Why: The sandbox hides the host home directory and has no network, so pip install --user cannot supply python-docx, and the service PATH resolved python3 to a linuxbrew path that does not exist inside the sandbox.
Evidence: SELF go test of execenv, tools, store, app, server, runmgr, config, and cmd/agent-system on this worktree. CI has not run.
Impact: Sessions inherit a read-only base layer. Extra packages are requested through python_env, auto-approved only from the allowlist, and mounted per conversation. Schema 35 adds the request and binding tables.
Refs: .task/feature-layered-python-env.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Real runs were fully serial: the direct path never set the kernel's
parallel tool mode, delegate_task handed the parent only the child's
160-char summary (the full text was dropped), MiniMax streamed its
reasoning inside content <think> blocks, and the EXT-16 sandbox hid
~/.local so python-docx/openpyxl/pptx could not even import. All four
were measured defects (F1/F2/F3/F5) in the delegation/routing proposal.
Why: Serial-only mutual exclusion is not enough for order-sensitive
tools - the card-stream test failed with out-of-order appends - so the
ordering moved into the kernel (SerialTools partition, Agent-Native
#44); process events pair by CallID (#42) and tool results write back
through the injected call context (#43).
Evidence: go test ./... green, including new regression anchors:
TestDelegateToolReturnsFullText, TestToolEventsPairByCallID,
TestToolExecModeAndSerialSet, TestOpenLLMClientReasoningSplitAuto,
TestSandboxArgvDepsLayer, TestExecEnvJoinsPythonPath.
Impact: Direct runs now execute independent same-turn calls
(searches, reads, delegate_task, review_findings) concurrently by
default (runtime.parallelTools=false restores sequential); card flow,
plans, workflows, exec primitives and file edits keep model-declared
order. delegate_task returns the capped full child text. MiniMax-*
models get reasoning_split=true so thinking streams via
reasoning_content. --exec-deps-dir/AGENT_SYSTEM_EXEC_DEPS_DIR mounts a
read-only dependency layer into the sandbox and merges PYTHONPATH.
Bumps deps/agent-native to c348441.
Refs: proposal 2026-10-10-agent-delegation-routing-sandbox.md (E1,
F1-F5); Agent-Native #42/#43/#44; Dev task feature/agent-e1-parallel-fixes.
Why: User rulings 4/5 plus the P2-P4 live evidence. Keyword scoring dimensions
(readability, actionability) kept failing valid documents - normal Chinese
section headings flagged as column titles, loops of 4 corrections - because
they grade writing preferences, not verifiable facts. Unverified numbers
(~10-13 per run) remained the largest quality leak through every phase.
And the verifier runs on the same model as the worker (lightweight falls back
to chat), so "independent" verification was self-review. Separately, svc
seeding after boot never registered the tavily tools until a restart because
keys were snapshotted at startup.
Changes: quality.HardFacts (lint actually ran + zero errors) replaces the
full ScoreBytes projection in CheckArtifacts - keyword dimensions remain in
ScoreBytes for eval visibility only. New fact-consistency check
(runtime.factCheck, default on): extract percentages/dates/large numbers from
deliverable text, trace each against the material corpus (attachment text +
tool evidence); misses get exactly one correction round (fix, drop, or mark
as target/estimate), never a loop. runVerifier skips same-source model
verification unless runtime.verifierSameModel is set (hard facts + fact check
still run). Search tools now register lazily, reading tavily keys per call
(settings/seeding take effect immediately).
Evidence: SELF - TestHardFactsIgnoresKeywordDimensions,
TestHardFactsKeepsLintUnavailableBlocking, TestUnverifiedFactsAndNotice,
TestFactCheckContinuationOnce (fact note fires, corrected run passes);
go vet + go test ./... pass; live before/after on the golden task set
recorded on the phase05 task card per the policy clause.
Impact: Gate stops rejecting valid documents on stylistic grounds; invented
figures get one forced correction round; same-model verification no longer
pretends to be independent; tavily config is hot. No contract or storage
changes.
Why: Q2 ruled exec tools stay disabled for now but code execution must
return later; the recovery path treats model-generated code as
untrusted. This abstracts the interpreter launch point in
exec_interpreter.go into an ExecBackend port (direct = byte-identical
status quo; sandbox = bwrap isolation) so downstream products can
re-enable execution behind isolation without further base surgery.
Evidence: go build/vet clean; go test ./... 32/32 packages green;
sandbox escape negatives all blocked locally (bwrap 0.11.1): home
secret unreadable (tmpfs /home), sibling session unreadable
(session-only bind), network blocked (--unshare-net), 400-process
spawn storm capped by ulimit -u 256 (fork: retry), 60s sleep killed at
3s timeout, orphans die with the namespace; session-dir write visible
on host; direct backend regression (exit=7 / exit=timeout texts)
unchanged.
Impact: run_shell/run_python route through the backend; workflow
ScriptCommand and the squad kernel ExecConfig stay direct (follow-up
scope); config key execBackend + env AGENT_SYSTEM_EXEC_BACKEND + CLI
--exec-backend; extension.Options.ExecBackend (SurfaceVersion
2.6.0-experimental); DisableExecTools remains the top-priority
fail-closed switch.
Refs: proposal 2026-10-09-ext-g1-b1-b3-exec-backend.md section 4
(EXT-16, G2-8 prototype); Backend #110 (DisableExecTools).
agent-exec-transport
weichenandCursor