GitNexus/eval/tests
Gergő Magyar eb116c8a07
fix(eval): exclude Claude Code's own sandbox-bootstrap noise from the planning-phase check (#2615)
The first fully successful real workflow_dispatch run on the self-hosted
runner (https://github.com/abhigyanpatwari/GitNexus/actions/runs/29843028596)
still failed: 17/18 sessions hit error_kind plan-evidence-invalid with
"phase changed unauthorized workspace path(s): .claude/.cc-writes,
.claude/commands, .env, .env.development, ...".

Reproduced directly on the runner (SSM, matching the real sandbox settings
exactly, including enableWeakerNestedSandbox): a single trivial "say OK"
prompt -- no real task, no real API key even -- is enough to make Claude
Code create a synthetic package.json/lockfiles/node_modules, a full set
of .env variants, and .claude/agents, .claude/commands, .claude/.cc-writes
in the workspace on every single session. None of this is something the
model decided to write; it's Claude Code's own internal bootstrap for
running inside an already-sandboxed environment, and it happens
regardless of task or prompt.

enforce_phase_workspace (the planning-phase boundary check: verify the
plan session touched only its one plan doc) already excludes .git for
exactly this class of reason -- harness/tool noise, not substantive diff.
Extends the same exclusion to the empirically-observed bootstrap set.
workspace_snapshot has exactly one use (this check, confirmed via every
caller), so widening its exclusion list can't hide anything in some other
context that actually cares about these paths changing.

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-21 19:19:15 +01:00
..
__init__.py docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
conftest.py docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
test_ce_plugin_runtime.py feat(skills): GitNexus Engineering Tool Kits (#2566) 2026-07-19 15:07:24 +01:00
test_errors.py docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
test_evolve.py feat(eval): run the skill-evolution loop online (#2571) 2026-07-20 05:37:07 +01:00
test_mcp_bridge.py fix: start MCP bridge correctly when using npx (#1114) 2026-04-27 18:19:02 +01:00
test_oracle_assets.py feat(skills): GitNexus Engineering Tool Kits (#2566) 2026-07-19 15:07:24 +01:00
test_parse_run_id.py docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
test_process_control.py feat(skills): GitNexus Engineering Tool Kits (#2566) 2026-07-19 15:07:24 +01:00
test_promotion_apply.py feat(skills): GitNexus Engineering Tool Kits (#2566) 2026-07-19 15:07:24 +01:00
test_property_based.py docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
test_proposer_sandbox.py fix(eval): bind resolved node to a fresh sandbox path (corrects #2607) (#2609) 2026-07-21 16:09:45 +01:00
test_runner_hardening.py fix(eval): exclude Claude Code's own sandbox-bootstrap noise from the planning-phase check (#2615) 2026-07-21 19:19:15 +01:00
test_sanitized_graph.py feat(skills): GitNexus Engineering Tool Kits (#2566) 2026-07-19 15:07:24 +01:00
test_task_assets.py fix(eval): size the buffered-fallback budget for the real graph index 2026-07-20 14:42:50 +00:00
test_tool_scripts.py docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
test_workflow_bench.py fix(eval): self-hosted skill-evolution runner + sandbox Python 3 trust fix (#2600) 2026-07-21 14:40:20 +01:00
test_workflow_bench_evolution.py feat(skills): GitNexus Engineering Tool Kits (#2566) 2026-07-19 15:07:24 +01:00
test_workflow_bench_sessions.py fix(eval): bind resolved node to a fresh sandbox path (corrects #2607) (#2609) 2026-07-21 16:09:45 +01:00