Compare commits

..

2 Commits

Author SHA1 Message Date
core-devops 7dada8a373 fix(queue): skip PRs with HTTP 403/404/405 merge errors instead of looping
The queue was retrying the same PR forever when merge returned HTTP 405
("User not allowed to merge PR"). This happened because ApiError was
caught by main() and returned 0, so the next tick tried the same PR again.

Changes:
- Add MergePermissionError(ApiError) for permanent merge failures (403/404/405)
- merge_pull() catches ApiError and re-raises MergePermissionError for
  these specific codes
- process_once() catches MergePermissionError, posts a comment on the PR
  explaining the permission issue, and returns 0 (moves to next tick)

The PR stays in the merge-queue label so future ticks can retry after
the permission issue is resolved (e.g., org owner grants Can-merge).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-17 13:53:58 +00:00
core-devops ea98e889e2 fix(ci): add secrets:read to sop-checklist and sop-tier-check workflows
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, l
sop-checklist / na-declarations (pull_request) N/A: (none)
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 2s
CI / Detect changes (pull_request) Successful in 4s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 10s
E2E API Smoke Test / detect-changes (pull_request) Successful in 7s
E2E Chat / detect-changes (pull_request) Successful in 7s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 5s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 7s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 3s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Successful in 1m12s
CI / Platform (Go) (pull_request) Successful in 4m34s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Successful in 53s
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 1m8s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 5s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 59s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 2s
gate-check-v3 / gate-check (pull_request) Successful in 3s
qa-review / approved (pull_request) Failing after 2s
security-review / approved (pull_request) Failing after 3s
sop-tier-check / tier-check (pull_request) Successful in 3s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 1m9s
CI / Canvas (Next.js) (pull_request) Successful in 6m9s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 1s
E2E Chat / E2E Chat (pull_request) Successful in 1s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 1s
CI / Python Lint & Test (pull_request) Successful in 6m30s
CI / all-required (pull_request) Successful in 5m37s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 1s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
These workflows use {{ secrets.SOP_TIER_CHECK_TOKEN }} and
{{ secrets.SOP_CHECKLIST_GATE_TOKEN }} in their env, but are missing
`secrets: read` in their workflow-level permissions block. Without it,
Gitea Actions cannot substitute the secret value — the env var is
empty/undefined → every API call returns 401 → the job exits 1.

The missing permission is currently causing sop-checklist to FAIL on
all PRs, which blocks the entire merge queue (14 PRs stuck).

This completes the fix from PR #1411 (which fixed qa-review.yml and
security-review.yml but missed these two sop-* workflows).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-17 13:16:15 +00:00
77 changed files with 189 additions and 3780 deletions
+19 -50
View File
@@ -153,38 +153,15 @@ def latest_statuses_by_context(statuses: list[dict]) -> dict[str, dict]:
return latest
def _is_tier_low_pending_ok(
latest_statuses: dict[str, dict],
context: str,
pr_labels: set[str],
) -> bool:
"""Return True if tier:low PR can tolerate sop-checklist pending state.
Per sop-checklist-config.yaml tier_failure_mode, tier:low uses soft-fail:
sop-checklist posts state=pending when acks are satisfied (missing
manager/ceo acks are informational only). The queue should accept
pending instead of waiting for success.
"""
if "tier:low" not in pr_labels:
return False
if "sop-checklist" not in context:
return False
status = latest_statuses.get(context) or {}
return status_state(status) == "pending"
def required_contexts_green(
latest_statuses: dict[str, dict],
contexts: list[str],
pr_labels: set[str] | None = None,
) -> tuple[bool, list[str]]:
missing_or_bad: list[str] = []
for context in contexts:
status = latest_statuses.get(context)
state = status_state(status or {})
if state != "success":
if pr_labels and _is_tier_low_pending_ok(latest_statuses, context, pr_labels):
continue # tier:low soft-fail: accept pending sop-checklist
missing_or_bad.append(f"{context}={state or 'missing'}")
return not missing_or_bad, missing_or_bad
@@ -237,7 +214,6 @@ def evaluate_merge_readiness(
pr_status: dict,
required_contexts: list[str],
pr_has_current_base: bool,
pr_labels: set[str] | None = None,
) -> MergeDecision:
# Check push-required contexts explicitly instead of combined state.
# Combined state can be "failure" due to non-blocking jobs
@@ -257,7 +233,7 @@ def evaluate_merge_readiness(
# The required_contexts list is the authoritative gate — it includes only
# the checks that actually block merges.
latest = latest_statuses_by_context(pr_status.get("statuses") or [])
ok, missing_or_bad = required_contexts_green(latest, required_contexts, pr_labels)
ok, missing_or_bad = required_contexts_green(latest, required_contexts)
if not ok:
return MergeDecision(False, "wait", "required contexts not green: " + ", ".join(missing_or_bad))
return MergeDecision(True, "merge", "ready")
@@ -282,32 +258,27 @@ def get_combined_status(sha: str) -> dict:
_, combined = api("GET", f"/repos/{OWNER}/{NAME}/commits/{sha}/status")
if not isinstance(combined, dict):
raise ApiError(f"status for {sha} response not object")
combined_statuses: list[dict] = combined.get("statuses") or []
# 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_raw = api(
_, all_statuses = api(
"GET",
f"/repos/{OWNER}/{NAME}/commits/{sha}/statuses",
query={"limit": "50"},
)
if isinstance(all_statuses_raw, list):
all_statuses: list[dict] = list(all_statuses_raw)
else:
all_statuses = []
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")
all_statuses = []
# Build latest per context: process combined (ascending→reverse=newest
# first), then fill gaps from all_statuses (already newest-first).
latest: dict[str, dict] = {}
for status in reversed(sorted(combined_statuses, key=lambda s: s.get("id") or 0)):
ctx = status.get("context")
if isinstance(ctx, str) and ctx not in latest:
latest[ctx] = status
for status in all_statuses:
ctx = status.get("context")
if isinstance(ctx, str) and ctx not in latest:
latest[ctx] = status
combined["statuses"] = list(latest.values())
# Fall back to the statuses[] already in the combined response.
pass
return combined
@@ -423,13 +394,11 @@ def process_once(*, dry_run: bool = False) -> int:
commits = get_pull_commits(pr_number)
current_base = pr_has_current_base(pr, commits, main_sha)
pr_status = get_combined_status(head_sha)
pr_labels = label_names(pr)
decision = evaluate_merge_readiness(
main_status=main_status,
pr_status=pr_status,
required_contexts=contexts,
pr_has_current_base=current_base,
pr_labels=pr_labels,
)
print(f"::notice::PR #{pr_number} decision={decision.action}: {decision.reason}")
@@ -463,10 +432,10 @@ def process_once(*, dry_run: bool = False) -> int:
post_comment(
pr_number,
(
"merge-queue: merge failed with HTTP 405 'User not allowed to merge PR'. "
"No available token has Can-merge permission on this repo. "
"Fix: grant Can-merge to a token, or add a maintain/admin collaborator. "
"Skipping to next queued PR on next tick."
f"merge-queue: merge failed with HTTP 405 'User not allowed to merge PR'. "
f"No available token has Can-merge permission on this repo. "
f"Fix: grant Can-merge to a token, or add a maintain/admin collaborator. "
f"Skipping to next queued PR — this PR will be retried on the next queue tick."
),
dry_run=dry_run,
)
-23
View File
@@ -206,29 +206,6 @@ CANDIDATES=$(jq -r --arg author "$PR_AUTHOR" --arg head "$PR_HEAD_SHA" "$JQ_FILT
debug "candidate non-author approvers: $(echo "$CANDIDATES" | tr '\n' ' ')"
if [ -z "$CANDIDATES" ]; then
# --- Guardrail (internal#503): explain the most common false
# "no candidates" red. Gitea's review event enum is EXACTLY
# APPROVED/REQUEST_CHANGES/COMMENT/PENDING. A wrong value ("APPROVE",
# lowercase, ...) is silently accepted (HTTP 200) and stored as
# state=PENDING. A correctly-started draft review has an EMPTY body;
# a NON-empty body + state==PENDING by a non-author == an intended
# verdict mis-filed by a wrong event string. Surface it actionably.
# This does NOT change the gate result (still fail-closed below) — it
# only converts a mystery red into a named, self-fixing error.
MISFILED_FILTER='.[]
| select(.state == "PENDING")
| select(.dismissed != true)
| select(.user.login != $author)
| select(((.body // "") | gsub("^\\s+|\\s+$";"") | length) > 0)
| "\(.id)\t\(.user.login)"'
MISFILED=$(jq -r --arg author "$PR_AUTHOR" "$MISFILED_FILTER" "$REVIEWS_JSON" 2>/dev/null || true)
if [ -n "$MISFILED" ]; then
echo "::error::${TEAM}-review: non-author review(s) were SUBMITTED but stored as PENDING — almost certainly the wrong Gitea review event string (internal#503)."
echo "::error::Gitea accepts ONLY the exact enum APPROVED / REQUEST_CHANGES / COMMENT. 'APPROVE' or lowercase is silently (HTTP 200) filed as PENDING and is invisible to this gate."
printf '%s\n' "$MISFILED" | while IFS="$(printf '\t')" read -r _rid _rl; do
[ -n "${_rid:-}" ] && echo "::error:: review id=${_rid} by '${_rl}': RE-SUBMIT via POST ${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}/reviews with {\"event\":\"APPROVED\"} (correct enum) — do NOT edit the DB."
done
fi
echo "::error::${TEAM}-review awaiting non-author APPROVE from ${TEAM} team (no candidates yet)"
exit 1
fi
+5 -7
View File
@@ -538,13 +538,11 @@ jobs:
all-required:
# Aggregator sentinel — RFC internal#219 §2 (Phase 4 — closes internal#286).
#
# Emits `CI / all-required (<event>)` where <event> is the workflow trigger
# (e.g. `CI / all-required (pull_request)`, `CI / all-required (push)`).
# Branch protection MUST be updated to require the event-suffixed name —
# requiring `CI / all-required` (bare, no suffix) silently blocks all merges
# because Gitea treats absent status contexts as pending (not skipped), and
# no workflow emits the bare name. Fixed: BP now requires
# `CI / all-required (pull_request)` per issue #1473.
# Single stable required-status name that branch protection points at;
# CI churns underneath in `needs:` without any protection edits. Mirrors
# the molecule-controlplane Phase 2a impl shipped in CP PR#112 and
# referenced by `internal#286` ("Phase 4 is a single small PR... mirrors
# CP's existing one").
#
# Closes the failure mode where status_check_contexts on molecule-core/main
# only listed `Secret scan` + `sop-tier-check` (the 2 meta-gates), so real
-4
View File
@@ -52,9 +52,5 @@ jobs:
# 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.
# NOTE: the event-suffixed context name is intentional — branch protection
# MUST require `CI / all-required (pull_request)` (with suffix), NOT the
# bare `CI / all-required`. Gitea treats absent contexts as pending, not
# skipped; requiring the bare name silently blocks all merges (issue #1473).
PUSH_REQUIRED_CONTEXTS: CI / all-required (push)
run: python3 .gitea/scripts/gitea-merge-queue.py
+4 -19
View File
@@ -104,7 +104,7 @@ jobs:
with:
python-version: "3.11"
- name: Compute next version from PyPI latest and existing tags
- name: Compute next version from PyPI latest
id: bump
run: |
set -eu
@@ -112,24 +112,9 @@ jobs:
| python -c "import sys,json; print(json.load(sys.stdin)['info']['version'])")
MAJOR=$(echo "$LATEST" | cut -d. -f1)
MINOR=$(echo "$LATEST" | cut -d. -f2)
TAG_LATEST=$(git tag --list "runtime-v${MAJOR}.${MINOR}.*" \
| sed -E 's/^runtime-v//' \
| grep -E '^[0-9]+\.[0-9]+\.[0-9]+$' \
| sort -V \
| tail -1 || true)
VERSION=$(PYPI_LATEST="$LATEST" TAG_LATEST="$TAG_LATEST" python - <<'PY'
import os
def parse(v):
return tuple(int(part) for part in v.split("."))
pypi = os.environ["PYPI_LATEST"]
tag = os.environ.get("TAG_LATEST") or pypi
base = max(parse(pypi), parse(tag))
print(f"{base[0]}.{base[1]}.{base[2] + 1}")
PY
)
echo "PyPI latest=$LATEST, latest runtime tag=${TAG_LATEST:-none} -> next=$VERSION"
PATCH=$(echo "$LATEST" | cut -d. -f3)
VERSION="${MAJOR}.${MINOR}.$((PATCH+1))"
echo "PyPI latest=$LATEST -> next=$VERSION"
if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+$'; then
echo "::error::computed version $VERSION does not match PEP 440 X.Y.Z"
exit 1
-1
View File
@@ -89,7 +89,6 @@ on:
permissions:
contents: read
pull-requests: read
secrets: read
jobs:
# bp-exempt: PR review bot signal; required merge state is enforced by CI / all-required.
-13
View File
@@ -30,11 +30,6 @@ jobs:
scan:
name: Scan diff for credential-shaped strings
runs-on: ubuntu-latest
# Hard CI gate — must complete or the PR is unmergable. 10-minute ceiling
# is generous for a diff-scan against a single SHA. If this times out, the
# runner is frozen and holding a slot — the step timeout triggers clean
# failure, releasing the runner for the next job.
timeout-minutes: 10
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
@@ -138,14 +133,6 @@ jobs:
[ -z "$f" ] && continue
[ "$f" = "$SELF_GITHUB" ] && continue
[ "$f" = "$SELF_GITEA" ] && continue
# Test-fixture exclude (internal#425): the secrets-detector's OWN
# unit-test corpus deliberately embeds credential-SHAPED example
# strings to exercise the detector. Verified 2026-05-18 synthetic
# (fabricated ghp_* fixtures, not real). Without this the scanner
# self-trips on its own fixtures and fail-closes every deploy.
# Same rationale as the SELF_* excludes above; gate NOT weakened
# (all other paths still fully scanned).
[ "$f" = "workspace-server/internal/secrets/patterns_test.go" ] && continue
if [ -n "$DIFF_RANGE" ]; then
ADDED=$(git diff --no-color --unified=0 "$BASE" "$HEAD" -- "$f" 2>/dev/null | grep -E '^\+[^+]' || true)
else
-1
View File
@@ -16,7 +16,6 @@ on:
permissions:
contents: read
pull-requests: read
secrets: read
jobs:
# bp-exempt: PR security review bot signal; required merge state is enforced by CI / all-required.
+5 -1
View File
@@ -84,8 +84,12 @@ on:
permissions:
contents: read
pull-requests: read
statuses: write
secrets: read
# NOTE: `statuses: write` is the GitHub-Actions name for POST /statuses.
# Gitea 1.22.6 may not gate on this permission key (it just checks the
# token), but listing it explicitly documents intent for the next
# platform-version upgrade.
statuses: write
jobs:
all-items-acked:
+1 -1
View File
@@ -105,7 +105,7 @@ export function EmptyState() {
{/* Template grid */}
{loading ? (
<div role="status" aria-live="polite" className="flex items-center justify-center gap-2 text-xs text-ink-mid py-4">
<div className="flex items-center justify-center gap-2 text-xs text-ink-mid py-4">
<Spinner />
Loading templates...
</div>
+2 -2
View File
@@ -459,7 +459,7 @@ function ProviderPickerModal({
)}
{entry.error && (
<div role="alert" aria-live="assertive" className="mt-1.5 text-[10px] text-bad">{entry.error}</div>
<div className="mt-1.5 text-[10px] text-bad">{entry.error}</div>
)}
</div>
))}
@@ -718,7 +718,7 @@ function AllKeysModal({
))}
{globalError && (
<div role="alert" aria-live="assertive" className="px-3 py-2 bg-red-950/40 border border-red-800/50 rounded-lg text-[11px] text-bad">
<div className="px-3 py-2 bg-red-950/40 border border-red-800/50 rounded-lg text-[11px] text-bad">
{globalError}
</div>
)}
+1 -1
View File
@@ -71,7 +71,7 @@ export function WorkspaceUsage({ workspaceId }: WorkspaceUsageProps) {
<SkeletonRow />
</>
) : error ? (
<p role="alert" aria-live="assertive" className="text-xs text-bad" data-testid="usage-error">
<p className="text-xs text-bad" data-testid="usage-error">
{error}
</p>
) : metrics ? (
@@ -11,21 +11,13 @@ import { render, screen, fireEvent, cleanup, act } from "@testing-library/react"
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { TestConnectionButton } from "../ui/TestConnectionButton";
import type { SecretGroup } from "@/types/secrets";
import { validateSecret, ApiError } from "@/lib/api/secrets";
import { validateSecret } from "@/lib/api/secrets";
// ─── Mock validateSecret ──────────────────────────────────────────────────────
// vi.mock is hoisted, so validateSecret (imported above) refers to the mocked
// namespace value once vi.mock runs. Use vi.mocked() to access it in tests.
vi.mock("@/lib/api/secrets", () => ({
validateSecret: vi.fn(),
ApiError: class ApiError extends Error {
status: number;
constructor(status: number, message: string) {
super(message);
this.name = "ApiError";
this.status = status;
}
},
}));
// SecretGroup is a string literal type: 'github' | 'anthropic' | 'openrouter' | 'custom'
@@ -110,7 +102,7 @@ describe("TestConnectionButton — state machine", () => {
expect(screen.getByText("Permission denied")).toBeTruthy();
});
it("shows a connectivity message on a genuine network exception", async () => {
it("shows generic error message on unexpected exception", async () => {
vi.mocked(validateSecret).mockRejectedValue(new Error("timeout"));
render(<TestConnectionButton provider={toGroup("anthropic")} secretValue="sk-..." />);
@@ -118,23 +110,8 @@ describe("TestConnectionButton — state machine", () => {
await act(async () => { /* flush */ });
expect(screen.getByRole("alert")).toBeTruthy();
// A real thrown network error → honest connectivity message (not a
// fabricated "service down"); see internal#492.
expect(document.body.querySelector('[role="alert"]')?.textContent).toMatch(
/could not reach the validation service/i,
);
});
it("does not claim a timeout when the validate endpoint 404s (internal#492)", async () => {
vi.mocked(validateSecret).mockRejectedValue(new ApiError(404, "Not Found"));
render(<TestConnectionButton provider={toGroup("anthropic")} secretValue="sk-..." />);
fireEvent.click(screen.getByRole("button"));
await act(async () => { /* flush */ });
const alert = document.body.querySelector('[role="alert"]')?.textContent ?? "";
expect(alert).not.toMatch(/timed out/i);
expect(alert).toMatch(/not available/i);
// The error detail is hardcoded to "Connection timed out. Service may be down."
expect(document.body.querySelector('[role="alert"]')?.textContent).toMatch(/timed out/i);
});
});
+19 -66
View File
@@ -2,11 +2,8 @@
// 04 · Chat — message thread + composer + sub-tabs.
// Wired to the same /workspaces/:id/a2a (method message/send) endpoint
// that the desktop ChatTab uses. Render parity with desktop ChatTab is
// achieved by reusing its renderers rather than forking a reduced
// mobile path: the Agent Comms sub-tab mounts the same AgentCommsPanel,
// and message attachments route through the same AttachmentPreview
// dispatch the desktop My-Chat bubble uses (#231/#232).
// that the desktop ChatTab uses, but with a slimmer surface: no
// attachments, no A2A topology overlay, no conversation tracing.
import { useEffect, useMemo, useRef, useState } from "react";
import ReactMarkdown from "react-markdown";
@@ -19,9 +16,6 @@ import {
useChatSend,
useChatSocket,
} from "@/components/tabs/chat/hooks";
import { AgentCommsPanel } from "@/components/tabs/chat/AgentCommsPanel";
import { AttachmentPreview } from "@/components/tabs/chat/AttachmentPreview";
import { downloadChatFile } from "@/components/tabs/chat/uploads";
import { toMobileAgent } from "./components";
import { MOBILE_FONT_MONO, MOBILE_FONT_SANS, usePalette } from "./palette";
@@ -310,17 +304,6 @@ export function MobileChat({
const removePendingFile = (index: number) =>
setPendingFiles((prev) => prev.filter((_, i) => i !== index));
// Route attachment downloads through the same authenticated helper
// the desktop ChatTab uses (downloadChatFile) so platform-scheme
// URIs get a real Blob with auth headers instead of about:blank.
const downloadAttachment = (att: ChatAttachment) => {
downloadChatFile(agentId, att).catch(() => {
// AttachmentPreview's own error affordance covers the in-bubble
// failure state; matches ChatTab's behaviour of not double-
// reporting a download failure.
});
};
const send = async () => {
const text = draft.trim();
if ((!text && pendingFiles.length === 0) || sending || !reachable) return;
@@ -450,19 +433,7 @@ export function MobileChat({
</div>
</div>
{/* Agent Comms — reuse the desktop AgentCommsPanel verbatim so
mobile renders the identical peer/A2A + delegation feed
(history GET + live socket events) instead of a placeholder
(#231). The panel owns its own scroll/load/error/empty
states, matching ChatTab's agent-comms tabpanel. */}
{tab === "a2a" && (
<div style={{ flex: 1, minHeight: 0, overflow: "hidden" }}>
<AgentCommsPanel workspaceId={agentId} />
</div>
)}
{/* Messages */}
{tab === "my" && (
<div
ref={scrollRef}
style={{
@@ -474,8 +445,20 @@ export function MobileChat({
gap: 8,
}}
>
{tab === "a2a" && (
<div
style={{
padding: "20px 4px",
textAlign: "center",
color: p.text3,
fontSize: 13,
}}
>
Agent Comms peer-to-peer A2A traffic surfaces in the Comms tab.
</div>
)}
{tab === "my" && historyLoading && (
<div role="status" aria-live="polite" style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
<div style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
Loading chat history
</div>
)}
@@ -510,7 +493,7 @@ export function MobileChat({
</div>
)}
{tab === "my" && !historyLoading && !historyError && messages.length === 0 && (
<div role="status" aria-live="polite" style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
<div style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
Send a message to start chatting.
</div>
)}
@@ -538,31 +521,9 @@ export function MobileChat({
overflowWrap: "anywhere",
}}
>
{m.content && (
<MarkdownBubble dark={dark} accent={p.accent}>
{m.content}
</MarkdownBubble>
)}
{m.attachments && m.attachments.length > 0 && (
<div
style={{
display: "flex",
flexWrap: "wrap",
gap: 4,
marginTop: m.content ? 6 : 0,
}}
>
{m.attachments.map((att, i) => (
<AttachmentPreview
key={`${m.id}-${i}`}
workspaceId={agentId}
attachment={att}
onDownload={downloadAttachment}
tone={mine ? "user" : "agent"}
/>
))}
</div>
)}
<MarkdownBubble dark={dark} accent={p.accent}>
{m.content}
</MarkdownBubble>
<div
style={{
fontSize: 10,
@@ -593,13 +554,7 @@ export function MobileChat({
</div>
)}
</div>
)}
{/* Footer ID + composer belong to My Chat only. The Agent Comms
tab is a read-only peer/A2A feed (parity with desktop
ChatTab, where the agent-comms tabpanel has no composer). */}
{tab === "my" && (
<>
{/* Footer ID */}
<div
style={{
@@ -791,8 +746,6 @@ export function MobileChat({
</button>
</div>
</div>
</>
)}
</div>
);
}
+2 -2
View File
@@ -251,11 +251,11 @@ export function MobileComms({ dark }: { dark: boolean }) {
<div style={{ padding: "0 14px", display: "flex", flexDirection: "column", gap: 8 }}>
{loading && items.length === 0 ? (
<div role="status" aria-live="polite" style={{ padding: "30px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
<div style={{ padding: "30px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
Loading recent comms
</div>
) : filtered.length === 0 ? (
<div role="status" aria-live="polite" style={{ padding: "30px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
<div style={{ padding: "30px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
No A2A traffic yet.
</div>
) : (
@@ -416,8 +416,6 @@ function DetailActivity({ workspaceId, dark }: { workspaceId: string; dark: bool
if (items === null) {
return (
<div
role="status"
aria-live="polite"
style={{
background: p.surface,
borderRadius: 16,
@@ -170,8 +170,6 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
<div style={{ padding: "0 14px" }}>
{loadingTemplates ? (
<div
role="status"
aria-live="polite"
style={{
padding: "24px 8px",
textAlign: "center",
@@ -21,14 +21,6 @@ import { MobileChat } from "../MobileChat";
vi.mock("@/lib/api");
import { api } from "@/lib/api";
// AgentCommsPanel (mounted by the Agent Comms sub-tab, #231) subscribes
// to the global socket via useSocketEvent. Stub it to a no-op so the
// panel mounts without the real ReconnectingSocket — the parity tests
// only assert the panel renders (vs the old static placeholder).
vi.mock("@/hooks/useSocketEvent", () => ({
useSocketEvent: vi.fn(),
}));
// ─── Mock store ───────────────────────────────────────────────────────────────
const mockAgentId = "ws-chat-test";
@@ -163,12 +155,6 @@ beforeEach(() => {
mockOnBack.mockClear();
mockStoreState.nodes = [];
mockStoreState.agentMessages = {};
// jsdom doesn't implement scrollIntoView. The Agent Comms tab now
// mounts AgentCommsPanel (#231), which scrolls its feed to bottom on
// arrival; a no-op stub keeps the panel from throwing under jsdom
// (same stub AgentCommsPanel's own render test installs).
