Compare commits
25 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 4af5cc420a | |||
| 51a0fd2688 | |||
| d4bf57392e | |||
| 369578e96a | |||
| c704e96117 | |||
| a86e3c7048 | |||
| f33c5bd65e | |||
| 3c1a46b067 | |||
| 3868143c01 | |||
| f3e979b78c | |||
| 4ed6e36ef1 | |||
| 2d7232cf41 | |||
| 2686b09449 | |||
| 25982862f7 | |||
| 4ce3bfa3aa | |||
| c9f53a2a28 | |||
| 7b84d09de2 | |||
| eb67db9d7f | |||
| 77e511f905 | |||
| 1a4d012383 | |||
| 146009af51 | |||
| 3a902747c3 | |||
| a50ed4169a | |||
| 7a768060e3 | |||
| 7a614f2e3b |
+131
-120
@@ -133,7 +133,6 @@ jobs:
|
||||
# the name match works on PRs that don't touch workspace-server/).
|
||||
platform-build:
|
||||
name: Platform (Go)
|
||||
needs: changes
|
||||
runs-on: ubuntu-latest
|
||||
# mc#774 (closed 2026-05-14): Phase 4 flip of the platform-build job.
|
||||
# Phase 4 (#656) originally flipped this to continue-on-error: false based on
|
||||
@@ -154,29 +153,29 @@ jobs:
|
||||
run:
|
||||
working-directory: workspace-server
|
||||
steps:
|
||||
- if: needs.changes.outputs.platform != 'true'
|
||||
- if: false
|
||||
working-directory: .
|
||||
run: echo "No platform/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
|
||||
with:
|
||||
go-version: 'stable'
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
run: go mod download
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
run: go build ./cmd/server
|
||||
# CLI (molecli) moved to standalone repo: git.moleculesai.app/molecule-ai/molecule-cli
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
run: go vet ./...
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
name: Install golangci-lint
|
||||
run: go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@v2.12.2
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
name: Run golangci-lint
|
||||
run: $(go env GOPATH)/bin/golangci-lint run --timeout 3m ./...
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
name: Diagnostic — per-package verbose 60s
|
||||
run: |
|
||||
set +e
|
||||
@@ -192,7 +191,7 @@ jobs:
|
||||
echo "::endgroup::"
|
||||
# mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
|
||||
continue-on-error: true
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
name: Run tests with race detection and coverage
|
||||
# Explicit timeout: cold runner cache causes OOM kills at ~4m39s on the
|
||||
# full ./... suite with race detection + coverage. A 10m per-step timeout
|
||||
@@ -200,7 +199,7 @@ jobs:
|
||||
# instead of OOM-killing. The job-level timeout (15m) is a backstop.
|
||||
run: go test -race -timeout 10m -coverprofile=coverage.out ./...
|
||||
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
name: Per-file coverage report
|
||||
# Advisory — lists every source file with its coverage so reviewers
|
||||
# can see at-a-glance where gaps are. Sorted ascending so the worst
|
||||
@@ -214,7 +213,7 @@ jobs:
|
||||
END {for (f in s) printf "%6.1f%% %s\n", s[f]/c[f], f}' \
|
||||
| sort -n
|
||||
|
||||
- if: needs.changes.outputs.platform == 'true'
|
||||
- if: always()
|
||||
name: Check coverage thresholds
|
||||
# Enforces two gates from #1823 Layer 1:
|
||||
# 1. Total floor (25% — ratchet plan in COVERAGE_FLOOR.md).
|
||||
@@ -302,7 +301,6 @@ jobs:
|
||||
# siblings — verified empirically on PR #2314).
|
||||
canvas-build:
|
||||
name: Canvas (Next.js)
|
||||
needs: changes
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
# Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
|
||||
@@ -311,20 +309,20 @@ jobs:
|
||||
run:
|
||||
working-directory: canvas
|
||||
steps:
|
||||
- if: needs.changes.outputs.canvas != 'true'
|
||||
- if: false
|
||||
working-directory: .
|
||||
run: echo "No canvas/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
|
||||
- if: needs.changes.outputs.canvas == 'true'
|
||||
- if: always()
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- if: needs.changes.outputs.canvas == 'true'
|
||||
- if: always()
|
||||
uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
|
||||
with:
|
||||
node-version: '22'
|
||||
- if: needs.changes.outputs.canvas == 'true'
|
||||
- if: always()
|
||||
run: rm -f package-lock.json && npm install
|
||||
- if: needs.changes.outputs.canvas == 'true'
|
||||
- if: always()
|
||||
run: npm run build
|
||||
- if: needs.changes.outputs.canvas == 'true'
|
||||
- if: always()
|
||||
name: Run tests with coverage
|
||||
# Coverage instrumentation is configured in canvas/vitest.config.ts
|
||||
# (provider: v8, reporters: text + html + json-summary). Step 2 of
|
||||
@@ -333,7 +331,7 @@ jobs:
|
||||
# tracked in #1815) after the team sees what current coverage is.
|
||||
run: npx vitest run --coverage
|
||||
- name: Upload coverage summary as artifact
|
||||
if: needs.changes.outputs.canvas == 'true' && always()
|
||||
if: always()
|
||||
# Pinned to v3 for Gitea act_runner v0.6 compatibility — v4+ uses
|
||||
# the GHES 3.10+ artifact protocol that Gitea 1.22.x does NOT
|
||||
# implement, surfacing as `GHESNotSupportedError: @actions/artifact
|
||||
@@ -350,16 +348,15 @@ jobs:
|
||||
# Shellcheck (E2E scripts) — required check, always runs.
|
||||
shellcheck:
|
||||
name: Shellcheck (E2E scripts)
|
||||
needs: changes
|
||||
runs-on: ubuntu-latest
|
||||
# Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
|
||||
continue-on-error: false
|
||||
steps:
|
||||
- if: needs.changes.outputs.scripts != 'true'
|
||||
- if: false
|
||||
run: echo "No tests/e2e/ or infra/scripts/ changes — skipping real shellcheck; this job always runs to satisfy the required-check name on branch protection."
