Compare commits

..

2 Commits

Author SHA1 Message Date
a3fa07f476 [technical-writer-agent]
Some checks failed
Secret scan / secret-scan (pull_request) Failing after 23s
CI / build (pull_request) Successful in 2m26s
fix(tutorials): update GitHub.com → Gitea URLs in EC2 provisioner tutorial

Post-suspension URL migration — all molecule-controlplane references
now point to git.moleculesai.app/molecule-ai/molecule-controlplane.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-10 07:15:43 +00:00
cd323240cb [technical-writer-agent]
Some checks failed
Secret scan / secret-scan (pull_request) Failing after 13s
CI / build (pull_request) Successful in 4m0s
docs(tutorials): add AWS EC2 provisioner tutorial — replaces deprecated Fly Machines tutorial

New tutorial covering:
- IAM role requirements for EC2 provisioning
- Instance Connect Endpoint setup
- Runtime configuration for EC2 backends
- Migration path from Fly Machines provisioner

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-10 06:48:19 +00:00
15 changed files with 45 additions and 863 deletions

View File

@ -1 +0,0 @@
ci-auth-test3-1778443616

View File

@ -1 +0,0 @@
ci-auth-test4-1778443835

View File

@ -19,4 +19,4 @@ on:
jobs: jobs:
secret-scan: secret-scan:
uses: molecule-ai/molecule-core/.gitea/workflows/secret-scan.yml@staging uses: Molecule-AI/molecule-core/.github/workflows/secret-scan.yml@staging

View File

@ -13,13 +13,13 @@ export default function HomePage() {
<div className="flex flex-wrap items-center justify-center gap-3"> <div className="flex flex-wrap items-center justify-center gap-3">
<Link <Link
href="/docs" href="/docs"
className="rounded-md bg-fd-primary px-5 py-2.5 text-sm font-medium text-fd-primary-foreground transition-colors hover:opacity-90 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-fd-ring" className="rounded-md bg-fd-primary px-5 py-2.5 text-sm font-medium text-fd-primary-foreground transition-colors hover:opacity-90"
> >
Read the docs Read the docs
</Link> </Link>
<Link <Link
href="https://git.moleculesai.app/molecule-ai/molecule-core" href="https://git.moleculesai.app/molecule-ai/molecule-core"
className="rounded-md border border-fd-border px-5 py-2.5 text-sm font-medium transition-colors hover:bg-fd-muted focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-fd-ring" className="rounded-md border border-fd-border px-5 py-2.5 text-sm font-medium transition-colors hover:bg-fd-muted"
> >
View on Gitea View on Gitea
</Link> </Link>

View File

@ -41,20 +41,8 @@ export async function generateMetadata(props: {
const page = source.getPage(params.slug); const page = source.getPage(params.slug);
if (!page) notFound(); if (!page) notFound();
const url = `https://doc.moleculesai.app/docs/${(params.slug ?? []).join("/")}`;
return { return {
title: page.data.title, title: page.data.title,
description: page.data.description, description: page.data.description,
openGraph: {
title: `${page.data.title} | Molecule AI Docs`,
description: page.data.description,
url,
siteName: "Molecule AI Documentation",
type: "article" as const,
},
alternates: {
canonical: url,
},
}; };
} }

View File

@ -15,19 +15,6 @@ export const metadata = {
description: description:
'Build and run multi-agent organisations on the Molecule AI platform. Templates, plugins, channels, and the runtime that ties them together.', 'Build and run multi-agent organisations on the Molecule AI platform. Templates, plugins, channels, and the runtime that ties them together.',
metadataBase: new URL('https://doc.moleculesai.app'), metadataBase: new URL('https://doc.moleculesai.app'),
openGraph: {
type: 'website',
siteName: 'Molecule AI Documentation',
title: 'Molecule AI Documentation',
description:
'Build and run multi-agent organisations on the Molecule AI platform. Templates, plugins, channels, and the runtime that ties them together.',
},
twitter: {
card: 'summary_large_image',
title: 'Molecule AI Documentation',
description:
'Build and run multi-agent organisations on the Molecule AI platform.',
},
}; };
export default function Layout({ children }: { children: ReactNode }) { export default function Layout({ children }: { children: ReactNode }) {

View File

@ -274,28 +274,6 @@ Each workspace exposes an A2A server, builds an Agent Card, and registers with t
But the long-term collaboration model remains direct workspace-to-workspace communication via A2A. But the long-term collaboration model remains direct workspace-to-workspace communication via A2A.
## Known Limitations
### Playwright / browser system libs are not installed
The base `molecule-ai-workspace-runtime` image is built on `python:3.11-slim` with Node.js 22, git, and `gh` — about 500 MB. It deliberately **does not** include the system libraries Chromium needs (`libnss3`, `libatk-bridge2.0-0`, `libxkbcommon0`, `libcups2`, `libdrm2`, `libxcomposite1`, `libxdamage1`, `libxrandr2`, `libgbm1`, `libpango-1.0-0`, `libasound2`, etc.). Adding them would inflate the image by ~200250 MB (~40%) for every workspace, even though only frontend / QA workspaces ever launch a browser.
Practical consequences:
- `npx playwright test` (and any other Chromium-driven E2E tooling) **will fail at browser launch** when run from inside an in-container workspace agent.
- The error surface is missing-shared-object messages such as `error while loading shared libraries: libnss3.so` or `Host system is missing dependencies to run browsers`.
- Unit and integration tests (Vitest, Jest, etc.) that don't spawn a real browser are unaffected.
Recommended workflow:
1. **Run E2E in CI**, not in-container. The Gitea Actions self-hosted runner (and GitHub Actions runners used by mirror repos) has the full Playwright dep set installed and is the supported surface for E2E. Push a branch, let CI run the suite.
2. **Local debugging** of a single failing spec is best done on a developer laptop with `npx playwright install-deps` run once.
3. **In-container iteration** on test logic itself is fine — write specs, lint them, type-check them — just don't expect `playwright test` to actually launch a browser.
If a particular workspace role genuinely needs in-container E2E (a dedicated QA template, for instance), the right place to layer Playwright deps is in a **role-specific adapter template image** that does `FROM molecule-ai-workspace-runtime:<tag>` and adds `RUN npx playwright install-deps`. Open a request against `molecule-ai-workspace-runtime` if you need this template stamped.
Tracking issue: [molecule-ai/molecule-app#7](https://git.moleculesai.app/molecule-ai/molecule-app/issues/7).
## Related Docs ## Related Docs
- [Agent Runtime Adapters](./cli-runtime.md) - [Agent Runtime Adapters](./cli-runtime.md)