Element.prototype.scrollIntoView =
vi.fn() as unknown as Element["scrollIntoView"];
// Set up spies on the real api methods. Tests override these per-call.
const getSpy = vi.spyOn(api, "get");
const postSpy = vi.spyOn(api, "post");
@@ -488,146 +474,3 @@ describe("MobileChat — chat history", () => {
expect(getSpy).toHaveBeenCalledTimes(2);
});
});
// ─── #232 · Attachment render parity with desktop ChatTab ────────────────────
//
// Regression for the CTO-reported mobile bug: MobileChat used to render
// only m.content (no attachment surface), so files sent/received in a
// conversation were invisible on mobile while desktop showed them. The
// fix routes m.attachments through the same AttachmentPreview the
// desktop ChatTab bubble uses.
describe("MobileChat — attachment render parity (#232)", () => {
beforeEach(() => {
mockStoreState.nodes = [onlineNode];
});
it("renders an attachment from a history message via AttachmentPreview", async () => {
const getSpy = vi.spyOn(api, "get");
// useChatHistory reads { messages, reached_end }.
getSpy.mockResolvedValueOnce({
messages: [
{
id: "m-att-1",
role: "agent",
content: "Here is the report",
attachments: [
{
name: "report.csv",
uri: "workspace://out/report.csv",
mimeType: "text/csv",
size: 2048,
},
],
timestamp: new Date().toISOString(),
},
],
reached_end: true,
});
let rr: ReturnType<typeof renderChat>;
await act(async () => {
rr = renderChat(mockAgentId);
});
const { container } = rr!;
// A non-image attachment renders the AttachmentChip download button
// with title="Download <name>" — same component the desktop bubble
// dispatches through AttachmentPreview.
await waitFor(() => {
const chip = container.querySelector('[title="Download report.csv"]');
expect(chip).toBeTruthy();
});
expect(container.textContent ?? "").toContain("report.csv");
});
});
// ─── #231 · Agent Comms (A2A/peer) render parity with desktop ChatTab ────────
//
// Regression for the CTO-reported mobile bug: the Agent Comms sub-tab
// rendered a static placeholder string ("peer-to-peer A2A traffic
// surfaces in the Comms tab") instead of the real feed. The fix mounts
// the same AgentCommsPanel the desktop ChatTab agent-comms tabpanel
// uses, so peer/A2A + delegation activity is visible on mobile.
describe("MobileChat — Agent Comms render parity (#231)", () => {
beforeEach(() => {
mockStoreState.nodes = [onlineNode];
});
it("mounts AgentCommsPanel on the Agent Comms tab (not the old placeholder)", async () => {
const getSpy = vi.spyOn(api, "get");
// 1st GET: useChatHistory (My Chat) on mount.
getSpy.mockResolvedValueOnce({ messages: [], reached_end: true });
// 2nd GET: AgentCommsPanel's activity load when the tab is shown.
// Empty list → panel renders its own empty state, which still
// proves AgentCommsPanel mounted (vs. the removed placeholder).
getSpy.mockResolvedValueOnce([]);
let rr: ReturnType<typeof renderChat>;
await act(async () => {
rr = renderChat(mockAgentId);
});
const { container } = rr!;
const commsTab = Array.from(container.querySelectorAll("button")).find(
(b) => b.textContent?.trim() === "Agent Comms",
);
expect(commsTab).toBeTruthy();
await act(async () => {
commsTab!.click();
});
await waitFor(() => {
const text = container.textContent ?? "";
// The panel's empty state — proves AgentCommsPanel mounted.
expect(text).toContain("No agent-to-agent communications yet.");
});
// The old hard-coded placeholder must be gone.
expect(container.textContent ?? "").not.toContain(
"peer-to-peer A2A traffic surfaces in the Comms tab",
);
// The panel hit its activity endpoint.
expect(getSpy).toHaveBeenCalledWith(
expect.stringContaining(`/workspaces/${mockAgentId}/activity`),
);
});
it("renders a peer message on the Agent Comms tab", async () => {
const getSpy = vi.spyOn(api, "get");
getSpy.mockResolvedValueOnce({ messages: [], reached_end: true });
// a2a_receive from a peer → AgentCommsPanel.toCommMessage maps it
// to an inbound bubble with the request text.
getSpy.mockResolvedValueOnce([
{
id: "act-1",
activity_type: "a2a_receive",
source_id: "peer-ws-uuid",
target_id: mockAgentId,
method: "message/send",
summary: "peer asked something",
request_body: { task: "Please review PR 42" },
response_body: null,
status: "ok",
created_at: new Date().toISOString(),
},
]);
let rr: ReturnType<typeof renderChat>;
await act(async () => {
rr = renderChat(mockAgentId);
});
const { container } = rr!;
const commsTab = Array.from(container.querySelectorAll("button")).find(
(b) => b.textContent?.trim() === "Agent Comms",
);
await act(async () => {
commsTab!.click();
});
await waitFor(() => {
expect(container.textContent ?? "").toContain("Please review PR 42");
});
});
});
@@ -160,14 +160,14 @@ export function OrgTokensTab() {
</code>
<button
onClick={handleCopy}
className="shrink-0 px-2 py-1.5 bg-emerald-800/40 hover:bg-emerald-700/50 border border-emerald-700/40 rounded text-[10px] text-good transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
className="shrink-0 px-2 py-1.5 bg-emerald-800/40 hover:bg-emerald-700/50 border border-emerald-700/40 rounded text-[10px] text-good transition-colors"
>
{copied ? 'Copied' : 'Copy'}
</button>
</div>
<button
onClick={() => setNewToken(null)}
className="text-[9px] text-good/60 hover:text-good transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
className="text-[9px] text-good/60 hover:text-good transition-colors"
>
Dismiss
</button>
@@ -219,7 +219,7 @@ export function OrgTokensTab() {
</div>
<button
onClick={() => setRevokeTarget(t)}
className="text-[10px] text-bad/70 hover:text-bad transition-colors px-2 py-1 shrink-0 focus:outline-none focus-visible:ring-2 focus-visible:ring-red-400 focus-visible:ring-offset-1"
className="text-[10px] text-bad/70 hover:text-bad transition-colors px-2 py-1 shrink-0"
>
Revoke
</button>
+23 -19
View File
@@ -3,24 +3,16 @@ import { useState, useCallback, useRef, useEffect } from 'react';
import type { Secret, SecretGroup } from '@/types/secrets';
import { useSecretsStore } from '@/stores/secrets-store';
import { StatusBadge } from '@/components/ui/StatusBadge';
import { RevealToggle } from '@/components/ui/RevealToggle';
import { KeyValueField } from '@/components/ui/KeyValueField';
import { ValidationHint } from '@/components/ui/ValidationHint';
import { TestConnectionButton } from '@/components/ui/TestConnectionButton';
import { validateSecretValue } from '@/lib/validation/secret-formats';
import { SERVICES } from '@/lib/services';
const AUTO_HIDE_MS = 30_000;
const VALIDATION_DEBOUNCE_MS = 400;
// Secret values are write-only from the browser: the server List endpoint
// "Never exposes values", there is no per-secret decrypt route, and the
// only decrypted path (GET /secrets/values) is bulk + token-gated for
// remote agents. The old eye/RevealToggle was a dead affordance — it
// flipped its own icon but could never reveal anything, which read as
// "this doesn't work" (esp. once clicked → eye-with-slash). We show an
// honest static indicator instead; rotation is via Edit.
const WRITE_ONLY_TITLE =
'Value is write-only and cannot be revealed — use Edit to replace/rotate it';
interface SecretRowProps {
secret: Secret;
workspaceId: string;
@@ -39,12 +31,28 @@ export function SecretRow({ secret, workspaceId }: SecretRowProps) {
const setSecretStatus = useSecretsStore((s) => s.setSecretStatus);
const isEditing = editingKey === secret.name;
const [revealed, setRevealed] = useState(false);
const [editValue, setEditValue] = useState('');
const [validationError, setValidationError] = useState<string | null>(null);
const [isSaving, setIsSaving] = useState(false);
const [saveError, setSaveError] = useState<string | null>(null);
const debounceRef = useRef<ReturnType<typeof setTimeout>>(undefined);
const editBtnRef = useRef<HTMLButtonElement>(null);
const revealTimerRef = useRef<ReturnType<typeof setTimeout>>(undefined);
// Auto-hide revealed value after 30s
useEffect(() => {
if (revealed) {
clearTimeout(revealTimerRef.current);
revealTimerRef.current = setTimeout(() => setRevealed(false), AUTO_HIDE_MS);
return () => clearTimeout(revealTimerRef.current);
}
}, [revealed]);
// Reset revealed state when panel closes (session-only)
useEffect(() => {
return () => setRevealed(false);
}, []);
// Debounced validation
useEffect(() => {
@@ -125,15 +133,11 @@ export function SecretRow({ secret, workspaceId }: SecretRowProps) {
{secret.masked_value}
</span>
<div className="secret-row__actions">
<span
data-testid="write-only-indicator"
className="secret-row__write-only"
role="img"
aria-label={`${secret.name} value is write-only and cannot be revealed; use Edit to replace it`}
title={WRITE_ONLY_TITLE}
>
🔒
</span>
<RevealToggle
revealed={revealed}
onToggle={() => setRevealed((r) => !r)}
label={`Toggle reveal ${secret.name}`}
/>
<StatusBadge status={secret.status} />
<button
type="button"
+3 -36
View File
@@ -16,40 +16,7 @@ interface TokensTabProps {
workspaceId: string;
}
// The settings panel passes the literal sentinel "global" when no canvas
// node is selected. Workspace tokens are inherently per-workspace — there
// is no /workspaces/global/tokens endpoint (querying the uuid column with
// "global" 500s on Postgres). The org-wide equivalent lives in the
// separate "Org API Keys" tab. Mirrors the sentinel-awareness that
// api/secrets.ts already has (workspaceId === 'global' → /settings/secrets).
const GLOBAL_WORKSPACE_ID = 'global';
export function TokensTab({ workspaceId }: TokensTabProps) {
if (workspaceId === GLOBAL_WORKSPACE_ID) {
return (
<div className="p-4 space-y-4">
<div>
<h3 className="text-sm font-semibold text-ink">API Tokens</h3>
<p className="text-[10px] text-ink-mid mt-0.5">
Bearer tokens for authenticating API calls to this workspace.
</p>
</div>
<div className="text-center py-6">
<p className="text-xs text-ink-mid">Select a workspace node first</p>
<p className="text-[10px] text-ink-mid mt-1">
Workspace tokens are scoped to a single workspace. Select a node
on the canvas to manage its tokens, or use the{' '}
<span className="text-accent font-medium">Org API Keys</span> tab
for org-wide API keys.
</p>
</div>
</div>
);
}
return <WorkspaceTokensTab workspaceId={workspaceId} />;
}
function WorkspaceTokensTab({ workspaceId }: TokensTabProps) {
const [tokens, setTokens] = useState<Token[]>([]);
const [loading, setLoading] = useState(true);
const [creating, setCreating] = useState(false);
@@ -140,14 +107,14 @@ function WorkspaceTokensTab({ workspaceId }: TokensTabProps) {
</code>
<button
onClick={handleCopy}
className="shrink-0 px-2 py-1.5 bg-emerald-800/40 hover:bg-emerald-700/50 border border-emerald-700/40 rounded text-[10px] text-good transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
className="shrink-0 px-2 py-1.5 bg-emerald-800/40 hover:bg-emerald-700/50 border border-emerald-700/40 rounded text-[10px] text-good transition-colors"
>
{copied ? 'Copied' : 'Copy'}
</button>
</div>
<button
onClick={() => setNewToken(null)}
className="text-[9px] text-good/60 hover:text-good transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1"
className="text-[9px] text-good/60 hover:text-good transition-colors"
>
Dismiss
</button>
@@ -192,7 +159,7 @@ function WorkspaceTokensTab({ workspaceId }: TokensTabProps) {
</div>
<button
onClick={() => setRevokeTarget(t)}
className="text-[10px] text-bad/70 hover:text-bad transition-colors px-2 py-1 focus:outline-none focus-visible:ring-2 focus-visible:ring-red-400 focus-visible:ring-offset-1"
className="text-[10px] text-bad/70 hover:text-bad transition-colors px-2 py-1"
>
Revoke
</button>
@@ -138,54 +138,14 @@ describe("SecretRow — display mode", () => {
expect(document.querySelector('[role="row"]')).toBeTruthy();
});
it("has Copy, Edit, Delete buttons", () => {
it("has Reveal, Copy, Edit, Delete buttons", () => {
render(<SecretRow secret={GITHUB_SECRET} workspaceId="ws-1" />);
expect(screen.getByTestId("reveal-toggle")).toBeTruthy();
expect(screen.getByRole("button", { name: /copy/i })).toBeTruthy();
expect(screen.getByRole("button", { name: /edit/i })).toBeTruthy();
expect(screen.getByRole("button", { name: /delete/i })).toBeTruthy();
});
// Regression: the reveal/eye control was a dead affordance. Clicking it
// flipped its own icon (eye → eye-with-slash) but never revealed the value,
// because secret values are write-only from the browser (server List
// "Never exposes values"; there is no per-secret decrypt endpoint and the
// client has no plaintext-fetch function). The honest fix removes the
// toggle and shows a static "write-only / cannot be revealed" indicator.
// See internal tracking issue + internal#210/#211.
it("does NOT render a reveal/eye toggle (values are write-only)", () => {
render(<SecretRow secret={GITHUB_SECRET} workspaceId="ws-1" />);
expect(screen.queryByTestId("reveal-toggle")).toBeNull();
expect(
screen.queryByRole("button", { name: /toggle reveal/i }),
).toBeNull();
});
it("shows a write-only indicator explaining the value cannot be revealed", () => {
render(<SecretRow secret={ANTHROPIC_SECRET} workspaceId="ws-1" />);
const indicator = screen.getByTestId("write-only-indicator");
expect(indicator).toBeTruthy();
// Affordance must be honest: explain it cannot be revealed and that
// Edit is the rotate path. It must not be a clickable button.
const title = indicator.getAttribute("title") ?? "";
expect(title.toLowerCase()).toMatch(/write-only|cannot be revealed/);
expect(indicator.tagName).not.toBe("BUTTON");
});
it("write-only indicator is present for the Anthropic/OAuth-token row too", () => {
// The reported bug singled out CLAUDE_CODE_OAUTH_TOKEN (anthropic group);
// the fix is group-agnostic — every row gets the same honest affordance.
const OAUTH_SECRET = {
name: "CLAUDE_CODE_OAUTH_TOKEN",
masked_value: "••••••••••••••••9d2a",
group: "anthropic" as const,
status: "unverified" as const,
updated_at: "2024-01-04",
};
render(<SecretRow secret={OAUTH_SECRET} workspaceId="ws-1" />);
expect(screen.queryByTestId("reveal-toggle")).toBeNull();
expect(screen.getByTestId("write-only-indicator")).toBeTruthy();
});
it("shows invalid status correctly", () => {
render(<SecretRow secret={CUSTOM_SECRET} workspaceId="ws-1" />);
expect(screen.getByTestId("status-badge").getAttribute("data-status")).toBe("invalid");
@@ -302,35 +302,3 @@ describe("TokensTab — error", () => {
expect(document.querySelector('[role="status"]')).toBeNull();
});
});
// ─── "global" sentinel (no node selected) ────────────────────────────────────
//
// Regression: SettingsPanel passes the literal "global" when no canvas
// node is selected. workspace tokens are per-workspace and there is no
// /workspaces/global/tokens endpoint — calling it 500'd
// ("invalid input syntax for type uuid: global"). The tab must NOT call
// the API in that state and must point the user at the Org API Keys tab.
describe("TokensTab — global sentinel (no node selected)", () => {
beforeEach(() => {
mockApiGet.mockReset();
mockApiPost.mockReset();
mockApiGet.mockRejectedValue(new Error("should not be called"));
});
it("does not call the API and shows a pointer to Org API Keys", async () => {
render(<TokensTab workspaceId="global" />);
await flush();
expect(mockApiGet).not.toHaveBeenCalled();
expect(mockApiPost).not.toHaveBeenCalled();
expect(document.body.textContent).toContain("Select a workspace node");
expect(document.body.textContent).toContain("Org API Keys");
// No error banner, no scary 500 surfacing.
expect(document.querySelector(".text-bad")).toBeNull();
});
it("has no create button in the global state", async () => {
render(<TokensTab workspaceId="global" />);
await flush();
expect(document.body.textContent).not.toContain("New Token");
});
});
+1 -1
View File
@@ -185,7 +185,7 @@ export function ActivityTab({ workspaceId }: Props) {
{/* Activity list */}
<div className="flex-1 overflow-y-auto p-3 space-y-1.5">
{loading && activities.length === 0 && (
<div role="status" aria-live="polite" className="text-xs text-ink-mid text-center py-8">Loading activity...</div>
<div className="text-xs text-ink-mid text-center py-8">Loading activity...</div>
)}
{error && (
+1 -1
View File
@@ -262,7 +262,7 @@ export function ChannelsTab({ workspaceId }: Props) {
</div>
{error && (
<div role="alert" aria-live="assertive" className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
<div className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
{error}
</div>
)}
+2 -128
View File
@@ -81,7 +81,7 @@ function AgentCardSection({ workspaceId }: { workspaceId: string }) {
spellCheck={false} rows={12}
className="w-full bg-surface-card border border-line rounded p-2 text-[10px] font-mono text-ink focus:outline-none focus:border-accent resize-none"
/>
{error && <div role="alert" aria-live="assertive" className="px-2 py-1 bg-red-900/30 border border-red-800 rounded text-[10px] text-bad">{error}</div>}
{error && <div className="px-2 py-1 bg-red-900/30 border border-red-800 rounded text-[10px] text-bad">{error}</div>}
<div className="flex gap-2">
<button type="button" onClick={handleSave} disabled={saving}
className="px-2 py-1 bg-accent hover:bg-accent-strong text-[10px] rounded text-white disabled:opacity-50 transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent focus-visible:ring-offset-1 focus-visible:ring-offset-surface">
@@ -109,130 +109,6 @@ function AgentCardSection({ workspaceId }: { workspaceId: string }) {
);
}
// --- Agent Abilities Section ---
//
// Always-visible on/off controls for the two workspace-level ability flags
// (broadcast_enabled, talk_to_user_enabled). Both are mutated through the
// same admin endpoint the ChatTab recovery banner already uses
// (PATCH /workspaces/:id/abilities) and reflected into the canvas store node
// data (broadcastEnabled / talkToUserEnabled) so every surface that reads
// useCanvasStore.nodes stays consistent without a full re-hydrate.
//
// Before this section there was NO canvas control for either flag: the
// backend was fully wired (workspace_abilities.go / workspace_broadcast.go /
// agent_message_writer.go, see commit 29b4bffb + internal#510/#511) but the
// only frontend affordance was the ChatTab recovery banner, which renders
// solely when talk_to_user_enabled===false and so is invisible under the
// TRUE default and never existed at all for broadcast.
function AgentAbilitiesSection({ workspaceId }: { workspaceId: string }) {
// Read the live ability flags off the canvas store node — the platform
// event stream hydrates these (canvas-topology.ts maps the workspace row's
// broadcast_enabled/talk_to_user_enabled onto node data), so this stays in
// sync with the recovery banner and avoids a duplicate GET. Mirrors the
// store-read pattern used by AgentCardSection above.
const node = useCanvasStore((s) =>
s.nodes?.find?.((n) => n.id === workspaceId),
);
// Defaults match the backend column defaults + canvas-topology mapping:
// broadcast_enabled defaults FALSE, talk_to_user_enabled defaults TRUE.
const broadcastEnabled = node?.data.broadcastEnabled ?? false;
const talkToUserEnabled = node?.data.talkToUserEnabled ?? true;
// Track an in-flight PATCH per field so a double-click can't fire two
// racing writes, and surface a one-line error if the server rejects.
const [pending, setPending] = useState<null | "broadcast" | "talk">(null);
const [error, setError] = useState<string | null>(null);
const patchAbility = async (
which: "broadcast" | "talk",
body: { broadcast_enabled: boolean } | { talk_to_user_enabled: boolean },
optimistic: Partial<{ broadcastEnabled: boolean; talkToUserEnabled: boolean }>,
) => {
setError(null);
setPending(which);
// Optimistic store update — the toggle flips immediately; on failure we
// roll back to the server-truth value the store last held.
const prev = {
broadcastEnabled,
talkToUserEnabled,
};
useCanvasStore.getState().updateNodeData(workspaceId, optimistic);
try {
await api.patch(`/workspaces/${workspaceId}/abilities`, body);
} catch (e) {
// Roll back the optimistic change to last-known server truth.
useCanvasStore.getState().updateNodeData(workspaceId, {
broadcastEnabled: prev.broadcastEnabled,
talkToUserEnabled: prev.talkToUserEnabled,
});
setError(
e instanceof Error ? e.message : "Failed to update ability — try again",
);
} finally {
setPending(null);
}
};
return (
<Section title="Agent Abilities">
<p className="text-[10px] text-ink-mid px-1 pb-1">
Workspace-level permissions for this agent. Changes apply immediately
(no restart required).
</p>
<div className="space-y-2">
<div>
<Toggle
label="Talk to user"
checked={talkToUserEnabled}
onChange={(v) =>
pending
? undefined
: patchAbility(
"talk",
{ talk_to_user_enabled: v },
{ talkToUserEnabled: v },
)
}
/>
<p className="text-[10px] text-ink-mid mt-0.5 ml-6">
When off, the agent&apos;s <code className="font-mono">send_message_to_user</code>{" "}
and <code className="font-mono">POST /notify</code> calls are
rejected (403) it must route updates through a parent workspace.
</p>
</div>
<div>
<Toggle
label="Broadcast to peers"
checked={broadcastEnabled}
onChange={(v) =>
pending
? undefined
: patchAbility(
"broadcast",
{ broadcast_enabled: v },
{ broadcastEnabled: v },
)
}
/>
<p className="text-[10px] text-ink-mid mt-0.5 ml-6">
When on, the agent may <code className="font-mono">POST /broadcast</code>{" "}
to message all non-removed agent workspaces in the org. Off by
default only privileged orchestrators should hold this.
</p>
</div>
</div>
{pending && (
<div className="mt-2 text-[10px] text-ink-mid">Saving</div>
)}
{error && (
<div className="mt-2 px-2 py-1 bg-red-900/30 border border-red-800 rounded text-[10px] text-bad">
{error}
</div>
)}
</Section>
);
}
// --- Main ConfigTab ---
interface ModelSpec {
@@ -1009,8 +885,6 @@ export function ConfigTab({ workspaceId }: Props) {
)}
</Section>
<AgentAbilitiesSection workspaceId={workspaceId} />
{/* Claude Settings — shown for claude-code runtime or claude/anthropic model names */}
{(config.runtime === "claude-code" ||
(config.runtime_config?.model || config.model || "").toLowerCase().includes("claude") ||
@@ -1121,7 +995,7 @@ export function ConfigTab({ workspaceId }: Props) {
)}
{error && (
<div role="alert" aria-live="assertive" className="mx-3 mb-2 px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">{error}</div>
<div className="mx-3 mb-2 px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">{error}</div>
)}
{!error && RUNTIMES_WITH_OWN_CONFIG.has(config.runtime || "") && (
<div className="mx-3 mb-2 px-3 py-1.5 bg-surface-sunken/50 border border-line rounded text-xs text-ink-mid">
+3 -3
View File
@@ -157,7 +157,7 @@ export function DetailsTab({ workspaceId, data }: Props) {
</select>
</Field>
{saveError && (
<div role="alert" aria-live="assertive" className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
<div className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
{saveError}
</div>
)}
@@ -203,7 +203,7 @@ export function DetailsTab({ workspaceId, data }: Props) {
{isRestartable && (
<div className="pt-2">
{restartError && (
<div role="alert" aria-live="assertive" className="mb-2 px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
<div className="mb-2 px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
{restartError}
</div>
)}
@@ -307,7 +307,7 @@ export function DetailsTab({ workspaceId, data }: Props) {
{/* Delete */}
<Section title="Danger Zone">
{deleteError && (
<div role="alert" aria-live="assertive" className="mb-2 px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
<div className="mb-2 px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
{deleteError}
</div>
)}
+1 -1
View File
@@ -82,7 +82,7 @@ export function EventsTab({ workspaceId }: Props) {
</div>
{error && (
<div role="alert" aria-live="assertive" className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
<div className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
{error}
</div>
)}
@@ -102,7 +102,7 @@ export function ExternalConnectionSection({ workspaceId }: Props) {
</div>
{error && (
<div role="alert" aria-live="assertive" className="mt-2 px-2 py-1 bg-red-900/30 border border-red-800 rounded text-[10px] text-bad">
<div className="mt-2 px-2 py-1 bg-red-900/30 border border-red-800 rounded text-[10px] text-bad">
{error}
</div>
)}
+3 -46
View File
@@ -45,54 +45,11 @@ export function FilesTab({ workspaceId, data }: Props) {
if (data && isExternalLikeRuntime(data.runtime)) {
return <NotAvailablePanel runtime={data.runtime} />;
}
return <PlatformOwnedFilesTab workspaceId={workspaceId} runtime={data?.runtime} />;
return <PlatformOwnedFilesTab workspaceId={workspaceId} />;
}
/** Picks the initial root for the FilesTab dropdown based on the
* workspace's runtime. Decision: per-runtime default (Hongming
* 2026-05-15, internal#425 Decisions §2).
*
* - openclaw → `/agent-home` (the agent's identity/state — the
* user-facing interesting files for that runtime live in
* `~/.openclaw/` inside the container, which `/agent-home` maps to
* via the Phase 2b docker-exec backend).
* - everything else (claude-code, hermes, external-like, undefined)
* → `/configs` (the legacy default — managed config that flows
* through the per-runtime indirection in
* workspace-server/internal/handlers/template_files_eic.go).