|
||||
- if: needs.changes.outputs.scripts == 'true'
|
||||
- if: always()
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- if: needs.changes.outputs.scripts == 'true'
|
||||
- if: always()
|
||||
name: Run shellcheck on tests/e2e/*.sh and infra/scripts/*.sh
|
||||
# shellcheck is pre-installed on ubuntu-latest runners (via apt).
|
||||
# infra/scripts/ is included because setup.sh + nuke.sh gate the
|
||||
@@ -370,16 +367,16 @@ jobs:
|
||||
find tests/e2e infra/scripts -type f -name '*.sh' -print0 \
|
||||
| xargs -0 shellcheck --severity=warning
|
||||
|
||||
- if: needs.changes.outputs.scripts == 'true'
|
||||
- if: always()
|
||||
name: Lint cleanup-trap hygiene (RFC #2873)
|
||||
run: bash tests/e2e/lint_cleanup_traps.sh
|
||||
|
||||
- if: needs.changes.outputs.scripts == 'true'
|
||||
- if: always()
|
||||
name: Run E2E bash unit tests (no live infra)
|
||||
run: |
|
||||
bash tests/e2e/test_model_slug.sh
|
||||
|
||||
- if: needs.changes.outputs.scripts == 'true'
|
||||
- if: always()
|
||||
name: Test ECR promote-tenant-image script (mock-driven, no live infra)
|
||||
# Covers scripts/promote-tenant-image.sh — the codified
|
||||
# :staging-latest → :latest ECR promote + tenant fleet redeploy
|
||||
@@ -389,7 +386,7 @@ jobs:
|
||||
run: |
|
||||
bash scripts/test-promote-tenant-image.sh
|
||||
|
||||
- if: needs.changes.outputs.scripts == 'true'
|
||||
- if: always()
|
||||
name: Shellcheck promote-tenant-image script
|
||||
# scripts/ is excluded from the bulk shellcheck pass above (legacy
|
||||
# SC3040/SC3043 cleanup pending). Run shellcheck explicitly on
|
||||
@@ -403,18 +400,15 @@ jobs:
|
||||
canvas-deploy-reminder:
|
||||
name: Canvas Deploy Reminder
|
||||
runs-on: ubuntu-latest
|
||||
# mc#774 root-fix: added job-level `if:` so ci-required-drift.py's
|
||||
# ci_job_names() detects this as github.ref-gated and skips it from F1.
|
||||
# The step-level exit 0 handles the "not main push" case; the job-level
|
||||
# `if:` makes the gating explicit so the drift script sees it.
|
||||
# continue-on-error removed (was mc#774 mask): step exits 0 when not applicable.
|
||||
needs: [changes, canvas-build]
|
||||
if: ${{ github.ref == 'refs/heads/main' }}
|
||||
# This job must run on PRs because all-required needs it. The step exits
|
||||
# 0 when it is not a main push, giving branch protection a green no-op
|
||||
# instead of a skipped/missing required dependency.
|
||||
needs: canvas-build
|
||||
steps:
|
||||
- name: Write deploy reminder to step summary
|
||||
env:
|
||||
COMMIT_SHA: ${{ github.sha }}
|
||||
CANVAS_CHANGED: ${{ needs.changes.outputs.canvas }}
|
||||
CANVAS_CHANGED: "true"
|
||||
EVENT_NAME: ${{ github.event_name }}
|
||||
REF_NAME: ${{ github.ref }}
|
||||
# github.server_url resolves via the workflow-level env override
|
||||
@@ -459,7 +453,6 @@ jobs:
|
||||
# Python Lint & Test — required check, always runs.
|
||||
python-lint:
|
||||
name: Python Lint & Test
|
||||
needs: changes
|
||||
runs-on: ubuntu-latest
|
||||
# Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
|
||||
continue-on-error: false
|
||||
@@ -469,25 +462,25 @@ jobs:
|
||||
run:
|
||||
working-directory: workspace
|
||||
steps:
|
||||
- if: needs.changes.outputs.python != 'true'
|
||||
- if: false
|
||||
working-directory: .
|
||||
run: echo "No workspace/** changes — skipping real lint+test; this job always runs to satisfy the required-check name on branch protection."
