fix(executor): surface the CLI stream error instead of the swallowed-stderr placeholder

When the `claude` CLI errors mid-stream, claude-agent-sdk throws a bare
`Exception("Command failed with exit code 1 …")` whose only text is the
useless `Check stderr output for details` placeholder — but the *actual*
failure reason (model 404, rate limit, auth) arrived a moment earlier as a
stream-json `ResultMessage(is_error=True)` carrying `result` text and
`api_error_status`. That was thrown away.

`_run_query` now captures `ResultMessage(is_error=True)` detail (and, as a
fallback, the trailing AssistantMessage text) and re-attaches it to the
raised exception as `_molecule_stream_detail`. `_format_process_error`
surfaces it as `cli_stream_error=…` and, when present, skips the
`_probe_claude_cli_error` re-probe (#160) — the probe can't replay the
failing `--model`/`--system-prompt` argv, so it may even succeed and
mislead. The probe stays as the last resort when there's nothing to salvage.

Regression context: the 2026-05-10 dev-team incident — six lead workspaces
404ing on every turn (`--model claude-code` → `api_error_status=404`,
"There's an issue with the selected model (claude-code)"), invisible for an
hour because the CLI wrote nothing to stderr and this text was discarded.
See internal#226 follow-up #5.

Tests: tests/test_executor_error_detail.py — 6 cases (format surfaces the
salvaged detail; format still probes when there's nothing salvaged; salvaged
detail takes precedence over the probe; _run_query annotates from
ResultMessage(is_error); _run_query falls back to assistant text; clean
success path unaffected). `pytest tests/` → 87 passed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.gitea/workflows/ci.yml