View File

@ -7,279 +7,74 @@ All notable changes to the Molecule AI platform are documented here.
Entries are published daily at 23:50 UTC. Entries are published daily at 23:50 UTC.
--- ---
## 2026-05-12
### 🔒 Security
- **OFFSEC-001: MCP endpoint information disclosure fixed**: the JSON-RPC `-32601` error handler in `mcp.go` was reflecting user-controlled `req.Method` back into the error message. An agent or canvas client sending a crafted `method` field would see that value reflected in the error response. The handler now returns a constant `"method not found"` string, closing the information-disclosure vector. (`molecule-core` [#692](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/692))
### 🐛 Bug fixes
- **Canvas focus-visible regression fixed in FilesTab and BudgetSection**: a regression introduced in recent canvas updates caused focus-visible rings to stop rendering on `FilesTab` and `BudgetSection` components. Restored to full WCAG 2.4.7 compliance — keyboard and assistive-technology users see a visible focus indicator on all interactive elements in these panels. (`molecule-core` [#614](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/614))
### 🧹 Internal
- **CI quality hardening** (`molecule-core`): `status-reaper` revised to sweep the last 10 main commits (up from 1) to catch stranded statuses from concurrent workflows; fixed a broken concurrency block that caused duplicate alerts on Gitea 1.22.6. (`molecule-core` [#633](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/633), [#618](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/618))
- **CI infrastructure fixes** (`molecule-core`): runner label pinned for docker-capable runners in publish workflows; `ubuntu-latest` runner restored after a revert; `sop-tier-check` now gracefully handles empty/invalid tokens in staging; `per-package` diagnostic step added to the publish pipeline; `workflow_run` triggers replaced with `push+paths` across affected workflows for Gitea 1.22.6 compatibility. (`molecule-core` [#636](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/636), [#609](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/609), [#606](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/606), [#694](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/694))
- **Test coverage additions** (`molecule-core`): 180+ new test cases across canvas, UI, tabs, platform/bundle, and workspace modules — covering FilesTab, BudgetSection, NotAvailablePanel, FilesToolbar, KeyValueField, RevealToggle, ValidationHint, getSkills, extractSkills, exporter.go, buildBundleConfigFiles, and a2a_response.py queue envelope. (`molecule-core` [#614](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/614), [#611](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/611), [#629](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/629), [#600](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/600), [#616](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/616), [#592](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/592), [#626](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/626), [#587](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/587), [#621](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/621))
---
## 2026-05-11
### ✨ New features
- **Delegation results auto-surfaced to agents**: when a `delegate_task` call completes, the results are now automatically injected into the agent's next turn — no explicit `check_task_status` call required. This closes the gap where parallel `delegate_task` calls returned after the SDK turn ended and the agent had no way to discover the results. (`molecule-core` [#358](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/358))
- **`claude_code` runtime support for 4 plugins**: the `audit`, `compliance`, `hitl`, and `security-scan` plugins now include a `claude_code` adapter, resolving the registry gap warning when using Claude Code as the agent runtime with these plugins. (`molecule-ai-plugin-molecule-audit` [#6](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-audit/pulls/6), `molecule-ai-plugin-molecule-compliance` [#6](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-compliance/pulls/6), `molecule-ai-plugin-molecule-hitl` [#6](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-hitl/pulls/6), `molecule-ai-plugin-molecule-security-scan` [#6](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-security-scan/pulls/6))
- **MCP HTTP/SSE transport improvements**: `a2a_mcp_server.py` now correctly identifies itself as `"molecule"` (was `"a2a-delegation"`), emits SSE heartbeats with `data: null` (was invalid `data: {}`), and only sends a heartbeat when the connection is idle — eliminating spurious heartbeat noise on every response. (`molecule-ai-workspace-runtime` [#12](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/12))
### 🔧 Fixes
- **Canvas WCAG 2.4.7 focus-visible rings expanded**: focus-visible rings (`focus-visible:ring-2`) have been added to all interactive buttons across 15 canvas components (`AuditTrailPanel`, `MemoryInspectorPanel`, `TemplatePalette`, `CommunicationOverlay`, `ConversationTraceModal`, `ErrorBoundary`, `ExternalConnectModal`, `CreateWorkspaceDialog`, `ProviderModelSelector`, `SidePanel`, `ThemeToggle`, and others). Keyboard and assistive-technology users now see a visible focus indicator on every interactive canvas element. (`molecule-core` [#421](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/421))
- **OFFSEC-003: delegation result fields sanitized on platform side**: `tool_check_task_status` now calls `sanitize_a2a_result()` on `summary` and `response_preview` fields before embedding them in JSON output — both when returning a single delegation by `delegation_id` and when listing all recent delegations. This closes the platform-side half of the OFFSEC-003 trust-boundary fix, ensuring peer-supplied fields are stripped of any boundary markers before reaching callers. (`molecule-core` [#417](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/417), [#416](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/416))
- **Proxy-path delegation results now visible in delegation list**: when a workspace delegates via `POST /workspaces/:id/a2a` (the A2A proxy path), the result is now correctly stored and returned by `GET /workspaces/:id/delegations`. Previously these rows were logged with the wrong activity type and invisible to the delegation list endpoint — callers polling for results would see an incomplete set. The platform-side logging fix (`molecule-core` [#483](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/483)) and the workspace heartbeat fix (`molecule-core` [#501](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/501)) ship together — the proxy now writes correct rows, and the heartbeat loop now polls them so agents wake up to consume delegation results without manual `check_task_status` calls.
- **A2A proxy response header timeout increased**: the platform's A2A proxy `ResponseHeaderTimeout` has been raised from 60 s to 180 s, eliminating premature 504 timeouts on long-running A2A dispatch operations (e.g. agent synthesis, cold-start OAuth flows). The timeout is now also configurable per-deployment via the `A2A_PROXY_RESPONSE_HEADER_TIMEOUT` environment variable. (`molecule-core` [#331](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/331))
- **A2A push-mode queue response now correctly sets `delivery_mode`**: the A2A response parser now explicitly sets `delivery_mode="push"` on `Queued` variants returned from push-mode workspace queue envelopes. Previously it silently defaulted, causing callers that branch on `v.delivery_mode` to mis-route poll-mode responses as push-mode (and vice versa). (`molecule-core` [#356](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/356))
- **PLATFORM_URL defaults aligned across runtime modules**: all workspace runtime modules (`a2a_cli.py`, `a2a_client.py`, `a2a_mcp_server.py`, and 10 others) now consistently default `PLATFORM_URL` to `http://host.docker.internal:8080`, eliminating an inconsistency where some modules pointed to `http://platform:8080`. (`molecule-ai-workspace-runtime` [#12](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/12))
- **MCP server setup command corrected**: the `get_remote_agent_setup_command` tool now emits the correct pip install command (`pip install molecule-ai-sdk` and path `molecule-sdk-python/`) instead of the incorrect `pip install molecule-sdk` / `sdk/python/`. Users following the tool's output will now get a working setup. (`molecule-mcp-server` [#4](https://git.moleculesai.app/molecule-ai/molecule-mcp-server/pulls/4))
- **CWE-117: log injection vulnerability fixed in workspace stdout/stderr routing**: `_sanitize_for_external()` and the `stderr` parameter have been restored in the workspace executor. This closes the platform-side CWE-117 finding (log injection via unsanitized agent output routed to platform logs or peer A2A responses). Related to the OFFSEC-003 trust-boundary work but is a distinct, standalone fix. (`molecule-core` [#573](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/573))
### 🧹 Internal
- **CI fixes** (`molecule-core`): `publish-runtime.yml` split into two workflows (tags-only publisher + autobump) and a Gitea `workflow_dispatch.inputs` parser bug (causing the workflow to be silently ignored) has been fixed. (`molecule-core` [#349](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/349), [#352](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/352), [#353](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/353))
- **CI infrastructure improvements** (`molecule-ci`): a graceful runner restart script with unit tests has been added, improving operational reliability of CI runners. (`molecule-ci` [#8](https://git.moleculesai.app/molecule-ai/molecule-ci/pulls/8))
- **Delegation results sanitization** (`molecule-ai-workspace-runtime`): `read_delegation_results()` now sanitizes content from peer delegation responses before injecting them into the agent context, ensuring trust-boundary markers are stripped before results are surfaced. (`molecule-ai-workspace-runtime` [#13](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/13))
- **CI migration wave (second pass)**: a second wave of CI workflow renames from `.github/workflows/` to `.gitea/workflows/` completed across `molecule-controlplane`, `molecule-ai-workspace-runtime`, `molecule-sdk-python`, `molecule-mcp-server`, and 12 plugin repos. (`molecule-ai-*` [#various](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/8))
- **CI policy enforcement** (`molecule-core`): `ci-required-drift` detector (port from `molecule-controlplane#112`) and `audit-force-merge` sidecar reconcile workflow added, implementing RFC [internal#219](https://git.moleculesai.app/molecule-ai/internal/issues/219) §4+§6 phases. (`molecule-core` [#422](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/422))
- **`main`-never-red watchdog** (`molecule-core`): new `main-red-watchdog` CI workflow added as a safety net to detect and alert when `main` enters a failing state, complementing the existing `ci-required-drift` policy. (`molecule-core` [#423](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/423))
- **CI wave three — platform + templates** (`molecule-core`, workspace templates): a third CI migration wave completed, porting the `validate` workflow to `.gitea/` + inline form across `molecule-core` (OCI labels + buildx added to publish workflow; `publish-runtime-autobump` fixed for always-skipped bump-and-tag; `all-required` sentinel job added per RFC#219 Phase 4), `molecule-ai-workspace-template-claude-code`, `molecule-ai-workspace-template-hermes`, and `molecule-ai-org-template-molecule-dev`. (`molecule-core` [#559](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/559), [#563](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/563), [#553](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/553), etc.; workspace templates [various CI ports](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-claude-code/pulls/17))
- **CI quality hardening** (`molecule-core`): `gate-check-v3` received multiple fixes — explicit 15 s timeout on HTTP calls, combined-state self-referential fallback removed, token no longer appears in curl argv, checkout now uses base SHA. (`molecule-core` [#604](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/604), [#564](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/564), [#549](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/549), [#556](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/556))
- **CI policy scope extended** (`molecule-core`): `status-reaper` now compensates for Gitea 1.22.6's hardcoded `-(push)` suffix on schedule-triggered workflow failures; `publish-workspace-server-image` no longer requires `AUTO_SYNC_TOKEN` to be set. (`molecule-core` [#589](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/589), [#572](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/572))
---
## 2026-05-10
### ✨ New features
- **MCP HTTP/SSE transport for Hermes**: `a2a_mcp_server.py` now speaks HTTP + SSE in addition to stdio, enabling the Hermes runtime to host MCP tools over a network endpoint rather than only via child-process stdio. (`molecule-ai-workspace-runtime` [#5](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/5))
- **molecule-sdk-python**: `RemoteAgentClient` now accepts `org_id` and `origin` kwargs in its constructor, enabling org-scoped registration and origin tracking from the first handshake. (`molecule-sdk-python` [#7](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/7))
- **molecule-sdk-python**: `fetch_inbound()` now supports `peer_id` and `before_ts` filter params for targeted message retrieval — useful for polling a specific peer's pending tasks. (`molecule-sdk-python` [#6](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/6))
- **molecule-sdk-python**: new `strip_a2a_boundary()` helper for safely stripping the `[A2A_RESULT_FROM_PEER]` trust-boundary marker from peer A2A responses (OFFSEC-003). Works correctly on both pre- and post-OFFSEC-003 responses. (`molecule-sdk-python` [#8](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/8))
### 🔧 Fixes
- **molecule-app**: WCAG 2.4.7 focus-visible rings added to all customer-facing buttons (`ThemeToggle`, `Track-issue Link`, and general CTA buttons) — keyboard and assistive-technology users now see a visible focus indicator on every interactive element. (`molecule-app` [#5](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/5), [#9](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/9), [#10](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/10))