|
||||
- if: needs.changes.outputs.python == 'true'
|
||||
- if: always()
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- if: needs.changes.outputs.python == 'true'
|
||||
- if: always()
|
||||
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
|
||||
with:
|
||||
python-version: '3.11'
|
||||
cache: pip
|
||||
cache-dependency-path: workspace/requirements.txt
|
||||
- if: needs.changes.outputs.python == 'true'
|
||||
- if: always()
|
||||
run: pip install -r requirements.txt pytest pytest-asyncio pytest-cov sqlalchemy>=2.0.0
|
||||
# Coverage flags + fail-under floor moved into workspace/pytest.ini
|
||||
# (issue #1817) so local `pytest` and CI use identical config.
|
||||
- if: needs.changes.outputs.python == 'true'
|
||||
- if: always()
|
||||
run: python -m pytest --tb=short
|
||||
|
||||
- if: needs.changes.outputs.python == 'true'
|
||||
- if: always()
|
||||
name: Per-file critical-path coverage (MCP / inbox / auth)
|
||||
# MCP-critical Python files have a per-file floor on top of the
|
||||
# 86% total floor in pytest.ini. See issue #2790 for full rationale.
|
||||
@@ -552,86 +545,104 @@ jobs:
|
||||
# red silently merged through. See internal#286 for the three concrete
|
||||
# tonight-of-2026-05-11 incidents that prompted the emergency bump.
|
||||
#
|
||||
# Three properties of this job each close a failure mode:
|
||||
# This job deliberately has no `needs:`. Gitea 1.22/act_runner can mark a
|
||||
# job-level `if: always()` + `needs:` sentinel as skipped before upstream
|
||||
# jobs settle, leaving branch protection with a permanent pending
|
||||
# `CI / all-required` context. Instead, this independent sentinel polls the
|
||||
# required commit-status contexts for this SHA and fails if any fail, skip,
|
||||
# or never emit.
|
||||
#
|
||||
# 1. `if: always()` — runs even when an upstream fails. Without it the
|
||||
# sentinel is `skipped` and protection treats that as missing → merge
|
||||
# ungated.
|
||||
# canvas-deploy-reminder is intentionally NOT included in all-required.needs.
|
||||
# It is an informational main-push reminder, not a PR quality gate. Keeping
|
||||
# it in this dependency list lets a skipped reminder skip the required
|
||||
# sentinel before the `always()` guard can emit a branch-protection status.
|
||||
#
|
||||
# 2. Assertion is `result == "success"` per dep, NOT `!= "failure"`.
|
||||
# A `skipped` upstream (job gated by `if:` evaluating false, matrix
|
||||
# entry that couldn't run) must NOT silently pass through.
|
||||
# `skipped`-as-green is exactly the failure mode this gate closes.
|
||||
#
|
||||
# 3. `needs:` is the canonical list of "what counts as required."
|
||||
# status_check_contexts will reference only `ci/all-required` (Step 5
|
||||
# follow-up — branch-protection PATCH is Owners-tier per
|
||||
# `feedback_never_admin_merge_bypass`, separate PR); a new job is
|
||||
# added simply by listing it in `needs:` here.
|
||||
# `.gitea/workflows/ci-required-drift.yml` files a [ci-drift] issue
|
||||
# hourly if this list diverges from status_check_contexts or from
|
||||
# audit-force-merge.yml's REQUIRED_CHECKS env (RFC §4 + §6).
|
||||
#
|
||||
# canvas-deploy-reminder IS now included in all-required.needs (mc#958 root-fix):
|
||||
# added job-level `if: github.ref == 'refs/heads/main'` so ci-required-drift.py's
|
||||
# ci_job_names() detects it as github.ref-gated and skips it from F1.
|
||||
# The step-level `if: ... || REF_NAME != refs/heads/main` exits 0 when not main,
|
||||
# so the job succeeds (not skipped) on non-main pushes — sentinel treats as green.
|
||||
#
|
||||
# Phase 3 (RFC #219 §1) safety: underlying build jobs carry
|
||||
# continue-on-error: true so their failures are masked to null (2026-05-12: re-enabled mc#774 interim)
|
||||
# (Gitea suppresses status reporting for CoE jobs). This sentinel
|
||||
# runs with continue-on-error: false so it always reports its
|
||||
# result to the API — without this, the required-status entry
|
||||
# (CI / all-required (pull_request)) is never created, which
|
||||
# blocks PR merges. When Phase 3 ends, flip underlying jobs to
|
||||
# continue-on-error: false; this sentinel can then be flipped to
|
||||
# continue-on-error: true if a Phase-4 regression requires it.
|
||||
continue-on-error: false
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 1
|
||||
needs:
|
||||
- changes
|
||||
- platform-build
|
||||
- canvas-build
|
||||
- shellcheck
|
||||
- python-lint
|
||||
- canvas-deploy-reminder
|
||||
if: ${{ always() }}
|
||||
timeout-minutes: 45
|
||||
steps:
|
||||
- name: Assert every required dependency succeeded
|
||||
- name: Wait for required CI contexts
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
API_ROOT: ${{ github.server_url }}/api/v1
|
||||
REPOSITORY: ${{ github.repository }}
|
||||
COMMIT_SHA: ${{ github.sha }}
|
||||
EVENT_NAME: ${{ github.event_name }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# `needs.*.result` is one of: success | failure | cancelled | skipped | null.