@@ -1,434 +0,0 @@
-name: CI
-
-# Ported from .github/workflows/ci.yml on 2026-05-11 per internal#326
-# (Class-A root: cross-repo `uses:` blocker for Gitea 1.22.6 —
-# feedback_gitea_cross_repo_uses_blocked).
-#
-# Root cause of the main-red CI on this repo:
-#   The .github/ original used
-#     uses: molecule-ai/molecule-ci/.github/workflows/validate-workspace-template.yml@main
-#   which Gitea 1.22.6 rejects (DEFAULT_ACTIONS_URL=github → 404 against
-#   the remote repo even though it lives on the same Gitea instance).
-#   Gitea reads .github/ as a fallback when .gitea/ is absent
-#   (reference_per_repo_gitea_vs_github_actions_dir), so the .github/
-#   workflow was firing on Gitea and failing in 1s.
-#
-# Fix shape: inline the validation logic directly. The canonical
-# validator in molecule-ai/molecule-ci already self-clones into the
-# runner via a direct HTTPS `git clone` step (validate-workspace-template.yml
-# does this verbatim) — so the inline port is just "do that clone +
-# invoke the validator script in-place", preserving the
-# single-source-of-truth property (each CI run still fetches the
-# canonical validator fresh).
-#
-# Four-surface migration audit (feedback_gitea_actions_migration_audit_pattern):
-#   1. YAML — no `workflow_dispatch.inputs`; no `merge_group`; preserved
-#      `on: [push, pull_request]` from the original. Added workflow-level
-#      env.GITHUB_SERVER_URL (feedback_act_runner_github_server_url).
-#   2. Cache — `actions/setup-python` `cache: pip` preserved; works against
-#      Gitea's built-in cache server when runner.cache is configured.
-#   3. Token — uses auto-injected GITHUB_TOKEN (Gitea-aliased). Validator
-#      job needs only `contents: read` (no write to issues/PRs).
-#   4. Docs — anonymous git-clone of molecule-ci (no token in URL); the
-#      molecule-ci repo is public on the Gitea instance.
-#
-# Fork-PR semantics: validate-runtime is intentionally skipped on fork
-# PRs because pip-install + docker-build + adapter-import are arbitrary
-# code execution. Internal PRs and main pushes get full coverage. The
-# `github.event.pull_request.head.repo.fork` field is null for non-PR
-# events; the `!= true` comparison defaults to running.
-#
-# Cross-links:
-#   - internal#326 — parent tracking issue
-#   - molecule-ai/molecule-ci/.github/workflows/validate-workspace-template.yml — pattern source
-#   - molecule-ai/molecule-core/.gitea/workflows/ci.yml — Gitea port style reference
-
-on: [push, pull_request]
-
-# Defense-in-depth de-dup ONLY (the t4-conformance unique-name fix is the
-# actual fail-closed primitive against the shared-host-daemon race; see
-# that job). Scope per workflow + ref + EVENT so the push run and the
-# pull_request run of the same internal-PR commit get DISTINCT groups —
-# they must both complete (each emits its own required-status context;
-# feedback_gitea_gate_check_required_list_not_combined_status). Never
-# per-SHA-global: that silently cross-cancels legit required checks
-# (feedback_concurrency_group_per_sha). cancel-in-progress:false so an
-# in-flight live T4 probe is never aborted mid-assertion (a cancelled
-# privileged probe would look like a gate failure / flake); a newer push
-# to the same ref+event simply queues behind it.
-concurrency:
-  group: ci-${{ github.workflow }}-${{ github.event_name }}-${{ github.ref }}
-  cancel-in-progress: false
-
-env:
-  # Belt-and-suspenders against the runner-default trap
-  # (feedback_act_runner_github_server_url). Runners are configured
-  # with this env via /opt/molecule/runners/config.yaml runner.envs,
-  # but pinning at the workflow level protects against a runner
-  # regenerated without the config file.
-  GITHUB_SERVER_URL: https://git.moleculesai.app
-
-# Defense-in-depth on the GITHUB_TOKEN scope. The validate-runtime job
-# runs untrusted-by-design code from the calling repo — pip-installs
-# requirements.txt (post-install hooks), imports adapter.py, and
-# docker-builds the Dockerfile. Each primitive can execute arbitrary
-# code with the token in env. Pinning `contents: read` means the worst
-# a malicious template PR can do with the token is read public repo
-# state — no write to issues, no push to branches, no comment-spam.
-permissions:
-  contents: read
-
-jobs:
-  validate-static:
-    name: Template validation (static)
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      # Canonical validator script lives in molecule-ci, fetched fresh on
-      # every run. Anonymous fetch of the public molecule-ci repo — no
-      # token needed; no actions/checkout cross-repo idiosyncrasies.
-      - name: Fetch molecule-ci canonical scripts
-        run: git clone --depth 1 https://git.moleculesai.app/molecule-ai/molecule-ci.git .molecule-ci-canonical
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-      # Secret scan — the most important check. Always runs, including
-      # on fork PRs (no third-party code executes here).
-      - name: Check for secrets
-        run: |
-          python3 - << 'PYEOF'
-          import os, re, sys
-          from pathlib import Path
-
-          PATTERNS = [
-              re.compile(r'''["']sk-ant-[a-zA-Z0-9]{50,}["']'''),
-              re.compile(r'''["']ghp_[a-zA-Z0-9]{36,}["']'''),
-              re.compile(r'''["']AKIA[A-Z0-9]{16}["']'''),
-              re.compile(r'''["'][a-zA-Z0-9/+=]{40}["']'''),
-              re.compile(r'''["']sk_test_[a-zA-Z0-9]{24,}["']'''),
-              re.compile(r'''["']Bearer\s+[a-zA-Z0-9_.-]{20,}["']'''),
-              re.compile(r'''ghp_[a-zA-Z0-9]{36,}'''),
-              re.compile(r'''sk-ant-[a-zA-Z0-9]{50,}'''),
-          ]
-          SKIP_DIRS = {'.molecule-ci', '.molecule-ci-canonical', '.git', 'node_modules', '__pycache__'}
-          EXTENSIONS = {'.yaml', '.yml', '.md', '.py', '.sh'}
-
-          def is_false_positive(line):
-              ctx = line.lower()
-              return '...' in ctx or '<example' in ctx or '</example' in ctx
-
-          root = Path(os.environ.get('GITHUB_WORKSPACE', '.'))
-          warnings = []
-          for dirpath, dirnames, filenames in os.walk(root):
-              dirnames[:] = [d for d in dirnames if d not in SKIP_DIRS]
-              for filename in filenames:
-                  if Path(filename).suffix not in EXTENSIONS:
-                      continue
-                  filepath = Path(dirpath) / filename
-                  try:
-                      with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
-                          for lineno, line in enumerate(f.readlines(), 1):
-                              for pattern in PATTERNS:
-                                  for match in pattern.finditer(line):
-                                      if not is_false_positive(line):
-                                          warnings.append(f"  {filepath}:{lineno}: {match.group(0)[:40]}...")
-                  except Exception:
-                      pass
-
-          if warnings:
-              print("::error::Potential secret found in committed files:")
-              for w in warnings:
-                  print(w)
-              sys.exit(1)
-          else:
-              print("::notice::No secrets detected")
-          PYEOF
-      # Static-only validator — file existence checks, YAML parse,
-      # AST inspection of adapter.py (no import). Doesn't execute any
-      # third-party code; safe on fork PRs.
-      - run: pip install pyyaml -q
-      - run: python3 .molecule-ci-canonical/scripts/validate-workspace-template.py --static-only
-
-  validate-runtime:
-    name: Template validation (runtime)
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    needs: validate-static
-    # Skip when the PR comes from a fork — those are external,
-    # untrusted, and would let attackers run pip install / docker build
-    # / adapter.py import on our runner.
-    if: github.event.pull_request.head.repo.fork != true
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - name: Fetch molecule-ci canonical scripts
-        run: git clone --depth 1 https://git.moleculesai.app/molecule-ai/molecule-ci.git .molecule-ci-canonical
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "pip"
-          cache-dependency-path: requirements.txt
-      - run: pip install pyyaml -q
-      # Install the template's runtime dependencies so the validator's
-      # check_adapter_runtime_load() can import adapter.py the same way
-      # the workspace container does at boot. Without this, a
-      # syntactically-valid adapter that ImportErrors on a missing
-      # transitive dep would build clean and crash on first user prompt.
-      - if: hashFiles('requirements.txt') != ''
-        run: pip install -q -r requirements.txt
-      - if: hashFiles('requirements.txt') == ''
-        run: pip install -q molecule-ai-workspace-runtime
-      - run: python3 .molecule-ci-canonical/scripts/validate-workspace-template.py
-      - name: Docker build smoke test
-        if: hashFiles('Dockerfile') != ''
-        run: |
-          # Graceful skip when the runner's job-container can't reach the
-          # Docker daemon (e.g. /var/run/docker.sock not mounted into the
-          # act job container, or the in-container uid not in the docker
-          # group). Without this guard, CI stays red even when the
-          # template's Dockerfile is fine — see internal#222 for the
-          # proper runner-config fix.
-          if ! docker info >/dev/null 2>&1; then
-            echo "::warning::docker daemon unreachable from runner job container — skipping Docker build smoke (runner-config gap, not a template issue)."
-            exit 0
-          fi
-          docker build -t template-test . --no-cache 2>&1 | tail -5 && echo "Docker build succeeded"
-
-  # --- Layer-3: real T4 tier-4 conformance gate (RFC internal#456 §11) ---
-  # NOT a string-match. Builds the actual image, runs it under the EXACT
-  # flags the controlplane provisioner emits for tier-4
-  # (userdata_containerized.go @ec2384c: --privileged --pid=host --network host
-  # -v /:/host -v /var/run/docker.sock:/var/run/docker.sock), then drives
-  # the *uniform T4 privilege contract* defined in
-  # molecule-ai/molecule-core's workspace-server/internal/provisioner/
-  # t4_privilege_contract.go and rendered via
-  # `go run ./workspace-server/cmd/t4-contract-dump`. Each capability
-  # in the YAML has a stable name, a shell probe that exits 0 on pass,
-  # and a severity (hard|advisory). Hard misses fail the gate; new
-  # capabilities propagate WITHOUT a per-template PR (just bump the
-  # MOLECULE_CORE_REF env, or let it float to main).
-  #
-  # PILOT (internal #174): this is the first template to consume the
-  # uniform contract. template-hermes / template-codex follow on
-  # sequenced PRs after this lands green.
-  #
-  # Anti-tautology (per memory feedback_hermes_listpeers_401_token_…):
-  # all probes run against a RUNNING container started via the real
-  # `docker run` flags the provisioner emits — no `chown` + immediate
-  # `stat` self-fulfilling pairs. The contract's
-  # `host_root_reach_via_nsenter` probe fails closed if `exec gosu agent`
-  # ever regresses, exactly as the Hermes equivalent does.
-  #
-  # The `list_peers_http_200` probe is OPT-IN (advisory by default in
-  # this template) because the platform a2a_mcp_server is only spun up
-  # by the real start.sh boot path with credentials we don't want in
-  # CI. The probe iterates capabilities; for `list_peers_http_200` we
-  # skip-with-warning if `/configs/.auth_token` is absent (smoke-mode).
-  # On a fresh prod provision the probe is exercised end-to-end by the
-  # post-pin live-verify (task #195).
-  #
-  # Concurrency-flake: per-run-unique `--name` + per-run-unique probe
-  # file paths under /host/tmp/. Push and pull_request runs of the
-  # same commit share a host Docker daemon (--network host); a static
-  # name would collide and false-negative. See sibling template-hermes
-  # ci.yml + task #207 for the canonical rationale.
-  t4-conformance:
-    name: T4 tier-4 conformance (live)
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    needs: validate-static
-    if: github.event.pull_request.head.repo.fork != true
-    env:
-      # The molecule-core ref the contract YAML is generated from.
-      # Default `main` floats with the latest contract; pin to a SHA
-      # for deterministic gate behavior across template branches.
-      # Adopters MAY override per-PR to test an unmerged contract change.
-      MOLECULE_CORE_REF: main
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # v6.0.0
-        with:
-          go-version: "1.25"
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-      - run: pip install -q pyyaml
-      - name: Fetch molecule-core + generate t4_capabilities.yaml from the uniform contract
-        run: |
-          set -euo pipefail
-          git clone --depth 1 --branch "${MOLECULE_CORE_REF}" \
-            https://git.moleculesai.app/molecule-ai/molecule-core.git .molecule-core
-          ( cd .molecule-core/workspace-server && go run ./cmd/t4-contract-dump ) > t4_capabilities.yaml
-          # Defense-in-depth: schema-version assertion so a contract
-          # bump that breaks the parser shape is caught here, not at
-          # runtime where it would look like a phantom capability miss.
-          grep -q '^version: 1$' t4_capabilities.yaml || { echo "::error::t4_capabilities.yaml schema version unrecognized"; exit 1; }
-          echo "=== contract preview ==="
-          head -40 t4_capabilities.yaml
-          echo "=== capability names ==="
-          grep '^  - name:' t4_capabilities.yaml
-      - name: Build the runtime image
-        run: |
-          if ! docker info >/dev/null 2>&1; then
-            echo "::error::docker daemon unreachable — T4 conformance gate CANNOT verify host-root reach. This is a hard gate; failing closed (do NOT treat as skip). Fix runner-config (internal#222) to unblock."
-            exit 1
-          fi
-          T4_TAG="t4-conformance-test:${GITHUB_RUN_ID:-local}-${GITHUB_RUN_ATTEMPT:-1}"
-          docker build -t "$T4_TAG" . --no-cache 2>&1 | tail -5
-      - name: Run under EXACT tier-4 provisioner flags + iterate contract capabilities
-        env:
-          # Per-run-unique probe-id. Used by individual capability
-          # probes (agent_home_writable, host_fs_write_readback) to
-          # scope their on-disk markers; without this, concurrent
-          # same-commit push+pull_request runs would collide on the
-          # /host/tmp/* path (see template-hermes ci.yml + task #207).
-          MOLECULE_T4_PROBE_ID: "${{ github.run_id }}-${{ github.run_attempt }}"
-          # Container name is computed in the script body and exported
-          # so the inline Python iterator can `docker exec` into it.
-          T4_PROBE_NAME: "t4probe-${{ github.run_id }}-${{ github.run_attempt }}"
-        run: |
-          set -euo pipefail
-          T4_TAG="t4-conformance-test:${GITHUB_RUN_ID:-local}-${GITHUB_RUN_ATTEMPT:-1}"
-          T4_PROBE="$T4_PROBE_NAME"
-          docker rm -f "$T4_PROBE" >/dev/null 2>&1 || true
-          docker run -d \
-            --name "$T4_PROBE" \
-            --network host \
-            --privileged \
-            --pid=host \
-            -v /:/host \
-            -v /var/run/docker.sock:/var/run/docker.sock \
-            -e MOLECULE_T4_PROBE_ID="$MOLECULE_T4_PROBE_ID" \
-            -e MOLECULE_T4_EGRESS_TARGETS="https://api.github.com/zen https://www.google.com/generate_204" \
-            --entrypoint /bin/sh \
-            "$T4_TAG" -c 'sleep 600' >/dev/null
-          trap 'docker rm -f "$T4_PROBE" >/dev/null 2>&1 || true; docker rmi -f "$T4_TAG" >/dev/null 2>&1 || true' EXIT
-
-          # ----- Reproduce SaaS-mode token agent-ownership pre-state -----
-          # The real entrypoint chowns /configs:agent before gosu; in this
-          # smoke probe /configs is unmounted, so reproduce the contract
-          # step. The `auth_token_agent_owned` probe THEN asserts the
-          # post-condition. This is NOT a tautology: the probe asserts
-          # `stat -c %u` returns 1000, which would fail if the entrypoint
-          # ever wrote the token as root in the live boot path
-          # (`host_root_reach_via_nsenter` + the gosu chain is the
-          # anti-regression guard for that — both probes must pass).
-          docker exec "$T4_PROBE" sh -c 'mkdir -p /configs && touch /configs/.auth_token && chown -R agent:agent /configs'
-
-          # ----- Iterate the contract YAML -----
-          # Pure-python YAML walker (PyYAML installed earlier). We
-          # don't exec the probe via shell-only because shell-parsing
-          # YAML is fragile; we do execute each probe IN the running
-          # container via `docker exec -u agent` so uid-1000 context is
-          # enforced.
-          python3 - <<'PYEOF'
-          import os, subprocess, sys, yaml
-          with open("t4_capabilities.yaml") as f:
-              doc = yaml.safe_load(f)
-          probe = os.environ["T4_PROBE_NAME"]
-          fails_hard = []
-          fails_soft = []
-          for cap in doc.get("capabilities", []):
-              name = cap["name"]
-              sev = cap.get("severity", "advisory")
-              probe_sh = cap["probe"]
-              # OPT-OUT semantics for capabilities that need a live
-              # platform/runtime not stood up in this probe. They are
-              # exercised end-to-end by the post-pin live-verify burst
-              # (task #195) instead.
-              if name == "list_peers_http_200":
-                  # Only run if the in-container runtime has spun up;
-                  # smoke-mode does not. Skip-with-notice keeps the
-                  # gate honest without false negatives.
-                  port = subprocess.run(
-                      ["docker","exec","-u","agent",probe,"sh","-c","[ -f /configs/.platform_port ]"],
-                      capture_output=True,
-                  ).returncode
-                  if port != 0:
-                      print(f"::notice::skipping {name} — runtime not booted in CI smoke probe; covered by live post-pin verify")
-                      continue
-              r = subprocess.run(
-                  ["docker","exec","-u","agent",probe,"sh","-c",probe_sh],
-                  capture_output=True, text=True,
-              )
-              if r.returncode == 0:
-                  print(f"  PASS  {name}  ({sev})")
-              else:
-                  msg = f"FAIL  {name}  ({sev}): rc={r.returncode}  source={cap.get('source','?')}"
-                  print(f"::error::{msg}")
-                  if r.stderr.strip():
-                      print(f"        stderr: {r.stderr.strip()}")
-                  if sev == "hard":
-                      fails_hard.append(name)
-                  else:
-                      fails_soft.append(name)
-          if fails_hard:
-              print(f"::error::T4 conformance FAILED — hard capabilities not satisfied: {fails_hard} (RFC internal#456 §11; the gate is fail-closed)")
-              sys.exit(1)
-          if fails_soft:
-              print(f"::warning::T4 conformance: advisory capabilities failed: {fails_soft} (non-blocking, but inspect)")
-          print(f"::notice::T4 tier-4 conformance PASS — uniform contract satisfied ({len(doc.get('capabilities',[]))} capabilities checked)")
-          PYEOF
-
-  # Aggregator that emits a single `validate` check name — matches the
-  # historical required-check name on this repo's branch protection.
-  validate:
-    name: validate
-    runs-on: ubuntu-latest
-    needs: [validate-static, validate-runtime, t4-conformance]
-    if: always()
-    timeout-minutes: 1
-    steps:
-      - name: Aggregate
-        run: |
-          static="${{ needs.validate-static.result }}"
-          runtime="${{ needs.validate-runtime.result }}"
-          t4="${{ needs.t4-conformance.result }}"
-          echo "validate-static:  $static"
-          echo "validate-runtime: $runtime"
-          echo "t4-conformance:   $t4"
-          if [ "$static" != "success" ]; then
-            echo "::error::validate-static did not succeed: $static"
-            exit 1
-          fi
-          # Treat `skipped` as a pass for fork-PR semantics (validate-runtime
-          # is intentionally skipped on forks; static coverage is the gate).
-          if [ "$runtime" != "success" ] && [ "$runtime" != "skipped" ]; then
-            echo "::error::validate-runtime did not succeed: $runtime"
-            exit 1
-          fi
-          # T4 conformance is a HARD gate on internal (non-fork) PRs and
-          # main pushes. `skipped` is only acceptable on fork PRs (where
-          # the `if:` fork guard short-circuits it) — there the static
-          # gate is the floor. Any other non-success fails the build:
-          # "verified" T4 requires this live gate green, never inference.
-          if [ "$t4" != "success" ] && [ "$t4" != "skipped" ]; then
-            echo "::error::t4-conformance did not succeed: $t4 — T4 host-root reach / token-ownership not verified on a live container. Failing closed (RFC internal#456 §11)."
-            exit 1
-          fi
-          echo "::notice::Template validation aggregate passed (static=$static, runtime=$runtime, t4=$t4)"
-
-  tests:
-    name: Adapter unit tests
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-      # pyyaml is the runtime dep that adapter.py's _load_providers reads
-      # /configs/config.yaml through. In production it arrives transitively
-      # via molecule-ai-workspace-runtime; in this minimal test env we
-      # install it explicitly so the YAML-loading code path is actually
-      # exercised (without it, _load_providers' broad except-Exception
-      # swallows the ImportError and silently falls back to _BUILTIN_PROVIDERS,
-      # which is exactly the behavior that bit us 2026-04-30 when CI
-      # claimed green on a build that couldn't route any third-party model).
-      - run: pip install -q pytest pytest-asyncio pyyaml
-      # Tests live under tests/ with their own pytest.ini that anchors
-      # rootdir there — keeps pytest from importing the package
-      # __init__.py (which does `from .adapter import ...` for runtime
-      # discovery and can't be satisfied without molecule_runtime
-      # installed). See tests/pytest.ini for the full rationale.
-      - run: python3 -m pytest tests/ -v