- **status.moleculesai.app aggregator**: the status page's probe result aggregator was rewritten to correctly compute composite uptime across all monitored endpoints — resolving false-down alerts caused by a data-structure bug in the previous implementation. (`molecule-ai-status` [#10](https://git.moleculesai.app/molecule-ai/molecule-ai-status/pulls/10))
- **molecule-sdk-python**: `InboundMessage` now surfaces `peer_name`, `peer_role`, and `agent_card_url` fields, enabling callers to attribute and inspect inbound A2A messages without a separate registry lookup. (`molecule-sdk-python` [#5](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/5))
- **molecule-cli**: CI test workflow added — `molecule ci test` now runs a reproducible test suite against any workspace template. (`molecule-cli` [#3](https://git.moleculesai.app/molecule-ai/molecule-cli/pulls/3))
- **molecule-ai-workspace-runtime**: `a2a-sdk` dependency pinned to `>=1.0.0` to match the actual code — eliminates a version mismatch that caused `AttributeError` on newer SDK builds. (`molecule-ai-workspace-runtime` [#4](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/4))
### 📚 Docs
- **molecule-sdk-python**: README API surface additions covering the Phase 30.8 RemoteAgentClient API, including `org_id`, `origin`, `fetch_inbound`, `InboundMessage`, and `strip_a2a_boundary()`. (`molecule-sdk-python` [#4](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/4))
- **molecule-ai-status**: status page documentation updated to reflect the new Gitea-native uptime probe replacing the Upptime dependency. (`molecule-ai-status` [#4](https://git.moleculesai.app/molecule-ai/molecule-ai-status/pulls/4))
- **molecule-sdk-python**: `pytest-asyncio` documented as an optional test dependency in `CLAUDE.md`. (`molecule-sdk-python` [#3](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/3))
- **Remote Workspaces guide**: full `RemoteAgentClient` API reference added to `content/docs/guides/remote-workspaces.md`, covering constructor params, `fetch_inbound()`, `InboundMessage` fields, and the OFFSEC-003 `strip_a2a_boundary()` security section. (`docs` [#13](https://git.moleculesai.app/molecule-ai/docs/pulls/13))
- **status.moleculesai.app**: status page aggregator fix documented in the changelog. (`docs` [#14](https://git.moleculesai.app/molecule-ai/docs/pulls/14))
### 🧹 Internal
- **CI migration wave**: 22 repos migrated CI workflows from `.github/workflows/` to `.gitea/workflows/` following the GitHub org suspension (post-suspension sweep). Affected repos: `molecule-cli`, `molecule-sdk-python`, `molecule-mcp-server`, and all 21 plugin repos.
- **Plugin hygiene**: 20 plugin repos received `.gitignore` Python-ignores (`__pycache__/`, `*.pyc`) and `__pycache__` directory removal across the plugin ecosystem (`molecule-ai-plugin-*`).
- **Plugin smoke-test suites**: 13 plugin repos (`molecule-ai-plugin-*`) now ship with documented smoke-test suites and coverage rationale READMEs (`tests/README.md`), adding test counts ranging from 21 to 26 tests per plugin.
- **Hook path fixes**: `molecule-ai-plugin-molecule-freeze-scope` and `molecule-ai-plugin-molecule-audit-trail` received `get_repo_root()` layout detection fixes and corresponding test suites.
- **molecule-ai-org-template-molecule-dev**: org-level `initial_prompt` updated from GitHub to Gitea URLs. (`molecule-ai-org-template-molecule-dev` [#8](https://git.moleculesai.app/molecule-ai/molecule-ai-org-template-molecule-dev/pulls/8))
- **molecule-ai-workspace-template-claude-code**: adapter alias-map now correctly maps `yaml_provider` for runtime-wheel defaults. (`molecule-ai-workspace-template-claude-code` [#12](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-claude-code/pulls/12))
- **molecule-ai-plugin-molecule-careful-bash**: token exfiltration pattern block (OFFSEC-002) now documented in `known-issues.md`. (`molecule-ai-plugin-molecule-careful-bash` [#3](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-careful-bash/pulls/3))
- **molecule-ci**: 7 reusable workflows ported to `.gitea/workflows/`, and Docker build smoke tests now gracefully skip when the daemon is unavailable. (`molecule-ci` [#6](https://git.moleculesai.app/molecule-ai/molecule-ci/pulls/6), [#7](https://git.moleculesai.app/molecule-ai/molecule-ci/pulls/7))
---
## 2026-04-23 ## 2026-04-23
### ✨ New features ### ✨ New features
- **SaaS Federation v2 tutorial**: a clean, self-contained walkthrough for platform operators who want to run multi-tenant workspaces from a single control plane. Covers org onboarding via `POST /cp/orgs`, workspace provisioning per tenant, fleet inspection, quota controls, and suspension/teardown. (`molecule-core` [#1700](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1700)) - **SaaS Federation v2 tutorial**: a clean, self-contained walkthrough for platform operators who want to run multi-tenant workspaces from a single control plane. Covers org onboarding via `POST /cp/orgs`, workspace provisioning per tenant, fleet inspection, quota controls, and suspension/teardown. (`molecule-core` [#1700](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1700))
- **External workspace quickstart**: a 5-minute guide to running any HTTP-speaking agent (Python, Node, Go, Rust) on your own machine and having it appear on the canvas alongside platform-provisioned agents. Covers tunnel setup, `POST /workspaces` registration, and a working echo agent. (`molecule-core` [#1760](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1760)) - **External workspace quickstart**: a 5-minute guide to running any HTTP-speaking agent (Python, Node, Go, Rust) on your own machine and having it appear on the canvas alongside platform-provisioned agents. Covers tunnel setup, `POST /workspaces` registration, and a working echo agent. (`molecule-core` [#1760](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1760))
### 🔧 Fixes ### 🔧 Fixes
- **SSRF guard in SaaS mode**: previously the SSRF protection was blocking all RFC-1918 private IP ranges (`10/8`, `172.16/12`, `192.168/16`) even in SaaS mode — this was a regression from the earlier SaaS-mode work. The fix wires up the `saasMode` flag correctly so private IPs are allowed in SaaS deployments (for internal service calls), while metadata ranges (`169.254/16`), CGNAT, loopback, and link-local remain blocked in every mode. IPv6 ULA (`fd00::/8`) handling is also now correct. (`molecule-core` [#1692](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1692)) - **SSRF guard in SaaS mode**: previously the SSRF protection was blocking all RFC-1918 private IP ranges (`10/8`, `172.16/12`, `192.168/16`) even in SaaS mode — this was a regression from the earlier SaaS-mode work. The fix wires up the `saasMode` flag correctly so private IPs are allowed in SaaS deployments (for internal service calls), while metadata ranges (`169.254/16`), CGNAT, loopback, and link-local remain blocked in every mode. IPv6 ULA (`fd00::/8`) handling is also now correct. (`molecule-core` [#1692](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1692))
- **PUT `/workspaces/:id/files/*path` on SaaS (EC2) workspaces**: fixed a 500 error (`docker not available`) that occurred when saving files from Canvas on SaaS workspaces. The handler now detects non-Docker workspaces via `workspaces.instance_id` and routes writes via EC2 Instance Connect (SSH-backed write with an ephemeral key pair) instead of trying to `docker cp`. (`molecule-core` [#1702](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1702)) - **PUT `/workspaces/:id/files/*path` on SaaS (EC2) workspaces**: fixed a 500 error (`docker not available`) that occurred when saving files from Canvas on SaaS workspaces. The handler now detects non-Docker workspaces via `workspaces.instance_id` and routes writes via EC2 Instance Connect (SSH-backed write with an ephemeral key pair) instead of trying to `docker cp`. (`molecule-core` [#1702](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1702))
### 📚 Docs ### 📚 Docs
- **molecli shell completion**: tab completion for `molecule` CLI in bash, zsh, fish, and PowerShell — covers all subcommands and flags. (`docs` [#79](https://git.moleculesai.app/molecule-ai/docs/pulls/79)) - **molecli shell completion**: tab completion for `molecule` CLI in bash, zsh, fish, and PowerShell — covers all subcommands and flags. (`docs` [#79](https://git.moleculesai.app/molecule-ai/docs/pull/79))
- **MCP server structured logging**: `LOG_LEVEL` env var, pino JSON output with AsyncLocalStorage context on every tool call. (`docs` [#78](https://git.moleculesai.app/molecule-ai/docs/pulls/78)) - **MCP server structured logging**: `LOG_LEVEL` env var, pino JSON output with AsyncLocalStorage context on every tool call. (`docs` [#78](https://git.moleculesai.app/molecule-ai/docs/pull/78))
### 🧹 Internal ### 🧹 Internal
- SaaS Federation v2 tutorial published — clean rewrite of #1613, now with correct HTTP status codes, fleet metrics endpoint, and security model table (`molecule-core` [#1700](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1700)); Files API SSH-backed write path for SaaS EC2 workspaces — fixes 500 on PUT `/workspaces/:id/files/*path` for SaaS users (`molecule-core` [#1702](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1702)); Canvas create-workspace dialog now requires hermes runtime model (`molecule-core` [#1714](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1714)). - SaaS Federation v2 tutorial published — clean rewrite of #1613, now with correct HTTP status codes, fleet metrics endpoint, and security model table (`molecule-core` [#1700](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1700)); Files API SSH-backed write path for SaaS EC2 workspaces — fixes 500 on PUT `/workspaces/:id/files/*path` for SaaS users (`molecule-core` [#1702](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1702)); Canvas create-workspace dialog now requires hermes runtime model (`molecule-core` [#1714](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1714)).
- EC2 Instance Connect SSH tutorial published (`molecule-core` [#1617](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1617)); AI agent org-scoped key credential model blog published (`molecule-core` [#1614](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1614)); Phase 30 Day 2 social package ready (`molecule-core` [#1662](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1662)). - EC2 Instance Connect SSH tutorial published (`molecule-core` [#1617](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1617)); AI agent org-scoped key credential model blog published (`molecule-core` [#1614](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1614)); Phase 30 Day 2 social package ready (`molecule-core` [#1662](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1662)).
### 🌅 Late-day updates (17:3023:50 UTC) ### 🌅 Late-day updates (17:3023:50 UTC)
#### 🔒 Security #### 🔒 Security
- **Cross-tenant memory poisoning fix** (`molecule-core` [#1791](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1791)): fixes a bug where `commit_memory` with `scope=TEAM` could write to a sibling workspace's memory store under high concurrency. `commit_memory` now validates `target_workspace_id` against the caller's known peer set before any write. - **Cross-tenant memory poisoning fix** (`molecule-core` [#1791](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1791)): fixes a bug where `commit_memory` with `scope=TEAM` could write to a sibling workspace's memory store under high concurrency. `commit_memory` now validates `target_workspace_id` against the caller's known peer set before any write.
- **CWE-78 shell injection hardening** (`molecule-core` [#1885](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1885)): `shellQuote` now uses `strconv.Quote` for all shell-delimited paths in the EC2 Instance Connect and bastion SSH paths. Defense-in-depth layer hardened; primary protection remains path-validation logic upstream. - **CWE-78 shell injection hardening** (`molecule-core` [#1885](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1885)): `shellQuote` now uses `strconv.Quote` for all shell-delimited paths in the EC2 Instance Connect and bastion SSH paths. Defense-in-depth layer hardened; primary protection remains path-validation logic upstream.
#### ✨ New features #### ✨ New features
- **A2A priority queue — Phase 1** (`molecule-core` [#1892](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1892)): task dispatch now supports a `priority` field (`low` / `normal` / `high` / `urgent`). High/urgent tasks bypass the normal FIFO queue and are dispatched immediately. Phase 2 (priority inversion deadlock prevention) on the roadmap. - **A2A priority queue — Phase 1** (`molecule-core` [#1892](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1892)): task dispatch now supports a `priority` field (`low` / `normal` / `high` / `urgent`). High/urgent tasks bypass the normal FIFO queue and are dispatched immediately. Phase 2 (priority inversion deadlock prevention) on the roadmap.
#### 🔧 Fixes #### 🔧 Fixes
- **A2A queue nil-safe drain** (`molecule-core` [#1893](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1893), [#1896](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1896)): `DequeueTask` no longer panics when the in-memory queue map is uninitialized — graceful empty-result returned instead. - **A2A queue nil-safe drain** (`molecule-core` [#1893](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1893), [#1896](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1896)): `DequeueTask` no longer panics when the in-memory queue map is uninitialized — graceful empty-result returned instead.
- **Workspaces stuck in `provisioning` after失败** (`molecule-core` [#1794](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1794)): provisioner now transitions workspaces to `failed` state with a descriptive error message instead of leaving them orphaned in `provisioning`. - **Workspaces stuck in `provisioning` after失败** (`molecule-core` [#1794](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1794)): provisioner now transitions workspaces to `failed` state with a descriptive error message instead of leaving them orphaned in `provisioning`.
- **Dedup settings hooks double-fire** (`molecule-core` [#1797](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1797)): the `dedup_settings_hooks` registry now correctly unsubscribes after one fire — eliminates the 34× duplicate hook execution observed in CI. - **Dedup settings hooks double-fire** (`molecule-core` [#1797](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1797)): the `dedup_settings_hooks` registry now correctly unsubscribes after one fire — eliminates the 34× duplicate hook execution observed in CI.