*
* When the runtime is undefined (legacy callers that don't thread
* `data` through, or a workspace whose runtime field hasn't loaded
* yet) the default is `/configs` — matches today's behaviour, no
* surprise.
*
* Note on `/agent-home` pre-Phase-2b: the backend short-circuits
* with HTTP 501 and the canonical "implementation pending" body.
* The tab renders empty + the error banner explains. This is by
* design — lets us land the canvas UX before the backend ships,
* per the RFC's phased rollout. The 501 is graceful: it doesn't
* poison error toasts or generate "workspace not found" noise.
*
* Adding a new runtime that should default to `/agent-home`: add it
* to the agentHomeDefaultRuntimes set below. Adding a runtime that
* should default to a different root: extend this function. */
const agentHomeDefaultRuntimes = new Set(["openclaw"]);
function defaultRootForRuntime(runtime: string | undefined): string {
if (runtime && agentHomeDefaultRuntimes.has(runtime)) {
return "/agent-home";
}
return "/configs";
}
function PlatformOwnedFilesTab({
workspaceId,
runtime,
}: {
workspaceId: string;
runtime?: string;
}) {
const [root, setRoot] = useState(() => defaultRootForRuntime(runtime));
function PlatformOwnedFilesTab({ workspaceId }: { workspaceId: string }) {
const [root, setRoot] = useState("/configs");
const [selectedFile, setSelectedFile] = useState<string | null>(null);
const [fileContent, setFileContent] = useState("");
const [editContent, setEditContent] = useState("");
@@ -3,22 +3,6 @@
import { useRef } from "react";
import { getIcon } from "./tree";
// secretShapeMarker is the canonical body the workspace-server Files
// API returns when a file's path OR content matched a credential
// regex (internal#425 RFC, Phase 2b — backed by
// workspace-server/internal/secrets.ScanBytes). The marker is a
// fixed prefix so the canvas can detect it without parsing JSON and
// without round-tripping the matched bytes through the editor (which
// would defeat the purpose — clipboard, browser history, log
// surfaces would all see them).
//
// Today (Phase 1 / before 2b ships) the backend returns 501 for the
// only root that uses this path, so the marker is dead code until
// 2b lands. Wiring it in now keeps the canvas + backend contracts
// aligned in one PR rather than a follow-up. The constant is
// importable so a future test can pin the exact string.
export const SECRET_SHAPE_DENIED_MARKER = "<denied: secret-shape>";
interface Props {
selectedFile: string | null;
fileContent: string;
@@ -47,22 +31,6 @@ export function FileEditor({
const editorRef = useRef<HTMLTextAreaElement>(null);
const isDirty = editContent !== fileContent;
// internal#425 Phase 3: detect the secret-shape denial marker and
// render a placeholder instead of the editor. The marker comes
// from workspace-server Phase 2b (secrets.ScanBytes) which refuses
// to surface the file's bytes. We deliberately don't expose
// the matched pattern's Name here — the canvas just shows the
// generic denial. The Files API log surface has the Pattern.Name
// for operators who need to debug a false positive.
const isSecretShapeDenied = fileContent === SECRET_SHAPE_DENIED_MARKER;
// /agent-home is read-only from the canvas (Phase 2b ships read +
// delete; Phase-2b-followup may add write). Edits to /configs are
// unchanged. Until 2b ships, /agent-home returns 501 so this
// read-only gate is also dead code, but wiring it in now keeps
// the UI honest the moment 2b lands without a follow-up canvas PR.
const isReadOnlyRoot = root !== "/configs";
if (!selectedFile) {
return (
<div className="flex-1 flex items-center justify-center">
@@ -107,42 +75,11 @@ export function FileEditor({
{/* Editor area */}
{loadingFile ? (
<div className="p-4 text-xs text-ink-mid">Loading...</div>
) : isSecretShapeDenied ? (
// Files API refused to surface this file's bytes because its
// path or content matched a credential regex
// (workspace-server/internal/secrets, internal#425 Phase 2b).
// We render a placeholder INSTEAD OF the textarea so the
// matched bytes never enter the DOM. Clipboard / view-source
// / element-inspector all see the placeholder, not the
// credential.
<div
role="region"
aria-label="File content denied"
className="flex-1 flex items-center justify-center p-6 bg-surface"
>
<div className="max-w-md text-center space-y-2">
<div className="text-2xl opacity-40">🛡</div>
<p className="text-[11px] font-mono text-warm">
{SECRET_SHAPE_DENIED_MARKER}
</p>
<p className="text-[10px] text-ink-mid leading-relaxed">
The platform refused to surface this file because its
path or content matched a credential-shape pattern.
The bytes never left the workspace container.
</p>
<p className="text-[10px] text-ink-mid leading-relaxed">
If this is a false positive (test fixture, docs example,
or content that happens to share a credential's shape),
rename the file or adjust the content via the workspace
terminal so the regex no longer matches, then refresh.
</p>
</div>
</div>
) : (
<textarea
ref={editorRef}
value={editContent}
readOnly={isReadOnlyRoot}
readOnly={root !== "/configs"}
onChange={(e) => setEditContent(e.target.value)}
onKeyDown={(e) => {
if ((e.metaKey || e.ctrlKey) && e.key === "s") {
@@ -38,15 +38,6 @@ export function FilesToolbar({
<option value="/home">/home</option>
<option value="/workspace">/workspace</option>
<option value="/plugins">/plugins</option>
{/* internal#425 Phase 1+3: container-internal $HOME root.
Backend lands the docker-exec dispatch in Phase 2b. Until
then the stub returns 501 with a canonical
"implementation pending" message — the dropdown renders
the option so the canvas affordance is design-frozen
even before the backend ships.
Runtime-default selection logic in FilesTab.tsx picks
this as the initial value for openclaw workspaces. */}
<option value="/agent-home">/agent-home</option>
</select>
<span className="text-[10px] text-ink-mid">{fileCount} files</span>
</div>
@@ -1,181 +0,0 @@
// @vitest-environment jsdom
/**
* Tests for the /agent-home root selector + per-runtime default-root
* + secret-shape denial placeholder (internal#425 Phase 3).
*
* Separate file so the diff is reviewable as a unit and the existing
* FilesToolbar / FileEditor / FilesTab tests don't have to grow
* agent-home-specific cases. Once Phase 2b lands, the read-only +
* 501-stub assertions here can be tightened (or moved into the main
* test file as the agent-home root becomes a first-class affordance).
*/
import React from "react";
import { render, screen, cleanup } from "@testing-library/react";
import { afterEach, describe, expect, it, vi } from "vitest";
import { FilesToolbar } from "../FilesToolbar";
import {
FileEditor,
SECRET_SHAPE_DENIED_MARKER,
} from "../FileEditor";
afterEach(cleanup);
describe("internal#425 Phase 3 — /agent-home root selector", () => {
it("dropdown includes /agent-home as an option", () => {
// Pins the affordance is in the DOM even pre-Phase-2b — the
// canvas design freezes today, the backend lands the dispatch
// later. Without this, a future refactor that drops the option
// would silently regress the RFC's Phase 1 contract (canvas
// visibility) without breaking any other test.
render(
<FilesToolbar
root="/configs"
setRoot={vi.fn()}
fileCount={0}
onNewFile={vi.fn()}
onUpload={vi.fn()}
onDownloadAll={vi.fn()}
onClearAll={vi.fn()}
onRefresh={vi.fn()}
/>,
);
const select = screen.getByRole("combobox", {
name: /file root directory/i,
}) as HTMLSelectElement;
const values = Array.from(select.options).map((o) => o.value);
expect(values).toContain("/agent-home");
});
it("dropdown shows /agent-home as the SELECTED root when prop is /agent-home", () => {
render(
<FilesToolbar
root="/agent-home"
setRoot={vi.fn()}
fileCount={0}
onNewFile={vi.fn()}
onUpload={vi.fn()}
onDownloadAll={vi.fn()}
onClearAll={vi.fn()}
onRefresh={vi.fn()}
/>,
);
const select = screen.getByRole("combobox", {
name: /file root directory/i,
}) as HTMLSelectElement;
expect(select.value).toBe("/agent-home");
});
});
describe("internal#425 Phase 3 — secret-shape denial placeholder", () => {
// Files API Phase 2b returns SECRET_SHAPE_DENIED_MARKER as the file
// body when the file's path or content matched a credential regex.
// The editor MUST render the marker as a placeholder, not pump it
// through the textarea — that would put the marker (and any future
// matched bytes if the backend contract changes) into the DOM
// value, clipboard, and inspector.
it("renders the denial placeholder INSTEAD of the textarea when fileContent is the marker", () => {
render(
<FileEditor
selectedFile="agent/.openclaw/secrets.env"
fileContent={SECRET_SHAPE_DENIED_MARKER}
editContent={SECRET_SHAPE_DENIED_MARKER}
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/agent-home"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
// Placeholder region present
expect(
screen.getByRole("region", { name: /file content denied/i }),
).toBeTruthy();
// Marker text visible (so a debugging operator sees the canonical
// contract string without having to dig into the source).
expect(screen.getByText(SECRET_SHAPE_DENIED_MARKER)).toBeTruthy();
// Critically: NO textarea — the bytes never reach a controlled
// input. A regression that re-introduces the textarea path would
// make the matched marker (and any future content) selectable +
// copyable.
expect(screen.queryByRole("textbox")).toBeNull();
});
it("renders the textarea normally when fileContent is regular content", () => {
render(
<FileEditor
selectedFile="config.yaml"
fileContent="name: openclaw\n"
editContent="name: openclaw\n"
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/configs"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
expect(screen.getByRole("textbox")).toBeTruthy();
expect(screen.queryByRole("region", { name: /file content denied/i }))
.toBeNull();
});
it("/agent-home renders textarea READ-ONLY for non-denied content", () => {
// Phase 2b ships read + delete on /agent-home; write semantics
// are decided later. Until then, the canvas presents the editor
// as read-only so a user can't type into a buffer that the
// backend will refuse to PUT. Without this gate, the user would
// edit, hit Save, get a 501, and lose their context for why.
render(
<FileEditor
selectedFile=".openclaw/agent-card.json"
fileContent='{"name":"openclaw"}'
editContent='{"name":"openclaw"}'
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/agent-home"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
const textarea = screen.getByRole("textbox") as HTMLTextAreaElement;
expect(textarea.readOnly).toBe(true);
});
it("/configs renders textarea WRITABLE (regression guard for the read-only gate)", () => {
render(
<FileEditor
selectedFile="config.yaml"
fileContent="name: x\n"
editContent="name: x\n"
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/configs"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
const textarea = screen.getByRole("textbox") as HTMLTextAreaElement;
expect(textarea.readOnly).toBe(false);
});
});
describe("internal#425 Phase 3 — marker constant is the canonical string", () => {
// The marker string is part of the canvas <-> workspace-server
// contract. The workspace-server emits this exact body; the canvas
// detects it by exact-equality. A typo on either side would
// silently break detection — the canvas would render the literal
// string in the textarea instead of the placeholder. Pin the
// contract value here.
it("matches the contract value '<denied: secret-shape>'", () => {
expect(SECRET_SHAPE_DENIED_MARKER).toBe("<denied: secret-shape>");
});
});
+1 -1
View File
@@ -275,7 +275,7 @@ export function ScheduleTab({ workspaceId }: Props) {
Enabled
</label>
</div>
{error && <div role="alert" aria-live="assertive" className="text-[10px] text-bad">{error}</div>}
{error && <div className="text-[10px] text-bad">{error}</div>}
<div className="flex gap-2">
<button
type="button"
+1 -1
View File
@@ -67,7 +67,7 @@ export function TracesTab({ workspaceId }: Props) {
</div>
{error && (
<div role="alert" aria-live="assertive" className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
<div className="px-3 py-1.5 bg-red-900/30 border border-red-800 rounded text-xs text-bad">
{error}
</div>
)}
@@ -1,165 +0,0 @@
// @vitest-environment jsdom
//
// Tests for the always-visible "Agent Abilities" section added to ConfigTab
// (internal#510 broadcast_enabled, internal#511 talk_to_user_enabled; backend
// wired in commit 29b4bffb).
//
// Problem this pins: the two workspace ability flags had complete wired
// backends but NO canvas control — broadcast had none at all, talk-to-user
// only surfaced as a ChatTab recovery banner that is invisible under its
// TRUE default. The CTO could not see or toggle either from canvas.
//
// What this suite pins:
// 1. An "Agent Abilities" section renders (always visible, not gated).
// 2. Both toggles render and reflect the store node's ability fields,
// including the asymmetric defaults (broadcast FALSE, talk TRUE).
// 3. Toggling a switch calls PATCH /workspaces/:id/abilities with the
// correct snake_case body and optimistically updates the store.
import { describe, it, expect, vi, afterEach, beforeEach } from "vitest";
import { render, screen, cleanup, waitFor, fireEvent } from "@testing-library/react";
import React from "react";
afterEach(cleanup);
const apiGet = vi.fn();
const apiPatch = vi.fn();
vi.mock("@/lib/api", () => ({
api: {
get: (path: string) => apiGet(path),
patch: (path: string, body?: unknown) => apiPatch(path, body),
put: vi.fn(),
post: vi.fn(),
del: vi.fn(),
},
}));
// Store node carries the ability flags hydrated by the platform stream
// (canvas-topology.ts maps broadcast_enabled/talk_to_user_enabled onto
// node.data). Mirror that shape so the section reads real values.
const storeUpdateNodeData = vi.fn();
const storeRestartWorkspace = vi.fn();
let nodeData: { broadcastEnabled?: boolean; talkToUserEnabled?: boolean } = {};
const makeState = () => ({
nodes: [{ id: "ws-test", data: nodeData }],
restartWorkspace: storeRestartWorkspace,
updateNodeData: storeUpdateNodeData,
});
vi.mock("@/store/canvas", () => ({
useCanvasStore: Object.assign(
(selector: (s: unknown) => unknown) => selector(makeState()),
{ getState: () => makeState() },
),
}));
vi.mock("../AgentCardSection", () => ({
AgentCardSection: () => <div data-testid="agent-card-stub" />,
}));
import { ConfigTab } from "../ConfigTab";
beforeEach(() => {
apiGet.mockReset();
apiPatch.mockReset();
apiPatch.mockResolvedValue({ status: "updated" });
storeUpdateNodeData.mockReset();
apiGet.mockImplementation((path: string) => {
if (path === `/workspaces/ws-test`) {
return Promise.resolve({ runtime: "claude-code" });
}
if (path === `/workspaces/ws-test/model`) {
return Promise.resolve({ model: "claude-opus-4-7" });
}
if (path === `/workspaces/ws-test/provider`) {
return Promise.resolve({ provider: "anthropic-oauth", source: "default" });
}
if (path === `/workspaces/ws-test/files/config.yaml`) {
return Promise.resolve({ content: "name: test\nruntime: claude-code\n" });
}
if (path === "/templates") {
return Promise.resolve([
{ id: "claude-code", name: "Claude Code", runtime: "claude-code", providers: [] },
]);
}
return Promise.reject(new Error(`unmocked api.get: ${path}`));
});
});
describe("ConfigTab Agent Abilities section", () => {
it("renders an always-visible 'Agent Abilities' section with both toggles", async () => {
nodeData = {}; // unset → defaults
render(<ConfigTab workspaceId="ws-test" />);
await waitFor(() => expect(apiGet).toHaveBeenCalled());
expect(
await screen.findByRole("button", { name: /Agent Abilities/i }),
).toBeTruthy();
expect(screen.getByText("Talk to user")).toBeTruthy();
expect(screen.getByText("Broadcast to peers")).toBeTruthy();
});
it("reflects the asymmetric defaults: talk-to-user ON, broadcast OFF", async () => {
nodeData = {}; // unset → backend defaults
render(<ConfigTab workspaceId="ws-test" />);
await waitFor(() => expect(apiGet).toHaveBeenCalled());
const talk = (await screen.findByText("Talk to user"))
.closest("label")!
.querySelector("input") as HTMLInputElement;
const broadcast = screen
.getByText("Broadcast to peers")
.closest("label")!
.querySelector("input") as HTMLInputElement;
expect(talk.checked).toBe(true);
expect(broadcast.checked).toBe(false);
});
it("reflects explicit store values", async () => {
nodeData = { broadcastEnabled: true, talkToUserEnabled: false };
render(<ConfigTab workspaceId="ws-test" />);
await waitFor(() => expect(apiGet).toHaveBeenCalled());
const talk = (await screen.findByText("Talk to user"))
.closest("label")!
.querySelector("input") as HTMLInputElement;
const broadcast = screen
.getByText("Broadcast to peers")
.closest("label")!
.querySelector("input") as HTMLInputElement;
expect(talk.checked).toBe(false);
expect(broadcast.checked).toBe(true);
});
it("PATCHes /abilities with talk_to_user_enabled and optimistically updates the store", async () => {
nodeData = {}; // talk defaults true
render(<ConfigTab workspaceId="ws-test" />);
await waitFor(() => expect(apiGet).toHaveBeenCalled());
const talk = (await screen.findByText("Talk to user"))
.closest("label")!
.querySelector("input") as HTMLInputElement;
fireEvent.click(talk); // true → false
await waitFor(() =>
expect(apiPatch).toHaveBeenCalledWith("/workspaces/ws-test/abilities", {
talk_to_user_enabled: false,
}),
);
expect(storeUpdateNodeData).toHaveBeenCalledWith("ws-test", {
talkToUserEnabled: false,
});
});
it("PATCHes /abilities with broadcast_enabled when the broadcast toggle is flipped", async () => {
nodeData = {}; // broadcast defaults false
render(<ConfigTab workspaceId="ws-test" />);
await waitFor(() => expect(apiGet).toHaveBeenCalled());
const broadcast = (await screen.findByText("Broadcast to peers"))
.closest("label")!
.querySelector("input") as HTMLInputElement;
fireEvent.click(broadcast); // false → true
await waitFor(() =>
expect(apiPatch).toHaveBeenCalledWith("/workspaces/ws-test/abilities", {
broadcast_enabled: true,
}),
);
expect(storeUpdateNodeData).toHaveBeenCalledWith("ws-test", {
broadcastEnabled: true,
});
});
});
@@ -2,7 +2,7 @@
import { useState, useCallback, useRef, useEffect } from 'react';
import type { TestConnectionState, SecretGroup } from '@/types/secrets';
import { validateSecret, ApiError } from '@/lib/api/secrets';
import { validateSecret } from '@/lib/api/secrets';
interface TestConnectionButtonProps {
provider: SecretGroup;
@@ -55,23 +55,9 @@ export function TestConnectionButton({
}
onResult?.(result.valid);
resetTimerRef.current = setTimeout(() => setState('idle'), RESET_DELAYS[nextState]!);
} catch (err) {
// Distinguish a real failure shape rather than always claiming a
// timeout. A reachable server that answered with an HTTP status
// (ApiError) did NOT time out — most commonly the validation route
// is not available (404/501), which must not masquerade as
// "service down". Only an actual thrown network/abort error is a
// connectivity failure.
} catch {
setState('failure');
if (err instanceof ApiError) {
setErrorDetail(
err.status === 404 || err.status === 501
? 'Key validation is not available for this service yet. The key was not tested.'
: `Could not verify key (server returned ${err.status}). Saving is unaffected.`,
);
} else {
setErrorDetail('Could not reach the validation service. Check your connection and try again.');
}
setErrorDetail('Connection timed out. Service may be down.');
onResult?.(false);
resetTimerRef.current = setTimeout(() => setState('idle'), RESET_DELAYS.failure);
}
@@ -99,7 +85,7 @@ export function TestConnectionButton({
function Spinner() {
return (
<svg aria-hidden="true" className="spinner" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<svg className="spinner" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2">
<path d="M12 2v4M12 18v4M4.93 4.93l2.83 2.83M16.24 16.24l2.83 2.83M2 12h4M18 12h4M4.93 19.07l2.83-2.83M16.24 7.76l2.83-2.83" />
</svg>
);
@@ -28,20 +28,8 @@ const mockValidateSecret = vi.fn();
vi.mock("@/lib/api/secrets", () => ({
validateSecret: (...args: unknown[]) => mockValidateSecret(...args),
ApiError: class ApiError extends Error {
status: number;
constructor(status: number, message: string) {
super(message);
this.name = "ApiError";
this.status = status;
}
},
}));
// Re-import the mocked ApiError so test cases construct the same class the
// component's `instanceof` check sees.
import { ApiError } from "@/lib/api/secrets";
beforeEach(() => {
vi.useFakeTimers();
vi.clearAllMocks();
@@ -213,27 +201,8 @@ describe("TestConnectionButton — failure path", () => {
});
describe("TestConnectionButton — catch path", () => {
it("does NOT claim a timeout when the validate endpoint 404s (regression: internal#492)", async () => {
// The validate route is unimplemented on the server and returns a fast
// 404. Before the fix this rendered the misleading hardcoded string
// "Connection timed out. Service may be down." It must instead state
// honestly that validation isn't available and the key was not tested.
mockValidateSecret.mockRejectedValue(new ApiError(404, "Not Found"));
render(
<TestConnectionButton provider="anthropic" secretValue="sk-ant-xxx" />,
);
fireEvent.click(document.querySelector('button[type="button"]')!);
await act(async () => {
await vi.advanceTimersByTimeAsync(0);
});
expect(document.body.textContent).not.toContain("Connection timed out");
expect(document.body.textContent).not.toContain("Service may be down");
expect(document.body.textContent).toContain("not available");
expect(document.body.textContent).toContain("not tested");
});
it("reports a non-404 server error with its status, not a timeout", async () => {
mockValidateSecret.mockRejectedValue(new ApiError(500, "Internal Server Error"));
it("shows 'Connection timed out' on network error", async () => {
mockValidateSecret.mockRejectedValue(new Error("timeout"));
render(
<TestConnectionButton provider="github" secretValue="ghp_xxx" />,
);
@@ -241,20 +210,7 @@ describe("TestConnectionButton — catch path", () => {
await act(async () => {
await vi.advanceTimersByTimeAsync(0);
});
expect(document.body.textContent).toContain("500");
expect(document.body.textContent).not.toContain("Connection timed out");
});
it("shows a connectivity message on a genuine network error", async () => {
mockValidateSecret.mockRejectedValue(new Error("network down"));
render(
<TestConnectionButton provider="github" secretValue="ghp_xxx" />,
);
fireEvent.click(document.querySelector('button[type="button"]')!);
await act(async () => {
await vi.advanceTimersByTimeAsync(0);
});
expect(document.body.textContent).toContain("Could not reach the validation service");
expect(document.body.textContent).toContain("Connection timed out");
});
it("calls onResult(false) on network error", async () => {
-8
View File
@@ -649,10 +649,6 @@
border-radius: 6px;
cursor: pointer;
}
.delete-dialog__cancel-btn:focus-visible {
outline: var(--focus-ring);
outline-offset: var(--focus-ring-offset);
}
.delete-dialog__confirm-btn {
background: var(--status-invalid);
@@ -662,10 +658,6 @@
border-radius: 6px;
cursor: pointer;
}
.delete-dialog__confirm-btn:focus-visible {
outline: var(--focus-ring);
outline-offset: var(--focus-ring-offset);
}
.delete-dialog__confirm-btn:disabled { opacity: 0.4; cursor: not-allowed; }
-1
View File
@@ -58,7 +58,6 @@ TOP_LEVEL_MODULES = {
"a2a_response",
"a2a_tools",
"a2a_tools_delegation",
"a2a_tools_identity",
"a2a_tools_inbox",
"a2a_tools_memory",
"a2a_tools_messaging",
@@ -399,21 +399,7 @@ func (h *WorkspaceHandler) proxyA2ARequest(ctx context.Context, workspaceID stri
// (no Do(), no maybeMarkContainerDead). The response is a synthetic
// {status:"queued"} envelope so the caller (canvas, another workspace)
// knows delivery is acknowledged but pending consumption.
deliveryMode, deliveryModeErr := lookupDeliveryMode(ctx, workspaceID)
if deliveryModeErr != nil {
// internal#497 fail-closed: a real DB/context error on the
// delivery-mode read MUST NOT silently fall through to the push
// dispatch path — that is exactly what silently misrouted every
// poll-mode peer for 5 days under the ce2db75f regression. Surface
// a structured error so the delegation is marked failed (loud +
// retryable) instead of dispatched to the wrong path.
log.Printf("ProxyA2A: delivery-mode lookup failed for %s: %v — failing closed", workspaceID, deliveryModeErr)
return 0, nil, &proxyA2AError{
Status: http.StatusServiceUnavailable,
Response: gin.H{"error": "delivery-mode lookup failed; refusing to dispatch to avoid silent misrouting"},
}
}
if deliveryMode == models.DeliveryModePoll {
if lookupDeliveryMode(ctx, workspaceID) == models.DeliveryModePoll {
if logActivity {
h.logA2AReceiveQueued(ctx, workspaceID, callerID, body, a2aMethod)
}
@@ -194,11 +194,6 @@ func (h *WorkspaceHandler) maybeMarkContainerDead(ctx context.Context, workspace
}
db.ClearWorkspaceKeys(ctx, workspaceID)
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
// Tracked via goAsync (not bare `go`) so the asyncWG can be drained
// before a test swaps the global db.DB. runRestartCycle reads db.DB
// before its provisioner gate, so an untracked detached goroutine
// races setupTestDB's t.Cleanup db.DB restore. Matches the already-
// correct site at a2a_proxy.go:648.
h.goAsync(func() { h.RestartByID(workspaceID) })
return true
}
@@ -246,9 +241,6 @@ func (h *WorkspaceHandler) preflightContainerHealth(ctx context.Context, workspa
}
db.ClearWorkspaceKeys(ctx, workspaceID)
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
// Tracked via goAsync (see maybeMarkContainerDead): preflight's
// detached restart must be drainable so it doesn't race the global
// db.DB swap in test cleanup.
h.goAsync(func() { h.RestartByID(workspaceID) })
return &proxyA2AError{
Status: http.StatusServiceUnavailable,
@@ -270,9 +262,8 @@ func (h *WorkspaceHandler) logA2AFailure(ctx context.Context, workspaceID, calle
errWsName = workspaceID
}
summary := "A2A request to " + errWsName + " failed: " + errMsg
parent := ctx
h.goAsync(func() {
logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
defer cancel()
LogActivity(logCtx, h.broadcaster, ActivityParams{
WorkspaceID: workspaceID,
@@ -318,9 +309,8 @@ func (h *WorkspaceHandler) logA2ASuccess(ctx context.Context, workspaceID, calle
}
summary := a2aMethod + " → " + wsNameForLog
toolTrace := extractToolTrace(respBody)
parent := ctx
h.goAsync(func() {
logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
defer cancel()
LogActivity(logCtx, h.broadcaster, ActivityParams{
WorkspaceID: workspaceID,
@@ -468,64 +458,40 @@ func parseUsageFromA2AResponse(body []byte) (inputTokens, outputTokens int64) {
return 0, 0
}
// lookupDeliveryMode returns the workspace's delivery_mode.
