fix(concierge): bake the no-self-secret-ops / safe-approval-demo rule into the identity prompt (core#2573) #2605

Merged
devops-engineer merged 1 commits from fix/2573-concierge-prompt-rule into main 2026-06-11 20:45:29 +00:00
Member

Follow-up to #2603 — the merge queue picked up #2603 at its first commit, so this prompt-bake commit never landed. The concierge's RBAC denies memory.write, so a behavior rule taught in chat dies on the next restart; the identity prompt (re-seeded from conciergeIdentityFiles every provision) is the durable surface. Adds one guardrail bullet: never run secret ops against your own workspace; approval demos use create_approval/create_request (in the image as of mcp-server 1.6.1) or a naturally gated op, never a secret write.

Refs core#2573.

🤖 Generated with Claude Code

Follow-up to #2603 — the merge queue picked up #2603 at its first commit, so this prompt-bake commit never landed. The concierge's RBAC denies memory.write, so a behavior rule taught in chat dies on the next restart; the identity prompt (re-seeded from conciergeIdentityFiles every provision) is the durable surface. Adds one guardrail bullet: never run secret ops against your own workspace; approval demos use create_approval/create_request (in the image as of mcp-server 1.6.1) or a naturally gated op, never a secret write. Refs core#2573. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
core-devops added 1 commit 2026-06-11 20:41:28 +00:00
fix(concierge): bake the no-self-secret-ops / safe-approval-demo rule into the identity prompt (core#2573)
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 3s
CI / Python Lint & Test (pull_request) Successful in 6s
E2E API Smoke Test / detect-changes (pull_request) Successful in 5s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 4s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 4s
Harness Replays / detect-changes (pull_request) Successful in 5s
sop-checklist / review-refire (pull_request_target) Has been skipped
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 4s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 6s
Harness Replays / Harness Replays (pull_request) Successful in 2s
gate-check-v3 / gate-check (pull_request_target) Successful in 5s
reserved-path-review / reserved-path-review (pull_request_target) Successful in 5s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 4s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 16s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 3s
CI / Detect changes (pull_request) Successful in 23s
CI / Canvas (Next.js) (pull_request) Successful in 1s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
CI / Canvas Deploy Status (pull_request) Successful in 1s
E2E Chat / detect-changes (pull_request) Successful in 29s
E2E Chat / E2E Chat (pull_request) Successful in 3s
Local Provision Lifecycle E2E / Local Provision Lifecycle E2E (stub) (pull_request) Successful in 32s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 45s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 55s
Local Provision Lifecycle E2E / Local Provision Lifecycle E2E (real image + MiniMax LLM, advisory) (pull_request) Failing after 23s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2m27s
CI / Platform (Go) (pull_request) Successful in 2m17s
CI / all-required (pull_request) Successful in 2s
security-review / approved (pull_request_target) Approved via pull_request_review trigger
reserved-path-review / reserved-path-review (pull_request_review) Successful in 4s
security-review / approved (pull_request_review) Successful in 4s
qa-review / approved (pull_request_target) Approved via pull_request_review trigger
qa-review / approved (pull_request_review) Successful in 12s
audit-force-merge / audit (pull_request_target) Successful in 14s
E2E Staging SaaS (full lifecycle) / pr-validate (pull_request) Waiting to run
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (pull_request) Waiting to run
E2E Staging SaaS (full lifecycle) / E2E Staging Platform Boot (pull_request) Waiting to run
E2E Staging SaaS (full lifecycle) / E2E Staging Concierge user_tasks (pull_request) Waiting to run
E2E Staging SaaS (full lifecycle) / E2E Staging Concierge Creates Workspace (pull_request) Waiting to run
E2E Staging SaaS (full lifecycle) / E2E Staging Concierge (compile+skip) (pull_request) Waiting to run
E2E Staging SaaS (full lifecycle) / E2E Staging Concierge Platform Agent (pull_request) Waiting to run
930b90132e
The concierge's RBAC denies memory.write, so a behavioral rule taught in
chat dies on the next restart. The identity prompt is re-seeded from
conciergeIdentityFiles on EVERY provision cycle — the durable surface.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
agent-reviewer-cr2 approved these changes 2026-06-11 20:44:14 +00:00
agent-reviewer-cr2 left a comment
Member

5-axis review complete for head 930b90132e.

Approved. This is a prompt-only follow-up to core#2603 that adds a durable concierge identity rule: do not run secret write/delete operations against the concierge's own workspace, and use create_approval/create_request or another naturally gated no-side-effect path for approval demos instead. Correctness matches the #2573 outage mitigation, robustness improves restart safety, security posture improves by avoiding destructive/state-changing demos, there is no runtime performance impact, and the wording is clear and scoped.

No production code paths, tests, or workflow behavior changed in this PR.

5-axis review complete for head 930b90132e8ea3ea59d51c1d23be8c20d2e704a0. Approved. This is a prompt-only follow-up to core#2603 that adds a durable concierge identity rule: do not run secret write/delete operations against the concierge's own workspace, and use create_approval/create_request or another naturally gated no-side-effect path for approval demos instead. Correctness matches the #2573 outage mitigation, robustness improves restart safety, security posture improves by avoiding destructive/state-changing demos, there is no runtime performance impact, and the wording is clear and scoped. No production code paths, tests, or workflow behavior changed in this PR.
devops-engineer merged commit cd4281fb0a into main 2026-06-11 20:45:29 +00:00
Sign in to join this conversation.
No Reviewers
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: molecule-ai/molecule-core#2605