, "Delegating to "+targetID, sqlmock.AnyArg(), "race-key").
 		WillReturnError(fmt.Errorf("pq: duplicate key value violates unique constraint \"activity_logs_idempotency_uniq\""))
 	// Re-query returns the winner.
 	mock.ExpectQuery("SELECT request_body->>'delegation_id', status").
@@ -1362,7 +1360,6 @@ func TestExtractResponseText_EmptyText(t *testing.T) {
 	got := extractResponseText(body)
 	if got != "" {
 		t.Errorf("empty text: got %q, want %q", got, "")
-	}
 }
 
 // ---------- ListDelegations: ledger has rows → returns them (no activity_logs fallback) ----------
@@ -1375,7 +1372,6 @@ func TestListDelegations_LedgerRowsReturned(t *testing.T) {
 	dh := NewDelegationHandler(wh, broadcaster)
 
 	now := time.Now()
-	deadline := now.Add(6 * time.Hour)
 	// Ledger query returns rows
 	ledgerRows := sqlmock.NewRows([]string{
 		"delegation_id", "caller_id", "callee_id", "task_preview",
@@ -1384,7 +1380,7 @@ func TestListDelegations_LedgerRowsReturned(t *testing.T) {
 	}).AddRow(
 		"del-ledger-001", "caller-uuid", "callee-uuid",
 		"Analyze the codebase for bugs", "in_progress", "", "",
-		&now, &deadline, now, now,
+		&now, &now.Add(6*time.Hour), now, now,
 	)
 	mock.ExpectQuery("SELECT d.delegation_id, d.caller_id, d.callee_id, d.task_preview").
 		WithArgs("caller-uuid").
@@ -1595,7 +1591,6 @@ func TestListDelegations_LedgerCompletedIncludesResultPreview(t *testing.T) {
 	dh := NewDelegationHandler(wh, broadcaster)
 
 	now := time.Now()
-	deadline := now.Add(6 * time.Hour)
 	ledgerRows := sqlmock.NewRows([]string{
 		"delegation_id", "caller_id", "callee_id", "task_preview",
 		"status", "result_preview", "error_detail", "last_heartbeat",
@@ -1603,7 +1598,7 @@ func TestListDelegations_LedgerCompletedIncludesResultPreview(t *testing.T) {
 	}).AddRow(
 		"del-complete-001", "caller-uuid", "callee-uuid",
 		"Run analysis", "completed", "Analysis complete: 42 issues found", "",
-		&now, &deadline, now, now,
+		&now, &now.Add(6*time.Hour), now, now,
 	)
 	mock.ExpectQuery("SELECT d.delegation_id, d.caller_id, d.callee_id, d.task_preview").
 		WithArgs("caller-uuid").
@@ -1650,7 +1645,6 @@ func TestListDelegations_LedgerFailedIncludesErrorDetail(t *testing.T) {
 	dh := NewDelegationHandler(wh, broadcaster)
 
 	now := time.Now()
-	deadline := now.Add(6 * time.Hour)
 	ledgerRows := sqlmock.NewRows([]string{
 		"delegation_id", "caller_id", "callee_id", "task_preview",
 		"status", "result_preview", "error_detail", "last_heartbeat",
@@ -1658,7 +1652,7 @@ func TestListDelegations_LedgerFailedIncludesErrorDetail(t *testing.T) {
 	}).AddRow(
 		"del-failed-001", "caller-uuid", "callee-uuid",
 		"Fetch data", "failed", "", "Callee workspace not reachable",
-		&now, &deadline, now, now,
+		&now, &now.Add(6*time.Hour), now, now,
 	)
 	mock.ExpectQuery("SELECT d.delegation_id, d.caller_id, d.callee_id, d.task_preview").
 		WithArgs("caller-uuid").

