feat(migration): phase 2.1-2.3 — sandbox dispatch + thin slice tool wrappers
Phase 2.1 — sandbox dispatch helper:
- strix/tools/_sandbox_dispatch.py: post_to_sandbox() centralizes the
host->container HTTP wire format. Connect=10s, read=150s timeouts mirror
legacy executor.py. 50 MB response cap (C18) prevents OOM from a runaway
tool. All errors surface as {"error": str} so the model can recover
instead of the run dying.
Phase 2.2 — C6 lock-protected JSONL writes:
- strix/tools/notes/notes_actions.py: notes.jsonl appends are now wrapped
in _notes_lock so concurrent agents can't interleave half-written lines.
Regression test in test_notes_jsonl_concurrency.py verifies 1000 parallel
writes produce exactly 1000 valid JSON lines.
Phase 2.3 — thin-slice SDK wrappers (think + todo + notes):
- strix/tools/_legacy_adapter.py: LegacyAgentStateAdapter shim — exposes
just enough surface (.agent_id) for legacy tools that close over
agent_state, sourced from ctx.context['agent_id'].
- strix/tools/thinking/thinking_sdk_tools.py: 1 tool (think).
- strix/tools/todo/todo_sdk_tools.py: 6 tools (create/list/update/done/
pending/delete) with bulk-form preserved.
- strix/tools/notes/notes_sdk_tools.py: 5 tools (create/list/get/update/
delete) with asyncio.to_thread around the lock-protected file I/O.
Tests: 22 new tests pass (10 sandbox dispatch + 2 concurrency + 10 SDK
local). Full suite still green.
Per-file ruff ignores added for SDK wrapper files: TC002 (RunContextWrapper
must be runtime-importable because the SDK calls get_type_hints() to
derive the JSON schema) and PLR0911 (sandbox dispatch's 10 short-circuit
returns are intentional, each a distinct documented failure mode).
Refs: PLAYBOOK.md §3.4, AUDIT_R3.md C6/C18.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -283,6 +283,16 @@ ignore = [
|
||||
"strix/tools/_decorator.py" = [
|
||||
"TC002", # FunctionTool imported for annotation
|
||||
]
|
||||
# SDK function-tool wrappers: the SDK calls get_type_hints() at registration
|
||||
# time to derive the JSON schema, which evaluates annotations at runtime —
|
||||
# so RunContextWrapper must be imported eagerly, not under TYPE_CHECKING.
|
||||
"strix/tools/todo/todo_sdk_tools.py" = ["TC002"]
|
||||
"strix/tools/notes/notes_sdk_tools.py" = ["TC002"]
|
||||
"strix/tools/thinking/thinking_sdk_tools.py" = ["TC002"]
|
||||
# Sandbox dispatch helper has many short-circuit error returns (auth fail,
|
||||
# size cap, decode fail, etc). Each is a distinct, documented failure mode
|
||||
# the model needs to see verbatim — collapsing them harms readability.
|
||||
"strix/tools/_sandbox_dispatch.py" = ["PLR0911"]
|
||||
# StrixSession + StrixTracingProcessor catch broad Exception intentionally:
|
||||
# the whole point is that compressor / sanitizer / disk failures must not
|
||||
# tear down the agent run (C10, C16). Calls already log at exception level.
|
||||
|
||||
Reference in New Issue
Block a user