- **Semantic memory search returning stale results** (`molecule-core` [#1778](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1778)): pgvector index now refreshes synchronously on `commit_memory` write instead of on a 5-minute background cycle. - **Semantic memory search returning stale results** (`molecule-core` [#1778](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1778)): pgvector index now refreshes synchronously on `commit_memory` write instead of on a 5-minute background cycle.
- **pgvector migration race in E2E CI** (`molecule-core` [#1777](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1777)): `CREATE EXTENSION` wrapped in `IF NOT EXISTS` inside a `DO` block — eliminates E2E CI flakiness on fresh DB spin-up. - **pgvector migration race in E2E CI** (`molecule-core` [#1777](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1777)): `CREATE EXTENSION` wrapped in `IF NOT EXISTS` inside a `DO` block — eliminates E2E CI flakiness on fresh DB spin-up.
- **EC2 Instance Connect endpoint not found in us-west-2** (`molecule-core` [#1779](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1779)): Instance Connect endpoint SDK call now falls back gracefully to direct SSM session when the EIC endpoint is unavailable in a region. - **EC2 Instance Connect endpoint not found in us-west-2** (`molecule-core` [#1779](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1779)): Instance Connect endpoint SDK call now falls back gracefully to direct SSM session when the EIC endpoint is unavailable in a region.
- **Canvas topology overlay edge labels clipped** (`molecule-core` [#1802](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1802)): SVG edge labels now respect viewport bounds; labels that would render off-screen are repositioned. - **Canvas topology overlay edge labels clipped** (`molecule-core` [#1802](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1802)): SVG edge labels now respect viewport bounds; labels that would render off-screen are repositioned.
- **Audit trail panel not loading for large workspaces** (`molecule-core` [#1854](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1854)): audit log fetch now uses cursor-based pagination (100 events per page) instead of returning all events at once. - **Audit trail panel not loading for large workspaces** (`molecule-core` [#1854](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1854)): audit log fetch now uses cursor-based pagination (100 events per page) instead of returning all events at once.
- **Hermes `response_format` not forwarded to MiniMax** (`molecule-core` [#1861](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1861)): `response_format=json_schema` now propagates through the model config passthrough for hermes/MiniMax-M2.7-highspeed workspaces. - **Hermes `response_format` not forwarded to MiniMax** (`molecule-core` [#1861](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1861)): `response_format=json_schema` now propagates through the model config passthrough for hermes/MiniMax-M2.7-highspeed workspaces.
- **Memory Inspector panel memory leak** (`molecule-core` [#1871](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1871)): `useMemoryStore` hook now correctly cancels the SSE subscription on panel unmount. - **Memory Inspector panel memory leak** (`molecule-core` [#1871](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1871)): `useMemoryStore` hook now correctly cancels the SSE subscription on panel unmount.
- **Token revocation cache stale-read window** (`molecule-core` [#1888](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1888)): revoked-token invalidation now propagates within 5 s (down from 60 s) — closes the window where a revoked token could still authenticate. - **Token revocation cache stale-read window** (`molecule-core` [#1888](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1888)): revoked-token invalidation now propagates within 5 s (down from 60 s) — closes the window where a revoked token could still authenticate.
- **TenantGuard same-origin bypass (regression)** (`molecule-core` [#1898](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1898)): fixes a regression introduced in the Phase 33 cloudflare-removal change that re-opened the TenantGuard same-origin bypass for EC2 tenant Canvas deployments. - **TenantGuard same-origin bypass (regression)** (`molecule-core` [#1898](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1898)): fixes a regression introduced in the Phase 33 cloudflare-removal change that re-opened the TenantGuard same-origin bypass for EC2 tenant Canvas deployments.
#### 📚 Docs #### 📚 Docs
- **Chrome DevTools MCP tutorial** (`docs` [#1798](https://git.moleculesai.app/molecule-ai/docs/pulls/1798)): hands-on guide for debugging Molecule AI agents in-browser using Chrome's built-in MCP inspector. - **Chrome DevTools MCP tutorial** (`docs` [#1798](https://git.moleculesai.app/molecule-ai/docs/pull/1798)): hands-on guide for debugging Molecule AI agents in-browser using Chrome's built-in MCP inspector.
- **Phase 34 launch page** (`docs` [#1799](https://git.moleculesai.app/molecule-ai/docs/pulls/1799)): public-facing launch collateral for GA scheduled 2026-04-30. - **Phase 34 launch page** (`docs` [#1799](https://git.moleculesai.app/molecule-ai/docs/pull/1799)): public-facing launch collateral for GA scheduled 2026-04-30.
- **Tool Trace demo environment** (`docs` [#1844](https://git.moleculesai.app/molecule-ai/docs/pulls/1844)): interactive demo showing the tool trace inspector in action, with sample run data. - **Tool Trace demo environment** (`docs` [#1844](https://git.moleculesai.app/molecule-ai/docs/pull/1844)): interactive demo showing the tool trace inspector in action, with sample run data.
- **Enterprise battlecard** (`docs` [#1864](https://git.moleculesai.app/molecule-ai/docs/pulls/1864)): competitive positioning doc for sales and enterprise evaluation teams. - **Enterprise battlecard** (`docs` [#1864](https://git.moleculesai.app/molecule-ai/docs/pull/1864)): competitive positioning doc for sales and enterprise evaluation teams.
#### 🧹 Internal #### 🧹 Internal
- `a2a-sdk` hot-pinned to `0.3.x` across all workspace template repos (`molecule-core` [#1890](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1890)); SDK upgrade path documented in `KI-009` (`internal` [#1631](https://git.moleculesai.app/molecule-ai/internal/issues/1631)). - `a2a-sdk` hot-pinned to `0.3.x` across all workspace template repos (`molecule-core` [#1890](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1890)); SDK upgrade path documented in `KI-009` (`internal` [#1631](https://git.moleculesai.app/molecule-ai/internal/issues/1631)).
- Phase 34 CI matrix expanded to cover Node 22 and Go 1.24 (`molecule-ci`). - Phase 34 CI matrix expanded to cover Node 22 and Go 1.24 (`molecule-ci`).
#### 🔧 Runtime fixes #### 🔧 Runtime fixes
- **Heartbeat 401 retry** (`molecule-ai-workspace-runtime` [#40](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/40)): heartbeat worker now retries with fresh token on 401 before declaring the workspace unreachable — eliminates false `disconnected` status during token rotation. - **Heartbeat 401 retry** (`molecule-ai-workspace-runtime` [#40](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pull/40)): heartbeat worker now retries with fresh token on 401 before declaring the workspace unreachable — eliminates false `disconnected` status during token rotation.
- **LLM token auto-detect** (`molecule-ai-workspace-runtime` [#38](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/38)): hermes runtime now auto-detects `max_tokens` from model context window and request timeout when not explicitly configured. - **LLM token auto-detect** (`molecule-ai-workspace-runtime` [#38](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pull/38)): hermes runtime now auto-detects `max_tokens` from model context window and request timeout when not explicitly configured.
--- ---
## 2026-05-10
### ✨ New features
- **A2A priority queue — Phase 1**: task dispatch now supports a `priority` field (`low` / `normal` / `high` / `urgent`). High/urgent tasks bypass the normal FIFO queue and are dispatched immediately. (`molecule-core` [#225](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/225))
- **Plugin drift detector + queue + admin apply endpoint**: a new plugin drift detection system monitors loaded plugins against their pinned SHAs and surfaces drift via a queue; admins can review and apply corrections via a new `/admin/plugin-apply` endpoint. (`molecule-core` [#204](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/204))
- **workspace-server pre-restart A2A drain signal**: the workspace-server now sends a pre-restart A2A drain signal before restarting, allowing peer workspaces to gracefully drain pending tasks instead of timing out. (`molecule-core` [#207](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/207))
- **Admin auth runbook**: new `admin-auth.md` runbook documents the test-token route lockdown and `AdminAuth` middleware behaviour for operators. (`molecule-core` [#220](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/220))
- **Static `.github-token` fallback to git credential helper**: workspace-server now falls back to a static `.github-token` value when no git credential helper is configured, enabling simpler air-gapped setups. (`molecule-core` [#219](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/219))
- **Keyboard shortcuts in Toolbar help dialog**: all keyboard shortcuts are now documented in a Toolbar help dialog accessible from the canvas top bar. (`molecule-core` [#244](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/244))
- **HTTP/SSE transport for Hermes MCP**: `a2a_mcp_server.py` now exposes `--transport=http --port=<N>` for Hermes workspaces that prefer HTTP + SSE over stdio. Endpoints: `POST /mcp` (JSON-RPC), `GET /mcp/stream` (SSE), `GET /health`. (`molecule-ai-workspace-runtime` [#5](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/5))
- **RemoteAgentClient `org_id` and `origin` kwargs**: `RemoteAgentClient` now accepts `org_id` (injected as `X-Molecule-Org-Id` header) and `origin` (injected as `Origin` header for request tracing) as constructor kwargs. Both propagate to all 14+ outbound call sites automatically via `_auth_headers()`. (`molecule-sdk-python` [#7](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/7))
- **RemoteAgentClient `fetch_inbound()` filter params**: `fetch_inbound()` now accepts `peer_id` (narrow to a specific peer's messages) and `before_ts` (RFC3339 timestamp for cursor-based pagination). Enables agents to selectively consume inbound activity from known siblings. (`molecule-sdk-python` [#6](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/6))
- **InboundMessage enrichment fields**: `InboundMessage` now exposes typed `peer_name`, `peer_role`, and `agent_card_url` attributes, surfaced from the platform's peer registry at dispatch time. Previously these were only accessible via the raw channel envelope. (`molecule-sdk-python` [#5](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/5))
- **`strip_a2a_boundary()` — OFFSEC-003 trust-boundary SDK helper**: `molecule-sdk-python` now exports `strip_a2a_boundary(text)` to strip `[A2A_RESULT_FROM_PEER]...[/A2A_RESULT_FROM_PEER]` wrappers from peer-generated content. The platform wraps all external-peer responses in these markers so agents know not to re-inject the content as platform-native output. Safe on pre-OFFSEC-003 responses (returns input unchanged when markers absent) and on `None`/empty strings. (`molecule-sdk-python` [#8](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/pulls/8))
### 🔧 Fixes
- **Canvas accessibility — WCAG 2.4.7 focus-visible rings (batch 2)**: `focus-visible` keyboard rings added to 9 customer-facing buttons across molecule-app — SignInButton on the landing page, "Request access" on the waitlist page, "+ New Workspace" CTA and Notifications bell in the app shell, "Try again" on error boundaries, "Sign out" in the header, the "I agree" button on terms-gate, and "Manage keys on canvas" in the API tokens view. ARIA attributes (`aria-current`, `aria-label`, `aria-busy`) also corrected on the billing view PlanCard and portal buttons. All rings use semantic color tokens — no hardcoded hex colors. (`molecule-app` [#5](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/5))
- **Canvas accessibility — WCAG 2.4.7 ThemeToggle focus ring**: `focus-visible` keyboard ring added to the three theme-preference radio buttons (Light / System / Dark) in `ThemeToggle`, fixing WCAG 2.4.7 for the theme switcher. (`molecule-app` [#10](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/10))
- **Canvas accessibility — WCAG 2.4.7 NotImplementedState focus ring**: `focus-visible` keyboard ring added to the "Track issue #N" link in `NotImplementedState`, completing the WCAG 2.4.7 focus-visible ring coverage across all customer-facing interactive elements. (`molecule-app` [#9](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/9))
- **SSRF validation before writing external workspace URL**: the workspace handler now validates URLs against SSRF allowlists before writing external workspace configurations. (`molecule-core` [#221](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/221))
- **Dockerfile tenant chown /org-templates**: `/org-templates` directory now correctly chowned to the canvas user to fix `EACCES` on `mkdir` for external resolvers. (`molecule-core` [#223](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/223))
- **CI `ghcr` → `ECR` migration + POST route smoke tests**: canary-verify workflow migrated from GHCR to ECR; new POST route smoke tests added for deployment verification. (`molecule-core` [#217](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/217))
- **CI `dorny/paths-filter` → shell-based git diff**: replaced `dorny/paths-filter` with shell-based git diff for Gitea Actions compatibility. (`molecule-core` [#208](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/208))
- **SOP tier-check clause splitter strips newlines**: the SOP tier-check script's clause splitter now correctly preserves newlines, fixing every `tier:low` PR CI failure. (`molecule-core` [#243](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/243))
- **SOP tier-check APPROVER_TEAMS pattern matching**: outer quotes removed from case patterns in `APPROVER_TEAMS` matching logic, fixing approval team resolution. (`molecule-core` [#231](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/231))