|
||||
# We assert success per dep (not != failure) — see RFC §2 reasoning above.
|
||||
# Null results are skipped: they come from Phase 3 (continue-on-error: true
|
||||
# suppresses status) or from jobs still in-flight. The sentinel succeeds
|
||||
# rather than blocking PRs on Phase 3 noise.
|
||||
results='${{ toJSON(needs) }}'
|
||||
echo "$results"
|
||||
echo "$results" | python3 -c '
|
||||
import json, sys
|
||||
ns = json.load(sys.stdin)
|
||||
# Phase 3 masked: jobs with continue-on-error: true may report "failure"
|
||||
# Remove when mc#774 handler test failures are resolved.
|
||||
PHASE3_MASKED = {"platform-build"}
|
||||
# Exclude null (Phase 3 suppressed / in-flight) from the bad list.
|
||||
bad = [(k, v.get("result")) for k, v in ns.items()
|
||||
if v.get("result") not in ("success", None, "cancelled", "skipped") and k not in PHASE3_MASKED]
|
||||
if bad:
|
||||
print(f"FAIL: jobs not green:", file=sys.stderr)
|
||||
for k, r in bad:
|
||||
print(f" - {k}: {r}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
pending = [(k, v.get("result")) for k, v in ns.items()
|
||||
if v.get("result") is None]
|
||||
cancelled = [(k, v.get("result")) for k, v in ns.items()
|
||||
if v.get("result") == "cancelled"]
|
||||
if pending:
|
||||
print(f"WARN: {len(pending)} job(s) still in-flight (result=null): " +
|
||||
", ".join(k for k, _ in pending), file=sys.stderr)
|
||||
if cancelled:
|
||||
print(f"INFO: {len(cancelled)} job(s) masked by continue-on-error: " +
|
||||
", ".join(k for k, _ in cancelled), file=sys.stderr)
|
||||
print(f"OK: all {len(ns)} required jobs succeeded (or Phase-3 suppressed)")
|
||||
'
|
||||
python3 - <<'PY'
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
token = os.environ["GITEA_TOKEN"]
|
||||
api_root = os.environ["API_ROOT"].rstrip("/")
|
||||
repo = os.environ["REPOSITORY"]
|
||||
sha = os.environ["COMMIT_SHA"]
|
||||
event = os.environ["EVENT_NAME"]
|
||||
required = [
|
||||
f"CI / Detect changes ({event})",
|
||||
f"CI / Platform (Go) ({event})",
|
||||
f"CI / Canvas (Next.js) ({event})",
|
||||
f"CI / Shellcheck (E2E scripts) ({event})",
|
||||
f"CI / Python Lint & Test ({event})",
|
||||
]
|
||||
terminal_bad = {"failure", "error"}
|
||||
deadline = time.time() + 40 * 60
|
||||
last_summary = None
|
||||
|
||||
def fetch_statuses():
|
||||
statuses = []
|
||||
for page in range(1, 6):
|
||||
url = f"{api_root}/repos/{repo}/commits/{sha}/statuses?page={page}&limit=100"
|
||||
req = urllib.request.Request(url, headers={"Authorization": f"token {token}"})
|
||||
with urllib.request.urlopen(req, timeout=10) as resp:
|
||||
chunk = json.load(resp)
|
||||
if not chunk:
|
||||
break
|
||||
statuses.extend(chunk)
|
||||
latest = {}
|
||||
for item in statuses:
|
||||
ctx = item.get("context")
|
||||
if not ctx:
|
||||
continue
|
||||
prev = latest.get(ctx)
|
||||
if prev is None or (item.get("updated_at") or item.get("created_at") or "") >= (prev.get("updated_at") or prev.get("created_at") or ""):
|
||||
latest[ctx] = item
|
||||
return latest
|
||||
|
||||
while True:
|
||||
try:
|
||||
latest = fetch_statuses()
|
||||
except (TimeoutError, OSError, urllib.error.URLError) as exc:
|
||||
if time.time() >= deadline:
|
||||
print(f"FAIL: status polling did not recover before deadline: {exc}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
print(f"WARN: status poll failed, retrying: {exc}", flush=True)
|
||||
time.sleep(15)
|
||||
continue
|
||||
states = {ctx: (latest.get(ctx) or {}).get("status") or (latest.get(ctx) or {}).get("state") or "missing" for ctx in required}
|
||||
summary = ", ".join(f"{ctx}={state}" for ctx, state in states.items())
|
||||
if summary != last_summary:
|
||||
print(summary, flush=True)
|
||||
last_summary = summary
|
||||
bad = {ctx: state for ctx, state in states.items() if state in terminal_bad}
|
||||
if bad:
|
||||
print("FAIL: required CI context failed:", file=sys.stderr)
|
||||
for ctx, state in bad.items():
|
||||
desc = (latest.get(ctx) or {}).get("description") or ""
|
||||
print(f" - {ctx}: {state} {desc}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
if all(state == "success" for state in states.values()):
|
||||
print(f"OK: all {len(required)} required CI contexts succeeded")
|
||||
sys.exit(0)
|
||||
if time.time() >= deadline:
|
||||
print("FAIL: timed out waiting for required CI contexts:", file=sys.stderr)
|
||||
for ctx, state in states.items():
|
||||
print(f" - {ctx}: {state}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
time.sleep(15)
|
||||
PY
|
||||
|
||||
@@ -12,6 +12,7 @@ import { useEffect, useState } from "react";
|
||||
|
||||
import { api } from "@/lib/api";
|
||||