.gitea/workflows/publish-image.yml

@@ -1,225 +0,0 @@
-name: publish-image
-
-# Builds the claude-code workspace template Dockerfile and pushes it to ECR as
-# `<REGISTRY>/workspace-template-claude-code:latest` + `:sha-<7>`.
-#
-# Ported/inlined from molecule-ci's publish-template-image.yml reusable
-# workflow. Cross-repo `uses:` is BLOCKED on Gitea 1.22.6 because
-# DEFAULT_ACTIONS_URL=github causes the runner to attempt the lookup against
-# github.com, which always 404s even for same-instance repos.
-# (feedback_gitea_cross_repo_uses_blocked)
-#
-# Registry: production uses ECR (MOLECULE_IMAGE_REGISTRY env var on EC2 /
-# Railway) backed by org-level AWS creds. The OSS default in registry.go is
-# ghcr.io/molecule-ai but the ECR repo `molecule-ai/workspace-template-claude-code`
-# already exists (created by the migration sweep). No GHCR token is in the
-# credentials store — Gitea's GITHUB_TOKEN cannot authenticate to ghcr.io.
-#
-# Gitea 1.22.6 hostile-shape checklist applied:
-#   - No workflow_dispatch.inputs (silently rejected on 1.22.6)
-#   - No merge_group: trigger
-#   - No cross-repo uses:
-#   - GITHUB_SERVER_URL pinned at workflow level
-#     (feedback_act_runner_github_server_url)
-#   - No on.push.paths: (would permanently block path-excluded pushes)
-#   - timeout-minutes on every job
-#
-# Cascade signal: molecule-core/publish-runtime.yml fans out by git-pushing
-# an updated `.runtime-version` file to this repo's main branch, which trips
-# the `on: push: branches: [main]` trigger here. The resolve-version job reads
-# that file and forwards the version as a RUNTIME_VERSION docker build-arg so
-# pip install resolves the exact fresh version.
-
-on:
-  push:
-    branches: [main]
-  workflow_dispatch:
-
-env:
-  # Belt-and-suspenders for act_runner runners regenerated without the
-  # config.yaml envs block. (feedback_act_runner_github_server_url)
-  GITHUB_SERVER_URL: https://git.moleculesai.app
-  ECR_REGISTRY: 153263036946.dkr.ecr.us-east-2.amazonaws.com
-  IMAGE_NAME: 153263036946.dkr.ecr.us-east-2.amazonaws.com/molecule-ai/workspace-template-claude-code
-  AWS_DEFAULT_REGION: us-east-2
-
-permissions:
-  contents: read
-
-jobs:
-  resolve-version:
-    name: Resolve runtime version
-    runs-on: ubuntu-latest
-    timeout-minutes: 2
-    outputs:
-      version: ${{ steps.read.outputs.version }}
-      sha: ${{ steps.read.outputs.sha }}
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - id: read
-        shell: bash
-        run: |
-          if [ -f .runtime-version ]; then
-            v="$(head -n1 .runtime-version | tr -d '[:space:]')"
-            echo "version=${v}" >> "$GITHUB_OUTPUT"
-            echo "resolved runtime version from .runtime-version: ${v}"
-          else
-            echo "version=" >> "$GITHUB_OUTPUT"
-            echo "no .runtime-version file — will use Dockerfile/requirements.txt pin"
-          fi
-          echo "sha=${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT"
-
-  publish:
-    name: Build & push workspace-template-claude-code image
-    # internal#512: pin to the dedicated Linux publish runners (label
-    # "publish" → molecule-runner-publish-1/2). MUST NOT use `ubuntu-latest`:
-    # that label is also advertised by the Windows/WSL self-hosted runners
-    # (hongming-pc-runner-*), so this docker build/push job lands
-    # non-deterministically on a Windows runner where `aws ecr
-    # get-login-password | docker login --password-stdin` fails with
-    # "Failed to initialize: protocol not available" and the image never
-    # publishes. Placement-dependent, NOT a transient flake. Mirrors the
-    # molecule-core convention (publish-workspace-server-image.yml /
-    # publish-runtime.yml / publish-canvas-image.yml: `runs-on: publish`)
-    # and the codex sibling fix (PR#9).
-    runs-on: publish
-    timeout-minutes: 30
-    needs: resolve-version
-    steps:
-      - name: Checkout
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-
-      - name: Lint — no bare imports of runtime modules
-        # Catches `from plugins import ...` style bare imports that work in the
-        # monorepo layout but explode at startup in the published container
-        # (ModuleNotFoundError). Runs before Docker login so a bad adapter
-        # returns red in seconds.
-        # Fallback module list mirrors scripts/build_runtime_package.py:
-        # TOP_LEVEL_MODULES as of 2026-04-27.
-        shell: bash
-        run: |
-          set -eu
-          FALLBACK_MODULES='plugins|adapter_base|config|main|preflight|prompt|coordinator|consolidation|events|heartbeat|transcript_auth|runtime_wedge|watcher|skill_loader|policies|adapters|builtin_tools|executor_helpers|a2a_executor|a2a_client|a2a_tools|a2a_cli|a2a_mcp_server|agent|agents_md|initial_prompt|molecule_ai_status|platform_auth|shared_runtime'
-          RUNTIME_MODULES=""
-          mkdir -p /tmp/runtime-wheel
-          if pip download --quiet molecule-ai-workspace-runtime --no-deps -d /tmp/runtime-wheel 2>/dev/null; then
-            WHEEL=$(ls /tmp/runtime-wheel/*.whl 2>/dev/null | head -1)
-            if [ -n "$WHEEL" ]; then
-              RUNTIME_MODULES=$(unzip -p "$WHEEL" molecule_runtime/_runtime_modules.json 2>/dev/null \
-                | python3 -c "import sys,json; m=json.load(sys.stdin); print('|'.join(sorted(set(m['top_level_modules']) | set(m['subpackages']))))" 2>/dev/null || echo "")
-            fi
-          fi
-          if [ -n "$RUNTIME_MODULES" ]; then
-            echo "::notice::lint module list from published wheel"
-          else
-            RUNTIME_MODULES="$FALLBACK_MODULES"
-            echo "::warning::could not read _runtime_modules.json from wheel — using inline fallback"
-          fi
-          if HITS=$(grep -nE "^\s*from (${RUNTIME_MODULES}) import" *.py 2>/dev/null); then
-            echo "::error::Bare imports of runtime modules found — use 'from molecule_runtime.<module> import'"
-            echo "$HITS" | sed 's/^/  /'
-            exit 1
-          fi
-          echo "::notice::no bare imports of runtime modules in *.py files"
-
-      - name: Log in to ECR
-        env:
-          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-        run: |
-          set -euo pipefail
-          aws ecr get-login-password --region us-east-2 | \
-            docker login --username AWS --password-stdin "${ECR_REGISTRY}"
-
-      - name: Verify Docker daemon access
-        run: |
-          set -euo pipefail
-          docker info >/dev/null 2>&1 || {
-            echo "::error::Docker daemon is not accessible — check runner sock mount"
-            exit 1
-          }
-          echo "Docker daemon OK"
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
-
-      - name: Ensure ECR repository exists
-        env:
-          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-        run: |
-          set -euo pipefail
-          repo_path="${IMAGE_NAME#*/}"
-          repo_path="${repo_path#*/}"  # strip registry host + first slash → molecule-ai/workspace-template-claude-code
-          if ! aws ecr describe-repositories --repository-names "${repo_path}" --region us-east-2 >/dev/null 2>&1; then
-            aws ecr create-repository \
-              --repository-name "${repo_path}" \
-              --image-scanning-configuration scanOnPush=true \
-              --region us-east-2 >/dev/null
-            echo "::notice::created ECR repository ${repo_path}"
-          else
-            echo "ECR repository ${repo_path} already exists"
-          fi
-
-      - name: Build image (load for smoke test, do not push yet)
-        # Build into runner-local docker first. Smoke test runs before push so
-        # a broken adapter.py never poisons :latest.
-        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
-        with:
-          context: .
-          file: ./Dockerfile
-          platforms: linux/amd64
-          load: true
-          push: false
-          tags: ${{ env.IMAGE_NAME }}:sha-${{ needs.resolve-version.outputs.sha }}
-          build-args: |
-            RUNTIME_VERSION=${{ needs.resolve-version.outputs.version }}
-          labels: |
-            org.opencontainers.image.source=https://git.moleculesai.app/${{ github.repository }}
-            org.opencontainers.image.revision=${{ github.sha }}
-            org.opencontainers.image.description=Molecule AI workspace template — claude-code runtime
-
-      - name: Smoke test — import every /app/*.py
-        # Boot the locally-loaded image and import each *.py module to verify
-        # all module-level imports resolve against the pip-installed runtime.
-        shell: bash
-        env:
-          IMAGE: ${{ env.IMAGE_NAME }}:sha-${{ needs.resolve-version.outputs.sha }}
-        run: |
-          set -eu
-          docker run --rm \
-            -e WORKSPACE_ID=smoke-test \
-            -e CLAUDE_CODE_OAUTH_TOKEN=sk-fake-smoke-token \
-            -e ANTHROPIC_API_KEY=sk-fake-smoke-key \
-            -e OPENAI_API_KEY=sk-fake-smoke-key \
-            --entrypoint sh "${IMAGE}" -c '
-            set -e
-            cd /app
-            for f in *.py; do
-              [ "$f" = "__init__.py" ] && continue
-              mod="${f%.py}"
-              python3 -c "import $mod" || { echo "::error::failed to import $mod"; exit 1; }
-              echo "  import $mod OK"
-            done
-          '
-          echo "::notice::${IMAGE}: all /app/*.py modules import cleanly"
-
-      - name: Push image to ECR (post-smoke)
-        # Smoke passed — push both :latest and :sha-<7>. build-push-action
-        # reuses the cached layers so this is a layer-push, not a rebuild.
-        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
-        with:
-          context: .
-          file: ./Dockerfile
-          platforms: linux/amd64
-          push: true
-          tags: |
-            ${{ env.IMAGE_NAME }}:latest
-            ${{ env.IMAGE_NAME }}:sha-${{ needs.resolve-version.outputs.sha }}
-          build-args: |
-            RUNTIME_VERSION=${{ needs.resolve-version.outputs.version }}
-          labels: |
-            org.opencontainers.image.source=https://git.moleculesai.app/${{ github.repository }}
-            org.opencontainers.image.revision=${{ github.sha }}
-            org.opencontainers.image.description=Molecule AI workspace template — claude-code runtime
-