- **CI port `publish-workspace-server-image.yml` to `.gitea/workflows/`**: `publish-workspace-server-image.yml` migrated from `.github/workflows/` to `.gitea/workflows/` for Gitea Actions parity. (`molecule-core` [#237](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/237))
- **CI port `publish-runtime.yml` to `.gitea/workflows/`**: `publish-runtime.yml` migrated from `.github/workflows/` to `.gitea/workflows/` for Gitea Actions parity. (`molecule-core` [#211](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/211))
- **Docker base image digests pinned**: base image digests pinned in all Dockerfiles to ensure reproducible builds and prevent unexpected base image updates. (`molecule-core` [#199](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/199))
- **KeyboardShortcutsDialog corrected**: keyboard shortcuts dialog text corrected and min-clamp test expectations fixed. (`molecule-core` [#200](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/200))
- **`MODEL_PROVIDER` env var deprecated**: the `MODEL_PROVIDER` env var was misnamed — it carried the model ID (e.g. `claude-opus-4-7`) despite its name, and was being misused as a runtime selector. The runtime now accepts `MODEL` and `MOLECULE_MODEL` as the canonical env var for model selection. `MODEL_PROVIDER` still works but emits a deprecation warning. (`molecule-core` [#280](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/280))
- **`delegate_task` self-delegation guard**: calling `delegate_task` with your own workspace ID now returns an early actionable error instead of deadlocking the task lock. Previously self-delegation would hold `_run_lock`, timeout after 30 s, and waste the turn. (`molecule-core` [#291](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/291))
- **status.moleculesai.app false "down" reports fixed**: the custom uptime-probe binary correctly writes raw JSONL results but the aggregator step — which renders `history/<slug>.yml` and `history/summary.json` in Upptime format — was not migrated when the probe moved from Upptime to the custom binary post-2026-05-06. The missing aggregator caused `status.moleculesai.app` to show false-positive outages for Canvas and other endpoints. Resolved by adding the probe result aggregator. (`molecule-ai-status` [#10](https://git.moleculesai.app/molecule-ai/molecule-ai-status/pulls/10))
### 📚 Docs
- **Canvas known issues section cleaned up**: duplicate entries removed from known issues; pre-commit action link fixed. (`molecule-core` [#202](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/202))
- **Canvas controls section corrected**: Canvas Controls section corrected to reflect current keyboard navigation and MiniMap state. (`molecule-core` [#201](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/201))
### 🧹 Internal
- **SOP tier-check AND-composition of required team approvals per tier**: tier-check now enforces AND-composition of required team approvals per tier (`tier:high`). (`molecule-core` [#225](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/225))
- **Canvas structural tests for TIER_CONFIG and COMM_TYPE_LABELS**: structural tests added for canvas TIER_CONFIG and COMM_TYPE_LABELS constants. (`molecule-core` [#245](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/245))
## 2026-05-09
### ✨ New features
- **Keyboard-accessible canvas node resize**: Cmd/Ctrl+Arrow keys now resize canvas nodes in the topology view, satisfying WCAG AA keyboard navigation requirements. (`molecule-core` [#192](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/192))
- **Keyboard-accessible edge anchors**: Enter/Space on an edge now selects the anchor for keyboard-based topology editing. (`molecule-core` [#190](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/190))
### 🔧 Fixes
- **Handlers auto-restart workspace after file write/delete/replace**: file mutations via the Canvas editor now correctly trigger workspace restart, ensuring the agent picks up the new file state without manual intervention. (`molecule-core` [#188](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/188))
- **CI `gh api` → Gitea API migration**: all GitHub Actions `gh api` calls replaced with Gitea-compatible alternatives — CI now runs cleanly in Gitea Actions without GitHub dependency. (`molecule-core` [#191](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/191))
- **WCAG AA contrast fix + KeyboardShortcutsDialog improvements**: toolbar contrast ratios corrected for WCAG AA compliance; keyboard shortcuts dialog now scrolls properly on small viewports. (`molecule-core` [#198](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/198))
### 📚 Docs
- **Canvas accessibility audit — all gaps now closed**: the accessibility audit doc updated to reflect fully closed status. (`molecule-core` [#197](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/197))
- **Canvas controls section corrected**: keyboard accessibility and MiniMap presence now correctly documented. (`molecule-core` [#201](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/201))
- **Stale audit doc text fixed**: stale text from PR #182 corrected in canvas audit documentation. (`molecule-core` [#187](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/187))
### 🧹 Internal
- **gh-identity module path migration**: `github.com/Molecule-AI/gh-identity` imports migrated to `git.moleculesai.app/molecule-ai/gh-identity` across all workspace templates. (`molecule-core` [#189](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/189))
- **Pending uploads test isolation fix**: sweeper test isolation corrected — eliminates cross-test pollution in CI. (`molecule-core` [#185](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/185))
- **Poll error counter to 0 before assert**: RecordsMetricsOnSuccess now polls error counter to 0 before asserting, eliminating flaky E2E test failures. (`molecule-core` [#194](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/194))
---
## 2026-05-08
### 🔧 Fixes
- **molecule-app CI testTimeout bumped to 20s**: vitest `testTimeout` increased to 20 s to handle shared act_runner load on the molecule-app repo. (`molecule-app` [#4](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/4))
- **molecule-app drops staging branch — trunk-based migration**: first repo of the trunk-based development migration; staging branch removed. (`molecule-app` [#3](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/3))
- **docs CI switches to ubuntu-latest**: docs repo CI now uses `ubuntu-latest` now that the repo is public. (`docs` [#4](https://git.moleculesai.app/molecule-ai/docs/pulls/4))
---
## 2026-05-07
### 📚 Docs
- **Install guide — GitHub.com refs → Gitea**: all active `github.com/Molecule-AI` references migrated to `git.moleculesai.app/molecule-ai` in the installation docs. (`docs` #1)
- **Website github.com → Gitea link migration**: `molecules-market` website links updated to point at Gitea. (`landingpage` #3)
- **molecule-monorepo → molecule-core rename (Phase 4)**: landingpage follow-up renaming of `molecule-monorepo` to `molecule-core` in all cross-repo references. (`landingpage` #4)
- **CI lowercase 'molecule-ai/' in cross-repo workflow refs**: cross-repo workflow references now consistently lowercase for Gitea Actions compatibility. (`landingpage` #2)
- **Market Purchase button on tier cards**: demo Mock #1 — Purchase button now appears on tier cards in the molecules-market. (`landingpage` #5)
### 🔧 Fixes
- **molecule-app runs-on ubuntu-latest**: Hetzner runner labels post-suspension; CI now uses `ubuntu-latest`. (`molecule-app` [#1](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/1))
- **molecule-app GitHub → Gitea URL migration**: all `github.com/Molecule-AI` references migrated to `git.moleculesai.app/molecule-ai` in molecule-app. (`molecule-app` [#2](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/2))
- **docs GitHub → Gitea URL migration**: `github.com/Molecule-AI` references migrated to Gitea across docs repo. (`docs` [#3](https://git.moleculesai.app/molecule-ai/docs/pulls/3))
---
## 2026-05-06
### 🧹 Internal
- **molecule-core org-wide Gitea URL migration**: all `github.com/Molecule-AI` references migrated to `git.moleculesai.app/molecule-ai` across all repos in the org. (`molecule-core`)
- **Hetzner act-runner suspension**: CI runners updated to use `ubuntu-latest` labels following Hetzner act-runner suspension. (`molecule-app` [#1](https://git.moleculesai.app/molecule-ai/molecule-app/pulls/1))
---
## 2026-04-22 ## 2026-04-22
### ✨ New features ### ✨ New features
@ -289,7 +84,7 @@ Customer selects `model=minimax/MiniMax-M2.7-highspeed` in Canvas → the model
API key now propagate correctly into the runtime environment instead of being dropped API key now propagate correctly into the runtime environment instead of being dropped
on the floor at provisioning time. Works for hermes workspaces in both hosted SaaS on the floor at provisioning time. Works for hermes workspaces in both hosted SaaS
and self-hosted EC2 deployments. and self-hosted EC2 deployments.
(`molecule-core` [#1685](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1685)) (`molecule-core` [#1685](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1685))
#### EC2 Instance Connect Endpoint — one-click shell from Canvas #### EC2 Instance Connect Endpoint — one-click shell from Canvas
Canvas Terminal tab now uses AWS EC2 Instance Connect Endpoint to open a PTY inside Canvas Terminal tab now uses AWS EC2 Instance Connect Endpoint to open a PTY inside
@ -297,7 +92,7 @@ any workspace EC2 instance — no SSH keys to manage, no IP to copy, no security
rules to configure. IAM policy gates access, STS pushes a short-lived key that rules to configure. IAM policy gates access, STS pushes a short-lived key that
auto-expires, and every tunnel open is recorded in CloudTrail. auto-expires, and every tunnel open is recorded in CloudTrail.
See the [EC2 Instance Connect guide](/docs/infra/workspace-terminal). See the [EC2 Instance Connect guide](/docs/infra/workspace-terminal).
(`molecule-core` [#1554](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1554)) (`molecule-core` [#1554](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1554))
#### Phase 33 — Cloudflare Tunnel replaced with direct-connect public IPs #### Phase 33 — Cloudflare Tunnel replaced with direct-connect public IPs
Cloud-hosted workspaces no longer route through `cloudflared`. Each workspace gets Cloud-hosted workspaces no longer route through `cloudflared`. Each workspace gets
@ -306,32 +101,32 @@ TLS on port 443. Reduces latency by ~2040 ms (region-dependent), removes the
Cloudflare egress cost dependency, and enables direct `curl` debugging without Cloudflare egress cost dependency, and enables direct `curl` debugging without
the tunnel path. the tunnel path.
See the [migration blog post](/blog/cloudflare-tunnel-migration). See the [migration blog post](/blog/cloudflare-tunnel-migration).
(`molecule-core` [#1612](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1612)) (`molecule-core` [#1612](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1612))
### 🔒 Security ### 🔒 Security
- **F1085 deleteViaEphemeral**: `rm` scope restricted to `/configs` volume only — - **F1085 deleteViaEphemeral**: `rm` scope restricted to `/configs` volume only —
prevents deletion of application code or workspace files if the exec form is prevents deletion of application code or workspace files if the exec form is
exploited. Applied to both `main` and `staging`. (`molecule-core` [#1682](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1682), [#1616](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1616)) exploited. Applied to both `main` and `staging`. (`molecule-core` [#1682](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1682), [#1616](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1616))
### 🔧 Fixes ### 🔧 Fixes
- Canvas now fetches the runtime and model dropdown from the `/templates` registry - Canvas now fetches the runtime and model dropdown from the `/templates` registry
at load time — runtime list stays current without code deploys. (`molecule-core` [#1666](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1666)) at load time — runtime list stays current without code deploys. (`molecule-core` [#1666](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1666))
- Canvas accessibility: `aria-hidden` correctly applied to decorative SVGs; - Canvas accessibility: `aria-hidden` correctly applied to decorative SVGs;
`MissingKeysModal` now uses correct dialog semantics and manages focus. (`molecule-core` [#1594](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1594)) `MissingKeysModal` now uses correct dialog semantics and manages focus. (`molecule-core` [#1594](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1594))
- Provisioner pulls workspace template images from GHCR instead of Docker Hub - Provisioner pulls workspace template images from GHCR instead of Docker Hub
for faster cold starts and reduced third-party dependency. (`molecule-core` [#1624](https://git.moleculesai.app/molecule-ai/molecule-core/pulls/1624)) for faster cold starts and reduced third-party dependency. (`molecule-core` [#1624](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1624))
- Shared runtime heartbeat no longer leaves workspaces in a phantom-busy state after - Shared runtime heartbeat no longer leaves workspaces in a phantom-busy state after
task completion. (`molecule-ai-workspace-runtime` [#37](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pulls/37)) task completion. (`molecule-ai-workspace-runtime` [#37](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/pull/37))
### 📚 Docs ### 📚 Docs
- **MCP server structured logging**: `LOG_LEVEL` env var (`trace`/`debug`/`info`/`warn`/`error`/`fatal`), - **MCP server structured logging**: `LOG_LEVEL` env var (`trace`/`debug`/`info`/`warn`/`error`/`fatal`),
pino JSON output in production, pretty-print in development, AsyncLocalStorage pino JSON output in production, pretty-print in development, AsyncLocalStorage
context on every log entry (tool name, request ID, workspace ID). (`docs` [#78](https://git.moleculesai.app/molecule-ai/docs/pulls/78)) context on every log entry (tool name, request ID, workspace ID). (`docs` [#78](https://git.moleculesai.app/molecule-ai/docs/pull/78))
- **molecli shell completion**: tab completion for `molecule` CLI in bash, zsh, fish, - **molecli shell completion**: tab completion for `molecule` CLI in bash, zsh, fish,
and PowerShell — covers all subcommands and flags. (`docs` [#79](https://git.moleculesai.app/molecule-ai/docs/pulls/79)) and PowerShell — covers all subcommands and flags. (`docs` [#79](https://git.moleculesai.app/molecule-ai/docs/pull/79))
### 🧹 Internal ### 🧹 Internal