workspace-server/internal/handlers/discovery_filter_test.go

@@ -1,160 +0,0 @@
-package handlers
-
-import (
-	"testing"
-)
-
-// filterPeersByQuery tests — nil-safe role/name filtering for peer discovery.
-
-func TestFilterPeersByQuery_EmptyQueryNoOp(t *testing.T) {
-	peers := []map[string]interface{}{
-		{"name": "foo", "role": "bar"},
-		{"name": "baz", "role": "qux"},
-	}
-	result := filterPeersByQuery(peers, "")
-	if len(result) != 2 {
-		t.Errorf("empty query: expected 2, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_WhitespaceQueryNoOp(t *testing.T) {
-	peers := []map[string]interface{}{
-		{"name": "foo", "role": "bar"},
-	}
-	result := filterPeersByQuery(peers, "   ")
-	if len(result) != 1 {
-		t.Errorf("whitespace-only query: expected 1, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_MatchName(t *testing.T) {
-	peers := []map[string]interface{}{
-		{"name": "backend-agent", "role": "sre"},
-		{"name": "frontend-agent", "role": "ui"},
-	}
-	result := filterPeersByQuery(peers, "backend")
-	if len(result) != 1 || result[0]["name"] != "backend-agent" {
-		t.Errorf("expected backend-agent, got %v", result)
-	}
-}
-
-func TestFilterPeersByQuery_MatchRole(t *testing.T) {
-	peers := []map[string]interface{}{
-		{"name": "agent-alpha", "role": "security engineer"},
-		{"name": "agent-beta", "role": "devops"},
-	}
-	result := filterPeersByQuery(peers, "engineer")
-	if len(result) != 1 || result[0]["name"] != "agent-alpha" {
-		t.Errorf("expected agent-alpha, got %v", result)
-	}
-}
-
-func TestFilterPeersByQuery_CaseInsensitive(t *testing.T) {
-	peers := []map[string]interface{}{
-		{"name": "AgentX", "role": "SRE"},
-	}
-	result := filterPeersByQuery(peers, "AGENTx")
-	if len(result) != 1 {
-		t.Errorf("expected 1 match (case-insensitive), got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_NilRoleNoPanic(t *testing.T) {
-	// This is the regression case for #730: queryPeerMaps explicitly sets
-	// peer["role"] = nil when the DB role is empty string. Before the fix,
-	// p["role"].(string) panics on nil. After the fix, it returns "" and
-	// no match occurs — which is the correct behaviour.
-	defer func() {
-		if r := recover(); r != nil {
-			t.Errorf("filterPeersByQuery panicked on nil role: %v", r)
-		}
-	}()
-	peers := []map[string]interface{}{
-		{"name": "some-agent", "role": nil},
-	}
-	result := filterPeersByQuery(peers, "some-agent")
-	if len(result) != 1 {
-		t.Errorf("expected 1 match by name, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_NilRoleQueryNoMatch(t *testing.T) {
-	// When role is nil and query does not match name, nothing matches.
-	defer func() {
-		if r := recover(); r != nil {
-			t.Errorf("filterPeersByQuery panicked on nil role: %v", r)
-		}
-	}()
-	peers := []map[string]interface{}{
-		{"name": "agent-alpha", "role": nil},
-	}
-	result := filterPeersByQuery(peers, "no-match")
-	if len(result) != 0 {
-		t.Errorf("expected 0 matches, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_NilNameNoPanic(t *testing.T) {
-	// Defensive check: name could also theoretically be nil.
-	defer func() {
-		if r := recover(); r != nil {
-			t.Errorf("filterPeersByQuery panicked on nil name: %v", r)
-		}
-	}()
-	peers := []map[string]interface{}{
-		{"name": nil, "role": "sre"},
-	}
-	result := filterPeersByQuery(peers, "sre")
-	if len(result) != 1 {
-		t.Errorf("expected 1 match by role, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_BothNilNoPanic(t *testing.T) {
-	defer func() {
-		if r := recover(); r != nil {
-			t.Errorf("filterPeersByQuery panicked on nil name+role: %v", r)
-		}
-	}()
-	peers := []map[string]interface{}{
-		{"name": nil, "role": nil},
-	}
-	result := filterPeersByQuery(peers, "")
-	if len(result) != 1 {
-		t.Errorf("empty query with nil name/role: expected 1, got %d", len(result))
-	}
-	result = filterPeersByQuery(peers, "anything")
-	if len(result) != 0 {
-		t.Errorf("non-empty query with nil name/role: expected 0, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_NoMatches(t *testing.T) {
-	peers := []map[string]interface{}{
-		{"name": "alpha", "role": "beta"},
-		{"name": "gamma", "role": "delta"},
-	}
-	result := filterPeersByQuery(peers, "zzz")
-	if len(result) != 0 {
-		t.Errorf("expected 0, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_EmptyPeers(t *testing.T) {
-	result := filterPeersByQuery([]map[string]interface{}{}, "query")
-	if len(result) != 0 {
-		t.Errorf("empty peers: expected 0, got %d", len(result))
-	}
-}
-
-func TestFilterPeersByQuery_MultipleMatches(t *testing.T) {
-	peers := []map[string]interface{}{
-		{"name": "backend-alpha", "role": "eng"},
-		{"name": "backend-beta", "role": "eng"},
-		{"name": "frontend", "role": "ui"},
-	}
-	result := filterPeersByQuery(peers, "backend")
-	if len(result) != 2 {
-		t.Errorf("expected 2 backend matches, got %d", len(result))
-	}
-}