import { type Template } from "@/lib/deploy-preflight";
|
||||
import { isSaaSTenant } from "@/lib/tenant";
|
||||
|
||||
import { tierCode } from "./palette";
|
||||
import { MOBILE_FONT_MONO, MOBILE_FONT_SANS, type MobilePalette, usePalette } from "./palette";
|
||||
@@ -26,6 +27,7 @@ const TIER_LABEL: Record<"T1" | "T2" | "T3" | "T4", string> = {
|
||||
|
||||
export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => void }) {
|
||||
const p = usePalette(dark);
|
||||
const isSaaS = isSaaSTenant();
|
||||
const [templates, setTemplates] = useState<Template[]>([]);
|
||||
const [loadingTemplates, setLoadingTemplates] = useState(true);
|
||||
const [tplId, setTplId] = useState<string | null>(null);
|
||||
@@ -43,7 +45,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
|
||||
setTemplates(list);
|
||||
if (list.length > 0) {
|
||||
setTplId(list[0].id);
|
||||
setTier(tierCode(list[0].tier));
|
||||
setTier(isSaaS ? "T4" : tierCode(list[0].tier));
|
||||
}
|
||||
})
|
||||
.catch(() => {
|
||||
@@ -55,7 +57,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
|
||||
return () => {
|
||||
cancelled = true;
|
||||
};
|
||||
}, []);
|
||||
}, [isSaaS]);
|
||||
|
||||
const handleSpawn = async () => {
|
||||
if (busy || !tplId) return;
|
||||
@@ -67,7 +69,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
|
||||
await api.post<{ id: string }>("/workspaces", {
|
||||
name: (name.trim() || chosen.name),
|
||||
template: chosen.id,
|
||||
tier: Number(tier.slice(1)),
|
||||
tier: isSaaS ? 4 : Number(tier.slice(1)),
|
||||
canvas: {
|
||||
x: Math.random() * 400 + 100,
|
||||
y: Math.random() * 300 + 100,
|
||||
@@ -203,7 +205,7 @@ export function MobileSpawn({ dark, onClose }: { dark: boolean; onClose: () => v
|
||||
>
|
||||
{templates.map((t) => {
|
||||
const on = tplId === t.id;
|
||||
const tCode = tierCode(t.tier);
|
||||
const tCode = isSaaS ? "T4" : tierCode(t.tier);
|
||||
return (
|
||||
<button
|
||||
key={t.id}
|
||||
|
||||
@@ -8,6 +8,7 @@ import {
|
||||
type PreflightResult,
|
||||
type Template,
|
||||
} from "@/lib/deploy-preflight";
|
||||
import { isSaaSTenant } from "@/lib/tenant";
|
||||
import { MissingKeysModal } from "@/components/MissingKeysModal";
|
||||
|
||||
/**
|
||||
@@ -105,7 +106,7 @@ export function useTemplateDeploy(
|
||||
const ws = await api.post<{ id: string }>("/workspaces", {
|
||||
name: template.name,
|
||||
template: template.id,
|
||||
tier: template.tier,
|
||||
tier: isSaaSTenant() ? 4 : template.tier,
|
||||
canvas: coords,
|
||||
...(model ? { model } : {}),
|
||||
});
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"bytes"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"regexp"
|
||||
|
||||
@@ -186,11 +186,16 @@ func (h *TemplatesHandler) List(c *gin.Context) {
|
||||
model = raw.RuntimeConfig.Model
|
||||
}
|
||||
|
||||
tier := raw.Tier
|
||||
if h.wh != nil && h.wh.IsSaaS() {
|
||||
tier = h.wh.DefaultTier()
|
||||
}
|
||||
|
||||
templates = append(templates, templateSummary{
|
||||
ID: id,
|
||||
Name: raw.Name,
|
||||
Description: raw.Description,
|
||||
Tier: raw.Tier,
|
||||
Tier: tier,
|
||||
Runtime: raw.Runtime,
|
||||
Model: model,
|
||||
Models: raw.RuntimeConfig.Models,
|
||||
@@ -340,6 +345,11 @@ func (h *TemplatesHandler) ListFiles(c *gin.Context) {
|
||||
if err != nil || path == walkRoot {
|
||||
return nil
|
||||
}
|
||||
// Skip symlinks to prevent path traversal via malicious symlinks
|
||||
// inside the workspace config directory (OFFSEC-010).
|
||||
if info.Mode()&os.ModeSymlink != 0 {
|
||||
return nil
|
||||
}
|
||||
rel, _ := filepath.Rel(walkRoot, path)
|
||||
// Enforce depth limit
|
||||
if strings.Count(rel, string(filepath.Separator))+1 > depth {
|
||||
|
||||
@@ -847,6 +847,58 @@ func TestListFiles_FallbackToHost_WithTemplate(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestListFiles_FallbackToHost_SkipsSymlinks(t *testing.T) {
|
||||
mock := setupTestDB(t)
|
||||
setupTestRedis(t)
|
||||
|
||||
tmpDir := t.TempDir()
|
||||
tmplDir := filepath.Join(tmpDir, "test-agent")
|
||||
if err := os.MkdirAll(tmplDir, 0755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(tmplDir, "config.yaml"), []byte("name: Test Agent\n"), 0644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
secret := filepath.Join(t.TempDir(), "secret.txt")
|
||||
if err := os.WriteFile(secret, []byte("do-not-list"), 0600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.Symlink(secret, filepath.Join(tmplDir, "leaked-secret")); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
handler := NewTemplatesHandler(tmpDir, nil, nil)
|
||||
|
||||
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
|
||||
WithArgs("ws-tmpl").