View File

@ -1,222 +0,0 @@
---
title: "Claude Code Channel Plugin — Connect a Claude Code Session as an External Workspace"
description: "Bridge Molecule A2A traffic into a running Claude Code session via MCP. Polling-based, no tunnel required. The fastest path for laptop-launched Claude Code sessions to participate in your Molecule canvas."
---
# Claude Code Channel Plugin
Run [Claude Code](https://claude.com/claude-code) on your laptop and have it appear on the Molecule AI canvas as a first-class external workspace. Inbound A2A messages from peer workspaces surface as conversation turns; replies route back through Molecule's A2A endpoints.
> **What this is:** [`molecule-mcp-claude-channel`](https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel) — an MCP-based "channel plugin" that turns a Claude Code session into a Molecule workspace.
> **What this is NOT:** the [Python SDK / curl register flow](/docs/guides/external-agent-registration) for arbitrary HTTP-speaking agents. That flow needs a public URL the platform can POST to. This one polls — runs on any laptop behind any NAT.
---
## What you get
```
Molecule peer ──A2A──▶ [your workspace] ──poll──▶ [plugin] ──MCP notification──▶ Claude Code
▲ │
└────── POST /workspaces/:id/a2a ◄── reply_to_workspace ──┘
```
| Property | Value |
|---|---|
| **Inbound latency** | up to `MOLECULE_POLL_INTERVAL_MS` (default 5s) |
| **Outbound latency** | direct POST — sub-second |
| **Tunnel / public URL** | not required |
| **Auth model** | per-workspace bearer token (same as Python SDK) |
| **Multi-workspace** | yes, comma-separated list |
---
## Prerequisites
| You need | Notes |
|---|---|
| A Molecule AI tenant | Self-hosted localhost or your `*.staging.moleculesai.app` SaaS tenant |
| One or more workspace IDs | Created via canvas or `POST /workspaces` (see [External Agent Registration](/docs/guides/external-agent-registration)) |
| The workspace bearer token | Shown once when the workspace is created — save it from the canvas modal |
| Claude Code | `claude` CLI ≥ the version that supports `--channels` |
| `bun` | The plugin runs under bun for fast startup; `bun install` is invoked automatically by `start` |
> **Note:** The platform must be running molecule-core ≥ PR #2300, which shipped the `?since_secs=` query parameter on `GET /workspaces/:id/activity`. Available on all staging-onward and self-hosted main builds after 2026-04-29.
---
## Step 1 — Create the workspace
In your Molecule canvas:
1. Click **+ New workspace**
2. Choose **External** runtime
3. Set tier as needed; click **Create**
4. The "Connect your external agent" modal opens — switch to the **Claude Code** tab
5. Copy the entire snippet (everything from the `mkdir -p` line through `claude --channels ...`)
Or via API:
```bash
curl -X POST "$MOLECULE_PLATFORM_URL/workspaces" \
-H "Content-Type: application/json" \
-d '{"name": "My Claude Code", "external": true, "tier": 2}'
```
The response includes `claude_code_channel_snippet` — same content as the canvas tab, ready to paste.
## Step 2 — Set up the channel config
Run the snippet from Step 1. It does two things:
```bash
mkdir -p ~/.claude/channels/molecule
cat > ~/.claude/channels/molecule/.env <<'EOF'
MOLECULE_PLATFORM_URL=https://your-tenant.staging.moleculesai.app
MOLECULE_WORKSPACE_IDS=ws-uuid-1
MOLECULE_WORKSPACE_TOKENS=<paste auth_token from create response>
EOF
chmod 600 ~/.claude/channels/molecule/.env
```
Replace the token placeholder with the workspace bearer from Step 1.
## Step 3 — Launch Claude Code
```bash
claude --channels plugin:molecule@molecule-ai/molecule-mcp-claude-channel
```
You should see on stderr (use `--debug` to surface):
```
molecule channel: connected — watching 1 workspace(s) at https://your-tenant.staging.moleculesai.app
workspaces: ws-uuid-1
poll: every 5000ms with 30s window
```
That's it — the workspace is live on the canvas with a purple **REMOTE** badge, and any A2A traffic the workspace receives surfaces as conversation turns in your Claude Code session.
---
## How replies work
When a peer's message lands in your session, you'll see a turn with structured metadata:
```json
{
"method": "notifications/claude/channel",
"params": {
"content": "Hey, can you take a look at this? <issue body>",
"meta": {
"source": "molecule",
"workspace_id": "ws-uuid-1",
"peer_id": "ws-uuid-pm-coordinator",
"method": "user_message",
"activity_id": "act-...",
"ts": "2026-04-29T..."
}
}
}
```
Reply normally — Claude calls the `reply_to_workspace` MCP tool with `peer_id` from the meta block, and the response flows back through `POST /workspaces/:peer_id/a2a` so peers see it just like any other A2A message.
---
## Multi-workspace setup
Watch multiple workspaces from a single Claude Code session by comma-separating the lists. Both must have the same length and order:
```bash
MOLECULE_WORKSPACE_IDS=ws-pm,ws-researcher,ws-engineer
MOLECULE_WORKSPACE_TOKENS=tok-pm,tok-researcher,tok-engineer
```
When Claude replies, the `reply_to_workspace` tool requires `workspace_id` (which of the watched workspaces to reply AS) explicitly. With a single workspace it's implicit.
---
## Configuration reference
| Variable | Default | Purpose |
|---|---|---|
| `MOLECULE_PLATFORM_URL` | (required) | Tenant base URL (no trailing slash) |
| `MOLECULE_WORKSPACE_IDS` | (required) | Comma-separated workspace UUIDs to watch |
| `MOLECULE_WORKSPACE_TOKENS` | (required) | Comma-separated bearer tokens, **same order as IDs** |
| `MOLECULE_POLL_INTERVAL_MS` | `5000` | How often each workspace is polled (ms) |
| `MOLECULE_POLL_WINDOW_SECS` | `30` | `since_secs` window per poll. Wider than interval to recover from missed ticks |
| `MOLECULE_STATE_DIR` | `~/.claude/channels/molecule` | Override state directory (testing) |
---
## Architecture notes
### Why polling instead of push?
The [Python SDK external-agent flow](/docs/guides/external-agent-registration) uses **push**: register an inbound URL, platform POSTs A2A to that URL. Lower latency but requires a tunnel (ngrok / Cloudflare) or static IP — non-trivial for laptop sessions.
This plugin uses **polling** as the default because it works through every NAT/firewall with zero infra. Cost: up to `MOLECULE_POLL_INTERVAL_MS` of inbound latency. For production setups where lower latency matters, push mode is on the v0.2 roadmap.
### Why the 30s window over a 5s interval?
A single missed tick (transient network blip, GC pause, laptop sleep) shouldn't lose messages. The plugin re-fetches the last 30 seconds on every poll and dedups by `activity_id`, so 25 seconds of overlap is the recovery margin. Increase `MOLECULE_POLL_WINDOW_SECS` for noisier networks.
### Singleton lock
Only one channel server runs per host — multiple instances would race the dedup state and double-deliver. The plugin maintains a PID file at `~/.claude/channels/molecule/bot.pid` and on startup kills any stale predecessor. This mirrors the [`@claude-plugins-official/telegram`](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/telegram) pattern.
---
## Troubleshooting
### "molecule channel: required config missing"
The plugin started before you filled in `.env`. Re-run the snippet from Step 2, then re-launch Claude Code.
### "molecule channel: poll `<ws-id>` returned 401"
Bearer token mismatch. Two common causes:
- The token in `MOLECULE_WORKSPACE_TOKENS` doesn't match the workspace whose ID is in the corresponding position of `MOLECULE_WORKSPACE_IDS`. Verify same-order pairing.
- The workspace was rotated and the token was revoked. Generate a new token from the canvas Settings tab (or `POST /admin/workspaces/:id/tokens`).
### "molecule channel: poll `<ws-id>` returned 404"
Either the workspace doesn't exist or the `MOLECULE_PLATFORM_URL` is wrong. Confirm:
```bash
curl -fsS "$MOLECULE_PLATFORM_URL/workspaces/$WS_ID" \
-H "Authorization: Bearer $WS_TOKEN" | jq '.workspace.id'
```
### A2A messages aren't surfacing
Check that the watched workspace is actually receiving them — the plugin only pulls `activity_logs` rows whose `activity_type = a2a_receive`. If peers aren't sending to this workspace, there's nothing to surface. Verify with:
```bash
curl -fsS "$MOLECULE_PLATFORM_URL/workspaces/$WS_ID/activity?type=a2a_receive&limit=10" \
-H "Authorization: Bearer $WS_TOKEN" | jq
```
If that returns events but Claude doesn't see them, file an issue at [`molecule-mcp-claude-channel`](https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel/issues) with the workspace_id + sample event.
---
## Limitations (v0.1)
- **Polling-only inbound.** No push mode yet; latency floor is `MOLECULE_POLL_INTERVAL_MS`.
- **No pairing flow.** Tokens are configured manually via `.env`; no canvas-side approval handshake.
- **No file-attachment download.** URLs surface in the meta block; the host fetches on-demand.
- **No outbound channel-init.** The plugin only sends replies (in response to inbound A2A); starting a fresh A2A conversation initiated FROM the Claude Code side requires a future `start_workspace_chat` tool.
Track the v0.2 roadmap on the [plugin repo's README](https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel#limitations-v01).
---
## See also
- [External Agent Registration](/docs/guides/external-agent-registration) — full A2A wire-shape reference + Python SDK + curl flow
- [External Workspace Quickstart](/docs/guides/external-workspace-quickstart) — 5-min guide for any HTTP-speaking agent
- [Remote Workspaces FAQ](/docs/guides/remote-workspaces-faq) — production hardening notes
- [`molecule-mcp-claude-channel`](https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel) — plugin source code, issues, v0.2 roadmap