.gitea/workflows/secret-scan.yml

@@ -1,196 +0,0 @@
-name: Secret scan
-
-# Hard CI gate. Refuses any PR / push whose diff additions contain a
-# recognisable credential. Defense-in-depth for the #2090-class incident
-# (2026-04-24): GitHub's hosted Copilot Coding Agent leaked a ghs_*
-# installation token into tenant-proxy/package.json via `npm init`
-# slurping the URL from a token-embedded origin remote. We can't fix
-# upstream's clone hygiene, so we gate here.
-#
-# Same regex set as the runtime's bundled pre-commit hook
-# (molecule-ai-workspace-runtime: molecule_runtime/scripts/pre-commit-checks.sh).
-# Keep the two sides aligned when adding patterns.
-#
-# Ported from .github/workflows/secret-scan.yml so the gate actually
-# fires on Gitea Actions. Differences from the GitHub version:
-#   - drops `merge_group` event (Gitea has no merge queue)
-#   - drops `workflow_call` (no cross-repo reusable invocation on Gitea)
-#   - SELF path updated to .gitea/workflows/secret-scan.yml
-# The job name + step name are identical to the GitHub workflow so the
-# status-check context (`Secret scan / Scan diff for credential-shaped
-# strings (pull_request)`) matches branch protection on this template
-# repo's main branch. Before this port, the required-status was satisfied
-# only via a compensating signed POST /statuses/{SHA} because the
-# .github/ workflow was silently shadowed by the .gitea/ directory taking
-# precedence on this repo
-# (reference_molecule_core_actions_gitea_only — same applies here).
-
-on:
-  pull_request:
-    types: [opened, synchronize, reopened]
-  push:
-    branches: [main, staging]
-
-jobs:
-  scan:
-    name: Scan diff for credential-shaped strings
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          fetch-depth: 2  # need previous commit to diff against on push events
-
-      # For pull_request events the diff base may be many commits behind
-      # HEAD and absent from the shallow clone. Fetch it explicitly.
-      - name: Fetch PR base SHA (pull_request events only)
-        if: github.event_name == 'pull_request'
-        run: git fetch --depth=1 origin ${{ github.event.pull_request.base.sha }}
-
-      - name: Refuse if credential-shaped strings appear in diff additions
-        env:
-          # Plumb event-specific SHAs through env so the script doesn't
-          # need conditional `${{ ... }}` interpolation per event type.
-          # github.event.before/after only exist on push events;
-          # pull_request has pull_request.base.sha / pull_request.head.sha.
-          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
-          PR_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
-          PUSH_BEFORE: ${{ github.event.before }}
-          PUSH_AFTER: ${{ github.event.after }}
-        run: |
-          # Pattern set covers GitHub family (the actual #2090 vector),
-          # Anthropic / OpenAI / Slack / AWS. Anchored on prefixes with low
-          # false-positive rates against agent-generated content. Mirror of
-          # molecule-ai-workspace-runtime/molecule_runtime/scripts/pre-commit-checks.sh
-          # — keep aligned.
-          SECRET_PATTERNS=(
-            'ghp_[A-Za-z0-9]{36,}'           # GitHub PAT (classic)
-            'ghs_[A-Za-z0-9]{36,}'           # GitHub App installation token
-            'gho_[A-Za-z0-9]{36,}'           # GitHub OAuth user-to-server
-            'ghu_[A-Za-z0-9]{36,}'           # GitHub OAuth user
-            'ghr_[A-Za-z0-9]{36,}'           # GitHub OAuth refresh
-            'github_pat_[A-Za-z0-9_]{82,}'   # GitHub fine-grained PAT
-            'sk-ant-[A-Za-z0-9_-]{40,}'      # Anthropic API key
-            'sk-proj-[A-Za-z0-9_-]{40,}'     # OpenAI project key
-            'sk-svcacct-[A-Za-z0-9_-]{40,}'  # OpenAI service-account key
-            'sk-cp-[A-Za-z0-9_-]{60,}'       # MiniMax API key (F1088 vector — caught only after the fact)
-            'xox[baprs]-[A-Za-z0-9-]{20,}'   # Slack tokens
-            'AKIA[0-9A-Z]{16}'               # AWS access key ID
-            'ASIA[0-9A-Z]{16}'               # AWS STS temp access key ID
-          )
-
-          # Determine the diff base. Each event type stores its SHAs in
-          # a different place — see the env block above.
-          case "${{ github.event_name }}" in
-            pull_request)
-              BASE="$PR_BASE_SHA"
-              HEAD="$PR_HEAD_SHA"
-              ;;
-            *)
-              BASE="$PUSH_BEFORE"
-              HEAD="$PUSH_AFTER"
-              ;;
-          esac
-
-          # On push events with shallow clones, BASE may be present in
-          # the event payload but absent from the local object DB
-          # (fetch-depth=2 doesn't always reach the previous commit
-          # across true merges). Try fetching it on demand. If the
-          # fetch fails — e.g. the SHA was force-overwritten — we fall
-          # through to the empty-BASE branch below, which scans the
-          # entire tree as if every file were new. Correct, just slow.
-          if [ -n "$BASE" ] && ! echo "$BASE" | grep -qE '^0+$'; then
-            if ! git cat-file -e "$BASE" 2>/dev/null; then
-              git fetch --depth=1 origin "$BASE" 2>/dev/null || true
-            fi
-          fi
-
-          # Files added or modified in this change.
-          if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$' || ! git cat-file -e "$BASE" 2>/dev/null; then
-            # New branch / no previous SHA / BASE unreachable — check the
-            # entire tree as added content. Slower, but correct on first
-            # push.
-            CHANGED=$(git ls-tree -r --name-only HEAD)
-            DIFF_RANGE=""
-          else
-            CHANGED=$(git diff --name-only --diff-filter=AM "$BASE" "$HEAD")
-            DIFF_RANGE="$BASE $HEAD"
-          fi
-
-          if [ -z "$CHANGED" ]; then
-            echo "No changed files to inspect."
-            exit 0
-          fi
-
-          # Self-exclude: this workflow file legitimately contains the
-          # pattern strings as regex literals. Without an exclude it would
-          # block its own merge. Both the .github/ original and this
-          # .gitea/ port are excluded so a sync between them stays clean.
-          SELF_GITHUB=".github/workflows/secret-scan.yml"
-          SELF_GITEA=".gitea/workflows/secret-scan.yml"
-
-          OFFENDING=""
-          # `while IFS= read -r` (not `for f in $CHANGED`) so filenames
-          # containing whitespace don't word-split silently — a path
-          # with a space would otherwise produce two iterations on
-          # tokens that aren't real filenames, breaking the
-          # self-exclude + diff lookup.
-          while IFS= read -r f; do
-            [ -z "$f" ] && continue
-            [ "$f" = "$SELF_GITHUB" ] && continue
-            [ "$f" = "$SELF_GITEA" ] && continue
-            if [ -n "$DIFF_RANGE" ]; then
-              ADDED=$(git diff --no-color --unified=0 "$BASE" "$HEAD" -- "$f" 2>/dev/null | grep -E '^\+[^+]' || true)
-            else
-              # No diff range (new branch first push) — scan the full file
-              # contents as if every line were new.
-              ADDED=$(cat "$f" 2>/dev/null || true)
-            fi
-            [ -z "$ADDED" ] && continue
-            for pattern in "${SECRET_PATTERNS[@]}"; do
-              if echo "$ADDED" | grep -qE "$pattern"; then
-                OFFENDING="${OFFENDING}${f} (matched: ${pattern})\n"
-                break
-              fi
-            done
-          done <<< "$CHANGED"
-
-          if [ -n "$OFFENDING" ]; then
-            echo "::error::Credential-shaped strings detected in diff additions:"
-            # `printf '%b' "$OFFENDING"` interprets backslash escapes
-            # (the literal `\n` we appended above becomes a newline)
-            # WITHOUT treating OFFENDING as a format string. Plain
-            # `printf "$OFFENDING"` is a format-string sink: a filename
-            # containing `%` would be interpreted as a conversion
-            # specifier, corrupting the error message (or printing
-            # `%(missing)` artifacts).
-            printf '%b' "$OFFENDING"
-            echo ""
-            echo "The actual matched values are NOT echoed here, deliberately —"
-            echo "round-tripping a leaked credential into CI logs widens the blast"
-            echo "radius (logs are searchable + retained)."
-            echo ""
-            echo "Recovery:"
-            echo "  1. Remove the secret from the file. Replace with an env var"
-            echo "     reference (e.g. \${{ secrets.GITHUB_TOKEN }} in workflows,"
-            echo "     process.env.X in code)."
-            echo "  2. If the credential was already pushed (this PR's commit"
-            echo "     history reaches a public ref), treat it as compromised —"
-            echo "     ROTATE it immediately, do not just remove it. The token"
-            echo "     remains valid in git history forever and may be in any"
-            echo "     log/cache that consumed this branch."
-            echo "  3. Force-push the cleaned commit (or stack a revert) and"
-            echo "     re-run CI."
-            echo ""
-            echo "If the match is a false positive (test fixture, docs example,"
-            echo "or this workflow's own regex literals): use a clearly-fake"
-            echo "placeholder like ghs_EXAMPLE_DO_NOT_USE that doesn't satisfy"
-            echo "the length suffix, OR add the file path to the SELF exclude"
-            echo "list in this workflow with a short reason."
-            echo ""
-            echo "Mirror of the regex set lives in the runtime's bundled"
-            echo "pre-commit hook (molecule-ai-workspace-runtime:"
-            echo "molecule_runtime/scripts/pre-commit-checks.sh) — keep aligned."
-            exit 1
-          fi
-
-          echo "✓ No credential-shaped strings in this change."

CLAUDE.md

@@ -72,27 +72,6 @@ Skills persist across restarts. Use them to codify best practices, coding standa
 ## Language
 Always respond in the same language the user uses. If Chinese, respond in Chinese. If English, respond in English. Match exactly.
 