|
||||
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).AddRow("Test Agent", "", ""))
|
||||
|
||||
w := httptest.NewRecorder()
|
||||
c, _ := gin.CreateTestContext(w)
|
||||
c.Params = gin.Params{{Key: "id", Value: "ws-tmpl"}}
|
||||
c.Request = httptest.NewRequest("GET", "/workspaces/ws-tmpl/files", nil)
|
||||
|
||||
handler.ListFiles(c)
|
||||
|
||||
if w.Code != http.StatusOK {
|
||||
t.Fatalf("expected 200, got %d: %s", w.Code, w.Body.String())
|
||||
}
|
||||
|
||||
var resp []map[string]interface{}
|
||||
if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, file := range resp {
|
||||
if file["path"] == "leaked-secret" {
|
||||
t.Fatalf("symlink should not be listed: %#v", resp)
|
||||
}
|
||||
}
|
||||
|
||||
if err := mock.ExpectationsWereMet(); err != nil {
|
||||
t.Errorf("unmet sqlmock expectations: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// ==================== GET /workspaces/:id/files/*path ====================
|
||||
|
||||
func TestReadFile_PathTraversal(t *testing.T) {
|
||||
@@ -1200,4 +1252,3 @@ func TestCWE78_DeleteFile_TraversalVariants(t *testing.T) {
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -161,15 +161,14 @@ func (h *WorkspaceHandler) Create(c *gin.Context) {
|
||||
|
||||
id := uuid.New().String()
|
||||
awarenessNamespace := workspaceAwarenessNamespace(id)
|
||||
if payload.Tier == 0 {
|
||||
// SaaS-aware default. SaaS → T4 (full host access; each
|
||||
// workspace runs on its own sibling EC2 so the tier boundary
|
||||
// is a Docker resource limit on the only container present —
|
||||
// no neighbour to protect from). Self-hosted → T3 (read-write
|
||||
// workspace mount + Docker daemon access, most templates'
|
||||
// baseline). Lower tiers (T1 sandboxed, T2 standard) remain
|
||||
// explicit opt-ins for low-trust agents. Matches the canvas
|
||||
// CreateWorkspaceDialog defaults so the API and the UI agree.
|
||||
if h.IsSaaS() {
|
||||
// SaaS hard gate: every hosted workspace gets its own sibling
|
||||
// EC2 instance, so T4 is the only meaningful runtime boundary.
|
||||
// Do not trust stale clients/templates that still send T1/T2/T3.
|
||||
payload.Tier = 4
|
||||
} else if payload.Tier == 0 {
|
||||
// Self-hosted default remains T3. Lower tiers (T1 sandboxed,
|
||||
// T2 standard) stay explicit opt-ins for low-trust local agents.
|
||||
payload.Tier = h.DefaultTier()
|
||||
}
|
||||
|
||||
|
||||
@@ -410,6 +410,44 @@ func TestWorkspaceCreate_DefaultsApplied(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestWorkspaceCreate_SaaSHardForcesTier4(t *testing.T) {
|
||||
mock := setupTestDB(t)
|
||||
setupTestRedis(t)
|
||||
broadcaster := newTestBroadcaster()
|
||||
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
|
||||
handler.SetCPProvisioner(&trackingCPProv{})
|
||||
|
||||
mock.ExpectBegin()
|
||||
mock.ExpectExec("INSERT INTO workspaces").
|
||||
WithArgs(sqlmock.AnyArg(), "SaaS External Agent", nil, 4, "external", sqlmock.AnyArg(), (*string)(nil), nil, "none", (*int64)(nil), models.DefaultMaxConcurrentTasks, "push").
|
||||
WillReturnResult(sqlmock.NewResult(0, 1))
|
||||
mock.ExpectCommit()
|
||||
mock.ExpectExec("INSERT INTO canvas_layouts").
|
||||
WithArgs(sqlmock.AnyArg(), float64(0), float64(0)).
|
||||
WillReturnResult(sqlmock.NewResult(0, 1))
|
||||
mock.ExpectExec("INSERT INTO structure_events").
|
||||
WillReturnResult(sqlmock.NewResult(0, 1))
|
||||
mock.ExpectExec("UPDATE workspaces SET url").
|
||||
WillReturnResult(sqlmock.NewResult(0, 1))
|
||||
mock.ExpectExec("INSERT INTO structure_events").
|
||||
WillReturnResult(sqlmock.NewResult(0, 1))
|
||||
|
||||
w := httptest.NewRecorder()
|
||||
c, _ := gin.CreateTestContext(w)
|
||||
body := `{"name":"SaaS External Agent","runtime":"external","external":true,"url":"https://example.com/agent","tier":2}`
|
||||
c.Request = httptest.NewRequest("POST", "/workspaces", bytes.NewBufferString(body))
|
||||
c.Request.Header.Set("Content-Type", "application/json")
|
||||
|
||||
handler.Create(c)
|
||||
|
||||
if w.Code != http.StatusCreated {
|
||||
t.Errorf("expected status 201, got %d: %s", w.Code, w.Body.String())
|
||||
}
|
||||
if err := mock.ExpectationsWereMet(); err != nil {
|
||||
t.Errorf("unmet sqlmock expectations: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// TestWorkspaceCreate_WithSecrets_Persists asserts that secrets in the create
|
||||
// payload are written to workspace_secrets inside the same transaction as the
|
||||
// workspace row, and that the handler returns 201.