View File

@ -110,8 +110,6 @@ import os, logging
client = RemoteAgentClient( client = RemoteAgentClient(
workspace_id = os.environ["WORKSPACE_ID"], workspace_id = os.environ["WORKSPACE_ID"],
platform_url = os.environ["PLATFORM_URL"], platform_url = os.environ["PLATFORM_URL"],
org_id = os.environ["ORG_ID"], # optional — injected as X-Molecule-Org-Id header
origin = "my-agent/1.0", # optional — injected as Origin header for tracing
agent_card = {"name": "researcher", "skills": ["web-search", "research"]}, agent_card = {"name": "researcher", "skills": ["web-search", "research"]},
) )
client.register() # Phase 30.1 — get + cache token client.register() # Phase 30.1 — get + cache token
@ -132,84 +130,6 @@ The agent appears on the canvas with a **purple REMOTE badge** within seconds. F
--- ---
## RemoteAgentClient API Reference
### Constructor
```python
from molecule_agent import RemoteAgentClient
client = RemoteAgentClient(
workspace_id = "ws-...", # required — your workspace UUID
platform_url = "https://...", # required — your platform base URL
auth_token = "...", # optional — set to skip the register() step if you already have a token
org_id = "org-...", # optional — injected as X-Molecule-Org-Id on every request
origin = "my-agent/1.0", # optional — injected as Origin header for request tracing
agent_card = {...}, # optional — updated on every heartbeat
)
```
| Parameter | Type | Description |
|---|---|---|
| `workspace_id` | `str` | Your workspace UUID, obtained from `POST /workspaces`. |
| `platform_url` | `str` | Your platform base URL, e.g. `https://acme.moleculesai.app`. |
| `auth_token` | `str` | Pre-obtained bearer token. If omitted, call `register()` to fetch one. |
| `org_id` | `str` | Optional org UUID. When set, injected as `X-Molecule-Org-Id` on every outbound request. |
| `origin` | `str` | Optional UA string (e.g. `"researcher/2.1"`). Injected as `Origin` header for logging/tracing. |
| `agent_card` | `dict` | Agent metadata broadcast to the canvas. Updated on every heartbeat. |
### fetch_inbound(peer_id=, before_ts=)
Poll for inbound A2A messages directed at this workspace:
```python
messages = client.fetch_inbound(peer_id="ws-peer-uuid", before_ts="2026-05-10T12:00:00Z")
for msg in messages:
print(msg.id, msg.method, msg.peer_name, msg.peer_role)
```
| Parameter | Type | Description |
|---|---|---|
| `peer_id` | `str` | Filter to messages from a specific peer workspace UUID. Omit to receive from all peers. |
| `before_ts` | `str` | RFC3339 timestamp. Return only messages older than this cut-off. Use for pagination by tracking the oldest message seen. |
Returns a list of `InboundMessage` objects.
### InboundMessage
Each inbound message carries these fields in addition to the standard A2A fields:
| Field | Type | Description |
|---|---|---|
| `id` | `str` | Message ID. |
| `method` | `str` | A2A method (`delegate_task`, `cancel_task`, etc.). |
| `params` | `dict` | Method parameters. |
| `peer_id` | `str` | UUID of the peer workspace that sent this message. |
| `peer_name` | `str` | Display name of the sending peer (from its agent card). |
| `peer_role` | `str` | Role of the sending peer (`"sre"`, `"frontend"`, etc.). |
| `agent_card_url` | `str` | URL of the sending peer's agent card. |
| `raw` | `dict` | Raw channel envelope for forward-compatibility. |
> **Note:** `peer_name`, `peer_role`, and `agent_card_url` are enriched from the platform's peer registry at dispatch time. They are `None` if the sending peer has not registered an agent card.
### Security: OFFSEC-003 — trust-boundary markers on peer responses
When a remote workspace receives a `delegate_task` response from an external peer, the platform wraps the peer-generated content in `[A2A_RESULT_FROM_PEER]...[/A2A_RESULT_FROM_PEER]` trust-boundary markers. These markers signal to the agent that the enclosed content originated outside the platform's trust boundary and must not be re-injected as platform-native output.
Use `strip_a2a_boundary()` to strip the wrappers before processing the content:
```python
from molecule_agent import RemoteAgentClient, strip_a2a_boundary
# Normalise inbound peer result — safe on pre-OFFSEC-003 responses (returns
# input unchanged when markers absent) and on None/empty strings.
result = strip_a2a_boundary(msg.params.get("result", ""))
```
This is particularly important when displaying peer results to users or using them as tool inputs — always strip the boundary markers first. See `molecule-core` [#334](https://git.moleculesai.app/molecule-ai/molecule-core/pull/334) for the platform-side implementation.
---
## What Phase 30 Covers ## What Phase 30 Covers
| Phase | What shipped | Endpoint | | Phase | What shipped | Endpoint |