//
// internal#497 / RFC#497 fail-closed (SURGICAL scope): the *specific*
// failure mode that hid the ce2db75f regression for 5 days is now
// propagated instead of silently swallowed — a CONTEXT error
// (context.Canceled / context.DeadlineExceeded). Under ce2db75f the
// detached delegation goroutine ran on a cancelled request context, every
// `SELECT delivery_mode` failed `context canceled`, this function returned
// push, the poll-mode short-circuit in proxyA2ARequest was skipped, and
// poll-mode peers (e.g. an operator laptop on molecule-mcp-claude-channel)
// silently never got their a2a_receive inbox row. A transient,
// systematic-once-triggered context cancellation became permanent
// invisible misrouting. Returning that error lets the caller fail loud
// (mark the delegation failed) instead of mis-dispatching.
//
// Scope is deliberately narrow: only ctx errors propagate. Other DB
// errors retain the long-standing documented "fall back to push (today's
// synchronous behavior)" contract — that path is loud + recoverable
// (502 / SSRF reject / restart), unlike the silent poll-mode drop, and
// the surrounding proxy (incl. the sibling checkWorkspaceBudget) is
// intentionally built around that fail-open-to-push behavior. Widening
// further is an RFC#497 follow-up, not part of this P0 fix.
//
// A genuinely *absent* configuration is NOT an error and still resolves to
// push (the safe synchronous default): sql.ErrNoRows, a NULL/empty column,
// or an unrecognised value all return (push, nil).
// lookupDeliveryMode returns the workspace's delivery_mode. On any DB
// error or missing row it returns DeliveryModePush — the fail-closed
// default. "Closed" here means "fall back to today's behavior (synchronous
// dispatch)" rather than "fall back to drop the request silently into
// activity_logs where the agent might never see it." A poll-mode workspace
// that briefly reads as push will get its A2A request dispatched to the
// stored URL (or a 502 if no URL); a push-mode workspace that briefly
// reads as poll would get its request silently queued with no dispatch.
// The first failure is loud + recoverable; the second is silent.
//
// The function is intentionally lookup-only — it never mutates the row.
// The register handler (registry.go) is the only writer for delivery_mode.
//
// See #2339 PR 1 for the column + register-flow side; this is the
// proxy-side read used for the short-circuit in proxyA2ARequest.
func lookupDeliveryMode(ctx context.Context, workspaceID string) (string, error) {
func lookupDeliveryMode(ctx context.Context, workspaceID string) string {
var mode sql.NullString
err := db.DB.QueryRowContext(ctx,
`SELECT delivery_mode FROM workspaces WHERE id = $1`, workspaceID,
).Scan(&mode)
if err != nil {
// internal#497: a context cancellation/deadline MUST NOT be
// swallowed into a silent push default — that is the exact 5-day
// silent-misrouting vector. Propagate so the caller fails closed.
if errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
log.Printf("ProxyA2A: lookupDeliveryMode(%s) context error (%v) — failing closed (NOT defaulting to push)", workspaceID, err)
return "", err
}
if !errors.Is(err, sql.ErrNoRows) {
log.Printf("ProxyA2A: lookupDeliveryMode(%s) failed (%v) — defaulting to push (non-ctx DB error; legacy fail-open-to-push contract)", workspaceID, err)
log.Printf("ProxyA2A: lookupDeliveryMode(%s) failed (%v) — defaulting to push", workspaceID, err)
}
return models.DeliveryModePush, nil
return models.DeliveryModePush
}
if !mode.Valid || mode.String == "" {
return models.DeliveryModePush, nil
return models.DeliveryModePush
}
if !models.IsValidDeliveryMode(mode.String) {
log.Printf("ProxyA2A: workspace %s has invalid delivery_mode=%q — defaulting to push", workspaceID, mode.String)
return models.DeliveryModePush, nil
return models.DeliveryModePush
}
return mode.String, nil
return mode.String
}
// logA2AReceiveQueued records a poll-mode "queued" A2A receive into
@@ -2235,18 +2235,12 @@ func TestProxyA2A_PushMode_NoShortCircuit(t *testing.T) {
}
}
// TestProxyA2A_PollMode_FailsClosedToPush verifies the LEGACY safety
// contract is PRESERVED for non-context DB errors: a generic DB error
// reading delivery_mode still defaults to push (today's behavior), NOT
// poll. Failing to push means a poll-mode workspace briefly attempts a
// real dispatch — visible failure (502 / SSRF rejection / restart
// cascade), not a silent drop into activity_logs where the agent might
// never look. Loud > silent, recoverable > lost.
//
// internal#497 narrows the fail-closed change to *context* errors only
// (the actual ce2db75f regression vector); generic DB errors keep this
// long-standing fail-open-to-push contract. The ctx-error fail-closed is
// covered by TestLookupDeliveryMode_ContextCanceled_FailsClosed.
// TestProxyA2A_PollMode_FailsClosedToPush verifies the safety contract:
// a DB error reading delivery_mode must default to push (the existing
// behavior), NOT poll. Failing to push means a poll-mode workspace
// briefly attempts a real dispatch — visible failure (502 / SSRF
// rejection / restart cascade), not a silent drop into activity_logs
// where the agent might never look. Loud > silent, recoverable > lost.
func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t) // empty Redis — forces resolveAgentURL DB lookup
@@ -2257,8 +2251,7 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
expectBudgetCheck(mock, wsID)
// lookupDeliveryMode hits a generic (non-context) DB error → must
// still default push (legacy contract preserved by internal#497).
// lookupDeliveryMode hits a transient DB error → must default push.
mock.ExpectQuery("SELECT delivery_mode FROM workspaces WHERE id").
WithArgs(wsID).
WillReturnError(sql.ErrConnDone)
@@ -2282,7 +2275,7 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
var resp map[string]interface{}
_ = json.Unmarshal(w.Body.Bytes(), &resp)
if resp["status"] == "queued" {
t.Errorf("generic DB error on delivery_mode lookup silently queued the request — must fail-open-to-push, got body: %s", w.Body.String())
t.Errorf("DB error on delivery_mode lookup silently queued the request — must fail-closed-to-push, got body: %s", w.Body.String())
}
}
@@ -2291,37 +2284,6 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
}
}
// TestLookupDeliveryMode_ContextCanceled_FailsClosed is the internal#497
// regression test for the SECONDARY defect. It pins the exact invariant
// that hid the ce2db75f regression for 5 days: when the delivery_mode read
// fails because the context was cancelled (precisely what happened in the
// detached delegation goroutine running on a returned request context),
// lookupDeliveryMode MUST return an error and MUST NOT silently return
// "push". Returning push there is what skipped the poll-mode short-circuit
// and silently dropped 100% of poll-mode peer deliveries.
//
// A pre-cancelled context makes QueryRowContext fail with
// context.Canceled deterministically — no DB rows are mocked because the
// query never reaches a result.
func TestLookupDeliveryMode_ContextCanceled_FailsClosed(t *testing.T) {
mock := setupTestDB(t)
// The query fails on the cancelled ctx before matching; provide a
// permissive expectation so sqlmock doesn't complain about the attempt.
mock.ExpectQuery("SELECT delivery_mode FROM workspaces WHERE id").
WillReturnError(context.Canceled)
ctx, cancel := context.WithCancel(context.Background())
cancel() // simulate the HTTP handler having returned (request ctx dead)
mode, err := lookupDeliveryMode(ctx, "ws-poll-peer")
if err == nil {
t.Fatalf("internal#497 regression: lookupDeliveryMode swallowed a context error and returned mode=%q with nil err — this is the exact 5-day silent-misrouting vector", mode)
}
if mode == models.DeliveryModePush {
t.Errorf("internal#497 regression: context error must NOT default to push (got mode=%q)", mode)
}
}
// ==================== a2aClient ResponseHeaderTimeout config ====================
func TestA2AClientResponseHeaderTimeout(t *testing.T) {
@@ -1,113 +0,0 @@
package handlers
import "encoding/json"
// agent_card_reconcile.go — server-side repair for the fleet-wide
// agent-card identity gap.
//
// Root cause: the runtime builds its AgentCard from config.name
// (workspace/main.py:198), and config.name is read from the
// CP-regenerated /configs/config.yaml whose `name:` field is the raw
// workspace UUID — NOT the friendly name the operator sees. The friendly
// name IS captured: POST /workspaces and PATCH /workspaces/:id (the
// canvas Details tab) write it to the trusted workspaces.name DB column.
// But /registry/register stores the runtime-supplied card verbatim
// (registry.go: `agent_card = EXCLUDED.agent_card`), so the stored card
// served at /.well-known/agent-card.json and returned to peers via
// agent_card_url ends up with name = UUID, description = "", role = null.
//
// Fix shape (deliberately minimal, no contract weakening): when the
// runtime-supplied card's `name` is empty or equals the workspace UUID
// (the placeholder the runtime had no better value for), the PLATFORM —
// not the agent — substitutes the friendly value from the trusted
// workspaces row. Identity stays platform-controlled: the agent never
// gains the ability to self-set its own name/role; the platform sources
// it from the operator-controlled DB column. We only ever FILL gaps
// (empty / UUID-placeholder); a card that already carries a real
// friendly name is never downgraded.
//
// list_peers / the /registry/:id/peers endpoint already resolve display
// names from workspaces.name directly (discovery.go / mcp_tools.go
// `SELECT w.id, w.name, ...`), so peer_name in delivered message tags
// was already correct — this fix closes the remaining surface: the
// agent_card blob itself (canvas Agent Card / Skills view, peer
// agent_card_url fetches, the well-known card).
//
// description / role degrade discovery the same way: an empty
// description and null role give peers nothing to reason about. We
// default description from the (now reconciled) name when blank and
// role from workspaces.role when the operator set one.
// reconcileAgentCardIdentity patches identity gaps in a runtime-supplied
// agent card from the trusted workspace DB row. It returns the
// (possibly rewritten) card bytes and whether anything changed. On any
// failure (malformed JSON, nothing to fill) it returns the input bytes
// unchanged with changed=false so the caller can store them verbatim —
// this is strictly no-worse-than-before, never a regression.
//
// Pure function: no DB / HTTP / globals, so it is exhaustively
// unit-testable (agent_card_reconcile_test.go) without booting the
// handler or a sqlmock.
func reconcileAgentCardIdentity(card json.RawMessage, workspaceID, dbName, dbRole string) (json.RawMessage, bool) {
var m map[string]any
if err := json.Unmarshal(card, &m); err != nil || m == nil {
// Malformed card — not this function's job to reject it (the
// upsert stores it as-is and downstream readers handle bad
// JSON). Return verbatim so byte-for-byte behaviour is
// preserved on the failure path.
return card, false
}
changed := false
// name: fill only when empty or the UUID placeholder. A dbName that
// is itself the UUID is a placeholder row (registry.go INSERT seeds
// name = id before the canvas sets a friendly one) — not a friendly
// name, so it is not an eligible source.
cardName, _ := m["name"].(string)
if (cardName == "" || cardName == workspaceID) &&
dbName != "" && dbName != workspaceID {
m["name"] = dbName
changed = true
}
// description: when blank, default to the (reconciled) name so peers
// and the canvas Agent Card view have a non-empty human label
// instead of "". Mirrors the runtime's own
// `config.description or config.name` fallback (main.py:199) but
// applied to the registry copy where the runtime's fallback was the
// UUID.
if desc, _ := m["description"].(string); desc == "" {
if n, _ := m["name"].(string); n != "" && n != workspaceID {
m["description"] = n
changed = true
}
}
// role: surface the operator-set workspaces.role when the card
// carries none. Discovery (peer_role) and the canvas Role row read
// workspaces.role directly; this just makes the standalone card
// self-describing too. Never overwrite a role the card already has.
if dbRole != "" {
if r, ok := m["role"].(string); !ok || r == "" {
m["role"] = dbRole
changed = true
}
}
if !changed {
// No-op: return the original bytes untouched so callers that
// compare/store get byte-identical input (re-marshalling would
// reorder keys for no reason).
return card, false
}
out, err := json.Marshal(m)
if err != nil {
// Re-marshal of a map we just unmarshalled should never fail;
// if it somehow does, fall back to the verbatim input rather
// than storing nothing.
return card, false
}
return out, true
}
@@ -1,166 +0,0 @@
package handlers
import (
"encoding/json"
"testing"
)
// TestReconcileAgentCardIdentity covers the server-side backfill that
// repairs the fleet-wide agent-card identity gap (internal#XXX): the
// runtime POSTs /registry/register with agent_card.name = the workspace
// UUID (because the CP-regenerated /configs/config.yaml sets name: <uuid>)
// while the trusted workspaces.name DB column — the value the canvas
// Details tab shows and lets the operator edit — holds the friendly
// name ("Claude Code Agent"). The platform reconciles them from the DB
// row (NOT from the agent — identity stays platform-controlled, not
// self-mutable).
func TestReconcileAgentCardIdentity(t *testing.T) {
const wsID = "3b81321b-1ec7-488c-96f7-72c42a968da6"
tests := []struct {
name string
card string
dbName string
dbRole string
wantName string
wantDesc string
wantRole string
wantChanged bool
}{
{
name: "name is the workspace UUID — backfill from DB",
card: `{"name":"3b81321b-1ec7-488c-96f7-72c42a968da6","description":"","capabilities":{"streaming":true}}`,
dbName: "Claude Code Agent",
dbRole: "",
wantName: "Claude Code Agent",
wantDesc: "Claude Code Agent",
wantRole: "",
wantChanged: true,
},
{
name: "empty name — backfill from DB",
card: `{"name":"","description":"x"}`,
dbName: "ops-agent",
dbRole: "sre",
wantName: "ops-agent",
wantDesc: "x",
wantRole: "sre",
wantChanged: true,
},
{
name: "role null in card, DB has role — backfill role only",
card: `{"name":"Reviewer","description":"Senior reviewer"}`,
dbName: "Reviewer",
dbRole: "code-reviewer",
wantName: "Reviewer",
wantDesc: "Senior reviewer",
wantRole: "code-reviewer",
wantChanged: true,
},
{
name: "card already has a real friendly name — do NOT clobber it",
// A richer card (e.g. an external channel agent) must win;
// the platform only fills gaps, never downgrades.
card: `{"name":"Claude Code (channel)","description":"Local Claude Code session bridged","role":"assistant"}`,
dbName: "hongming-pc",
dbRole: "operator",
wantName: "Claude Code (channel)",
wantDesc: "Local Claude Code session bridged",
wantRole: "assistant",
wantChanged: false,
},
{
name: "no DB name available — leave UUID name untouched (no worse than before)",
card: `{"name":"3b81321b-1ec7-488c-96f7-72c42a968da6","description":""}`,
dbName: "",
dbRole: "",
wantName: "3b81321b-1ec7-488c-96f7-72c42a968da6",
wantDesc: "",
wantRole: "",
wantChanged: false,
},
{
name: "dbName equals UUID (placeholder row) — not a friendly name, leave untouched",
card: `{"name":"3b81321b-1ec7-488c-96f7-72c42a968da6"}`,
dbName: "3b81321b-1ec7-488c-96f7-72c42a968da6",
dbRole: "",
wantName: "3b81321b-1ec7-488c-96f7-72c42a968da6",
wantDesc: "",
wantRole: "",
wantChanged: false,
},
{
name: "malformed card JSON — return unchanged, no panic",
card: `{not json`,
dbName: "Claude Code Agent",
dbRole: "",
wantChanged: false,
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
out, changed := reconcileAgentCardIdentity(
json.RawMessage(tc.card), wsID, tc.dbName, tc.dbRole,
)
if changed != tc.wantChanged {
t.Fatalf("changed = %v, want %v", changed, tc.wantChanged)
}
if !tc.wantChanged {
// Unchanged path must return the input bytes verbatim.
if string(out) != tc.card {
t.Fatalf("unchanged path mutated bytes:\n got %s\n want %s", out, tc.card)
}
return
}
var got map[string]any
if err := json.Unmarshal(out, &got); err != nil {
t.Fatalf("output not valid JSON: %v (%s)", err, out)
}
if g, _ := got["name"].(string); g != tc.wantName {
t.Errorf("name = %q, want %q", g, tc.wantName)
}
if g, _ := got["description"].(string); g != tc.wantDesc {
t.Errorf("description = %q, want %q", g, tc.wantDesc)
}
if tc.wantRole != "" {
if g, _ := got["role"].(string); g != tc.wantRole {
t.Errorf("role = %q, want %q", g, tc.wantRole)
}
}
})
}
}
// TestReconcileAgentCardIdentity_PreservesOtherFields ensures the
// reconcile is a minimal in-place patch — capabilities, version,
// skills and any unknown future fields survive untouched.
func TestReconcileAgentCardIdentity_PreservesOtherFields(t *testing.T) {
card := `{"name":"ws-uuid","description":"","version":"1.0.0",` +
`"capabilities":{"streaming":true,"pushNotifications":true},` +
`"skills":[{"id":"a","name":"a"}],"configuration_status":"ready"}`
out, changed := reconcileAgentCardIdentity(
json.RawMessage(card), "ws-uuid", "Friendly Name", "",
)
if !changed {
t.Fatal("expected changed = true")
}
var got map[string]any
if err := json.Unmarshal(out, &got); err != nil {
t.Fatalf("invalid JSON: %v", err)
}
if got["version"] != "1.0.0" {
t.Errorf("version not preserved: %v", got["version"])
}
if got["configuration_status"] != "ready" {
t.Errorf("configuration_status not preserved: %v", got["configuration_status"])
}
caps, ok := got["capabilities"].(map[string]any)
if !ok || caps["streaming"] != true {
t.Errorf("capabilities not preserved: %v", got["capabilities"])
}
skills, ok := got["skills"].([]any)
if !ok || len(skills) != 1 {
t.Errorf("skills not preserved: %v", got["skills"])
}
}
@@ -17,17 +17,6 @@ var gitIdentitySlugPattern = regexp.MustCompile(`[^a-z0-9]+`)
// docs/authorship.md (when it exists).
const gitIdentityEmailDomain = "agents.moleculesai.app"
// gitAskpassHelperPath is the in-container path of the askpass helper
// installed by every workspace runtime image (workspace/Dockerfile in
// molecule-core; scripts/git-askpass.sh → /usr/local/bin/molecule-askpass
// in each external template-* repo). The helper reads GIT_HTTP_USERNAME
// / GIT_HTTP_PASSWORD (falling back to GITEA_USER / GITEA_TOKEN) from
// env and emits them on the git credential-prompt protocol. Setting
// GIT_ASKPASS to this path is what wires container-side HTTPS git auth
// to the persona credentials already arriving via workspace_secrets,
// with no on-disk .gitconfig / .git-credentials mutation required.
const gitAskpassHelperPath = "/usr/local/bin/molecule-askpass"
// applyAgentGitIdentity sets GIT_AUTHOR_* / GIT_COMMITTER_* env vars so
// every commit from this workspace container carries a distinct author
// in `git log` and `git blame`. Git reads these env vars before falling
@@ -61,34 +50,6 @@ func applyAgentGitIdentity(envVars map[string]string, workspaceName string) {
setIfEmpty(envVars, "GIT_AUTHOR_EMAIL", authorEmail)
setIfEmpty(envVars, "GIT_COMMITTER_NAME", authorName)
setIfEmpty(envVars, "GIT_COMMITTER_EMAIL", authorEmail)
applyGitAskpass(envVars)
}
// applyGitAskpass points git at the in-image askpass helper so that any
// HTTPS git operation against a remote without a pre-configured
// credential.helper picks up the persona credentials already present in
// the container env (GIT_HTTP_USERNAME / GIT_HTTP_PASSWORD, or
// GITEA_USER / GITEA_TOKEN as fallback — the latter pair is what
// loadPersonaEnvFile delivers from the operator-host bootstrap kit).
//
// Idempotent: if GIT_ASKPASS is already set (e.g. by an operator-
// supplied workspace_secret or an env-mutator plugin), the existing
// value wins. This lets a workspace opt out by setting GIT_ASKPASS=""
// or pointing at a different helper.
//
// No vendor-specific behaviour lives in this function — the host the
// credentials apply to is determined entirely by the deployer choosing
// when to populate GIT_HTTP_USERNAME / GIT_HTTP_PASSWORD (or
// GITEA_USER / GITEA_TOKEN). The helper script itself is generic and
// has no hardcoded hostnames, so it's safe to ship inside the
// open-source workspace template images alongside the platform-managed
// claude-code image.
func applyGitAskpass(envVars map[string]string) {
if envVars == nil {
return
}
setIfEmpty(envVars, "GIT_ASKPASS", gitAskpassHelperPath)
}
// slugifyForEmail collapses a workspace name to a safe email localpart:
@@ -75,53 +75,6 @@ func TestApplyAgentGitIdentity_NilMapIsSafe(t *testing.T) {
applyAgentGitIdentity(nil, "PM")
}
func TestApplyAgentGitIdentity_SetsGitAskpass(t *testing.T) {
// GIT_ASKPASS is what wires container-side HTTPS git auth to the
// persona credentials (GITEA_USER/GITEA_TOKEN, etc.) that
// loadPersonaEnvFile delivers via workspace_secrets. Without this,
// `git push` inside the container would fall through to interactive
// prompts (impossible) or a missing credential.helper (401).
env := map[string]string{}
applyAgentGitIdentity(env, "Frontend Engineer")
if env["GIT_ASKPASS"] != "/usr/local/bin/molecule-askpass" {
t.Errorf("GIT_ASKPASS: got %q, want %q",
env["GIT_ASKPASS"], "/usr/local/bin/molecule-askpass")
}
}
func TestApplyAgentGitIdentity_RespectsAskpassOverride(t *testing.T) {
// A workspace_secret or env-mutator plugin must be able to point at
// a custom askpass helper without us clobbering it. Symmetric with
// the GIT_AUTHOR_NAME override test above.
env := map[string]string{
"GIT_ASKPASS": "/opt/custom/askpass",
}
applyAgentGitIdentity(env, "Backend Engineer")
if env["GIT_ASKPASS"] != "/opt/custom/askpass" {
t.Errorf("GIT_ASKPASS should not be overwritten, got %q", env["GIT_ASKPASS"])
}
}
func TestApplyAgentGitIdentity_AskpassSkippedOnEmptyName(t *testing.T) {
// The empty-name early-return covers GIT_ASKPASS too — a provisioning
// glitch that dropped the workspace name shouldn't half-configure the
// container (identity vars empty but askpass wired). All-or-nothing.
env := map[string]string{}
applyAgentGitIdentity(env, "")
if _, ok := env["GIT_ASKPASS"]; ok {
t.Errorf("empty name should not set GIT_ASKPASS, got %q", env["GIT_ASKPASS"])
}
}
func TestApplyGitAskpass_NilMapIsSafe(t *testing.T) {
defer func() {
if r := recover(); r != nil {
t.Errorf("applyGitAskpass panicked on nil map: %v", r)
}
}()
applyGitAskpass(nil)
}
func TestSlugifyForEmail(t *testing.T) {
cases := []struct {
in, want string
@@ -163,32 +163,8 @@ func (h *DelegationHandler) Delegate(c *gin.Context) {
},
})
// Fire-and-forget: send A2A in a background goroutine.
//
// internal#497 — the goroutine MUST NOT inherit the HTTP request's
// cancellation. `ctx` here is c.Request.Context(); the handler returns
// 202 a few lines below, which cancels that context immediately. Before
// this fix (regression ce2db75f) executeDelegation ran on the
// request-scoped ctx, so every DB op + proxy call in the detached
// goroutine failed `context canceled` the instant the 202 was written.
// That silently broke 100% of A2A peer delegations fleet-wide since
// 2026-05-12 (poll-mode peers never got their a2a_receive inbox row;
// lookupDeliveryMode swallowed the ctx error and defaulted to push).