|
||||
|
||||
@@ -158,6 +158,7 @@ type cpProvisionRequest struct {
|
||||
Tier int `json:"tier"`
|
||||
PlatformURL string `json:"platform_url"`
|
||||
Env map[string]string `json:"env"`
|
||||
ConfigFiles map[string]string `json:"config_files,omitempty"`
|
||||
}
|
||||
|
||||
type cpProvisionResponse struct {
|
||||
@@ -181,6 +182,11 @@ func (p *CPProvisioner) Start(ctx context.Context, cfg WorkspaceConfig) (string,
|
||||
}
|
||||
env["ADMIN_TOKEN"] = p.adminToken
|
||||
}
|
||||
configFiles, err := collectCPConfigFiles(cfg)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("cp provisioner: collect config files: %w", err)
|
||||
}
|
||||
|
||||
req := cpProvisionRequest{
|
||||
OrgID: p.orgID,
|
||||
WorkspaceID: cfg.WorkspaceID,
|
||||
@@ -188,6 +194,7 @@ func (p *CPProvisioner) Start(ctx context.Context, cfg WorkspaceConfig) (string,
|
||||
Tier: cfg.Tier,
|
||||
PlatformURL: cfg.PlatformURL,
|
||||
Env: env,
|
||||
ConfigFiles: configFiles,
|
||||
}
|
||||
|
||||
body, err := json.Marshal(req)
|
||||
@@ -314,6 +321,7 @@ func collectCPConfigFiles(cfg WorkspaceConfig) (map[string]string, error) {
|
||||
}
|
||||
return files, nil
|
||||
}
|
||||
|
||||
// Stop terminates the workspace's EC2 instance via the control plane.
|
||||
//
|
||||
// Looks up the actual EC2 instance_id from the workspaces table before
|
||||
@@ -468,7 +476,9 @@ func (p *CPProvisioner) IsRunning(ctx context.Context, workspaceID string) (bool
|
||||
// Don't leak the body — upstream errors may echo headers.
|
||||
return true, fmt.Errorf("cp provisioner: status: unexpected %d", resp.StatusCode)
|
||||
}
|
||||
var result struct{ State string `json:"state"` }
|
||||
var result struct {
|
||||
State string `json:"state"`
|
||||
}
|
||||
// Cap body read at 64 KiB for parity with Start — a misconfigured
|
||||
// or compromised CP streaming a huge body could otherwise exhaust
|
||||
// memory in this hot path (called reactively per-request from
|
||||
|
||||
@@ -2,10 +2,13 @@ package provisioner
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/base64"
|
||||
"encoding/json"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
@@ -213,6 +216,53 @@ func TestStart_HappyPath(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestStart_SendsTemplateAndGeneratedConfigFiles(t *testing.T) {
|
||||
tmpl := t.TempDir()
|
||||
if err := os.WriteFile(filepath.Join(tmpl, "config.yaml"), []byte("name: template\n"), 0o600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.Mkdir(filepath.Join(tmpl, "prompts"), 0o700); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(tmpl, "prompts", "system.md"), []byte("hello"), 0o600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
var body cpProvisionRequest
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
|
||||
t.Errorf("decode request: %v", err)
|
||||
}
|
||||
w.WriteHeader(http.StatusCreated)
|
||||
_, _ = io.WriteString(w, `{"instance_id":"i-abc123","state":"pending"}`)
|
||||
}))
|
||||
defer srv.Close()
|
||||
|
||||
p := &CPProvisioner{baseURL: srv.URL, orgID: "org-1", httpClient: srv.Client()}
|
||||
_, err := p.Start(context.Background(), WorkspaceConfig{
|
||||
WorkspaceID: "ws-1",
|
||||
Runtime: "claude-code",
|
||||
Tier: 4,
|
||||
PlatformURL: "http://tenant",
|
||||
TemplatePath: tmpl,
|
||||
ConfigFiles: map[string][]byte{
|
||||
"config.yaml": []byte("name: generated\n"),
|
||||
},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("Start: %v", err)
|
||||
}
|
||||
|
||||
wantConfig := base64.StdEncoding.EncodeToString([]byte("name: generated\n"))
|
||||
if got := body.ConfigFiles["config.yaml"]; got != wantConfig {
|
||||
t.Errorf("config.yaml payload = %q, want generated override %q", got, wantConfig)
|
||||
}
|
||||
wantPrompt := base64.StdEncoding.EncodeToString([]byte("hello"))
|
||||
if got := body.ConfigFiles["prompts/system.md"]; got != wantPrompt {
|
||||
t.Errorf("prompt payload = %q, want %q", got, wantPrompt)
|
||||
}
|
||||
}
|
||||
|
||||
// TestStart_Non201ReturnsStructuredError — when CP returns 401 with a
|
||||
// structured {"error":"..."} body, Start surfaces that error message.
|
||||
// Verifies the defense against log-leaking raw upstream bodies.
|
||||
@@ -416,9 +466,9 @@ func TestStop_4xxResponseSurfacesError(t *testing.T) {
|
||||
func TestStop_2xxVariantsAllSucceed(t *testing.T) {
|
||||
primeInstanceIDLookup(t, map[string]string{"ws-1": "i-ok"})
|
||||
for _, code := range []int{
|
||||
http.StatusOK, // 200
|
||||
http.StatusAccepted, // 202
|
||||
http.StatusNoContent, // 204
|
||||
http.StatusOK, // 200
|
||||
http.StatusAccepted, // 202
|
||||
http.StatusNoContent, // 204
|
||||
} {
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
|
||||
w.WriteHeader(code)
|
||||
@@ -486,11 +536,11 @@ func TestIsRunning_ParsesStateField(t *testing.T) {
|
||||
_, _ = io.WriteString(w, `{"state":"`+state+`"}`)
|
||||
}))
|
||||
p := &CPProvisioner{
|
||||
baseURL: srv.URL,
|
||||
orgID: "org-1",
|
||||
baseURL: srv.URL,
|
||||
orgID: "org-1",
|
||||
sharedSecret: "s3cret",
|
||||
adminToken: "tok-xyz",
|
||||
httpClient: srv.Client(),
|
||||
httpClient: srv.Client(),
|
||||
}
|
||||
got, err := p.IsRunning(context.Background(), "ws-1")
|
||||
srv.Close()
|
||||
|
||||
@@ -773,6 +773,15 @@ func ApplyTierConfig(hostCfg *container.HostConfig, cfg WorkspaceConfig, configM
|
||||
|
||||
// CopyTemplateToContainer copies files from a host directory into /configs in the container.