-## Workspace ownership tier — T4 (top-tier)
-
-**T4 (top-tier) workspaces grant full host control.** The Docker socket is mounted into the container; the runtime is started with `--privileged`; the workspace owner can `docker exec` into siblings on the same host and read/write anything the host kernel will let it touch.
-
-What this means in practice:
-
-- The container's home directory `~/.claude/` (and its `sessions/`, `session-env/`, `settings.json`) is persisted across restarts via a host bind mount. Anything you (or the SDK) write there survives container churn — but ownership can drift.
-- If you see `EPERM` / "permission denied" on `~/.claude/` writes after a restart — particularly on `settings.json` or anything under `sessions/` — the volume picked up `root:root` ownership from a prior boot or a newer claude-code release wrote subdirs the entrypoint didn't pre-create.
-- Recovery (do this yourself; you have the rights): `sudo chown -R agent:agent ~/.claude/`. The entrypoint already runs a recursive chown unconditionally on every boot, so a restart also clears it — but `sudo chown` is faster and doesn't drop the active session.
-- The provisioned `~/.claude/settings.json` is informational: it documents that `permission_mode='bypassPermissions'` is the canonical operating mode, which is also set programmatically in `claude_sdk_executor.py` (the file is NOT the source of truth — the SDK kwargs are).
-
-If `cat ~/.claude/settings.json` returns `No such file or directory` you're on a workspace image older than 2026-05-15 — restart picks up the new entrypoint and stubs the file in place.
-
-## Knowing your own model
-
-Use the `get_runtime_identity` MCP tool to know what model you actually are. It reads the live process env (`MODEL`, `MODEL_PROVIDER`, `MOLECULE_MODEL`, `ANTHROPIC_BASE_URL`, `TIER`, `WORKSPACE_ID`, `ADAPTER_MODULE`) and returns the resolved values — no HTTP call, always works, always permitted by RBAC. Do NOT guess from your system prompt or from `requirements.txt`; the operator may have routed you to a different model via persona env between boots.
-
-## Editing your own agent_card
-
-Use the `update_agent_card` MCP tool to update this workspace's `agent_card` on the platform. Pass a JSON object — the platform validates required fields server-side. The change is broadcast as an `agent_card_updated` event so the canvas reflects the new card live. The tool is gated on `memory.write` capability, so read-only agents won't accidentally rewrite the card; T4 owners always have this capability.
-
 ## Runtime wedge integration
 
 The `runtime_wedge` module (in `molecule_runtime`) is the universal cross-cutting holder for "this Python process can no longer serve queries — only a workspace restart will recover." It surfaces unrecoverable wedges to two consumers:

Dockerfile

@@ -5,23 +5,8 @@ FROM python:3.11-slim
 # --add-assignee`, `git clone`, etc. per their idle/cron prompts).
 # Without these the team's claim-and-ship loop silently returns
 # "(no response generated)" because tools error out.
-#
-# T4 escalation leg (RFC internal#456 §9 / PR#474):
-#   sudo + util-linux(nsenter) + docker.io(CLI) are baked here so the
-#   uid-1000 `agent` (see useradd below — UNCHANGED, agent stays
-#   uid-1000) has a wired, audited path to host root inside the
-#   provisioner's `--privileged --pid=host -v /:/host
-#   -v /var/run/docker.sock:/var/run/docker.sock` container. Without
-#   sudo, a uid-1000 process in --privileged CANNOT nsenter/chroot
-#   /host (--privileged grants caps to root, not uid-1000) and cannot
-#   use the root:docker 0660 docker.sock — T4 would be
-#   provisioner-shape-only (the documented ABSENT-escalation-leg gap).
-#   The sudoers drop-in + docker-group add are below, after useradd,
-#   so `agent` exists. This is ADDITIVE: it does NOT change the agent
-#   uid and does NOT change /configs token ownership (still uid-1000,
-#   enforced by entrypoint.sh + the Layer-3 conformance gate).
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    curl gosu nodejs npm ca-certificates git sudo util-linux docker.io \
+    curl gosu nodejs npm ca-certificates git \
     && install -m 0755 -d /etc/apt/keyrings \
     && curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | tee /etc/apt/keyrings/githubcli-archive-keyring.gpg > /dev/null \
     && chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg \
@@ -32,31 +17,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 # Install claude-code CLI via npm
 RUN npm install -g @anthropic-ai/claude-code 2>/dev/null || true
 
-# Create agent user — UNCHANGED. The agent runs as uid-1000; the T4
-# escalation leg below is additive and does NOT promote the agent to
-# root. claude-code still refuses --dangerously-skip-permissions as
-# root, and /configs/.auth_token must stay agent-owned (Hermes
-# list_peers 401 class — RFC internal#456 §10).
+# Create agent user
 RUN useradd -u 1000 -m -s /bin/bash agent
-
-# --- T4 escalation leg (RFC internal#456 §9.3 / PR#474) ---
-# Wired path: uid-1000 agent -> host root inside the provisioner's
-# --privileged --pid=host -v /:/host -v docker.sock container.
-#   1. NOPASSWD sudoers drop-in (mode 0440, visudo-validated at build
-#      so a malformed sudoers can never ship a broken-sudo image).
-#   2. agent in the `docker` group so the bind-mounted root:docker
-#      0660 /var/run/docker.sock is usable without sudo.
-# Atomic co-sequencing (RFC §10): this ships in the SAME image
-# revision as the uid-1000 + agent-owned-token entrypoint contract;
-# the Layer-3 conformance gate asserts BOTH on the running container.
-RUN set -eux; \
-    printf 'agent ALL=(ALL) NOPASSWD:ALL\n' > /etc/sudoers.d/agent-t4; \
-    chmod 0440 /etc/sudoers.d/agent-t4; \
-    visudo -cf /etc/sudoers.d/agent-t4; \
-    groupadd -f docker; \
-    usermod -aG docker agent; \
-    id agent
-
 WORKDIR /app
 
 # RUNTIME_VERSION is forwarded from the reusable publish workflow as
@@ -119,27 +81,6 @@ COPY scripts/molecule-git-token-helper.sh /app/scripts/molecule-git-token-helper
 COPY scripts/molecule-gh-token-refresh.sh /app/scripts/molecule-gh-token-refresh.sh
 RUN chmod +x /app/scripts/molecule-git-token-helper.sh /app/scripts/molecule-gh-token-refresh.sh
 
-# Generic GIT_ASKPASS helper — image-side companion to molecule-core PR
-# #1525 (workspace-server applyAgentGitIdentity, merge_sha 73a09443a086).
-# Reads HTTPS Basic-Auth credentials from env vars (GIT_HTTP_USERNAME /
-# GIT_HTTP_PASSWORD, with GITEA_USER / GITEA_TOKEN as fallback) and emits
-# them on the git credential-prompt protocol, so container-side `git` can
-# authenticate to any private HTTPS remote without on-disk ~/.gitconfig
-# or ~/.git-credentials mutation. The platform provisioner sets
-# GIT_ASKPASS=/usr/local/bin/molecule-askpass via applyAgentGitIdentity;
-# until this binary ships in the runtime image, git invocations error
-# with "exec: /usr/local/bin/molecule-askpass: not found" (forward-only
-# pin gap — same class as Hermes list_peers and codex template breakage,
-# fixed image-side here).
-#
-# No hardcoded hostnames or vendor names — the script body is identical
-# to the one shipped in molecule-core workspace/scripts/molecule-askpass
-# and the parallel external workspace template repos, so any deployer
-# can fork this template and use it against their own git host without
-# editing.
-COPY scripts/molecule-askpass /usr/local/bin/molecule-askpass
-RUN chmod +x /usr/local/bin/molecule-askpass
-
 # Drop-priv entrypoint — claude-code refuses --dangerously-skip-permissions
 # as root, so we run molecule-runtime as the agent user (uid 1000).
 # The script handles volume-ownership fix + session-dir symlink before

adapter.py

@@ -144,20 +144,6 @@ def _normalize_provider(entry: dict):
         "model_aliases": _coerce_string_list(entry.get("model_aliases"), lowercase=True),
         "base_url": entry.get("base_url") or None,
         "auth_env": _coerce_string_list(entry.get("auth_env"), lowercase=False),
-        # Which env var the boot-time vendor-key projection writes the
-        # vendor key INTO. Defaults to ANTHROPIC_AUTH_TOKEN (Bearer-style
-        # — correct for MiniMax/GLM/DeepSeek Anthropic-compat shims).
-        # Kimi For Coding's gateway authenticates with the x-api-key
-        # header (per kimi.com's official Claude Code doc), which the
-        # Anthropic SDK / claude CLI emits from ANTHROPIC_API_KEY — so
-        # that provider's entry sets auth_token_env: ANTHROPIC_API_KEY.
-        # Env-var names are case-sensitive; preserve case.
-        "auth_token_env": (
-            entry.get("auth_token_env")
-            if isinstance(entry.get("auth_token_env"), str)
-            and entry.get("auth_token_env").strip()
-            else "ANTHROPIC_AUTH_TOKEN"
-        ),
     }
 
 
@@ -460,18 +446,12 @@ _VENDOR_KEY_NAMES = frozenset({
 
 
 def _project_vendor_auth(provider: dict) -> None:
-    """Project a per-vendor API key onto the provider's auth-token env at boot.
-
-    Third-party Anthropic-compat providers (MiniMax, Z.ai, DeepSeek)
-    reuse the Anthropic SDK's wire format with a Bearer token, which the
-    ``claude`` CLI / claude-code-sdk reads from ``ANTHROPIC_AUTH_TOKEN``.
-    Kimi For Coding's gateway instead authenticates with the
-    ``x-api-key`` header (per kimi.com's official Claude Code
-    integration doc), which the SDK emits from ``ANTHROPIC_API_KEY`` —
-    so the projection target is per-provider, declared as
-    ``auth_token_env`` in the registry (default ``ANTHROPIC_AUTH_TOKEN``
-    preserves the existing MiniMax/GLM/DeepSeek behavior unchanged).
+    """Project a per-vendor API key onto ANTHROPIC_AUTH_TOKEN at boot.
 
+    Third-party Anthropic-compat providers (MiniMax, Z.ai, Moonshot,
+    DeepSeek) all reuse the Anthropic SDK's wire format, which means the
+    ``claude`` CLI / claude-code-sdk reads the bearer token from
+    ``ANTHROPIC_AUTH_TOKEN`` no matter which vendor is being talked to.
     Pre-#244 the canvas surfaced the vendor-specific name
     (``MINIMAX_API_KEY``, etc.) to the user — so a user who saved only
     that name hit a silent 401 on first call while the boot audit said
@@ -479,24 +459,21 @@ def _project_vendor_auth(provider: dict) -> None:
     / hermes PR #38.
 