//
// context.WithoutCancel detaches cancellation/deadline while PRESERVING
// all context values (trace/correlation/tenant ids that proxyA2ARequest
// and the broadcaster read off ctx) — this is the established pattern in
// this package (a2a_proxy.go:850, a2a_proxy_helpers.go:525,
// registry.go:822). The 30-minute ceiling matches the prior internal
// budget executeDelegation used before ce2db75f and the proxy's own
// absolute agent-dispatch ceiling (a2a_proxy.go forwardCtx).
delegationCtx, cancelDelegation := context.WithTimeout(
context.WithoutCancel(ctx), 30*time.Minute,
)
go func() {
defer cancelDelegation()
h.executeDelegation(delegationCtx, sourceID, body.TargetID, delegationID, a2aBody)
}()
// Fire-and-forget: send A2A in background goroutine
go h.executeDelegation(ctx, sourceID, body.TargetID, delegationID, a2aBody)
// Broadcast event so canvas shows delegation in real-time
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationSent), sourceID, map[string]interface{}{
@@ -16,65 +16,6 @@ import (
"github.com/gin-gonic/gin"
)
// ---------- internal#497 regression: detached goroutine ctx must outlive the handler ----------
// TestDelegate_DetachedContext_SurvivesRequestCancellation pins the
// load-bearing invariant that regression ce2db75f violated: the context
// handed to executeDelegation in the fire-and-forget goroutine must NOT be
// cancelled when the HTTP handler returns 202 (which cancels
// c.Request.Context()). Before the fix, executeDelegation ran on the
// request-scoped ctx, so every DB op + proxy call failed `context
// canceled` the instant the 202 was written — silently breaking 100% of
// A2A peer delegations fleet-wide since 2026-05-12.
//
// This test asserts the exact ctx-derivation contract used by Delegate
// (context.WithoutCancel(parent) + a timeout budget): the derived context
// (a) stays alive after the parent is cancelled, and (b) still carries
// parent values (trace/correlation/tenant ids the downstream proxy +
// broadcaster read off ctx). It is intentionally DB-free and fast.
func TestDelegate_DetachedContext_SurvivesRequestCancellation(t *testing.T) {
type ctxKey string
const traceKey ctxKey = "trace-id"
// Simulate c.Request.Context() carrying a correlation value.
parent, cancelParent := context.WithCancel(
context.WithValue(context.Background(), traceKey, "trace-abc-123"),
)
// Exact derivation Delegate uses for the detached goroutine.
delegationCtx, cancelDelegation := context.WithTimeout(
context.WithoutCancel(parent), 30*time.Minute,
)
defer cancelDelegation()
// The HTTP handler "returns 202" → request context is cancelled.
cancelParent()
if err := parent.Err(); err == nil {
t.Fatal("precondition: parent context should be cancelled after the handler returns")
}
// (a) Cancellation MUST NOT propagate to the detached context.
select {
case <-delegationCtx.Done():
t.Fatalf("regression: detached delegation ctx was cancelled by the handler returning (err=%v) — executeDelegation would fail every DB op with `context canceled`", delegationCtx.Err())
default:
// alive — correct
}
// (b) Parent values MUST still be readable (WithoutCancel preserves
// values; trace/correlation/tenant ids the proxy + broadcaster use).
if got, _ := delegationCtx.Value(traceKey).(string); got != "trace-abc-123" {
t.Errorf("detached ctx lost the parent trace value: got %q, want %q", got, "trace-abc-123")
}
// And it still has a real deadline (the 30m budget), so it is not an
// unbounded background context.
if _, hasDeadline := delegationCtx.Deadline(); !hasDeadline {
t.Error("detached ctx must carry the 30-minute timeout budget, but has no deadline")
}
}
// ---------- Delegate: missing target_id → 400 ----------
func TestDelegate_MissingTargetID(t *testing.T) {
@@ -8,7 +8,6 @@ import (
"fmt"
"net/http"
"net/http/httptest"
"sync"
"testing"
"time"
@@ -23,39 +22,8 @@ import (
"github.com/redis/go-redis/v9"
)
// liveTestHandlers tracks every WorkspaceHandler built during the test
// binary's lifetime so setupTestDB can drain their in-flight goAsync
// goroutines (notably the detached RestartByID restart cycle, which
// reads the global db.DB) BEFORE restoring db.DB. Without this drain a
// fire-and-forget restart goroutine spawned by one test outlives that
// test and races the db.DB swap in a later test's t.Cleanup — the
// 0x...d548 data race on platform/internal/db.DB.
var (
liveTestHandlersMu sync.Mutex
liveTestHandlers []*WorkspaceHandler
)
func init() {
gin.SetMode(gin.TestMode)
newHandlerHook = func(h *WorkspaceHandler) {
liveTestHandlersMu.Lock()
liveTestHandlers = append(liveTestHandlers, h)
liveTestHandlersMu.Unlock()
}
}
// drainTestAsync waits for every tracked handler's goAsync goroutines to
// finish. Called from setupTestDB's cleanup before db.DB is restored so
// no detached restart/provision goroutine is mid-read of db.DB when the
// pointer is swapped.
func drainTestAsync() {
liveTestHandlersMu.Lock()
handlers := make([]*WorkspaceHandler, len(liveTestHandlers))
copy(handlers, liveTestHandlers)
liveTestHandlersMu.Unlock()
for _, h := range handlers {
h.waitAsyncForTest()
}
}
// setupTestDB creates a sqlmock DB and assigns it to the global db.DB.
@@ -74,16 +42,7 @@ func setupTestDB(t *testing.T) sqlmock.Sqlmock {
}
prevDB := db.DB
db.DB = mockDB
t.Cleanup(func() {
// Drain detached async goroutines (e.g. goAsync(RestartByID),
// which reads db.DB in runRestartCycle before its provisioner
// gate) BEFORE swapping db.DB back. Doing the restore first
// would let an in-flight restart goroutine read db.DB while
// this line writes it — the data race this guards against.
drainTestAsync()
db.DB = prevDB
mockDB.Close()
})
t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
// Disable SSRF checks for the duration of this test only. Restore
// the previous state via t.Cleanup so that TestIsSafeURL_* tests
@@ -218,14 +218,6 @@ func loadWorkspaceEnv(orgBaseDir, filesDir string) map[string]string {
// check, or when the env file does not exist (workspaces without a role —
// or running on hosts that don't ship the bootstrap dir — keep their old
// behavior).
//
// Token-file fallback: the newer prod-team personas (agent-dev-a,
// agent-dev-b, agent-pm) ship `token` + `universal-auth.env` only — no
// legacy plaintext `env` file. When the env-file load produces zero rows,
// loadPersonaTokenFile fills in GITEA_TOKEN / GITEA_USER / GITEA_USER_EMAIL
// from the token file so the GIT_ASKPASS helper has something to emit.
// The env-file form remains authoritative when present (it may carry
// richer rows like GITEA_TOKEN_SCOPES / GITEA_SSH_KEY_PATH).
func loadPersonaEnvFile(role string, out map[string]string) {
if !isSafeRoleName(role) {
if role != "" {
@@ -237,61 +229,7 @@ func loadPersonaEnvFile(role string, out map[string]string) {
if root == "" {
root = "/etc/molecule-bootstrap/personas"
}
before := len(out)
parseEnvFile(filepath.Join(root, role, "env"), out)
if len(out) == before {
// No env-file rows landed (file absent, or present-but-empty).
// Try the token-only persona shape used by the prod-team
// identities. Existing keys in out are preserved.
loadPersonaTokenFile(role, out)
}
}
// loadPersonaTokenFile populates GITEA_TOKEN / GITEA_USER / GITEA_USER_EMAIL
// from a persona dir that ships only the bare `token` file — the shape used
// by the production agent personas (agent-dev-a, agent-dev-b, agent-pm).
// Those dirs do not carry an `env` file because their non-Gitea creds come
// from Infisical Universal Auth at runtime (universal-auth.env), so the
// historical loadPersonaEnvFile path silently no-ops on them.
//
// File layout: $MOLECULE_PERSONA_ROOT/<role>/token (mode 600, plain text).
// The token contents become GITEA_TOKEN (whitespace-trimmed); the role
// name becomes GITEA_USER; GITEA_USER_EMAIL is synthesised as
// <role>@<gitIdentityEmailDomain> to match the email shape that
// applyAgentGitIdentity uses for its slug-derived authorship addresses.
//
// Silent no-op when the role fails the safe-segment check, when the
// token file does not exist, or when its contents are empty after
// trimming. Existing keys in out are not overwritten — the caller's
// later .env layers and any prior loadPersonaEnvFile rows always win.
func loadPersonaTokenFile(role string, out map[string]string) {
if out == nil {
return
}
if !isSafeRoleName(role) {
return
}
root := os.Getenv("MOLECULE_PERSONA_ROOT")
if root == "" {
root = "/etc/molecule-bootstrap/personas"
}
data, err := os.ReadFile(filepath.Join(root, role, "token"))
if err != nil {
return
}
token := strings.TrimSpace(string(data))
if token == "" {
return
}
if _, ok := out["GITEA_TOKEN"]; !ok {
out["GITEA_TOKEN"] = token
}
if _, ok := out["GITEA_USER"]; !ok {
out["GITEA_USER"] = role
}
if _, ok := out["GITEA_USER_EMAIL"]; !ok {
out["GITEA_USER_EMAIL"] = role + "@" + gitIdentityEmailDomain
}
}
// isSafeRoleName accepts a single path segment of [A-Za-z0-9_-]+. Rejects
@@ -164,181 +164,3 @@ func TestIsSafeRoleName_Acceptance(t *testing.T) {
}
}
}
// TestLoadPersonaTokenFile_TokenOnlyPersona: the prod-team personas
// (agent-dev-a / agent-dev-b / agent-pm) ship `token` only — no `env`
// file. loadPersonaEnvFile's fallback path must populate GITEA_TOKEN /
// GITEA_USER / GITEA_USER_EMAIL from the token contents + role name so
// the GIT_ASKPASS helper has something to emit.
func TestLoadPersonaTokenFile_TokenOnlyPersona(t *testing.T) {
root := t.TempDir()
roleDir := filepath.Join(root, "agent-dev-a")
if err := os.MkdirAll(roleDir, 0o755); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(roleDir, "token"),
[]byte("token-bytes-redacted\n"), 0o600); err != nil {
t.Fatal(err)
}
t.Setenv("MOLECULE_PERSONA_ROOT", root)
out := map[string]string{}
loadPersonaEnvFile("agent-dev-a", out)
want := map[string]string{
"GITEA_TOKEN": "token-bytes-redacted",
"GITEA_USER": "agent-dev-a",
"GITEA_USER_EMAIL": "agent-dev-a@" + gitIdentityEmailDomain,
}
if len(out) != len(want) {
t.Fatalf("got %d keys, want %d: %#v", len(out), len(want), out)
}
for k, v := range want {
if out[k] != v {
t.Errorf("out[%q] = %q; want %q", k, out[k], v)
}
}
}
// TestLoadPersonaTokenFile_EnvFileWins: when BOTH an env file and a
// token file exist in the same persona dir, the env file is the more-
// specific declaration and wins outright — the fallback must not fire
// at all. This pins precedence so a persona later migrated to the
// richer env-file form (carrying GITEA_TOKEN_SCOPES / GITEA_SSH_KEY_PATH)
// doesn't get its token silently overridden by the fallback.
func TestLoadPersonaTokenFile_EnvFileWins(t *testing.T) {
root := t.TempDir()
roleDir := filepath.Join(root, "agent-dev-b")
if err := os.MkdirAll(roleDir, 0o755); err != nil {
t.Fatal(err)
}
envBody := "GITEA_USER=env-form-user\nGITEA_TOKEN=env-form-token\n" +
"GITEA_USER_EMAIL=env-form@example.invalid\nGITEA_TOKEN_SCOPES=write:repository\n"
if err := os.WriteFile(filepath.Join(roleDir, "env"), []byte(envBody), 0o600); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(roleDir, "token"),
[]byte("token-form-token\n"), 0o600); err != nil {
t.Fatal(err)
}
t.Setenv("MOLECULE_PERSONA_ROOT", root)
out := map[string]string{}
loadPersonaEnvFile("agent-dev-b", out)
if out["GITEA_USER"] != "env-form-user" {
t.Errorf("env file should win for GITEA_USER; got %q", out["GITEA_USER"])
}
if out["GITEA_TOKEN"] != "env-form-token" {
t.Errorf("env file should win for GITEA_TOKEN; got %q", out["GITEA_TOKEN"])
}
if out["GITEA_USER_EMAIL"] != "env-form@example.invalid" {
t.Errorf("env file should win for GITEA_USER_EMAIL; got %q", out["GITEA_USER_EMAIL"])
}
if out["GITEA_TOKEN_SCOPES"] != "write:repository" {
t.Errorf("env file extras must be preserved; got GITEA_TOKEN_SCOPES=%q", out["GITEA_TOKEN_SCOPES"])
}
}
// TestLoadPersonaTokenFile_NeitherFile: persona dir exists but ships
// neither env nor token — silent no-op. This is the legitimate case
// for a partially-provisioned persona during bootstrap; callers expect
// an empty map, no error, no log noise.
func TestLoadPersonaTokenFile_NeitherFile(t *testing.T) {
root := t.TempDir()
roleDir := filepath.Join(root, "agent-pm")
if err := os.MkdirAll(roleDir, 0o755); err != nil {
t.Fatal(err)
}
t.Setenv("MOLECULE_PERSONA_ROOT", root)
out := map[string]string{}
loadPersonaEnvFile("agent-pm", out)
if len(out) != 0 {
t.Errorf("expected empty out when neither env nor token exists; got %#v", out)
}
}
// TestLoadPersonaTokenFile_EmptyToken: a token file with only
// whitespace must be treated as absent — never emit
// GITEA_TOKEN="" / GITEA_USER=<role> / GITEA_USER_EMAIL=<role>@... because
// that would set GITEA_USER without a usable token, and the askpass
// helper would then prompt with an empty password. Silent no-op is the
// correct behavior — let downstream auth fall through to its existing
// "no credentials available" path.
func TestLoadPersonaTokenFile_EmptyToken(t *testing.T) {
root := t.TempDir()
roleDir := filepath.Join(root, "agent-dev-a")
if err := os.MkdirAll(roleDir, 0o755); err != nil {
t.Fatal(err)
}
// Whitespace-only contents: spaces, tabs, newlines.
if err := os.WriteFile(filepath.Join(roleDir, "token"),
[]byte(" \t\n \n"), 0o600); err != nil {
t.Fatal(err)
}
t.Setenv("MOLECULE_PERSONA_ROOT", root)
out := map[string]string{}
loadPersonaEnvFile("agent-dev-a", out)
if len(out) != 0 {
t.Errorf("expected empty out when token file is whitespace-only; got %#v", out)
}
}
// TestLoadPersonaTokenFile_TrimsWhitespace: tokens shipped from the
// operator-host bootstrap kit may have a trailing newline (the
// canonical `printf "%s\n" "$token" > token` shape). The fallback must
// trim leading + trailing whitespace so the askpass helper emits the
// raw token bytes — Gitea's PAT validator rejects tokens with embedded
// whitespace.
func TestLoadPersonaTokenFile_TrimsWhitespace(t *testing.T) {
root := t.TempDir()
roleDir := filepath.Join(root, "agent-dev-b")
if err := os.MkdirAll(roleDir, 0o755); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(roleDir, "token"),
[]byte("\n raw-token-bytes \n\n"), 0o600); err != nil {
t.Fatal(err)
}
t.Setenv("MOLECULE_PERSONA_ROOT", root)
out := map[string]string{}
loadPersonaEnvFile("agent-dev-b", out)
if out["GITEA_TOKEN"] != "raw-token-bytes" {
t.Errorf("token whitespace not trimmed; got %q", out["GITEA_TOKEN"])
}
}
// TestLoadPersonaTokenFile_RejectsUnsafeRole: defense-in-depth — even
// in the fallback path, role names that fail isSafeRoleName must not
// touch the filesystem. Mirrors TestLoadPersonaEnvFile_RejectsTraversal.
func TestLoadPersonaTokenFile_RejectsUnsafeRole(t *testing.T) {
root := t.TempDir()
// Plant a token at /tmp/.../token so a bad traversal would reach it.
if err := os.WriteFile(filepath.Join(root, "token"),
[]byte("stolen-token\n"), 0o600); err != nil {
t.Fatal(err)
}
t.Setenv("MOLECULE_PERSONA_ROOT", filepath.Join(root, "personas"))
for _, bad := range []string{"..", "../personas", "/abs", "with/slash", "."} {
out := map[string]string{}
loadPersonaTokenFile(bad, out)
if len(out) != 0 {
t.Errorf("role %q should have been rejected; got %#v", bad, out)
}
}
}
// TestLoadPersonaTokenFile_NilMapSafe: callers pass a fresh map in
// practice, but defense-in-depth — a nil map must not panic.
func TestLoadPersonaTokenFile_NilMapSafe(t *testing.T) {
defer func() {
if r := recover(); r != nil {
t.Fatalf("nil map caused panic: %v", r)
}
}()
loadPersonaTokenFile("agent-dev-a", nil)
}
+3 -31
View File
@@ -327,33 +327,7 @@ func (h *RegistryHandler) Register(c *gin.Context) {
}
}
// Reconcile the runtime-supplied card's identity fields against the
// trusted workspaces row before storing. The runtime builds its card
// from config.name, which the CP-regenerated /configs/config.yaml
// sets to the workspace UUID — so without this the stored card
// served at /.well-known/agent-card.json and returned to peers via
// agent_card_url has name = UUID, description = "", role = null even
// though the operator-controlled workspaces.name holds the friendly
// name the canvas shows. We only FILL gaps from the DB (never
// downgrade a card that already carries a real name); identity stays
// platform-controlled — the agent cannot self-set these. Best-effort:
// a lookup failure leaves the card exactly as the runtime sent it
// (no-worse-than-before). See agent_card_reconcile.go.
reconciledCard := payload.AgentCard
{
var dbName, dbRole sql.NullString
if qErr := db.DB.QueryRowContext(ctx,
`SELECT name, role FROM workspaces WHERE id = $1`, payload.ID,
).Scan(&dbName, &dbRole); qErr == nil {
if rc, did := reconcileAgentCardIdentity(
payload.AgentCard, payload.ID, dbName.String, dbRole.String,
); did {
reconciledCard = rc
log.Printf("Registry register: reconciled agent_card identity for %s from workspaces row", payload.ID)
}
}
}
agentCardStr := string(reconciledCard)
agentCardStr := string(payload.AgentCard)
// urlForUpsert: poll-mode workspaces don't need a URL. Empty input
// becomes NULL via sql.NullString so the row's URL stays clean (the
@@ -439,12 +413,10 @@ func (h *RegistryHandler) Register(c *gin.Context) {
}
}
// Broadcast WORKSPACE_ONLINE — use the reconciled card so the canvas
// Agent Card view live-updates with the friendly name, matching what
// was just persisted (not the runtime's raw UUID-name card).
// Broadcast WORKSPACE_ONLINE
if err := h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), payload.ID, map[string]interface{}{
"url": cachedURL,
"agent_card": reconciledCard,
"agent_card": payload.AgentCard,
"delivery_mode": effectiveMode,
}); err != nil {
log.Printf("Registry broadcast error: %v", err)
@@ -56,10 +56,8 @@ const (
// (an externally routable address) is used directly.
func (h *WorkspaceHandler) gracefulPreRestart(ctx context.Context, workspaceID string) {
// Non-blocking send — don't stall the restart cycle.
// Run in a tracked async goroutine (goAsync, not bare `go`) so the
// caller (runRestartCycle) can proceed to stopForRestart without
// waiting, while the test harness can still drain it before swapping
// the global db.DB (resolveAgentURLForRestartSignal reads db.DB).
// Run in a detached goroutine so the caller (runRestartCycle) can
// proceed to stopForRestart without waiting.
h.goAsync(func() {
signalCtx, cancel := context.WithTimeout(context.Background(), restartSignalTimeout)
defer cancel()
@@ -1,117 +0,0 @@
package handlers
// template_files_agent_home_stub_test.go — pins the Phase-1 stub
// contract for the /agent-home root added by internal#425 RFC.
//
// Today (pre-Phase-2b), every Files API verb against `?root=/agent-home`
// must return HTTP 501 with the canonical pending-message body. The
// stub MUST NOT:
// 1. Hit the DB (the workspace might not even exist yet from the
// canvas's POV — the root selector is testable without one).
// 2. Touch the EIC tunnel / Docker / template-dir paths — those
// would 500/404/[] depending on the env and confuse the canvas.
// 3. Accept writes/deletes that the future docker-exec backend
// would reject — fail closed.
//
// When Phase 2b lands, this file gets replaced by a real
// docker-exec dispatch test; the stub-message constant in
// templates.go disappears.
import (
"net/http"
"net/http/httptest"
"strings"
"testing"
"github.com/gin-gonic/gin"
)
// TestAgentHomeAllowedRoot pins that /agent-home is in the allowedRoots
// set. Without this, a future refactor that drops the key would
// silently degrade the canvas root selector to a 400 instead of the
// stub 501.
func TestAgentHomeAllowedRoot(t *testing.T) {
if !allowedRoots["/agent-home"] {
t.Fatal("/agent-home must be in allowedRoots — RFC #425 contract")
}
}
// TestAgentHomeStub_AllVerbs_Return501 pins the canonical stub
// response across all four verbs. Each must:
//
// - status 501
// - body contains the canonical "/agent-home not implemented" prefix
// - NOT contain "workspace not found" (proves we short-circuit before
// the DB lookup)
//
// Driven as a table to keep symmetry — adding a fifth verb in the
// future means adding one row here.
func TestAgentHomeStub_AllVerbs_Return501(t *testing.T) {
cases := []struct {
name string
method string
invoke func(c *gin.Context)
}{
{
name: "ListFiles",
method: "GET",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).ListFiles(c) },
},
{
name: "ReadFile",
method: "GET",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).ReadFile(c) },
},
{
name: "WriteFile",
method: "PUT",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).WriteFile(c) },
},
{
name: "DeleteFile",
method: "DELETE",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).DeleteFile(c) },
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{
{Key: "id", Value: "ws-stub"},
// Path param without leading slash so DeleteFile's
// filepath.IsAbs guard doesn't 400 before the root
// dispatch runs. The List/Read/Write paths strip the
// leading slash themselves and accept either form.
{Key: "path", Value: "notes.md"},
}
// WriteFile binds JSON; provide a minimal valid body so the
// short-circuit isn't masked by the bind-error path.
var body string
if tc.method == "PUT" {
body = `{"content":"x"}`
}
c.Request = httptest.NewRequest(
tc.method,
"/workspaces/ws-stub/files/notes.md?root=/agent-home",
strings.NewReader(body),
)
if body != "" {
c.Request.Header.Set("Content-Type", "application/json")
}
tc.invoke(c)
if w.Code != http.StatusNotImplemented {
t.Fatalf("expected 501, got %d: %s", w.Code, w.Body.String())
}
if !strings.Contains(w.Body.String(), "/agent-home not implemented") {
t.Errorf("body should contain canonical stub message; got %s", w.Body.String())
}
if strings.Contains(w.Body.String(), "workspace not found") {
t.Errorf("stub leaked through to DB lookup; body=%s", w.Body.String())
}
})
}
}
@@ -19,7 +19,6 @@ package handlers
import (
"bytes"
"context"
"errors"
"fmt"
"log"
"os"
@@ -358,28 +357,6 @@ func writeFileViaEIC(ctx context.Context, instanceID, runtime, root, relPath str
var stderr bytes.Buffer
sshCmd.Stderr = &stderr
if err := sshCmd.Run(); err != nil {
// When the per-op context deadline (eicFileOpTimeout) fires,
// exec.CommandContext SIGKILLs the ssh subprocess and Run()
// returns the bare "signal: killed" with empty stderr. That
// surfaced to the canvas as an opaque
// `500 {"error":"ssh install: signal: killed ()"}` which gave
// the operator no idea the workspace was simply mid-provision
// with a slow/unready EIC tunnel (internal#423). Detect the
// deadline explicitly and return an actionable message instead
// — the EIC mechanism, timeout value, and success path are all
// unchanged; this only improves the error a stuck write emits.
if cerr := ctx.Err(); cerr != nil {
reason := "timed out after " + eicFileOpTimeout.String()
if errors.Is(cerr, context.Canceled) && !errors.Is(cerr, context.DeadlineExceeded) {
reason = "was cancelled"
}
return fmt.Errorf(
"ssh install: EIC tunnel to workspace %s — "+
"the workspace may still be provisioning (slow/unready SSH); "+
"retry once it is online, or apply provider credentials via "+
"Settings → Secrets (encrypted, does not use this file-write path)",
reason)
}
return fmt.Errorf("ssh install: %w (%s)", err, strings.TrimSpace(stderr.String()))
}
log.Printf("writeFileViaEIC: ws instance=%s runtime=%s root=%s wrote %d bytes → %s",
@@ -1,71 +0,0 @@
package handlers
// template_files_eic_write_timeout_test.go — pins the actionable-error
// behavior added for internal#423.