|
||||
func (p *Provisioner) CopyTemplateToContainer(ctx context.Context, containerID, templatePath string) error {
|
||||
buf, err := buildTemplateTar(templatePath)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
return p.cli.CopyToContainer(ctx, containerID, "/configs", buf, container.CopyToContainerOptions{})
|
||||
}
|
||||
|
||||
func buildTemplateTar(templatePath string) (*bytes.Buffer, error) {
|
||||
// Resolve symlinks at the root before walking. filepath.Walk does
|
||||
// NOT follow a symlink that IS the root — it Lstats the path, sees
|
||||
// a symlink (non-directory), and emits exactly one entry without
|
||||
@@ -795,6 +804,15 @@ func (p *Provisioner) CopyTemplateToContainer(ctx context.Context, containerID,
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
// OFFSEC-010: skip symlinks to prevent path traversal via malicious
|
||||
// template symlinks (e.g. template/.ssh → /root/.ssh). filepath.Walk
|
||||
// follows symlinks by default, so without this guard a crafted symlink
|
||||
// inside the template directory could escape to include arbitrary host
|
||||
// files in the tar archive. We intentionally skip rather than error so
|
||||
// a broken symlink in an org template is a silent no-op.
|
||||
if info.Mode()&os.ModeSymlink != 0 {
|
||||
return nil
|
||||
}
|
||||
rel, err := filepath.Rel(templatePath, path)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -835,13 +853,13 @@ func (p *Provisioner) CopyTemplateToContainer(ctx context.Context, containerID,
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to create tar from %s: %w", templatePath, err)
|
||||
return nil, fmt.Errorf("failed to create tar from %s: %w", templatePath, err)
|
||||
}
|
||||
if err := tw.Close(); err != nil {
|
||||
return fmt.Errorf("failed to close tar writer: %w", err)
|
||||
return nil, fmt.Errorf("failed to close tar writer: %w", err)
|
||||
}
|
||||
|
||||
return p.cli.CopyToContainer(ctx, containerID, "/configs", &buf, container.CopyToContainerOptions{})
|
||||
return &buf, nil
|
||||
}
|
||||
|
||||
// WriteFilesToContainer writes in-memory files into /configs in the container.
|
||||
|
||||
@@ -1,7 +1,9 @@
|
||||
package provisioner
|
||||
|
||||
import (
|
||||
"archive/tar"
|
||||
"errors"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
@@ -80,6 +82,54 @@ func TestStartSeedsConfigsBeforeContainerStart(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestBuildTemplateTar_SkipsSymlinks(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
if err := os.WriteFile(filepath.Join(dir, "config.yaml"), []byte("name: safe\n"), 0644); err != nil {
|
||||
t.Fatalf("write config: %v", err)
|
||||
}
|
||||
outside := filepath.Join(t.TempDir(), "secret.txt")
|
||||
if err := os.WriteFile(outside, []byte("do-not-copy\n"), 0644); err != nil {
|
||||
t.Fatalf("write outside target: %v", err)
|
||||
}
|
||||
if err := os.Symlink(outside, filepath.Join(dir, "linked-secret.txt")); err != nil {
|
||||
t.Fatalf("create symlink: %v", err)
|
||||
}
|
||||
|
||||
buf, err := buildTemplateTar(dir)
|
||||
if err != nil {
|
||||
t.Fatalf("buildTemplateTar: %v", err)
|
||||
}
|
||||
|
||||
names := map[string]string{}
|
||||
tr := tar.NewReader(buf)
|
||||
for {
|
||||
hdr, err := tr.Next()
|
||||
if errors.Is(err, io.EOF) {
|
||||
break
|
||||
}
|
||||
if err != nil {
|
||||
t.Fatalf("read tar: %v", err)
|
||||
}
|
||||
body, err := io.ReadAll(tr)
|
||||
if err != nil {
|
||||
t.Fatalf("read body for %s: %v", hdr.Name, err)
|
||||
}
|
||||
names[hdr.Name] = string(body)
|
||||
}
|
||||
|
||||
if got := names["config.yaml"]; got != "name: safe\n" {
|
||||
t.Fatalf("config.yaml body = %q, want safe config", got)
|
||||
}
|
||||
if _, ok := names["linked-secret.txt"]; ok {
|
||||
t.Fatalf("symlink entry was copied into template tar: %#v", names)
|
||||
}
|
||||
for name, body := range names {
|
||||
if strings.Contains(body, "do-not-copy") {
|
||||
t.Fatalf("symlink target leaked through %s: %q", name, body)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// baseHostConfig returns a fresh HostConfig with typical pre-tier binds,
|
||||
// mimicking what Start() builds before calling ApplyTierConfig.
|
||||
func baseHostConfig(pluginsPath string) *container.HostConfig {
|
||||
|
||||
Reference in New Issue
Block a user