     Behavior:
-      * Let ``target`` = the provider's ``auth_token_env`` (default
-        ``ANTHROPIC_AUTH_TOKEN``).
       * If the matched provider's ``auth_env`` lists any of
         ``_VENDOR_KEY_NAMES`` and that var is set, copy its value into
-        ``target`` so the SDK finds it.
-      * **Idempotent**: if ``target`` is already set we do NOT
-        overwrite — an explicit operator value (workspace secret)
-        always wins over auto-projection.
-      * Logs the projection by NAME (e.g. ``KIMI_API_KEY ->
-        ANTHROPIC_API_KEY``); never logs the secret VALUE. Same
+        ``ANTHROPIC_AUTH_TOKEN`` so the SDK finds it.
+      * **Idempotent**: if ``ANTHROPIC_AUTH_TOKEN`` is already set we
+        do NOT overwrite — an explicit operator value (workspace
+        secret) always wins over auto-projection.
+      * Logs the projection by NAME (e.g. ``MINIMAX_API_KEY ->
+        ANTHROPIC_AUTH_TOKEN``); never logs the secret VALUE. Same
         contract as ``_audit_auth_env_presence``.
       * No-op for providers whose ``auth_env`` doesn't reference a
         vendor-specific name (oauth, anthropic-api, or a third-party
         entry that hasn't been added to the registry yet).
     """
     auth_env = provider.get("auth_env") or ()
-    target = provider.get("auth_token_env") or "ANTHROPIC_AUTH_TOKEN"
-    if os.environ.get(target):
+    if os.environ.get("ANTHROPIC_AUTH_TOKEN"):
         # Operator override wins — never clobber an explicit value.
         return
     for name in auth_env:
@@ -505,10 +482,10 @@ def _project_vendor_auth(provider: dict) -> None:
         value = os.environ.get(name)
         if not value:
             continue
-        os.environ[target] = value
+        os.environ["ANTHROPIC_AUTH_TOKEN"] = value
         logger.info(
-            "auth env projection: %s -> %s (provider=%s)",
-            name, target, provider.get("name", "<unknown>"),
+            "auth env projection: %s -> ANTHROPIC_AUTH_TOKEN (provider=%s)",
+            name, provider.get("name", "<unknown>"),
         )
         return
 

claude_sdk_executor.py

@@ -377,21 +377,37 @@ def _format_process_error(exc: BaseException) -> str:
     ``_probe_claude_cli_error`` so the operator sees the real failure
     reason (e.g. ``You've hit your limit · resets Apr 17``) instead of
     chasing ghosts in the workspace logs.
+
+    internal#226: prefer ``exc._molecule_stream_detail`` — the failure
+    reason ``_run_query`` salvaged from the CLI's stream-json
+    ``ResultMessage(is_error=True)`` (model 404, api_error_status, etc.)
+    before the SDK threw it away. That's the *exact* error for *this*
+    invocation; the ``_probe_claude_cli_error`` re-probe is a last resort
+    (it can't replay the failing ``--model``/``--system-prompt`` argv, so
+    it may even succeed and mislead — which is exactly what happened with
+    ``--model claude-code`` on 2026-05-10).
     """
     parts = [f"{type(exc).__name__}: {exc}"]
     exit_code = getattr(exc, "exit_code", None)
     if exit_code is not None:
         parts.append(f"exit_code={exit_code}")
+    stream_detail = getattr(exc, "_molecule_stream_detail", None)
+    if stream_detail:
+        trimmed = stream_detail[:_PROCESS_ERROR_STDERR_MAX_CHARS]
+        if len(stream_detail) > _PROCESS_ERROR_STDERR_MAX_CHARS:
+            trimmed += f"... [{len(stream_detail) - _PROCESS_ERROR_STDERR_MAX_CHARS} more chars truncated]"
+        parts.append(f"cli_stream_error={trimmed!r}")
     stderr = getattr(exc, "stderr", None)
     if stderr:
         trimmed = stderr[:_PROCESS_ERROR_STDERR_MAX_CHARS]
         if len(stderr) > _PROCESS_ERROR_STDERR_MAX_CHARS:
             trimmed += f"... [{len(stderr) - _PROCESS_ERROR_STDERR_MAX_CHARS} more chars truncated]"
         parts.append(f"stderr={trimmed!r}")
-    elif exit_code is None and _SWALLOWED_STDERR_MARKER in str(exc):
-        # #160: generic exception with the swallowed-stderr placeholder.
-        # Probe the CLI directly — this is the only way to surface the real
-        # error when the SDK lost it in translation.
+    elif exit_code is None and not stream_detail and _SWALLOWED_STDERR_MARKER in str(exc):
+        # #160: generic exception with the swallowed-stderr placeholder AND no
+        # stream detail to fall back on — probe the CLI directly as a last
+        # resort. (If _run_query salvaged a stream detail we already have the
+        # real error; the probe is unreliable since it can't replay the argv.)
         probed = _probe_claude_cli_error()
         if probed:
             parts.append(f"probed_cli_error={probed!r}")
@@ -586,6 +602,12 @@ class ClaudeSDKExecutor(AgentExecutor):
         assistant_chunks: list[str] = []
         result_text: str | None = None
         session_id: str | None = None
+        # Captured from a ResultMessage(is_error=True) — the CLI's stream-json
+        # carries the *actual* failure reason (model 404, rate limit, auth) in
+        # the result text + api_error_status BEFORE the SDK throws a bare
+        # "Command failed with exit code 1" that loses it. Stashed so the
+        # except arm below can re-attach it (see _format_process_error).
+        stream_error_detail: str | None = None
         self._active_stream = sdk.query(prompt=prompt, options=options)
         try:
             async for message in self._active_stream:
@@ -606,6 +628,34 @@ class ClaudeSDKExecutor(AgentExecutor):
                     if sid:
                         session_id = sid
                     result_text = getattr(message, "result", None)
+                    if getattr(message, "is_error", False):
+                        api_status = getattr(message, "api_error_status", None)
+                        stream_error_detail = (
+                            (f"api_error_status={api_status} " if api_status else "")
+                            + f"result={result_text!r}"
+                        )
+        except BaseException as exc:  # noqa: BLE001 — re-raised; we only annotate
+            # The claude-agent-sdk raises a bare Exception / ProcessError when
+            # the CLI subprocess errors mid-stream — but the actionable detail
+            # (model not found, rate limit, auth) arrived earlier as a
+            # ResultMessage(is_error) / synthetic AssistantMessage and is about
+            # to be discarded. Re-attach it so _format_process_error surfaces
+            # it instead of the useless "Check stderr output for details"
+            # placeholder. (The 2026-05-10 dev-team incident: `--model
+            # claude-code` → api_error_status=404, "There's an issue with the
+            # selected model (claude-code)" — invisible for an hour because
+            # the CLI wrote nothing to stderr and this text was thrown away.)
+            detail = stream_error_detail
+            if not detail:
+                last_assistant = "".join(assistant_chunks).strip()
+                if last_assistant:
+                    detail = last_assistant[:_PROCESS_ERROR_STDERR_MAX_CHARS]
+            if detail and getattr(exc, "_molecule_stream_detail", None) is None:
+                try:
+                    exc._molecule_stream_detail = detail  # type: ignore[attr-defined]
+                except Exception:  # pragma: no cover — exotic frozen exception
+                    pass
+            raise
         finally:
             self._active_stream = None
         text = result_text if result_text is not None else "".join(assistant_chunks)

config.yaml

@@ -31,16 +31,6 @@ tier: 2
 #   model_aliases  : exact lowercase ids (e.g. ["sonnet", "opus"])
 #   base_url       : ANTHROPIC_BASE_URL to set; null = CLI default (anthropic-native)
 #   auth_env       : env vars accepted; any one being set satisfies auth
-#   auth_token_env : (optional) the env var the boot-time vendor-key
-#                    projection writes the vendor key INTO. Defaults to
-#                    ANTHROPIC_AUTH_TOKEN (Bearer-style; correct for
-#                    MiniMax/GLM/DeepSeek Anthropic-compat shims). Kimi
-#                    For Coding's gateway authenticates with the
-#                    x-api-key header per kimi.com's official Claude Code
-#                    integration doc, which the Anthropic SDK / claude
-#                    CLI emits from ANTHROPIC_API_KEY (NOT the Bearer
-#                    ANTHROPIC_AUTH_TOKEN) — so its entry sets
-#                    auth_token_env: ANTHROPIC_API_KEY.
 providers:
   - name: anthropic-oauth
     auth_mode: oauth
@@ -83,27 +73,13 @@ providers:
     base_url: https://api.z.ai/api/anthropic
     auth_env: [GLM_API_KEY, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY]
 
-  # Kimi For Coding — Moonshot's coding-agent tier (K2.6 / "Kimi for
-  # Coding"). Per kimi.com's OFFICIAL Claude Code integration doc
-  # (kimi.com/code/docs/en/third-party-tools/other-coding-agents.html,
-  # "Claude Code" section) the contract is:
-  #   ANTHROPIC_BASE_URL=https://api.kimi.com/coding/   (trailing slash)
-  #   ANTHROPIC_API_KEY=<the Kimi key>                  (x-api-key header)
-  # The `sk-kimi-*` key (KIMI_API_KEY in SSOT) authenticates ONLY against
-  # this gateway — the legacy api.moonshot.ai/anthropic surface 401s it.
-  # The gateway routes to the served K2.6 model regardless of the Claude
-  # model name on the wire (proven end-to-end via the OpenClaw template's
-  # api.kimi.com/coding path, winnerProvider=custom-api-kimi-com).
-  # auth_token_env pins the projection to ANTHROPIC_API_KEY (x-api-key)
-  # rather than the default ANTHROPIC_AUTH_TOKEN (Bearer), which this
-  # gateway rejects.
-  - name: kimi-coding
+  # Moonshot AI — Kimi family. platform.kimi.ai/docs/guide/agent-support.
+  - name: moonshot
     auth_mode: third_party_anthropic_compat
     model_prefixes: [kimi-]
     model_aliases: []
-    base_url: https://api.kimi.com/coding/
-    auth_env: [KIMI_API_KEY, ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN]
-    auth_token_env: ANTHROPIC_API_KEY
+    base_url: https://api.moonshot.ai/anthropic
+    auth_env: [KIMI_API_KEY, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY]
 
   # DeepSeek — api-docs.deepseek.com/guides/anthropic_api. Note: their
   # endpoint silently maps unknown model ids to deepseek-v4-flash, so a
@@ -199,23 +175,15 @@ runtime_config:
       name: Z.ai GLM-4.5 (third-party, Anthropic-API-compatible)
       required_env: [GLM_API_KEY]
 
-    # --- Kimi For Coding (third-party, Anthropic-API-compatible) ---
-    # Routed via the `kimi-coding` provider entry above: the adapter
-    # auto-sets ANTHROPIC_BASE_URL=https://api.kimi.com/coding/ and
-    # projects KIMI_API_KEY → ANTHROPIC_API_KEY (x-api-key) per
-    # kimi.com's official Claude Code integration doc. The gateway
-    # serves the K2.6 model regardless of the wire model id; the id
-    # below is the gateway's own served-model name (mirrors the proven
-    # OpenClaw `kimi-for-coding` route). K2.5 / K2 stay as aliases for
-    # workspaces pinned to the older labels — they hit the same gateway.
-    - id: kimi-for-coding
-      name: Kimi K2.6 (Kimi For Coding, third-party Anthropic-API-compatible)
-      required_env: [KIMI_API_KEY]
+    # --- Moonshot AI Kimi family (third-party, Anthropic-API-compatible) ---
+    # KIMI_API_KEY → ANTHROPIC_AUTH_TOKEN projection at boot.
+    # platform.kimi.ai for docs. K2.5 is the latest agentic-coding tier;
+    # K2 stays as a cheaper option.
     - id: kimi-k2.5
-      name: Kimi K2.5 (Kimi For Coding, third-party Anthropic-API-compatible)
+      name: Moonshot Kimi K2.5 (third-party, Anthropic-API-compatible)
       required_env: [KIMI_API_KEY]
     - id: kimi-k2
-      name: Kimi K2 (Kimi For Coding, third-party Anthropic-API-compatible)
+      name: Moonshot Kimi K2 (third-party, Anthropic-API-compatible)
       required_env: [KIMI_API_KEY]
 