//
// When the per-op context deadline (eicFileOpTimeout) fires,
// exec.CommandContext SIGKILLs the ssh subprocess and Run() returns the
// bare "signal: killed" with empty stderr. Before the fix that surfaced
// to the canvas as an opaque `500 {"error":"ssh install: signal:
// killed ()"}` — useless to an operator whose workspace was simply
// mid-provision with a slow/unready EIC tunnel. The fix detects the
// deadline explicitly (errors.Is(ctx.Err(), context.DeadlineExceeded))
// and returns a message that names the cause and the
// Settings → Secrets workaround.
import (
"context"
"strings"
"testing"
"time"
)
// TestWriteFileViaEIC_DeadlineExceeded_ActionableError stubs
// withEICTunnel so the *real* inner closure runs against a context that
// has already exceeded its deadline. The ssh subprocess fails (no real
// sshd on the fake port) and ctx.Err() == DeadlineExceeded, so the new
// branch must fire and produce an actionable message — NOT the opaque
// "signal: killed ()" string the canvas used to show.
func TestWriteFileViaEIC_DeadlineExceeded_ActionableError(t *testing.T) {
prev := withEICTunnel
withEICTunnel = func(_ context.Context, instanceID string, fn func(s eicSSHSession) error) error {
// Run the real inner closure. It closes over the ctx that
// writeFileViaEIC derived from our already-cancelled parent, so
// the ssh subprocess is killed immediately and ctx.Err()
// resolves — exactly the eicFileOpTimeout-expiry shape.
return fn(eicSSHSession{
instanceID: instanceID,
osUser: "ubuntu",
localPort: 1, // nothing listening → ssh fails fast
keyPath: "/nonexistent/key",
})
}
t.Cleanup(func() { withEICTunnel = prev })
// Drive the real writeFileViaEIC. Pass a parent whose deadline has
// already passed: the context.WithTimeout(ctx, eicFileOpTimeout)
// derived inside writeFileViaEIC inherits the expired parent
// deadline, so ctx.Err() == context.DeadlineExceeded by the time
// the killed ssh subprocess returns — the exact production shape
// (eicFileOpTimeout expiry), exercised deterministically.
parent, cancel := context.WithDeadline(context.Background(), time.Now().Add(-time.Second))
defer cancel()
err := writeFileViaEIC(parent, "i-test", "claude-code", "/configs", "config.yaml", []byte("model: sonnet\n"))
if err == nil {
t.Fatalf("expected an error from a killed ssh subprocess, got nil")
}
msg := err.Error()
// Must NOT leak the opaque bare-signal string to the operator.
if strings.Contains(msg, "signal: killed ()") {
t.Fatalf("error still surfaces the opaque %q form: %q", "signal: killed ()", msg)
}
// Must name the cause and the Secrets workaround so the canvas
// shows something actionable.
for _, want := range []string{"timed out", "provisioning", "Settings", "Secrets"} {
if !strings.Contains(msg, want) {
t.Errorf("actionable error missing %q; got: %q", want, msg)
}
}
}
@@ -18,35 +18,11 @@ import (
)
// allowedRoots are the container paths that the Files API can browse.
//
// `/agent-home` (added 2026-05-15, internal#425 RFC) is the container's
// own $HOME — `/root` for openclaw, `/home/agent` for claude-code/hermes
// — browsed via `docker exec` rather than host-side `find`. The
// dispatch is stubbed today (returns 501); full implementation lands in
// Phase 2b of the RFC. The allowedRoots key is added now so the canvas
// can design its root-selector UI against the final shape and the
// stub-vs-full transition is server-side only.
var allowedRoots = map[string]bool{
"/configs": true,
"/workspace": true,
"/home": true,
"/plugins": true,
"/agent-home": true,
}
// agentHomeStubMessage is the body returned by every Files API verb
// when `?root=/agent-home` is requested before Phase 2b lands. Keep the
// status code 501 (Not Implemented) — the route exists, the verb is
// understood, but the handler is unimplemented. Distinguishes from
// 400/404 so a canvas behind a less-current server can render a clean
// "feature pending" state instead of a generic error.
const agentHomeStubMessage = "/agent-home not implemented yet (internal#425 RFC Phase 2b — docker-exec backend pending)"
// isAgentHomeStubRequest returns true when the request targets the
// stubbed /agent-home root. Centralised so every verb in this file
// short-circuits with the same response shape.
func isAgentHomeStubRequest(rootPath string) bool {
return rootPath == "/agent-home"
"/configs": true,
"/workspace": true,
"/home": true,
"/plugins": true,
}
// maxUploadFiles limits the number of files in a single import/replace.
@@ -248,14 +224,7 @@ func (h *TemplatesHandler) ListFiles(c *gin.Context) {
// ?depth= — max depth to recurse (default: 1, max: 5)
rootPath := c.DefaultQuery("root", "/configs")
if !allowedRoots[rootPath] {
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins, /agent-home"})
return
}
// /agent-home dispatch is stubbed pre-Phase-2b. Short-circuit before
// the DB lookup + EIC dance so a canvas exercising the new root key
// gets a clean 501 instead of a half-effort response.
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
subPath := c.DefaultQuery("path", "")
@@ -424,11 +393,7 @@ func (h *TemplatesHandler) ReadFile(c *gin.Context) {
ctx := c.Request.Context()
rootPath := c.DefaultQuery("root", "/configs")
if !allowedRoots[rootPath] {
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins, /agent-home"})
return
}
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
@@ -541,11 +506,7 @@ func (h *TemplatesHandler) WriteFile(c *gin.Context) {
ctx := c.Request.Context()
rootPath := c.DefaultQuery("root", "/configs")
if !allowedRoots[rootPath] {
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins, /agent-home"})
return
}
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
var wsName, instanceID, runtime string
@@ -622,11 +583,7 @@ func (h *TemplatesHandler) DeleteFile(c *gin.Context) {
ctx := c.Request.Context()
rootPath := c.DefaultQuery("root", "/configs")
if !allowedRoots[rootPath] {
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins, /agent-home"})
return
}
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
var wsName, instanceID, runtime string
@@ -10,20 +10,8 @@ import (
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/wsauth"
"github.com/gin-gonic/gin"
"github.com/google/uuid"
)
// validWorkspaceID returns true when id is a syntactically valid UUID.
// workspace_id is a `uuid` column; passing a non-UUID (e.g. the canvas
// "global" sentinel sent when no node is selected) makes Postgres raise
// `invalid input syntax for type uuid`, which previously leaked as an
// opaque 500. Reject up front with a clean 400 instead. Mirrors the
// uuid.Parse guard already used in handlers/activity.go.
func validWorkspaceID(id string) bool {
_, err := uuid.Parse(id)
return err == nil
}
// TokenHandler exposes user-facing token management for workspaces.
// Routes: GET/POST/DELETE /workspaces/:id/tokens (behind WorkspaceAuth).
type TokenHandler struct{}
@@ -43,10 +31,6 @@ type tokenListItem struct {
// never the plaintext or hash).
func (h *TokenHandler) List(c *gin.Context) {
workspaceID := c.Param("id")
if !validWorkspaceID(workspaceID) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace id"})
return
}
limit := 50
if v := c.Query("limit"); v != "" {
@@ -69,7 +53,6 @@ func (h *TokenHandler) List(c *gin.Context) {
LIMIT $2 OFFSET $3
`, workspaceID, limit, offset)
if err != nil {
log.Printf("tokens: list query failed for workspace %s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to list tokens"})
return
}
@@ -102,10 +85,6 @@ const maxTokensPerWorkspace = 50
// exactly once in the response — it cannot be recovered afterwards.
func (h *TokenHandler) Create(c *gin.Context) {
workspaceID := c.Param("id")
if !validWorkspaceID(workspaceID) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace id"})
return
}
// Rate limit: max active tokens per workspace
var count int
@@ -138,10 +117,6 @@ func (h *TokenHandler) Create(c *gin.Context) {
func (h *TokenHandler) Revoke(c *gin.Context) {
workspaceID := c.Param("id")
tokenID := c.Param("tokenId")
if !validWorkspaceID(workspaceID) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace id"})
return
}
result, err := db.DB.ExecContext(c.Request.Context(), `
UPDATE workspace_auth_tokens
@@ -41,15 +41,6 @@ import (
func init() { gin.SetMode(gin.TestMode) }
// Workspace IDs are validated as UUIDs up front (tokens.go validWorkspaceID),
// so handler tests must pass syntactically valid UUIDs. Fixed values keep
// sqlmock WithArgs assertions deterministic.
const (
wsUUID1 = "11111111-1111-1111-1111-111111111111"
wsUUID2 = "22222222-2222-2222-2222-222222222222"
wsUUID3 = "33333333-3333-3333-3333-333333333333"
)
// withMockDB swaps `db.DB` for a sqlmock and returns the mock plus a
// restore func. Tests use this in place of setupTokenTestDB which
// skips on a missing real DB.
@@ -90,13 +81,13 @@ func TestTokenHandler_List_HappyPath(t *testing.T) {
created := time.Date(2026, 4, 1, 12, 0, 0, 0, time.UTC)
last := created.Add(time.Hour)
mock.ExpectQuery(`SELECT id, prefix, created_at, last_used_at\s+FROM workspace_auth_tokens`).
WithArgs(wsUUID1, 50, 0).
WithArgs("ws-1", 50, 0).
WillReturnRows(sqlmock.NewRows([]string{"id", "prefix", "created_at", "last_used_at"}).
AddRow("tok-1", "abc12345", created, last).
AddRow("tok-2", "def67890", created, nil))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", w.Code, w.Body.String())
@@ -130,7 +121,7 @@ func TestTokenHandler_List_EmptyResult(t *testing.T) {
WillReturnRows(sqlmock.NewRows([]string{"id", "prefix", "created_at", "last_used_at"}))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-2/tokens", gin.Params{{Key: "id", Value: wsUUID2}})
"/workspaces/ws-2/tokens", gin.Params{{Key: "id", Value: "ws-2"}})
if w.Code != http.StatusOK {
t.Fatalf("expected 200 on empty list, got %d", w.Code)
@@ -155,7 +146,7 @@ func TestTokenHandler_List_QueryError(t *testing.T) {
WillReturnError(errors.New("connection refused"))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-3/tokens", gin.Params{{Key: "id", Value: wsUUID3}})
"/workspaces/ws-3/tokens", gin.Params{{Key: "id", Value: "ws-3"}})
if w.Code != http.StatusInternalServerError {
t.Errorf("query error must surface as 500, got %d", w.Code)
@@ -167,13 +158,13 @@ func TestTokenHandler_List_RespectsLimit(t *testing.T) {
defer cleanup()
mock.ExpectQuery(`SELECT id, prefix, created_at, last_used_at`).
WithArgs(wsUUID1, 10, 5).
WithArgs("ws-1", 10, 5).
WillReturnRows(sqlmock.NewRows([]string{"id", "prefix", "created_at", "last_used_at"}))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Request = httptest.NewRequest("GET", "/workspaces/ws-1/tokens?limit=10&offset=5", nil)
c.Params = gin.Params{{Key: "id", Value: wsUUID1}}
c.Params = gin.Params{{Key: "id", Value: "ws-1"}}
NewTokenHandler().List(c)
if w.Code != http.StatusOK {
@@ -195,7 +186,7 @@ func TestTokenHandler_List_ScanError(t *testing.T) {
AddRow("tok-1", "abc", "not-a-timestamp", nil))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusInternalServerError {
t.Errorf("scan error must surface as 500, got %d: %s", w.Code, w.Body.String())
@@ -210,11 +201,11 @@ func TestTokenHandler_Create_RateLimited(t *testing.T) {
// Count query returns 50 (== max) → 429.
mock.ExpectQuery(`SELECT COUNT\(\*\) FROM workspace_auth_tokens`).
WithArgs(wsUUID1).
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"count"}).AddRow(50))
w := makeReq(t, NewTokenHandler().Create, "POST",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusTooManyRequests {
t.Errorf("max active tokens should 429, got %d", w.Code)
@@ -234,7 +225,7 @@ func TestTokenHandler_Create_IssueFails(t *testing.T) {
WillReturnError(errors.New("disk full"))
w := makeReq(t, NewTokenHandler().Create, "POST",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusInternalServerError {
t.Errorf("IssueToken DB error must 500, got %d", w.Code)
@@ -251,7 +242,7 @@ func TestTokenHandler_Create_HappyPath(t *testing.T) {
WillReturnResult(sqlmock.NewResult(1, 1))
w := makeReq(t, NewTokenHandler().Create, "POST",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusCreated {
t.Fatalf("expected 201, got %d: %s", w.Code, w.Body.String())
@@ -266,7 +257,7 @@ func TestTokenHandler_Create_HappyPath(t *testing.T) {
if body.AuthToken == "" {
t.Errorf("auth_token must be present and non-empty in response")
}
if body.WorkspaceID != wsUUID1 {
if body.WorkspaceID != "ws-1" {
t.Errorf("workspace_id mismatch: %q", body.WorkspaceID)
}
}
@@ -278,12 +269,12 @@ func TestTokenHandler_Revoke_HappyPath(t *testing.T) {
defer cleanup()
mock.ExpectExec(`UPDATE workspace_auth_tokens\s+SET revoked_at = now\(\)`).
WithArgs("tok-1", wsUUID1).
WithArgs("tok-1", "ws-1").
WillReturnResult(sqlmock.NewResult(0, 1))
w := makeReq(t, NewTokenHandler().Revoke, "DELETE",
"/workspaces/ws-1/tokens/tok-1", gin.Params{
{Key: "id", Value: wsUUID1},
{Key: "id", Value: "ws-1"},
{Key: "tokenId", Value: "tok-1"},
})
@@ -298,12 +289,12 @@ func TestTokenHandler_Revoke_NotFound(t *testing.T) {
// 0 rows affected → token not found OR already revoked.
mock.ExpectExec(`UPDATE workspace_auth_tokens`).
WithArgs("tok-ghost", wsUUID1).
WithArgs("tok-ghost", "ws-1").
WillReturnResult(sqlmock.NewResult(0, 0))
w := makeReq(t, NewTokenHandler().Revoke, "DELETE",
"/workspaces/ws-1/tokens/tok-ghost", gin.Params{
{Key: "id", Value: wsUUID1},
{Key: "id", Value: "ws-1"},
{Key: "tokenId", Value: "tok-ghost"},
})
@@ -321,7 +312,7 @@ func TestTokenHandler_Revoke_DBError(t *testing.T) {
w := makeReq(t, NewTokenHandler().Revoke, "DELETE",
"/workspaces/ws-1/tokens/tok-1", gin.Params{
{Key: "id", Value: wsUUID1},
{Key: "id", Value: "ws-1"},
{Key: "tokenId", Value: "tok-1"},
})
@@ -330,59 +321,6 @@ func TestTokenHandler_Revoke_DBError(t *testing.T) {
}
}
// ---- UUID validation (regression: "global" sentinel 500) ------------
// The canvas Settings → Workspace Tokens tab sent the literal sentinel
// "global" as the workspace id when no node was selected. workspace_id
// is a `uuid` column, so the query raised
// `invalid input syntax for type uuid: "global"` which leaked as an
// opaque 500. List/Create/Revoke now reject any non-UUID id with a
// clean 400 before touching the DB. No DB expectation is set on the
// mock — a DB hit would fail ExpectationsWereMet, proving short-circuit.
func TestTokenHandler_RejectsNonUUIDWorkspaceID(t *testing.T) {
h := NewTokenHandler()
cases := []struct {
name string
run func(c *gin.Context)
method string
params gin.Params
}{
{"List", h.List, "GET", gin.Params{{Key: "id", Value: "global"}}},
{"Create", h.Create, "POST", gin.Params{{Key: "id", Value: "global"}}},
{"Revoke", h.Revoke, "DELETE", gin.Params{
{Key: "id", Value: "global"},
{Key: "tokenId", Value: "tok-1"},
}},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
mock, cleanup := withMockDB(t)
defer cleanup()
w := makeReq(t, tc.run, tc.method,
"/workspaces/global/tokens", tc.params)
if w.Code != http.StatusBadRequest {
t.Fatalf("%s with non-UUID id must 400, got %d: %s",
tc.name, w.Code, w.Body.String())
}
var body struct {
Error string `json:"error"`
}
_ = json.Unmarshal(w.Body.Bytes(), &body)
if body.Error != "invalid workspace id" {
t.Errorf("%s: want error=%q, got %q",
tc.name, "invalid workspace id", body.Error)
}
// No query/exec was expected → if the handler hit the DB
// this fails, proving the guard short-circuits before SQL.
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("%s leaked a DB call past the uuid guard: %v", tc.name, err)
}
})
}
}
// Compile-time noise removal: the imports list pulls in the sql /
// driver packages and the silenced ctx so a future scenario that
// needs them doesn't have to re-add the import. Documented here so
@@ -11,7 +11,6 @@ import (
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/wsauth"
"github.com/gin-gonic/gin"
"github.com/google/uuid"
)
func init() { gin.SetMode(gin.TestMode) }
@@ -168,14 +167,11 @@ func TestTokenHandler_RevokeWrongWorkspace(t *testing.T) {
h := NewTokenHandler()
// Try to revoke with a different (valid-UUID) workspace ID that does
// not own the token — should 404. A valid UUID is required so this
// exercises the ownership branch, not the up-front uuid-shape 400.
otherWS := uuid.NewString()
// Try to revoke with a different workspace ID — should 404
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: otherWS}, {Key: "tokenId", Value: tokenID}}
c.Request = httptest.NewRequest("DELETE", "/workspaces/"+otherWS+"/tokens/"+tokenID, nil)
c.Params = gin.Params{{Key: "id", Value: "wrong-workspace-id"}, {Key: "tokenId", Value: tokenID}}
c.Request = httptest.NewRequest("DELETE", "/workspaces/wrong/tokens/"+tokenID, nil)
h.Revoke(c)
if w.Code != http.StatusNotFound {
@@ -80,15 +80,6 @@ type WorkspaceHandler struct {
asyncWG sync.WaitGroup
}
// newHandlerHook, when non-nil, is invoked for every WorkspaceHandler
// created via NewWorkspaceHandler. It is nil in production (zero cost);
// the test harness sets it so setupTestDB can drain every handler's
// in-flight async goroutines before swapping the global db.DB. Without
// this, a detached restart goroutine (maybeMarkContainerDead ->
// goAsync(RestartByID) -> runRestartCycle reads db.DB) races the
// db.DB restore in another test's t.Cleanup.
var newHandlerHook func(*WorkspaceHandler)
func (h *WorkspaceHandler) goAsync(fn func()) {
h.asyncWG.Add(1)
go func() {
@@ -117,9 +108,6 @@ func NewWorkspaceHandler(b events.EventEmitter, p *provisioner.Provisioner, plat
if p != nil {
h.provisioner = p
}
if newHandlerHook != nil {
newHandlerHook(h)
}
return h
}
@@ -237,10 +237,10 @@ func (h *WorkspaceHandler) Restart(c *gin.Context) {
// the silent-drop bugs PRs #2811/#2824 closed). RestartWorkspaceAuto
// enforces CP-FIRST ordering matching the other dispatchers — see
// docs/architecture/backends.md.
h.goAsync(func() {
go func() {
h.RestartWorkspaceAutoOpts(context.Background(), id, templatePath, configFiles, payload, resetClaudeSession)
})
h.goAsync(func() { h.sendRestartContext(id, restartData) })
}()
go h.sendRestartContext(id, restartData)
c.JSON(http.StatusOK, gin.H{"status": "provisioning", "config_dir": configLabel, "reset_session": resetClaudeSession})
}
@@ -610,9 +610,7 @@ func (h *WorkspaceHandler) runRestartCycle(workspaceID string) {
h.provisionWorkspaceAutoSync(workspaceID, "", nil, payload)
// sendRestartContext is a one-way notification to the new container; safe
// to fire async — the next restart cycle won't depend on it completing.
// Tracked via goAsync so the test harness can drain it before the
// global db.DB swap (sendRestartContext reads db.DB).
h.goAsync(func() { h.sendRestartContext(workspaceID, restartData) })
go h.sendRestartContext(workspaceID, restartData)
}
// Pause handles POST /workspaces/:id/pause
@@ -178,21 +178,12 @@ func (p *CPProvisioner) Start(ctx context.Context, cfg WorkspaceConfig) (string,
// /admin/liveness and other admin-gated platform endpoints (core#831).
// p.adminToken is read from os.Getenv("ADMIN_TOKEN") at provisioner creation;
// it is also used for CP→platform HTTP auth but those are separate concerns.
//
// Forensic #145 hardening: tenant workspaces run on EC2 via this path, so
// the SCM-write-token denylist (see buildContainerEnv) is enforced here
// too. Always build a filtered copy — never pass cfg.EnvVars through
// verbatim — so a latent persona-merged GITEA_TOKEN can't reach the
// tenant container regardless of whether ADMIN_TOKEN is set.
env := make(map[string]string, len(cfg.EnvVars)+1)
for k, v := range cfg.EnvVars {
if isSCMWriteTokenKey(k) {
log.Printf("CPProvisioner.Start: dropped SCM-write credential %q from tenant workspace env (forensic #145 guard)", k)
continue
}
env[k] = v
}
env := cfg.EnvVars
if p.adminToken != "" {
env = make(map[string]string, len(cfg.EnvVars)+1)
for k, v := range cfg.EnvVars {
env[k] = v
}
env["ADMIN_TOKEN"] = p.adminToken
}
// Collect template files and generated configs, with OFFSEC-010 guards:
@@ -643,28 +643,6 @@ func ValidateWorkspaceAccess(access, workspacePath string) error {
}
}
// scmWriteTokenKeys is the explicit denylist of environment variable names
// that carry a Git SCM *write* credential (push / merge / approve). These
// must never reach a tenant workspace container — see the forensic #145
// rationale in buildContainerEnv. Kept as an exact-match set rather than a
// substring/prefix heuristic so the guard is auditable and can't silently
// over-strip a legitimately-named var.
var scmWriteTokenKeys = map[string]struct{}{
"GITEA_TOKEN": {},
"GITHUB_TOKEN": {},
"GH_TOKEN": {}, // gh CLI honours GH_TOKEN as a GITHUB_TOKEN alias
"GITLAB_TOKEN": {},
"GL_TOKEN": {}, // glab CLI alias
"BITBUCKET_TOKEN": {},
}
// isSCMWriteTokenKey reports whether an env var name is a known Git SCM
// write credential that must be stripped from tenant workspace env.
func isSCMWriteTokenKey(key string) bool {
_, ok := scmWriteTokenKeys[key]
return ok
}
// buildContainerEnv assembles the initial environment variables injected
// into every workspace container.
//
@@ -701,21 +679,6 @@ func buildContainerEnv(cfg WorkspaceConfig) []string {
env = append(env, fmt.Sprintf("AWARENESS_URL=%s", cfg.AwarenessURL))
}
for k, v := range cfg.EnvVars {
// Forensic #145 hardening: tenant workspace containers run
// agent-controlled code and must NEVER receive a Git SCM *write*
// credential. Without merge/approve creds in-container the
// two-eyes review gate is structurally self-bypass-proof — an
// agent that forges an approval has no token to act on it. A
// latent path exists (loadPersonaEnvFile merges a per-role
// persona `GITEA_TOKEN` into cfg.EnvVars when MOLECULE_PERSONA_ROOT
// is set on a tenant host); it is inert today (persona dirs are
// operator-host-only) but unguarded. Strip SCM-write tokens here
// by construction so the invariant holds regardless of whether
// that path ever becomes reachable.
if isSCMWriteTokenKey(k) {
log.Printf("buildContainerEnv: dropped SCM-write credential %q from workspace env (forensic #145 guard)", k)
continue
}
env = append(env, fmt.Sprintf("%s=%s", k, v))
}
// Inject ADMIN_TOKEN from the platform server's environment so workspace
@@ -725,15 +725,10 @@ func TestBuildContainerEnv_AwarenessOnlyWhenBothSet(t *testing.T) {
}
func TestBuildContainerEnv_CustomEnvVarsAppended(t *testing.T) {
// NOTE: this test previously asserted GITHUB_TOKEN passed through
// verbatim. That assertion encoded the forensic #145 latent leak as
// expected behavior. Post-guard, ordinary custom env still flows but
// SCM-write credentials are stripped — see
// TestBuildContainerEnv_StripsSCMWriteTokens for the negative assertion.
cfg := WorkspaceConfig{
WorkspaceID: "ws-x",
PlatformURL: "http://localhost:8080",
EnvVars: map[string]string{"CUSTOM": "value", "ANTHROPIC_API_KEY": "sk-not-an-scm-token"},
EnvVars: map[string]string{"CUSTOM": "value", "GITHUB_TOKEN": "fake-token-for-test"},
}
env := buildContainerEnv(cfg)
seen := map[string]string{}
@@ -746,8 +741,8 @@ func TestBuildContainerEnv_CustomEnvVarsAppended(t *testing.T) {
if seen["CUSTOM"] != "value" {
t.Errorf("CUSTOM env missing, got env=%v", env)
}
if seen["ANTHROPIC_API_KEY"] != "sk-not-an-scm-token" {
t.Errorf("non-SCM custom env must still pass through, got env=%v", env)
if seen["GITHUB_TOKEN"] != "fake-token-for-test" {
t.Errorf("GITHUB_TOKEN env missing, got env=%v", env)
}
// Built-in defaults still present
if seen["MOLECULE_URL"] == "" {
@@ -755,129 +750,6 @@ func TestBuildContainerEnv_CustomEnvVarsAppended(t *testing.T) {
}
}
// ---------- forensic #145: SCM-write-token denylist guard ----------
// TestBuildContainerEnv_StripsSCMWriteTokens is the core negative
// assertion: a tenant workspace env constructed via buildContainerEnv MUST
// NOT contain any Git SCM *write* credential, regardless of how it got into
// cfg.EnvVars. This proves the two-eyes review gate stays structurally
// self-bypass-proof — an agent in-container has no merge/approve token to
// act on a forged approval. See forensic #145.