workspace-server/internal/handlers/handlers_test.go

@@ -29,20 +29,14 @@ func init() {
 // setupTestDB creates a sqlmock DB and assigns it to the global db.DB.
 // It also disables the SSRF URL check so that httptest.NewServer loopback
 // URLs and fake hostnames (*.example) used in tests don't trigger rejections.
-//
-// IMPORTANT: db.DB is saved before assignment and restored via t.Cleanup so
-// that tests running after this one are not polluted by a closed mock.
-// This is the single root cause of the systemic CI/Platform (Go) failures on
-// main HEAD 8026f020 (mc#975).
 func setupTestDB(t *testing.T) sqlmock.Sqlmock {
 	t.Helper()
 	mockDB, mock, err := sqlmock.New()
 	if err != nil {
 		t.Fatalf("failed to create sqlmock: %v", err)
 	}
-	prevDB := db.DB
 	db.DB = mockDB
-	t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
+	t.Cleanup(func() { mockDB.Close() })
 
 	// Disable SSRF checks for the duration of this test only. Restore
 	// the previous state via t.Cleanup so that TestIsSafeURL_* tests
@@ -62,11 +56,6 @@ func setupTestDB(t *testing.T) sqlmock.Sqlmock {
 	return mock
 }
 
-func waitForHandlerAsyncBeforeDBCleanup(t *testing.T, h *WorkspaceHandler) {
-	t.Helper()
-	t.Cleanup(h.waitAsyncForTest)
-}
-
 // setupTestRedis creates a miniredis instance and assigns it to the global db.RDB.
 func setupTestRedis(t *testing.T) *miniredis.Miniredis {
 	t.Helper()
@@ -366,11 +355,6 @@ func TestWorkspaceCreate(t *testing.T) {
 }
 
 func TestBuildProvisionerConfig_IncludesAwarenessSettings(t *testing.T) {
-	mock := setupTestDB(t)
-	mock.ExpectQuery(`SELECT digest FROM runtime_image_pins`).
-		WithArgs("claude-code").
-		WillReturnError(sql.ErrNoRows)
-
 	broadcaster := newTestBroadcaster()
 	handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", "/tmp/configs")
 
@@ -382,7 +366,7 @@ func TestBuildProvisionerConfig_IncludesAwarenessSettings(t *testing.T) {
 		"ws-123",
 		"/tmp/configs/template",
 		map[string][]byte{"config.yaml": []byte("name: test")},
-		models.CreateWorkspacePayload{Tier: 2, Runtime: "claude-code", WorkspaceDir: "/tmp/workspace", WorkspaceAccess: "read_write"},
+		models.CreateWorkspacePayload{Tier: 2, Runtime: "claude-code"},
 		map[string]string{"OPENAI_API_KEY": "sk-test"},
 		"/tmp/plugins",
 		"workspace:ws-123",