     # --- DeepSeek (third-party, Anthropic-API-compatible) ---

entrypoint.sh

@@ -42,15 +42,6 @@ log_boot_context
 if [ "$(id -u)" = "0" ]; then
     # Configs volume is created by Docker as root; agent needs write access
     # for plugin installs, memory writes, .auth_token rotation, etc.
-    #
-    # T4 atomic-co-sequencing contract (RFC internal#456 §10): the T4
-    # escalation leg (sudo NOPASSWD + docker group, baked in the
-    # Dockerfile) is ADDITIVE. The agent still runs uid-1000 and
-    # /configs/.auth_token MUST remain agent-owned — escalation must
-    # NOT regress the Hermes list_peers-401 token-ownership class.
-    # This chown -R is the agent-ownership half of that contract; the
-    # Layer-3 conformance gate asserts owner_uid==1000 on the running
-    # container alongside the host-root-reach assertion.
     chown -R agent:agent /configs 2>/dev/null
     # /workspace handling — only chown when the contents are root-owned
     # (typical on Docker Desktop on Windows where host uid maps to 0).
@@ -79,36 +70,9 @@ if [ "$(id -u)" = "0" ]; then
     # finds it when running as agent. The provisioner's mount point is
     # hardcoded to /root/.claude/sessions; we don't want to change the
     # platform contract just for this template.
-    #
-    # NOTE (T4 perms regression): on FIRST boot the host volume mount for
-    # /home/agent/.claude doesn't exist yet — entrypoint creates it and
-    # the chown lands inside the `if -d /root/.claude/sessions` guard.
-    # On SECOND boot with a populated /home/agent/.claude (sessions/,
-    # session-env/, settings.json — any of which the SDK or agent has
-    # written between boots) the dir may already be root-owned because
-    # the SDK's working files inherited root's uid when written under
-    # the prior root segment of an earlier entrypoint, OR because a
-    # newer claude-code release writes new subdirs we don't create here.
-    # That leaves uid-1000 agent EPERMing on every settings/session write
-    # ("permission restrictions" surfaced to the canvas as a generic
-    # Bash failure). Fix: create the well-known subdirs idempotently
-    # and run the chown unconditionally (no-op when ownership is already
-    # correct, fast on small trees). Stub ~/.claude/settings.json too so
-    # the agent's introspection (cat ~/.claude/settings.json) succeeds
-    # and shows operating mode — bypassPermissions is the canonical
-    # mode set programmatically by claude_sdk_executor.py.
-    mkdir -p /home/agent/.claude/sessions /home/agent/.claude/session-env
-    if [ ! -f /home/agent/.claude/settings.json ]; then
-        cat > /home/agent/.claude/settings.json <<'EOF'
-{
-  "permissions": {"defaultMode": "bypassPermissions"},
-  "_note": "Mode is also set programmatically by claude_sdk_executor.py (permission_mode='bypassPermissions'); this file is informational and lets `cat ~/.claude/settings.json` succeed."
-}
-EOF
-    fi
-    chown -R agent:agent /home/agent/.claude 2>/dev/null
+    mkdir -p /home/agent/.claude
     if [ -d /root/.claude/sessions ]; then
-        chown -R agent:agent /root/.claude 2>/dev/null
+        chown -R agent:agent /root/.claude /home/agent/.claude 2>/dev/null
         ln -sfn /root/.claude/sessions /home/agent/.claude/sessions
     fi
 

scripts/molecule-askpass

@@ -1,35 +0,0 @@
-#!/bin/sh
-# git-askpass helper. Reads HTTPS Basic-Auth credentials from env vars so
-# the deployer can wire git authentication for any private remote without
-# touching ~/.gitconfig or ~/.git-credentials inside the container.
-#
-# Wire-up: set GIT_ASKPASS=/usr/local/bin/molecule-askpass in the
-# container env, then export GIT_HTTP_USERNAME / GIT_HTTP_PASSWORD (or the
-# GITEA_USER / GITEA_TOKEN fallback pair). When git encounters an HTTPS
-# auth challenge on a host that has no credential.helper configured for
-# it, git invokes GIT_ASKPASS twice — once with a "Username for ..."
-# prompt and once with a "Password for ..." prompt. We pattern-match on
-# that prompt and emit the matching env var.
-#
-# No hardcoded hostnames or vendor names — the deployer decides which
-# host these credentials apply to by virtue of setting GIT_ASKPASS only
-# when the target remote is in scope. The helper itself is reusable for
-# any HTTPS git remote.
-#
-# Failure mode: if the env vars are unset, we emit an empty string and
-# let git surface "Authentication failed" — this is intentional, so a
-# misconfigured deployment fails loudly at first push instead of silently
-# falling through to an unrelated credential chain.
-
-case "$1" in
-    Username*)
-        printf '%s\n' "${GIT_HTTP_USERNAME:-${GITEA_USER:-}}"
-        ;;
-    Password*)
-        printf '%s\n' "${GIT_HTTP_PASSWORD:-${GITEA_TOKEN:-}}"
-        ;;
-    *)
-        # Unknown prompt — emit empty and let git decide.
-        printf '\n'
-        ;;
-esac

tests/test_adapter_prevalidate.py

@@ -129,13 +129,12 @@ _FIXTURE_PROVIDERS_YAML = textwrap.dedent("""
         base_url: https://api.z.ai/api/anthropic
         auth_env: [ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY]
 
-      - name: kimi-coding
+      - name: moonshot
         auth_mode: third_party_anthropic_compat
         model_prefixes: [kimi-]
         model_aliases: []
-        base_url: https://api.kimi.com/coding/
-        auth_env: [KIMI_API_KEY, ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN]
-        auth_token_env: ANTHROPIC_API_KEY
+        base_url: https://api.moonshot.ai/anthropic
+        auth_env: [ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY]
 
       - name: deepseek
         auth_mode: third_party_anthropic_compat
@@ -555,7 +554,7 @@ def test_load_providers_parses_yaml_and_normalizes(tmp_path):
     names = [p["name"] for p in result]
     assert names == [
         "anthropic-oauth", "anthropic-api", "xiaomi-mimo", "minimax",
-        "zai", "kimi-coding", "deepseek",
+        "zai", "moonshot", "deepseek",
     ]
     # YAML lists must be normalized to tuples for downstream lookup ergonomics.
     assert isinstance(result[0]["model_aliases"], tuple)
@@ -565,16 +564,15 @@ def test_load_providers_parses_yaml_and_normalizes(tmp_path):
 @pytest.mark.parametrize("model,expected_provider,expected_url", [
     ("GLM-4.6", "zai", "https://api.z.ai/api/anthropic"),
     ("glm-4.5", "zai", "https://api.z.ai/api/anthropic"),
-    ("kimi-k2.5", "kimi-coding", "https://api.kimi.com/coding/"),
-    ("kimi-for-coding", "kimi-coding", "https://api.kimi.com/coding/"),
+    ("kimi-k2.5", "moonshot", "https://api.moonshot.ai/anthropic"),
     ("deepseek-v4-pro", "deepseek", "https://api.deepseek.com/anthropic"),
 ])
 @pytest.mark.asyncio
 async def test_setup_routes_extra_providers(
     adapter, monkeypatch, configs_dir, model, expected_provider, expected_url
 ):
-    """The Z.ai / Kimi-For-Coding / DeepSeek providers must route
-    correctly: model id → provider entry → ANTHROPIC_BASE_URL.
+    """The Z.ai / Moonshot / DeepSeek providers added in this PR must
+    route correctly: model id → provider entry → ANTHROPIC_BASE_URL.
     Parametrized to keep the matrix coverage tight without 3 near-identical
     test bodies. Locks in the per-vendor base_url so a future YAML edit
     that mistypes z.ai's `/api/anthropic` suffix gets caught.