//
// This test FAILS on the pre-guard code (where buildContainerEnv passed
// cfg.EnvVars through verbatim) and PASSES once the denylist filter is in
// place — i.e. the guard is proven by construction, not by environment
// accident.
func TestBuildContainerEnv_StripsSCMWriteTokens(t *testing.T) {
scmTokens := []string{
"GITEA_TOKEN", "GITHUB_TOKEN", "GH_TOKEN",
"GITLAB_TOKEN", "GL_TOKEN", "BITBUCKET_TOKEN",
}
t.Run("normal path — SCM tokens explicitly set in EnvVars", func(t *testing.T) {
envVars := map[string]string{"CUSTOM": "ok", "ANTHROPIC_API_KEY": "sk-keep"}
for _, k := range scmTokens {
envVars[k] = "leaked-write-credential-" + k
}
cfg := WorkspaceConfig{
WorkspaceID: "ws-tenant",
PlatformURL: "http://localhost:8080",
Tier: 2,
EnvVars: envVars,
}
assertNoSCMWriteToken(t, buildContainerEnv(cfg), scmTokens)
// Sanity: non-SCM custom env is NOT collateral-damaged by the filter.
if !envContains(buildContainerEnv(cfg), "CUSTOM=ok") {
t.Errorf("filter must not strip non-SCM custom env")
}
if !envContains(buildContainerEnv(cfg), "ANTHROPIC_API_KEY=sk-keep") {
t.Errorf("filter must not strip non-SCM API keys")
}
})
t.Run("persona-file path — simulates loadPersonaEnvFile merge", func(t *testing.T) {
// The latent path: handlers.loadPersonaEnvFile() merges a per-role
// persona env file (carrying GITEA_USER, GITEA_TOKEN, …) into the
// workspace env map when MOLECULE_PERSONA_ROOT is set on a tenant
// host. We can't invoke that cross-package helper here, but its
// observable effect is exactly "a GITEA_TOKEN appears in
// cfg.EnvVars". Constructing that condition directly proves the
// guard holds even if the latent path becomes reachable.
cfg := WorkspaceConfig{
WorkspaceID: "ws-tenant",
PlatformURL: "http://localhost:8080",
Tier: 2,
EnvVars: map[string]string{
// Persona identity fields that are SAFE to keep (read-only
// identity, not a write credential):
"GITEA_USER": "backend-engineer",
"GITEA_USER_EMAIL": "backend-engineer@agents.moleculesai.app",
// The credential that must be stripped:
"GITEA_TOKEN": "persona-merged-write-pat",
"GITEA_TOKEN_SCOPES": "write:repository",
},
}
got := buildContainerEnv(cfg)
assertNoSCMWriteToken(t, got, scmTokens)
// Non-credential persona identity may still flow through — only the
// write token is the denied surface.
if !envContains(got, "GITEA_USER=backend-engineer") {
t.Errorf("non-credential persona identity (GITEA_USER) should not be stripped")
}
})
}
// TestCPProvisionerEnv_StripsSCMWriteTokens covers the tenant-EC2 path:
// CPProvisioner.Start builds the env map the control plane forwards to the
// EC2 workspace container. The same forensic #145 denylist must hold there.
func TestCPProvisionerEnv_StripsSCMWriteTokens(t *testing.T) {
// isSCMWriteTokenKey is the single source of truth shared by both
// buildContainerEnv (local Docker) and CPProvisioner.Start (tenant EC2).
// Assert it classifies every known SCM-write var as denied and leaves
// ordinary / read-only-identity vars alone.
for _, k := range []string{
"GITEA_TOKEN", "GITHUB_TOKEN", "GH_TOKEN",
"GITLAB_TOKEN", "GL_TOKEN", "BITBUCKET_TOKEN",
} {
if !isSCMWriteTokenKey(k) {
t.Errorf("isSCMWriteTokenKey(%q) = false, want true (SCM-write credential must be denied)", k)
}
}
for _, k := range []string{
"GITEA_USER", "GITEA_USER_EMAIL", "ANTHROPIC_API_KEY",
"CUSTOM", "PLATFORM_URL", "ADMIN_TOKEN", "",
} {
if isSCMWriteTokenKey(k) {
t.Errorf("isSCMWriteTokenKey(%q) = true, want false (must not over-strip non-SCM env)", k)
}
}
}
func assertNoSCMWriteToken(t *testing.T, env []string, scmTokens []string) {
t.Helper()
for _, e := range env {
key := e
if i := strings.IndexByte(e, '='); i >= 0 {
key = e[:i]
}
for _, banned := range scmTokens {
if key == banned {
t.Errorf("SCM-write credential %q leaked into workspace env (forensic #145 invariant violated): %q", banned, e)
}
}
}
}
func envContains(env []string, want string) bool {
for _, e := range env {
if e == want {
return true
}
}
return false
}
// ---------- buildWorkspaceMount — #65 workspace_access ----------
func TestBuildWorkspaceMount_SelectionMatrix(t *testing.T) {
@@ -1,226 +0,0 @@
// Package secrets provides the canonical SSOT for credential-shaped
// regex patterns used by:
//
// - the CI `Secret scan` workflow (.gitea/workflows/secret-scan.yml)
// - the runtime's bundled pre-commit hook
// (molecule-ai-workspace-runtime/molecule_runtime/scripts/pre-commit-checks.sh)
// - the upcoming Phase 2b docker-exec Files API backend, which has
// to refuse to surface files whose path OR content matches a
// credential shape (RFC internal#425, Hongming 2026-05-15)
//
// Before this package, the same regex set lived as duplicate bash
// arrays in two unrelated repos; adding a pattern required editing
// both, and pattern drift was caught only via secret-scan workflow
// failures on PRs that had unrelated changes (#2090-class incident
// vector). Centralising in Go makes the Files API the SSOT, with the
// YAML + bash arrays generated/asserted from this package so drift
// is detected at CI time, not at exfiltration time.
//
// This file is Phase 2a of the internal#425 RFC. Phase 2b will import
// `Patterns` from `template_files_docker_exec.go` to gate
// `listFilesViaDockerExec` / `readFileViaDockerExec` against
// secret-shaped paths AND content. Until 2b lands, the package has
// one consumer: this package's own unit tests, which pin the regex
// strings so a refactor that drops or weakens one is caught here.
package secrets
import (
"fmt"
"regexp"
"sync"
)
// Pattern is one named credential shape — a human label plus the
// compiled regex. The label appears in CI error output ("matched:
// github-pat") so an operator can identify the family without seeing
// the actual matched bytes (echoing the bytes widens the blast radius
// per the secret-scan workflow's recovery prose).
type Pattern struct {
// Name is a short kebab-case identifier (e.g. "github-pat",
// "anthropic-api-key"). Stable across versions — consumers may
// switch on it.
Name string
// Description is a one-line human-readable explanation of what
// the pattern matches. Used in CI error messages and the Files
// API "<denied: secret-shape>" placeholder rationale.
Description string
// regexSource is the regex literal in Go-RE2 syntax. Stored as a
// string so the slice declaration below stays readable; compiled
// once via sync.Once into a *regexp.Regexp.
regexSource string
}
// Patterns is the canonical credential-shape regex set.
//
// Adding a pattern here:
//
// 1. Add a new Pattern{} entry below with a kebab-case Name, a
// one-line Description, and the regex literal. Anchor on a
// low-false-positive prefix.
// 2. Add a positive + negative test case in patterns_test.go.
// 3. Mirror the regex string into:
// a. .gitea/workflows/secret-scan.yml SECRET_PATTERNS array
// b. molecule-ai-workspace-runtime/molecule_runtime/scripts/pre-commit-checks.sh
// (or wait for the codegen target that consumes this slice — TBD
// follow-up; tracked in the Phase 2a PR description.)
//
// The order is: alphabetical within each provider family, families
// grouped by ecosystem (GitHub family, AI-provider family, chat
// family, cloud family). Keep this stable so diffs are reviewable.
var Patterns = []Pattern{
// --- GitHub token family ---
{
Name: "github-pat-classic",
Description: "GitHub personal access token (classic)",
regexSource: `ghp_[A-Za-z0-9]{36,}`,
},
{
Name: "github-app-installation-token",
Description: "GitHub App installation token (#2090 vector)",
regexSource: `ghs_[A-Za-z0-9]{36,}`,
},
{
Name: "github-oauth-user-to-server",
Description: "GitHub OAuth user-to-server token",
regexSource: `gho_[A-Za-z0-9]{36,}`,
},
{
Name: "github-oauth-user",
Description: "GitHub OAuth user token",
regexSource: `ghu_[A-Za-z0-9]{36,}`,
},
{
Name: "github-oauth-refresh",
Description: "GitHub OAuth refresh token",
regexSource: `ghr_[A-Za-z0-9]{36,}`,
},
{
Name: "github-pat-fine-grained",
Description: "GitHub fine-grained personal access token",
regexSource: `github_pat_[A-Za-z0-9_]{82,}`,
},
// --- AI-provider API key family ---
{
Name: "anthropic-api-key",
Description: "Anthropic API key",
regexSource: `sk-ant-[A-Za-z0-9_-]{40,}`,
},
{
Name: "openai-project-key",
Description: "OpenAI project API key",
regexSource: `sk-proj-[A-Za-z0-9_-]{40,}`,
},
{
Name: "openai-service-account-key",
Description: "OpenAI service-account API key",
regexSource: `sk-svcacct-[A-Za-z0-9_-]{40,}`,
},
{
Name: "minimax-api-key",
Description: "MiniMax API key (F1088 vector)",
regexSource: `sk-cp-[A-Za-z0-9_-]{60,}`,
},
// --- Chat-platform token family ---
{
Name: "slack-token",
Description: "Slack token (xoxb/xoxa/xoxp/xoxr/xoxs)",
regexSource: `xox[baprs]-[A-Za-z0-9-]{20,}`,
},
// --- Cloud-provider credential family ---
{
Name: "aws-access-key-id",
Description: "AWS access key ID",
regexSource: `AKIA[0-9A-Z]{16}`,
},
{
Name: "aws-sts-temp-access-key-id",
Description: "AWS STS temporary access key ID",
regexSource: `ASIA[0-9A-Z]{16}`,
},
}
// compiledOnce protects the lazy build of compiledPatterns. We compile
// lazily so package init is cheap; callers pay only on first match
// (typically once per workspace-server boot).
var (
compiledOnce sync.Once
compiledPatterns []*compiledPattern
compileErr error
)
type compiledPattern struct {
Name string
Description string
Re *regexp.Regexp
}
// compileAll compiles every Pattern.regexSource into a *regexp.Regexp.
// Called once via compiledOnce. Any compile failure here is a build
// bug (the unit tests assert each regex compiles) — surfacing via
// returned error so callers don't panic in request handling.
func compileAll() {
out := make([]*compiledPattern, 0, len(Patterns))
for _, p := range Patterns {
re, err := regexp.Compile(p.regexSource)
if err != nil {
compileErr = fmt.Errorf("secrets: pattern %q failed to compile: %w", p.Name, err)
return
}
out = append(out, &compiledPattern{Name: p.Name, Description: p.Description, Re: re})
}
compiledPatterns = out
}
// ScanBytes returns a non-nil Match if any pattern matches anywhere
// inside b. Returns (nil, nil) on no match. Returns (nil, err) only
// if a regex in the package fails to compile — that's a build bug,
// not a runtime data issue.
//
// Match contains the pattern Name + Description so the caller can
// emit a path-or-content-denial rationale WITHOUT round-tripping the
// matched bytes (which would defeat the purpose). The matched bytes
// stay inside this function.
//
// The Files API Phase 2b backend will call ScanBytes on:
//
// - the absolute path string (catches a file literally named
// `ghs_abc.txt`)
// - the file content (catches a credential pasted into a workspace
// file by an agent or user — the Files API refuses to surface it
// and the canvas renders "<denied: secret-shape>")
//
// Ordering: patterns are tried in declaration order. First match
// wins. This means narrower patterns (e.g. `sk-svcacct-…`) should
// appear in `Patterns` before broader ones (`sk-…`) — today there's
// no overlap, so order is descriptive only.
func ScanBytes(b []byte) (*Match, error) {
compiledOnce.Do(compileAll)
if compileErr != nil {
return nil, compileErr
}
for _, cp := range compiledPatterns {
if cp.Re.Match(b) {
return &Match{Name: cp.Name, Description: cp.Description}, nil
}
}
return nil, nil
}
// ScanString is the string-input convenience wrapper around ScanBytes.
// Identical semantics — the body never copies, []byte(s) is a
// zero-copy reinterpret for the regex matcher.
func ScanString(s string) (*Match, error) {
return ScanBytes([]byte(s))
}
// Match describes which pattern caught a value. Deliberately does
// NOT include the matched substring — callers must not echo it.
type Match struct {
// Name is the pattern's kebab-case identifier (e.g. "github-pat-classic").
Name string
// Description is the human-readable line for UI / log surfaces.
Description string
}
@@ -1,189 +0,0 @@
package secrets
import (
"strings"
"testing"
)
// TestEveryPatternCompiles pins that every Pattern.regexSource is a
// valid Go-RE2 expression. Without this, a bad regex would silently
// disable ScanBytes for everything after it (the lazy compile would
// set compileErr and ScanBytes would return that error every call).
func TestEveryPatternCompiles(t *testing.T) {
for _, p := range Patterns {
if p.Name == "" {
t.Errorf("pattern with empty Name: regex=%q", p.regexSource)
}
if p.Description == "" {
t.Errorf("pattern %q has empty Description", p.Name)
}
}
// Force compile + check error.
if _, err := ScanBytes([]byte("placeholder")); err != nil {
t.Fatalf("ScanBytes init failed: %v", err)
}
}
// TestNoDuplicateNames — a duplicate pattern Name would make the
// "first match wins" semantics surprising to readers and any caller
// switching on Match.Name (none today but adding the guard is cheap).
func TestNoDuplicateNames(t *testing.T) {
seen := map[string]bool{}
for _, p := range Patterns {
if seen[p.Name] {
t.Errorf("duplicate pattern Name: %q", p.Name)
}
seen[p.Name] = true
}
}
// TestKnownPatternsAllPresent — pins which specific Name values are
// expected. A future refactor that renames or removes one without
// updating consumers (CI workflow, runtime pre-commit hook, Files
// API Phase 2b backend) would silently widen the leak surface.
// Failing here forces the rename to be intentional.
func TestKnownPatternsAllPresent(t *testing.T) {
expected := []string{
"github-pat-classic",
"github-app-installation-token",
"github-oauth-user-to-server",
"github-oauth-user",
"github-oauth-refresh",
"github-pat-fine-grained",
"anthropic-api-key",
"openai-project-key",
"openai-service-account-key",
"minimax-api-key",
"slack-token",
"aws-access-key-id",
"aws-sts-temp-access-key-id",
}
got := map[string]bool{}
for _, p := range Patterns {
got[p.Name] = true
}
for _, want := range expected {
if !got[want] {
t.Errorf("expected pattern %q missing from Patterns slice", want)
}
}
}
// TestPositiveMatches — for each pattern, supply a representative
// shape and assert ScanBytes returns a Match with the right Name.
// These are TEST FIXTURES, not real credentials — each is the
// pattern's prefix + a long-enough trailing run of placeholder chars.
// `EXAMPLE` is sprinkled in to make grep-finds in CI logs obviously
// fake to a human reader (matches saved memory
// feedback_assert_exact_not_substring: tighten by Name not body).
func TestPositiveMatches(t *testing.T) {
cases := []struct {
fixture string
expectedName string
}{
{"ghp_" + "EXAMPLE111122223333444455556666777788889999", "github-pat-classic"},
{"ghs_" + "EXAMPLE111122223333444455556666777788889999", "github-app-installation-token"},
{"gho_" + "EXAMPLE111122223333444455556666777788889999", "github-oauth-user-to-server"},
{"ghu_" + "EXAMPLE111122223333444455556666777788889999", "github-oauth-user"},
{"ghr_" + "EXAMPLE111122223333444455556666777788889999", "github-oauth-refresh"},
{"github_pat_EXAMPLE" + strings.Repeat("1", 80), "github-pat-fine-grained"},
{"sk-ant-EXAMPLE" + strings.Repeat("1", 40), "anthropic-api-key"},
{"sk-proj-EXAMPLE" + strings.Repeat("1", 40), "openai-project-key"},
{"sk-svcacct-EXAMPLE" + strings.Repeat("1", 40), "openai-service-account-key"},
{"sk-cp-EXAMPLE" + strings.Repeat("1", 60), "minimax-api-key"},
{"xoxb-" + strings.Repeat("a", 25), "slack-token"},
{"xoxa-" + strings.Repeat("a", 25), "slack-token"},
// AWS regex requires [0-9A-Z]{16} — uppercase + digits only.
{"AKIA1234567890ABCDEF", "aws-access-key-id"},
{"ASIA1234567890ABCDEF", "aws-sts-temp-access-key-id"},
}
for _, tc := range cases {
t.Run(tc.expectedName, func(t *testing.T) {
m, err := ScanBytes([]byte(tc.fixture))
if err != nil {
t.Fatalf("ScanBytes(%q) errored: %v", tc.fixture, err)
}
if m == nil {
t.Fatalf("ScanBytes(%q) returned no match — expected %q", tc.fixture, tc.expectedName)
}
if m.Name != tc.expectedName {
t.Errorf("ScanBytes(%q) matched %q; expected %q", tc.fixture, m.Name, tc.expectedName)
}
})
}
}
// TestNegativeShapes — strings that look credential-adjacent but
// shouldn't match (too short, wrong prefix, missing trailing bytes).
// Failing here means a pattern is too loose, which would generate
// false-positive denial in Files API and false-positive workflow
// failures in CI.
func TestNegativeShapes(t *testing.T) {
cases := []string{
// Too-short variants — anchored on the length suffix.
"ghp_tooshort",
"ghs_alsoshort1234",
"github_pat_short",
"sk-ant-short",
"sk-cp-not-enough-bytes-here",
// Looks like one of the prefixes but isn't (different letter).
"gha_EXAMPLE_thirty_six_or_more_chars_here_xxx",
// Slack family — wrong letter after xox.
"xoxz-aaaaaaaaaaaaaaaaaaaaaaaaa",
// AWS-shaped but wrong length suffix.
"AKIATOOSHORT",
// Empty / whitespace.
"",
" ",
// Plain prose mentioning the prefix as part of a longer word.
"see also `ghp_HOWTO.md` in the repo",
}
for _, c := range cases {
t.Run(c, func(t *testing.T) {
m, err := ScanBytes([]byte(c))
if err != nil {
t.Fatalf("ScanBytes(%q) errored: %v", c, err)
}
if m != nil {
t.Errorf("ScanBytes(%q) unexpectedly matched %q", c, m.Name)
}
})
}
}
// TestScanString_NoOp — sanity-check ScanString is the zero-copy
// wrapper around ScanBytes. Without this, a future refactor that
// makes ScanString do its own thing (e.g. accidentally normalise
// case) would diverge silently.
func TestScanString_NoOp(t *testing.T) {
in := "ghp_" + "EXAMPLE111122223333444455556666777788889999"
m1, err1 := ScanBytes([]byte(in))
if err1 != nil {
t.Fatalf("ScanBytes errored: %v", err1)
}
m2, err2 := ScanString(in)
if err2 != nil {
t.Fatalf("ScanString errored: %v", err2)
}
if m1 == nil || m2 == nil {
t.Fatalf("expected matches; got bytes=%+v string=%+v", m1, m2)
}
if m1.Name != m2.Name {
t.Errorf("ScanString and ScanBytes returned different Names: %q vs %q", m1.Name, m2.Name)
}
}
// TestMatch_NoRoundtrip — assert the Match struct does NOT include
// the matched substring as a field. Adding such a field would
// regress the "matched bytes never leave ScanBytes" invariant that
// makes this package safe to call from log/UI surfaces. This is a
// reflection-light contract test — checks the field names statically.
func TestMatch_NoRoundtrip(t *testing.T) {
var m Match
// If someone adds a `Matched string` (or similar) field, this
// test reads as the canonical place to update + reconsider.
_ = m.Name
_ = m.Description
// The two-field shape is part of the public contract; new fields
// require deliberation about whether they leak the secret value.
}
-13
View File
@@ -62,19 +62,6 @@ RUN chmod +x ./scripts/molecule-git-token-helper.sh
COPY scripts/molecule-gh-token-refresh.sh ./scripts/
RUN chmod +x ./scripts/molecule-gh-token-refresh.sh
# Generic GIT_ASKPASS helper. Reads HTTPS Basic-Auth credentials from env
# vars (GIT_HTTP_USERNAME / GIT_HTTP_PASSWORD, with GITEA_USER / GITEA_TOKEN
# as fallback) and emits them on the git credential-prompt protocol so
# container-side `git` can authenticate to any private HTTPS remote
# without on-disk .gitconfig / .git-credentials mutation. The platform
# provisioner sets GIT_ASKPASS=/usr/local/bin/molecule-askpass via
# applyAgentGitIdentity (workspace-server/internal/handlers/agent_git_identity.go).
# Filename is the only project-specific marker; the script body contains
# no vendor literals and is identical to the script shipped in each
# open-source workspace template (scripts/git-askpass.sh).
COPY scripts/molecule-askpass /usr/local/bin/molecule-askpass
RUN chmod +x /usr/local/bin/molecule-askpass
# Dirs and permissions
RUN mkdir -p /workspace /plugins /home/agent/.claude /home/agent/.config /home/agent/.local \
/home/agent/.molecule-token-cache && \
-12
View File
@@ -35,14 +35,12 @@ from a2a_tools import (
tool_commit_memory,
tool_delegate_task,
tool_delegate_task_async,
tool_get_runtime_identity,
tool_get_workspace_info,
tool_inbox_peek,
tool_inbox_pop,
tool_list_peers,
tool_recall_memory,
tool_send_message_to_user,
tool_update_agent_card,
tool_wait_for_message,
)
from platform_tools.registry import TOOLS as _PLATFORM_TOOL_SPECS
@@ -132,10 +130,6 @@ async def handle_tool_call(name: str, arguments: dict) -> str:
return await tool_get_workspace_info(
source_workspace_id=arguments.get("source_workspace_id") or None,
)
elif name == "get_runtime_identity":
return await tool_get_runtime_identity()
elif name == "update_agent_card":
return await tool_update_agent_card(arguments.get("card"))
elif name == "commit_memory":
return await tool_commit_memory(
arguments.get("content", ""),
@@ -172,12 +166,6 @@ async def handle_tool_call(name: str, arguments: dict) -> str:
arguments.get("message", ""),
workspace_id=arguments.get("workspace_id") or None,
)
elif name == "get_runtime_identity":
return await tool_get_runtime_identity()
elif name == "update_agent_card":
return await tool_update_agent_card(
arguments.get("card"),
)
return f"Unknown tool: {name}"
-12
View File
@@ -167,15 +167,3 @@ from a2a_tools_inbox import ( # noqa: E402 (import after the top-of-module imp
tool_inbox_pop,
tool_wait_for_message,
)
# Identity tool handlers — extracted to a2a_tools_identity. Ports the
# two T4-tier MCP tools (``tool_get_runtime_identity`` +
# ``tool_update_agent_card``) from molecule-ai-workspace-runtime PR#17.
# That repo is mirror-only (reference_runtime_repo_is_mirror_only);
# this is the canonical edit point, and the wheel mirror is
# regenerated by publish-runtime.yml on merge.
from a2a_tools_identity import ( # noqa: E402 (import after the top-of-module imports)
tool_get_runtime_identity,
tool_update_agent_card,
)
-187
View File
@@ -1,187 +0,0 @@
"""Identity tool handlers — single-concern slice of the a2a_tools surface.
Owns the two MCP tools that close the T4-tier workspace owner-permission
gaps reported via the canvas:
* ``tool_get_runtime_identity`` — env-only; returns model, model_provider,
molecule_model, anthropic_base_url, tier, workspace_id, runtime
(ADAPTER_MODULE). No HTTP call. Always permitted by RBAC — even
read-only agents may know what model they are.
* ``tool_update_agent_card`` — POSTs the card to ``/registry/update-card``
with the workspace's own bearer (same auth path as ``tool_commit_memory``
via ``a2a_tools_rbac.auth_headers_for_heartbeat``). The platform
replaces the stored card and broadcasts an ``agent_card_updated``
event so the canvas reflects the new card live. Gated on
``memory.write`` capability via the existing RBAC permission map so
read-only roles can't silently rewrite the platform card.
Both originated as a port of molecule-ai-workspace-runtime PR#17
(``feat(mcp): add update_agent_card + get_runtime_identity tools``).
The mirror-only PR#17 was closed without merge per
``reference_runtime_repo_is_mirror_only``; the canonical edit point is
this monorepo at ``workspace/`` and the wheel mirror is regenerated
automatically by the publish-runtime workflow.
Imports the auth-header primitive from ``a2a_tools_rbac`` (iter 4a) —
NOT from ``a2a_tools`` — to avoid a circular import with the
kitchen-sink re-export module.
"""
from __future__ import annotations
import json
import os
from typing import Any
import httpx
from a2a_client import PLATFORM_URL
from a2a_tools_rbac import (
auth_headers_for_heartbeat as _auth_headers_for_heartbeat,
check_memory_write_permission as _check_memory_write_permission,
)
def _runtime_identity_payload() -> dict[str, Any]:
"""Build the identity dict — env-only, no I/O.
Factored out from ``tool_get_runtime_identity`` so tests can assert
against the exact key set without re-parsing JSON. The MCP tool
handler ``tool_get_runtime_identity`` is the only public caller in
production; tests call this helper directly.
"""
return {
"model": os.environ.get("MODEL", ""),
"model_provider": os.environ.get("MODEL_PROVIDER", ""),
"molecule_model": os.environ.get("MOLECULE_MODEL", ""),
"anthropic_base_url": os.environ.get("ANTHROPIC_BASE_URL", ""),
"tier": os.environ.get("TIER", ""),
"workspace_id": os.environ.get("WORKSPACE_ID", ""),
# Adapter module is the closest thing the runtime has to a
# "template slug" — e.g. "adapter" for claude-code-default,
# "hermes" for hermes-template, etc. Picked from
# $ADAPTER_MODULE env baked by each template's Dockerfile.
"runtime": os.environ.get("ADAPTER_MODULE", ""),
}
async def tool_get_runtime_identity() -> str:
"""Return this runtime's identity — model, provider, tier, IDs.