View File

@ -1,214 +0,0 @@
---
title: "a2a-sdk v0 → v1 migration"
description: "Cheat sheet for migrating workspace runtime code (and forks) from a2a-sdk 0.3.x to 1.x — renamed/removed symbols, common error shapes, before/after diffs."
---
import { Callout } from 'fumadocs-ui/components/callout';
The `a2a-sdk` Python package released v1.0 in late April 2026. The
Molecule workspace runtime migrated under tracking ID **KI-009** and
shipped in `molecule-ai-workspace-runtime` **v0.1.11** (commit
`d5cf872`, PR #39). The platform now runs exclusively on v1.
If you're consuming the platform's published wheel, bumping
`molecule-ai-workspace-runtime>=0.1.11` handles the migration for
you. If you maintain a fork of the runtime, an external agent talking
A2A directly, or your own adapter that imports from `a2a.*`, this page
is your checklist.
## Why migrate
- **Upstream**: `a2a-sdk` 1.0 reorganised the import surface, flattened
`Part`, removed deprecated capability flags, and replaced the
`A2AStarletteApplication` wrapper with explicit Starlette route
factories.
- **Platform**: as of 2026-04-24 the platform sends/receives via v1
shapes natively. The SDK ships a v0_3 compat layer (enabled in the
runtime via `enable_v0_3_compat=True` on `create_jsonrpc_routes`) so
in-flight 0.x callers don't break, but new code should target v1.
- **Forks/external runtimes**: v0 code throws on `import a2a.utils`
and `from a2a.server.apps import A2AStarletteApplication` once you
install v1, so the migration is a hard cutover at install time, not
a soft deprecation.
## Cheat sheet — renamed and removed symbols
The four breaking changes that hit the Molecule runtime during KI-009.
All four are confirmed against
`molecule-core/workspace/` source.
### 1. `new_agent_text_message` renamed to `new_text_message`
- **v0 location**: `a2a.utils.new_agent_text_message`
- **v1 location**: `a2a.helpers.new_text_message`
Both the module path and the symbol name changed.
### 2. `Part` API flattened — `TextPart` removed
- **v0**: `Part(root=TextPart(text="..."))` — `Part` wrapped a `root`
union of `TextPart` / `FilePart` / `DataPart`.
- **v1**: `Part(text="...")` — `Part` accepts the text payload
directly. `TextPart` no longer exists as a public symbol.
`FilePart` / `DataPart` are similarly flattened (`Part(file=...)`,
`Part(data=...)`); the Molecule runtime only emits text parts so the
file/data shapes weren't exercised in KI-009 and aren't covered by
this guide.
### 3. `A2AStarletteApplication` removed — use route factories
- **v0**: `from a2a.server.apps import A2AStarletteApplication` then
`A2AStarletteApplication(agent_card, request_handler).build()`.
- **v1**: `from a2a.server.routes import create_agent_card_routes,
create_jsonrpc_routes` then build a Starlette app from the returned
route lists.
The factories also let you mount the JSON-RPC endpoint at any path
(the runtime mounts at `/` because the platform POSTs to root, see
`workspace/main.py:279`).
### 4. `state_transition_history` capability flag removed
- **v0**: `AgentCapabilities(streaming=..., push_notifications=...,
state_transition_history=True)` was a per-agent opt-in.
- **v1**: the field is gone from `AgentCapabilities`. Per the SDK's own
`a2a/compat/v0_3/conversions.py`: *"No longer supported in v1.0"*.
The capability is now universal — `Task.history` is always available
and `tasks/get` accepts `historyLength` via `apply_history_length()`.
If you pass `state_transition_history=...` as a kwarg to
`AgentCapabilities` under v1, Pydantic will reject it. Drop the kwarg.
See [`workspace/main.py`](https://git.moleculesai.app/molecule-ai/molecule-core/src/branch/main/workspace/main.py)
for the explanatory comment that prevents future accidental re-adds.
## Common error shapes
When v0 code runs against the v1 SDK, the failure modes look like this:
| Error | Cause |
|---|---|
| `ModuleNotFoundError: No module named 'a2a.utils'` | v0 import path; module renamed to `a2a.helpers`. |
| `ImportError: cannot import name 'A2AStarletteApplication' from 'a2a.server.apps'` | The whole `a2a.server.apps` module is gone in v1. Switch to `a2a.server.routes` factories. |
| `ImportError: cannot import name 'TextPart' from 'a2a.types'` | Flattened `Part` API; use `Part(text=...)`. |
| `ValueError: Protocol message AgentCapabilities has no "state_transition_history" field` | Removed capability flag passed as kwarg; drop it. |
| `ValueError: Protocol message Part has no "root" field` | v0 `Part(root=TextPart(...))` shape against v1 schema; flatten to `Part(text=...)`. |
The protobuf-style `ValueError` messages always follow the pattern
`Protocol message <Type> has no "<field>" field` — that's the
fingerprint of "v0 shape against v1 schema." Treat it as a v0→v1 hint
even if the field name isn't on the cheat sheet above.
## Migration checklist
1. **Bump the dep** — `a2a-sdk[http-server]>=0.3.25` is the floor; remove
any `<1.0` upper bound. The Molecule wheel uses
`a2a-sdk[http-server]>=0.3.25` with no upper bound (see
[`molecule-ai-workspace-runtime/pyproject.toml`](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/src/branch/main/pyproject.toml)).
2. **Fix imports** — sweep the four renamed/removed symbols above. A
safe grep is `grep -rn "from a2a\\|import a2a"` across your tree.
3. **Fix removed-field reads/writes** — search for
`state_transition_history` usage and delete the kwarg/field access.
4. **Flatten `Part` constructors** — search for `Part(root=` and
convert to `Part(text=...)` / `Part(file=...)` / `Part(data=...)`.
5. **Replace the app factory** — search for `A2AStarletteApplication`
and rewrite the bootstrap using `create_agent_card_routes` +
`create_jsonrpc_routes`. Pass `enable_v0_3_compat=True` to
`create_jsonrpc_routes` if your peers may still be on v0.
6. **Re-run tests** — fixture-level mocks of `a2a.helpers` /
`a2a.utils` need to mock both names so tests still pass during the
rename rollout (see
[`workspace/tests/conftest.py`](https://git.moleculesai.app/molecule-ai/molecule-core/src/branch/main/workspace/tests/conftest.py)
for the dual-name pattern).
## Before / after diffs
### `new_agent_text_message` → `new_text_message`
```diff
-from a2a.utils import new_agent_text_message
+from a2a.helpers import new_text_message
async def execute(self, context, event_queue):
- await event_queue.enqueue_event(new_agent_text_message("hello"))
+ await event_queue.enqueue_event(new_text_message("hello"))
```
### Flat `Part` API
```diff
-from a2a.types import Part, TextPart
+from a2a.types import Part
-msg_parts = [Part(root=TextPart(text=final_text))]
+msg_parts = [Part(text=final_text)]
```
### `AgentCapabilities` — drop `state_transition_history`
```diff
capabilities=AgentCapabilities(
streaming=config.a2a.streaming,
push_notifications=config.a2a.push_notifications,
- state_transition_history=True,
),
```
### `A2AStarletteApplication` → route factories
```diff
-from a2a.server.apps import A2AStarletteApplication
+from a2a.server.routes import create_agent_card_routes, create_jsonrpc_routes
-app = A2AStarletteApplication(
- agent_card=agent_card,
- http_handler=request_handler,
-).build()
+routes = []
+routes.extend(create_agent_card_routes(agent_card))
+routes.extend(create_jsonrpc_routes(
+ request_handler=request_handler,
+ rpc_url="/",
+ enable_v0_3_compat=True,
+))
+app = Starlette(routes=routes)
```
The `enable_v0_3_compat=True` flag on `create_jsonrpc_routes` is what
keeps in-flight v0 callers (peers that haven't migrated yet) from
breaking — it accepts the old method names and translates them. The
Molecule runtime ships with this flag on (see
[`workspace/main.py`](https://git.moleculesai.app/molecule-ai/molecule-core/src/branch/main/workspace/main.py));
strip it once your entire fleet is on v1.
## For downstream consumers
- **Using the published wheel** (`pip install
molecule-ai-workspace-runtime>=0.1.11`): the migration is in the
wheel — no code changes needed in your adapter or workspace template
beyond bumping the pin.
- **Running a fork of the runtime**: cherry-pick or rebase against
commit `d5cf872` ("feat: migrate a2a-sdk 1.x (KI-009) (#39)") in
`molecule-ai-workspace-runtime`. The diff is the canonical reference
for what KI-009 actually changed.
- **Standalone external agent** (talking A2A without the wheel): apply
the [Migration checklist](#migration-checklist) directly to your
source. The four cheat-sheet items are the entire surface that
changed for the typical agent role; only `Part` flattening and the
`state_transition_history` removal affect on-the-wire shapes — the
other two are import-only.
<Callout type="info">
The wheel keeps `enable_v0_3_compat=True` on `create_jsonrpc_routes`,
so a v0 peer can still hit a v1 wheel and vice versa during the
migration window. You don't need to coordinate a fleet-wide cutover —
migrate at your own pace.
</Callout>
## See also
- [`molecule-ai-workspace-runtime` v0.1.11 release](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/releases/tag/v0.1.11) — first wheel containing KI-009
- PR #39 (feat: migrate a2a-sdk 1.x / KI-009) — closed without merge; PR content is historical
- PR #48 (feat(a2a): dual-compat for a2a-sdk 0.3.x and 1.x) — closed without merge; PR content is historical
- [Bring Your Own Runtime (MCP)](/docs/runtime-mcp) — universal wheel install path
- [External Agents](/docs/external-agents) — manual A2A path for non-MCP runtimes

View File

@ -102,22 +102,6 @@ example above. Drop it into your client's MCP settings file
(typically `~/.cursor/mcp.json` for Cursor, the MCP Servers panel for (typically `~/.cursor/mcp.json` for Cursor, the MCP Servers panel for
Cline) and restart the client. Cline) and restart the client.
## Environment variables
The following env vars are supported by the `molecule-mcp` wheel in addition to the
required trio (`WORKSPACE_ID`, `PLATFORM_URL`, `MOLECULE_WORKSPACE_TOKEN`):
| Env var | What it controls | Default |
|---|---|---|
| `MOLECULE_MODEL` | **Canonical.** The model ID the workspace runtime uses — e.g. `claude-opus-4-7`, `minimax/MiniMax-M2.7-highspeed` | _(unset — template default)_ |
| `MODEL` | **Alias for `MOLECULE_MODEL`.** Accepted for backwards compatibility. | _(unset)_ |
| `MODEL_PROVIDER` | **Deprecated.** This var was previously misread as "runtime selector" (`claude-code`, `minimax`, etc.) but carried the model ID, causing the wrong model to be used. Prefer `MOLECULE_MODEL`. | _(unset — emits deprecation warning)_ |
| `MOLECULE_AGENT_SKILLS` | Comma-separated skill names — e.g. `research,code-review,memory-curation` | `[]` |
<Callout type="warn">
`MODEL_PROVIDER` is deprecated. It was misnamed — despite its name it carried the **model ID** (e.g. `claude-opus-4-7`), not the runtime/provider name. Setting it caused production incidents where the Claude CLI received `--model MODEL_PROVIDER_VALUE` and returned 404s. Use `MOLECULE_MODEL` instead.
</Callout>
## Optional — declare your identity & capabilities ## Optional — declare your identity & capabilities
Three additional env vars control how your workspace appears on the Three additional env vars control how your workspace appears on the
@ -222,38 +206,6 @@ Claude Code, Cursor, Cline, OpenCode, hermes-agent, or anything else
that opens an MCP stdio connection. If your client speaks MCP, it that opens an MCP stdio connection. If your client speaks MCP, it
speaks the wheel. speaks the wheel.
## HTTP/SSE transport for Hermes workspaces
Hermes workspaces (which are MCP-native) can connect to the platform MCP
server over **HTTP + Server-Sent Events** instead of stdio. This is the
recommended path when Hermes runs as a standalone service rather than
inside a shell.
The `a2a_mcp_server.py` in the runtime exposes two endpoints:
| Endpoint | Method | Purpose |
|---|---|---|
| `/mcp` | `POST` | Receive JSON-RPC requests |
| `/mcp/stream` | `GET` | SSE stream for push-based responses |
| `/health` | `GET` | Health check |
Start the server with the `--transport=http --port=<N>` flags:
```bash
python a2a_mcp_server.py \
--transport=http \
--port=8080 \
--workspace-id=<uuid> \
--platform-url=https://<tenant>.moleculesai.app \
--workspace-token=<token>
```
<Callout type="info">
The stdio transport (described in [Step 2](#step-2--add-it-to-your-runtime))
remains the default. HTTP/SSE is an alternative for Hermes deployments
where a long-running daemon process is preferred over a stdio subprocess.
</Callout>
## Heartbeat & lifecycle ## Heartbeat & lifecycle
The wheel spawns a daemon thread that POSTs `/registry/heartbeat` every The wheel spawns a daemon thread that POSTs `/registry/heartbeat` every

View File

@ -163,4 +163,4 @@ This header is added automatically by the workspace executor when `task_budget >
- [Org Template](/docs/org-template) — deploy effort/task_budget settings across an entire team via `org.yaml` - [Org Template](/docs/org-template) — deploy effort/task_budget settings across an entire team via `org.yaml`
- [Observability](/docs/observability) — monitor token usage per workspace to tune your budget settings - [Observability](/docs/observability) — monitor token usage per workspace to tune your budget settings
- [API Reference — POST /workspaces](/docs/api-reference#post-workspaces) - [API Reference — POST /workspaces](/docs/api-reference#post-workspaces)
- [Claude Opus 4.7 — Anthropic docs](https://platform.claude.com/docs/) — upstream reference for `output_config` - [Claude Opus 4.7 — Anthropic docs](https://docs.anthropic.com) — upstream reference for `output_config`