Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 hongming-pc2
|
062096b20d |
@@ -1,232 +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]
|
||||
|
||||
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"
|
||||
|
||||
# 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]
|
||||
if: always()
|
||||
timeout-minutes: 1
|
||||
steps:
|
||||
- name: Aggregate
|
||||
run: |
|
||||
static="${{ needs.validate-static.result }}"
|
||||
runtime="${{ needs.validate-runtime.result }}"
|
||||
echo "validate-static: $static"
|
||||
echo "validate-runtime: $runtime"
|
||||
if [ "$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: $runtime"
|
||||
exit 1
|
||||
fi
|
||||
echo "::notice::Template validation aggregate passed (static=$static, runtime=$runtime)"
|
||||
|
||||
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
|
||||
+54
-4
@@ -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)
|
||||
|
||||
@@ -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"
|
||||
Reference in New Issue
Block a user