Env-only; no HTTP call. Useful so the agent can answer "what model
am I?" correctly instead of guessing from a stale system prompt
that the operator may have changed between boots.
Returns the identity as a JSON-encoded string (the dispatch contract
every MCP tool in this module follows). Tests that want to assert
individual fields can call ``_runtime_identity_payload()`` directly,
or ``json.loads`` the return value.
Always permitted by RBAC — there is no sensitive information here
that isn't already available to the process via ``os.environ``.
The point of the tool is to surface those env values to the agent
layer in a stable, documented shape rather than expecting every
agent runtime to know to ``echo $MODEL``.
"""
return json.dumps(_runtime_identity_payload(), indent=2)
async def tool_update_agent_card(card: Any) -> str:
"""Update this workspace's agent_card on the platform.
POSTs the provided card to ``/registry/update-card`` with the
workspace's own bearer token (same auth path as ``tool_commit_memory``
and ``tool_get_workspace_info``). The platform validates required
fields server-side, replaces the stored card, and broadcasts an
``agent_card_updated`` event so the canvas updates live.
Args:
card: A JSON-serialisable object (typically a dict) holding the
new card. The platform validates required fields server-side.
Returns:
JSON-encoded string. Body:
- ``{"success": true, "status": "updated"}`` on success;
- ``{"success": false, "error": "<msg>", "status_code": <int>}``
on platform error;
- ``{"success": false, "error": "<reason>"}`` on local validation
(non-dict card, missing WORKSPACE_ID, network error).
Permission gate: this tool requires the ``memory.write`` RBAC
capability — same gate as ``tool_commit_memory``. The check runs
inline rather than at the dispatcher layer to keep ``a2a_mcp_server``
permission-agnostic (the gate sits with the implementation, not the
transport). Read-only roles get a clear error string back instead
of a 403 from the platform.
We re-check ``isinstance(card, dict)`` here defensively rather than
trust the MCP schema validator alone — the schema only constrains
the transport, not the in-process call surface used by tests and
sibling modules.
"""
payload = await _update_agent_card_impl(card)
return json.dumps(payload, indent=2)
async def _update_agent_card_impl(card: Any) -> dict[str, Any]:
"""Dict-returning core of ``tool_update_agent_card``.
Split out so tests can assert against the raw dict shape (status
codes, error messages) without re-parsing JSON on every assertion.
The string-returning ``tool_update_agent_card`` is a thin wrapper
invoked by the MCP dispatcher.
"""
# RBAC: require memory.write permission. Same gate as
# tool_commit_memory (the agent already needs this capability to
# persist anything outbound). Read-only roles can still call
# get_runtime_identity / get_workspace_info to introspect — those
# are env-only / read-only and have no inline gate.
if not _check_memory_write_permission():
return {
"success": False,
"error": (
"RBAC — this workspace does not have the 'memory.write' "
"permission required to update the agent_card."
),
}
if not isinstance(card, dict):
return {
"success": False,
"error": "card must be a JSON object (dict)",
}
ws_id = os.environ.get("WORKSPACE_ID", "")
if not ws_id:
return {
"success": False,
"error": "WORKSPACE_ID env not set; cannot identify caller",
}
try:
async with httpx.AsyncClient(timeout=10.0) as client:
resp = await client.post(
f"{PLATFORM_URL}/registry/update-card",
json={"workspace_id": ws_id, "agent_card": card},
headers=_auth_headers_for_heartbeat(),
)
if resp.status_code == 200:
body: dict[str, Any] = {}
try:
body = resp.json()
except Exception:
pass
return {
"success": True,
"status": body.get("status", "updated"),
}
# Non-200 — surface what the platform returned.
error_msg = ""
try:
error_msg = resp.json().get("error", "") or resp.text
except Exception:
error_msg = resp.text
return {
"success": False,
"status_code": resp.status_code,
"error": error_msg,
}
except Exception as e:
return {"success": False, "error": f"network error: {e}"}
-10
View File
@@ -340,16 +340,6 @@ _CLI_A2A_COMMAND_KEYWORDS: dict[str, str | None] = {
"delegate_task_async": "delegate --async",
"check_task_status": "status",
"get_workspace_info": "info",
# `get_runtime_identity` + `update_agent_card` are MCP-first
# capabilities — the CLI subprocess interface doesn't expose them
# today. `get_runtime_identity` is env-only and an agent on a
# CLI-only runtime can already `echo $MODEL` etc, so there's no
# functional gap. `update_agent_card` requires a JSON object
# argument that wouldn't survive a positional-arg shell invocation
# cleanly. Mapped to None — flip to a keyword if a2a_cli grows
# `identity` / `card` subcommands in the future.
"get_runtime_identity": None,
"update_agent_card": None,
# `broadcast_message` is not exposed via the CLI subprocess interface
# today — it's an MCP-first capability. If a2a_cli grows a `broadcast`
# subcommand, map it here and the alignment test will gate the change.
-59
View File
@@ -57,14 +57,12 @@ from a2a_tools import (
tool_commit_memory,
tool_delegate_task,
tool_delegate_task_async,
tool_get_runtime_identity,
tool_get_workspace_info,
tool_inbox_peek,
tool_inbox_pop,
tool_list_peers,
tool_recall_memory,
tool_send_message_to_user,
tool_update_agent_card,
tool_wait_for_message,
)
@@ -291,61 +289,6 @@ _GET_WORKSPACE_INFO = ToolSpec(
section=A2A_SECTION,
)
_GET_RUNTIME_IDENTITY = ToolSpec(
name="get_runtime_identity",
short=(
"Return this runtime's identity — model, model_provider, tier, "
"workspace_id, runtime template. Reads from process env; no HTTP call."
),
when_to_use=(
"Use this to answer 'what model am I?' truthfully instead of "
"guessing from a stale system prompt — the operator may have "
"routed you to a different model via persona env between boots. "
"Always permitted by RBAC: even read-only agents may know what "
"model they are. Distinct from get_workspace_info — that one "
"calls the platform for ID/role/tier/parent (workspace metadata); "
"this one returns the live process env (MODEL, MODEL_PROVIDER, "
"MOLECULE_MODEL, ANTHROPIC_BASE_URL, TIER, WORKSPACE_ID, "
"ADAPTER_MODULE)."
),
input_schema={"type": "object", "properties": {}},
impl=tool_get_runtime_identity,
section=A2A_SECTION,
)
_UPDATE_AGENT_CARD = ToolSpec(
name="update_agent_card",
short=(
"Replace this workspace's agent_card on the platform. The "
"platform validates required fields and broadcasts an "
"agent_card_updated event so the canvas reflects the change live."
),
when_to_use=(
"Use when the workspace's capabilities, skills, description, or "
"name change and the canvas display needs to follow. The "
"platform stores the new card and pushes an "
"``agent_card_updated`` event to subscribers. Gated behind the "
"``memory.write`` RBAC capability — read-only roles cannot "
"rewrite the card. Tier-1+ owners always have this capability."
),
input_schema={
"type": "object",
"properties": {
"card": {
"type": "object",
"description": (
"The new agent_card object (name, version, "
"description, skills, etc). Server-side validation "
"rejects payloads missing required fields."
),
},
},
"required": ["card"],
},
impl=tool_update_agent_card,
section=A2A_SECTION,
)
_BROADCAST_MESSAGE = ToolSpec(
name="broadcast_message",
short=(
@@ -699,8 +642,6 @@ TOOLS: list[ToolSpec] = [
_CHECK_TASK_STATUS,
_LIST_PEERS,
_GET_WORKSPACE_INFO,
_GET_RUNTIME_IDENTITY,
_UPDATE_AGENT_CARD,
_BROADCAST_MESSAGE,
_SEND_MESSAGE_TO_USER,
# Inbox (standalone-only; in-container returns informational error)
-35
View File
@@ -1,35 +0,0 @@
#!/bin/sh
# git-askpass helper. Reads HTTPS Basic-Auth credentials from env vars so
# the deployer can wire git authentication for any private remote without
# touching ~/.gitconfig or ~/.git-credentials inside the container.
#
# Wire-up: set GIT_ASKPASS=/usr/local/bin/molecule-askpass in the
# container env, then export GIT_HTTP_USERNAME / GIT_HTTP_PASSWORD (or the
# GITEA_USER / GITEA_TOKEN fallback pair). When git encounters an HTTPS
# auth challenge on a host that has no credential.helper configured for
# it, git invokes GIT_ASKPASS twice — once with a "Username for ..."
# prompt and once with a "Password for ..." prompt. We pattern-match on
# that prompt and emit the matching env var.
#
# No hardcoded hostnames or vendor names — the deployer decides which
# host these credentials apply to by virtue of setting GIT_ASKPASS only
# when the target remote is in scope. The helper itself is reusable for
# any HTTPS git remote.
#
# Failure mode: if the env vars are unset, we emit an empty string and
# let git surface "Authentication failed" — this is intentional, so a
# misconfigured deployment fails loudly at first push instead of silently
# falling through to an unrelated credential chain.
case "$1" in
Username*)
printf '%s\n' "${GIT_HTTP_USERNAME:-${GITEA_USER:-}}"
;;
Password*)
printf '%s\n' "${GIT_HTTP_PASSWORD:-${GITEA_TOKEN:-}}"
;;
*)
# Unknown prompt — emit empty and let git decide.
printf '\n'
;;
esac
@@ -5,8 +5,6 @@
- **check_task_status**: Poll the status of a task started with delegate_task_async; returns result when done.
- **list_peers**: List the workspaces this agent can communicate with — name, ID, status, role for each.
- **get_workspace_info**: Get this workspace's own info — ID, name, role, tier, parent, status.
- **get_runtime_identity**: Return this runtime's identity — model, model_provider, tier, workspace_id, runtime template. Reads from process env; no HTTP call.
- **update_agent_card**: Replace this workspace's agent_card on the platform. The platform validates required fields and broadcasts an agent_card_updated event so the canvas reflects the change live.
- **broadcast_message**: Send a message to ALL agent workspaces in the org simultaneously. Requires broadcast_enabled=true on this workspace (set by user/admin).
- **send_message_to_user**: Send a message directly to the user's canvas chat — pushed instantly via WebSocket. Use this to: (1) acknowledge a task immediately ('Got it, I'll start working on this'), (2) send interim progress updates while doing long work, (3) deliver follow-up results after delegation completes, (4) attach files (zip, pdf, csv, image) for the user to download via the `attachments` field (NEVER paste file URLs in `message`). The message appears in the user's chat as if you're proactively reaching out.
- **wait_for_message**: Block until the next inbound message (canvas user OR peer agent) arrives, or until ``timeout_secs`` elapses.
@@ -29,12 +27,6 @@ Call this first when you need to delegate but don't know the target's ID. Access
### get_workspace_info
Use to introspect your own identity (e.g. before reporting back to the user, or to determine whether you're a tier-0 root that can write GLOBAL memory).
### get_runtime_identity
Use this to answer 'what model am I?' truthfully instead of guessing from a stale system prompt — the operator may have routed you to a different model via persona env between boots. Always permitted by RBAC: even read-only agents may know what model they are. Distinct from get_workspace_info — that one calls the platform for ID/role/tier/parent (workspace metadata); this one returns the live process env (MODEL, MODEL_PROVIDER, MOLECULE_MODEL, ANTHROPIC_BASE_URL, TIER, WORKSPACE_ID, ADAPTER_MODULE).
### update_agent_card
Use when the workspace's capabilities, skills, description, or name change and the canvas display needs to follow. The platform stores the new card and pushes an ``agent_card_updated`` event to subscribers. Gated behind the ``memory.write`` RBAC capability — read-only roles cannot rewrite the card. Tier-1+ owners always have this capability.
### broadcast_message
Use for urgent, org-wide signals: critical status changes, emergency stop instructions, coordinated task announcements. Every non-removed workspace receives the message in its activity log (poll-mode agents see it on their next poll; push-mode canvases get a real-time banner). This tool returns an error if broadcast_enabled is false — a user or admin must enable it via the workspace abilities settings first.
-390
View File
@@ -1,390 +0,0 @@
"""Tests for ``tool_get_runtime_identity`` and ``tool_update_agent_card``.
These two MCP tools close the T4-tier workspace owner-permission gaps
reported via the canvas:
- the agent could not update its own ``agent_card`` (no MCP tool
wrapped the existing ``POST /registry/update-card`` endpoint);
- the agent could not identify which model it was running (the
``MODEL`` env var is injected by ``provisioner.workspace_provision``
but nothing surfaced it back to the agent).
Ported from molecule-ai-workspace-runtime PR#17 (mirror-only repo;
canonical edit point per ``reference_runtime_repo_is_mirror_only``).
Adapted to core's conventions:
* tool functions return ``str`` (JSON-encoded), matching every other
tool in ``a2a_tools_*`` modules. Tests ``json.loads`` to inspect.
* permission check ``memory.write`` runs inline in
``tool_update_agent_card`` (same pattern as
``a2a_tools_memory.tool_commit_memory``).
* ``WORKSPACE_ID`` is read directly from ``os.environ`` core does
not have the runtime's validated-cache layer (``molecule_runtime.
builtin_tools.validation``).
"""
from __future__ import annotations
import json
import pytest
# --- Drift gate: re-export aliases on a2a_tools ------------------------------
class TestBackCompatAliases:
"""Pin that ``a2a_tools.tool_*`` resolves to the same callable as
``a2a_tools_identity.tool_*``. Refactor wrapping (e.g. a doc-string
wrapper that loses the function identity) silently breaks call
sites that ``patch("a2a_tools.tool_update_agent_card", ...)``
this gate makes that drift fail fast."""
def test_tool_get_runtime_identity_alias(self):
import a2a_tools
import a2a_tools_identity
assert a2a_tools.tool_get_runtime_identity is a2a_tools_identity.tool_get_runtime_identity
def test_tool_update_agent_card_alias(self):
import a2a_tools
import a2a_tools_identity
assert a2a_tools.tool_update_agent_card is a2a_tools_identity.tool_update_agent_card
# --- tool_get_runtime_identity ----------------------------------------------
class TestGetRuntimeIdentity:
"""The tool returns env-derived runtime identity. No HTTP call."""
@pytest.mark.asyncio
async def test_returns_all_known_env_fields(self, monkeypatch):
from a2a_tools_identity import tool_get_runtime_identity
monkeypatch.setenv("MODEL", "claude-opus-4-7")
monkeypatch.setenv("MODEL_PROVIDER", "anthropic")
monkeypatch.setenv("TIER", "T4")
monkeypatch.setenv("WORKSPACE_ID", "ws-abc")
monkeypatch.setenv("ADAPTER_MODULE", "adapter")
monkeypatch.setenv("MOLECULE_MODEL", "claude-opus-4-7")
monkeypatch.setenv("ANTHROPIC_BASE_URL", "https://api.anthropic.com")
out = await tool_get_runtime_identity()
# MCP tools return JSON-encoded strings (matches the contract
# every other tool_* in a2a_tools_* uses).
assert isinstance(out, str)
parsed = json.loads(out)
assert parsed["model"] == "claude-opus-4-7"
assert parsed["model_provider"] == "anthropic"
assert parsed["tier"] == "T4"
assert parsed["workspace_id"] == "ws-abc"
assert parsed["runtime"] == "adapter"
assert parsed["molecule_model"] == "claude-opus-4-7"
assert parsed["anthropic_base_url"] == "https://api.anthropic.com"
@pytest.mark.asyncio
async def test_missing_env_returns_empty_strings(self, monkeypatch):
"""Tool MUST NOT raise when env vars are absent — every key is
present but the value is the empty string. The agent then knows
the slot exists but is unset."""
from a2a_tools_identity import tool_get_runtime_identity
for var in (
"MODEL", "MODEL_PROVIDER", "TIER", "WORKSPACE_ID",
"ADAPTER_MODULE", "MOLECULE_MODEL", "ANTHROPIC_BASE_URL",
):
monkeypatch.delenv(var, raising=False)
parsed = json.loads(await tool_get_runtime_identity())
assert parsed["model"] == ""
assert parsed["model_provider"] == ""
assert parsed["tier"] == ""
assert parsed["workspace_id"] == ""
assert parsed["runtime"] == ""
assert parsed["molecule_model"] == ""
assert parsed["anthropic_base_url"] == ""
@pytest.mark.asyncio
async def test_no_http_call_made(self, monkeypatch):
"""``get_runtime_identity`` is env-only — must not open
httpx.AsyncClient even if the call would otherwise succeed.
Tripwire any client construction."""
import httpx
from a2a_tools_identity import tool_get_runtime_identity
class _Tripwire:
def __init__(self, *_a, **_kw):
raise AssertionError(
"tool_get_runtime_identity must not open httpx.AsyncClient"
)
monkeypatch.setattr(httpx, "AsyncClient", _Tripwire)
# Must not raise.
await tool_get_runtime_identity()
@pytest.mark.asyncio
async def test_helper_dict_matches_string_payload(self, monkeypatch):
"""``_runtime_identity_payload`` is the dict-returning helper
used by both the public tool and tests. Verify the public tool
json.dumps the same dict no field is dropped or renamed by
the encoding step."""
from a2a_tools_identity import (
_runtime_identity_payload,
tool_get_runtime_identity,
)
monkeypatch.setenv("MODEL", "claude-opus-4-7")
monkeypatch.setenv("TIER", "T4")
monkeypatch.setenv("WORKSPACE_ID", "ws-helper-check")
helper = _runtime_identity_payload()
tool_str = await tool_get_runtime_identity()
assert json.loads(tool_str) == helper
# --- tool_update_agent_card -------------------------------------------------
class _MockResponse:
def __init__(self, status_code: int, payload: dict):
self.status_code = status_code
self._payload = payload
self.text = json.dumps(payload)
def json(self):
return self._payload
class _MockClient:
"""Drop-in for httpx.AsyncClient context manager.
Records the URL + json body + headers the tool POSTed so the test
can assert against them. Returns the canned _MockResponse passed
in at construction time.
"""
def __init__(self, *, response: _MockResponse, captured: dict):
self._response = response
self._captured = captured
async def __aenter__(self):
return self
async def __aexit__(self, *_args):
return False
async def post(self, url, *, json=None, headers=None, **_kw): # noqa: A002
self._captured["url"] = url
self._captured["json"] = json
self._captured["headers"] = headers
return self._response
@pytest.fixture
def _grant_memory_write(monkeypatch):
"""Force the inline RBAC gate inside ``tool_update_agent_card`` to
succeed. The gate calls
``a2a_tools_rbac.check_memory_write_permission`` which inspects
``$MOLECULE_ROLES`` / the role table; the patch sidesteps that
machinery so tests can focus on the platform-call shape.
"""
import a2a_tools_identity
monkeypatch.setattr(
a2a_tools_identity, "_check_memory_write_permission", lambda: True
)
class TestUpdateAgentCard:
@pytest.mark.asyncio
async def test_posts_to_registry_update_card(
self, monkeypatch, _grant_memory_write,
):
"""Hits POST {PLATFORM_URL}/registry/update-card with the
workspace bearer and the {workspace_id, agent_card} body shape
the platform handler expects (workspace-server
``internal/handlers/registry.go``)."""
import a2a_tools_identity
monkeypatch.setenv("WORKSPACE_ID", "ws-42")
# Ensure PLATFORM_URL re-import sees a deterministic value —
# a2a_client imports it at module load so we patch the symbol
# on a2a_tools_identity directly (the module's own reference).
monkeypatch.setattr(a2a_tools_identity, "PLATFORM_URL", "http://test.invalid")
captured: dict = {}
response = _MockResponse(200, {"status": "updated"})
def _client_factory(*_a, **_kw):
return _MockClient(response=response, captured=captured)
monkeypatch.setattr(a2a_tools_identity.httpx, "AsyncClient", _client_factory)
monkeypatch.setattr(
a2a_tools_identity, "_auth_headers_for_heartbeat",
lambda: {"Authorization": "Bearer ws-token-xyz"},
)
card = {"name": "agent-foo", "version": "0.1.0", "description": "demo"}
result_str = await a2a_tools_identity.tool_update_agent_card(card)
result = json.loads(result_str)
# URL: PLATFORM_URL + /registry/update-card
assert captured["url"] == "http://test.invalid/registry/update-card"
# The platform handler expects {workspace_id, agent_card}; the
# agent_card is the raw object the agent submitted.
body = captured["json"]
assert body["workspace_id"] == "ws-42"
assert body["agent_card"] == card
# Auth header from auth_headers_for_heartbeat is forwarded
# verbatim — same path commit_memory uses.
assert captured["headers"]["Authorization"] == "Bearer ws-token-xyz"
assert result["success"] is True
assert result["status"] == "updated"
@pytest.mark.asyncio
async def test_propagates_server_error(
self, monkeypatch, _grant_memory_write,
):
"""Non-200 from platform surfaces as a structured error to the
agent. The agent sees {success:false, status_code, error} and
can decide whether to retry, fall back, or escalate."""
import a2a_tools_identity
monkeypatch.setenv("WORKSPACE_ID", "ws-42")
monkeypatch.setattr(a2a_tools_identity, "PLATFORM_URL", "http://test.invalid")
captured: dict = {}
response = _MockResponse(400, {"error": "invalid card"})
monkeypatch.setattr(
a2a_tools_identity.httpx, "AsyncClient",
lambda *a, **kw: _MockClient(response=response, captured=captured),
)
monkeypatch.setattr(
a2a_tools_identity, "_auth_headers_for_heartbeat", lambda: {},
)
result = json.loads(
await a2a_tools_identity.tool_update_agent_card({"name": "x"})
)
assert result["success"] is False
assert result["status_code"] == 400
assert "invalid card" in str(result["error"]).lower()
@pytest.mark.asyncio
async def test_rejects_non_dict_card(self, _grant_memory_write):
"""The MCP schema constrains transport callers to pass a dict;
in-process callers (tests, sibling modules) can still pass any
type. Reject non-dict defensively so the platform isn't asked
to validate JSON-encoded strings or lists."""
from a2a_tools_identity import tool_update_agent_card
result = json.loads(await tool_update_agent_card("not-a-dict"))
assert result["success"] is False
assert "dict" in str(result["error"]).lower()
@pytest.mark.asyncio
async def test_workspace_id_missing_returns_error(
self, monkeypatch, _grant_memory_write,
):
"""If WORKSPACE_ID is not set the tool refuses to issue the
request it would otherwise POST with an empty workspace_id
and let the platform return a confusing 400."""
from a2a_tools_identity import tool_update_agent_card
monkeypatch.delenv("WORKSPACE_ID", raising=False)
result = json.loads(await tool_update_agent_card({"name": "x"}))
assert result["success"] is False
assert "workspace_id" in str(result["error"]).lower()
@pytest.mark.asyncio
async def test_denies_when_memory_write_permission_missing(self, monkeypatch):
"""The agent's RBAC role must grant ``memory.write`` to update
the card. Read-only roles get an RBAC error string back
immediately, never touching the platform."""
import a2a_tools_identity
monkeypatch.setenv("WORKSPACE_ID", "ws-42")
monkeypatch.setattr(
a2a_tools_identity, "_check_memory_write_permission", lambda: False,
)
# Tripwire httpx — must not be called when RBAC denies.
import httpx
class _Tripwire:
def __init__(self, *_a, **_kw):
raise AssertionError("RBAC denial must short-circuit before httpx call")
monkeypatch.setattr(httpx, "AsyncClient", _Tripwire)
result = json.loads(
await a2a_tools_identity.tool_update_agent_card({"name": "x"}),
)
assert result["success"] is False
assert "memory.write" in str(result["error"]).lower()
@pytest.mark.asyncio
async def test_network_exception_returns_structured_error(
self, monkeypatch, _grant_memory_write,
):
"""A network exception (DNS failure, connect timeout, etc) is
wrapped into a structured error dict instead of bubbling up
to the MCP transport layer."""
import a2a_tools_identity
monkeypatch.setenv("WORKSPACE_ID", "ws-42")
monkeypatch.setattr(a2a_tools_identity, "PLATFORM_URL", "http://test.invalid")
class _ExplodingClient:
async def __aenter__(self):
return self
async def __aexit__(self, *_a):
return False
async def post(self, *_a, **_kw):
raise RuntimeError("simulated DNS failure")
monkeypatch.setattr(
a2a_tools_identity.httpx, "AsyncClient",
lambda *a, **kw: _ExplodingClient(),
)
result = json.loads(
await a2a_tools_identity.tool_update_agent_card({"name": "x"})
)
assert result["success"] is False
assert "network" in str(result["error"]).lower()
# --- Registry contract ------------------------------------------------------
class TestRegistryContract:
"""Pin the new tools' registration in platform_tools.registry. The
structural tests in ``test_platform_tools.py`` already check
registryMCP alignment; these are tighter assertions specific to
the two new tools so a future contributor deleting one entry sees
a focused failure."""
def test_get_runtime_identity_in_registry(self):
from platform_tools.registry import by_name
spec = by_name("get_runtime_identity")
assert spec.section == "a2a"
# No input parameters — env-only call.
assert spec.input_schema == {"type": "object", "properties": {}}
# impl points at the actual tool function, not a shim.
from a2a_tools_identity import tool_get_runtime_identity
assert spec.impl is tool_get_runtime_identity
def test_update_agent_card_in_registry(self):
from platform_tools.registry import by_name
spec = by_name("update_agent_card")
assert spec.section == "a2a"
assert "card" in spec.input_schema["properties"]
assert spec.input_schema["required"] == ["card"]
from a2a_tools_identity import tool_update_agent_card
assert spec.impl is tool_update_agent_card