tests/test_executor_error_detail.py

@@ -0,0 +1,221 @@
+"""Pin the CLI-stream-error surfacing in _run_query + _format_process_error.
+
+When the `claude` CLI errors mid-stream, the claude-agent-sdk throws a bare
+``Exception("Command failed with exit code 1 …")`` whose only text is the
+useless ``Check stderr output for details`` placeholder — but the *actual*
+failure reason (model 404, rate limit, auth) arrived a moment earlier as a
+stream-json ``ResultMessage(is_error=True)`` carrying ``result`` text and
+``api_error_status``. ``_run_query`` salvages that onto the exception
+(``_molecule_stream_detail``); ``_format_process_error`` surfaces it.
+
+Regression context: the 2026-05-10 dev-team incident — six lead workspaces
+404ing on every turn (``--model claude-code`` → ``api_error_status=404``,
+"There's an issue with the selected model (claude-code)"), invisible for an
+hour because the CLI wrote nothing to stderr and that text was thrown away.
+See internal#226.
+
+Stub pattern mirrors test_runtime_wedge_mirror.py — same _ensure_module /
+_ensure_attr / _load_executor helpers so a real-package install on a
+workstation still wins over the stubs.
+"""
+
+import os
+import sys
+import types
+from unittest.mock import MagicMock
+
+import pytest
+
+
+# ---- Stubs (mirror test_runtime_wedge_mirror.py) ----
+
+
+def _ensure_module(dotted: str) -> types.ModuleType:
+    if dotted not in sys.modules:
+        sys.modules[dotted] = types.ModuleType(dotted)
+    return sys.modules[dotted]
+
+
+def _ensure_attr(mod: types.ModuleType, name: str, value: object) -> None:
+    if not hasattr(mod, name):
+        setattr(mod, name, value)
+
+
+def _install_executor_stubs():
+    sdk = _ensure_module("claude_agent_sdk")
+    _ensure_attr(sdk, "ClaudeAgentOptions", MagicMock(name="ClaudeAgentOptions"))
+    _ensure_attr(sdk, "AssistantMessage", type("AssistantMessage", (), {}))
+    _ensure_attr(sdk, "TextBlock", type("TextBlock", (), {}))
+    _ensure_attr(sdk, "ResultMessage", type("ResultMessage", (), {}))
+    _ensure_attr(sdk, "query", MagicMock(name="query"))
+
+    _ensure_module("a2a")
+    _ensure_module("a2a.server")
+    a2a_exec = _ensure_module("a2a.server.agent_execution")
+    _ensure_attr(a2a_exec, "AgentExecutor", type("AgentExecutor", (), {}))
+    _ensure_attr(a2a_exec, "RequestContext", type("RequestContext", (), {}))
+    a2a_events = _ensure_module("a2a.server.events")
+    _ensure_attr(a2a_events, "EventQueue", type("EventQueue", (), {}))
+    a2a_helpers = _ensure_module("a2a.helpers")
+    _ensure_attr(a2a_helpers, "new_text_message", lambda *_a, **_kw: None)
+
+    _ensure_module("molecule_runtime")
+    rw = _ensure_module("molecule_runtime.runtime_wedge")
+    _ensure_attr(rw, "mark_wedged", lambda *_a, **_kw: None)
+    _ensure_attr(rw, "clear_wedge", lambda *_a, **_kw: None)
+    helpers = _ensure_module("molecule_runtime.executor_helpers")
+    for name in (
+        "auto_push_hook", "brief_summary", "collect_outbound_files", "commit_memory",
+        "extract_attached_files", "extract_message_text", "get_a2a_instructions",
+        "get_hma_instructions", "read_delegation_results", "recall_memories",
+        "set_current_task",
+    ):
+        _ensure_attr(helpers, name, lambda *_a, **_kw: ("" if "instr" in name or "summary" in name else None))
+    _ensure_attr(helpers, "collect_outbound_files", lambda *_a, **_kw: [])
+    _ensure_attr(helpers, "extract_attached_files", lambda *_a, **_kw: [])
+    _ensure_attr(helpers, "get_mcp_server_path", lambda *_a, **_kw: "/dev/null")
+    _ensure_attr(helpers, "get_system_prompt", lambda *_a, **_kw: "")
+    _ensure_attr(helpers, "sanitize_agent_error", lambda e: str(e))
+    _ensure_attr(helpers, "CONFIG_MOUNT", "/configs")
+    _ensure_attr(helpers, "WORKSPACE_MOUNT", "/workspace")
+    _ensure_attr(helpers, "MEMORY_CONTENT_MAX_CHARS", 10000)
+
+
+def _load_executor():
+    _install_executor_stubs()
+    parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+    if parent_dir not in sys.path:
+        sys.path.insert(0, parent_dir)
+    sys.modules.pop("claude_sdk_executor", None)
+    import claude_sdk_executor  # noqa: WPS433
+    return claude_sdk_executor
+
+
+def _async_stream(messages, raise_at_end=None):
+    """Build a fake `sdk.query(...)` return value: an async iterator that
+    yields ``messages`` then (optionally) raises — exactly the shape the
+    claude-agent-sdk produces when the CLI errors after emitting a
+    ResultMessage(is_error)."""
+    class _Stream:
+        def __aiter__(self):
+            return self
+
+        def __init__(self):
+            self._it = iter(messages)
+
+        async def __anext__(self):
+            try:
+                return next(self._it)
+            except StopIteration:
+                if raise_at_end is not None:
+                    raise raise_at_end
+                raise StopAsyncIteration
+
+    return _Stream()
+
+
+# ─── _format_process_error: surface the salvaged stream detail ───────────
+
+
+def test_format_process_error_surfaces_molecule_stream_detail():
+    mod = _load_executor()
+    exc = Exception("Command failed with exit code 1 — Check stderr output for details")
+    exc._molecule_stream_detail = (
+        'api_error_status=404 result="There\'s an issue with the selected '
+        'model (claude-code). It may not exist or you may not have access."'
+    )
+    out = mod._format_process_error(exc)
+    assert "cli_stream_error=" in out
+    assert "api_error_status=404" in out
+    assert "claude-code" in out
+    # When we already salvaged the real error, don't ALSO re-probe the CLI
+    # (the probe can't replay the failing --model argv and may mislead).
+    assert "probed_cli_error" not in out
+
+
+def test_format_process_error_still_probes_when_no_stream_detail(monkeypatch):
+    """The #160 fallback (probe the CLI when only the swallowed-stderr
+    placeholder is present) still fires when _run_query had nothing to
+    salvage."""
+    mod = _load_executor()
+    monkeypatch.setattr(mod, "_probe_claude_cli_error", lambda: "You've hit your limit · resets Apr 17")
+    exc = Exception("Command failed with exit code 1 — Check stderr output for details")
+    out = mod._format_process_error(exc)
+    assert "probed_cli_error=" in out
+    assert "hit your limit" in out
+
+
+def test_format_process_error_stream_detail_takes_precedence_over_probe(monkeypatch):
+    mod = _load_executor()
+    probe = MagicMock(name="_probe_claude_cli_error", return_value="<should not be called>")
+    monkeypatch.setattr(mod, "_probe_claude_cli_error", probe)
+    exc = Exception("Command failed with exit code 1 — Check stderr output for details")
+    exc._molecule_stream_detail = "api_error_status=429 result='rate limited'"
+    out = mod._format_process_error(exc)
+    assert "cli_stream_error=" in out
+    probe.assert_not_called()
+
+
+# ─── _run_query: salvage the detail onto the raised exception ────────────
+
+
+@pytest.mark.asyncio
+async def test_run_query_annotates_exception_from_is_error_result_message():
+    mod = _load_executor()
+    sdk = sys.modules["claude_agent_sdk"]
+
+    rm = sdk.ResultMessage()
+    rm.session_id = "sess-1"
+    rm.result = "There's an issue with the selected model (claude-code)."
+    rm.is_error = True
+    rm.api_error_status = 404
+
+    boom = Exception("Command failed with exit code 1 (exit code: 1)\nCheck stderr output for details")
+    sdk.query = MagicMock(return_value=_async_stream([rm], raise_at_end=boom))
+
+    ex = mod.ClaudeSDKExecutor(system_prompt="", config_path="/tmp", heartbeat=None, model="opus")
+    with pytest.raises(Exception) as ei:
+        await ex._run_query("hi", options=MagicMock())
+    detail = getattr(ei.value, "_molecule_stream_detail", None)
+    assert detail is not None
+    assert "api_error_status=404" in detail
+    assert "claude-code" in detail
+    # And it threads through the formatter the executor's error path uses.
+    assert "cli_stream_error=" in mod._format_process_error(ei.value)
+
+
+@pytest.mark.asyncio
+async def test_run_query_falls_back_to_assistant_text_when_no_error_result():
+    mod = _load_executor()
+    sdk = sys.modules["claude_agent_sdk"]
+
+    tb = sdk.TextBlock()
+    tb.text = "helpful pre-crash context from the model"
+    am = sdk.AssistantMessage()
+    am.content = [tb]
+
+    boom = Exception("Command failed with exit code 1 — Check stderr output for details")
+    sdk.query = MagicMock(return_value=_async_stream([am], raise_at_end=boom))
+
+    ex = mod.ClaudeSDKExecutor(system_prompt="", config_path="/tmp", heartbeat=None, model="opus")
+    with pytest.raises(Exception) as ei:
+        await ex._run_query("hi", options=MagicMock())
+    assert getattr(ei.value, "_molecule_stream_detail", None) == "helpful pre-crash context from the model"
+
+
+@pytest.mark.asyncio
+async def test_run_query_clean_success_unaffected():
+    """No exception → no annotation, normal QueryResult."""
+    mod = _load_executor()
+    sdk = sys.modules["claude_agent_sdk"]
+
+    rm = sdk.ResultMessage()
+    rm.session_id = "sess-ok"
+    rm.result = "done"
+    rm.is_error = False
+    sdk.query = MagicMock(return_value=_async_stream([rm]))
+
+    ex = mod.ClaudeSDKExecutor(system_prompt="", config_path="/tmp", heartbeat=None, model="opus")
+    res = await ex._run_query("hi", options=MagicMock())
+    assert res.text == "done"
+    assert res.session_id == "sess-ok"

tests/test_provider_routing.py

@@ -219,6 +219,7 @@ def test_glm_kimi_deepseek_also_project(adapter_module, monkeypatch):
     """
     cases = [
         ("zai", "GLM_API_KEY"),
+        ("moonshot", "KIMI_API_KEY"),
         ("deepseek", "DEEPSEEK_API_KEY"),
     ]
     for provider_name, env_name in cases:
@@ -241,83 +242,3 @@ def test_glm_kimi_deepseek_also_project(adapter_module, monkeypatch):
             f"{env_name} must project onto ANTHROPIC_AUTH_TOKEN for "
             f"provider={provider_name}"
         )
-
-
-def test_kimi_coding_projects_into_anthropic_api_key(adapter_module, monkeypatch):
-    """Kimi For Coding's gateway authenticates with the x-api-key header
-    (kimi.com official Claude Code doc), which the Anthropic SDK / claude
-    CLI emits from ANTHROPIC_API_KEY — NOT the Bearer ANTHROPIC_AUTH_TOKEN
-    used by MiniMax/GLM/DeepSeek. The kimi-coding provider sets
-    auth_token_env: ANTHROPIC_API_KEY so KIMI_API_KEY projects there.
-
-    Regression guard for the original mis-route: KIMI_API_KEY landing in
-    ANTHROPIC_AUTH_TOKEN against api.kimi.com/coding 401s.
-    """
-    import os
-    _clear_all_auth_env(monkeypatch, adapter_module)
-    monkeypatch.setenv("KIMI_API_KEY", "sk-kimi-sentinel")
-    provider = {
-        "name": "kimi-coding",
-        "auth_mode": "third_party_anthropic_compat",
-        "model_prefixes": ("kimi-",),
-        "model_aliases": (),
-        "base_url": "https://api.kimi.com/coding/",
-        "auth_env": ("KIMI_API_KEY", "ANTHROPIC_API_KEY", "ANTHROPIC_AUTH_TOKEN"),
-        "auth_token_env": "ANTHROPIC_API_KEY",
-    }
-
-    adapter_module._project_vendor_auth(provider)
-
-    assert os.environ.get("ANTHROPIC_API_KEY") == "sk-kimi-sentinel", (
-        "KIMI_API_KEY must project onto ANTHROPIC_API_KEY (x-api-key) for "
-        "the kimi-coding provider per kimi.com's official Claude Code doc"
-    )
-    assert os.environ.get("ANTHROPIC_AUTH_TOKEN") is None, (
-        "KIMI_API_KEY must NOT land in ANTHROPIC_AUTH_TOKEN — the Bearer "
-        "header 401s against api.kimi.com/coding (the original mis-route)"
-    )
-
-
-def test_kimi_coding_operator_anthropic_api_key_wins(adapter_module, monkeypatch):
-    """Idempotency holds for the per-provider target too: an explicit
-    operator ANTHROPIC_API_KEY is never clobbered by the projection."""
-    import os
-    _clear_all_auth_env(monkeypatch, adapter_module)
-    monkeypatch.setenv("KIMI_API_KEY", "sk-kimi-sentinel")
-    monkeypatch.setenv("ANTHROPIC_API_KEY", "operator-value")
-    provider = {
-        "name": "kimi-coding",
-        "auth_mode": "third_party_anthropic_compat",
-        "model_prefixes": ("kimi-",),
-        "model_aliases": (),
-        "base_url": "https://api.kimi.com/coding/",
-        "auth_env": ("KIMI_API_KEY", "ANTHROPIC_API_KEY", "ANTHROPIC_AUTH_TOKEN"),
-        "auth_token_env": "ANTHROPIC_API_KEY",
-    }
-
-    adapter_module._project_vendor_auth(provider)
-
-    assert os.environ.get("ANTHROPIC_API_KEY") == "operator-value", (
-        "explicit operator ANTHROPIC_API_KEY must win over auto-projection"
-    )
-
-
-def test_normalize_provider_parses_auth_token_env(adapter_module):
-    """_normalize_provider surfaces auth_token_env; absent → the
-    ANTHROPIC_AUTH_TOKEN default (preserves MiniMax/GLM/DeepSeek)."""
-    with_override = adapter_module._normalize_provider({
-        "name": "kimi-coding",
-        "auth_mode": "third_party_anthropic_compat",
-        "base_url": "https://api.kimi.com/coding/",
-        "auth_env": ["KIMI_API_KEY", "ANTHROPIC_API_KEY"],
-        "auth_token_env": "ANTHROPIC_API_KEY",
-    })
-    assert with_override["auth_token_env"] == "ANTHROPIC_API_KEY"
-
-    default = adapter_module._normalize_provider({
-        "name": "minimax",
-        "auth_mode": "third_party_anthropic_compat",
-        "base_url": "https://api.minimax.io/anthropic",
-        "auth_env": ["MINIMAX_API_KEY"],
-    })
-    assert default["auth_token_env"] == "ANTHROPIC_AUTH_TOKEN"