You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
DeepSeek Harness (dsh, 0.1.0-rc.5) harvest for CodeWhale v0.9.8 — read-only research of /Volumes/VIXinSSD/CW/dsh, filed as the action list for the v0.9.8 cycle.
Core finding on Auto-Review (answers the "too much machinery" feedback)
dsh has NO LLM reviewer, guardian agent, or auto-review tier at all. Its model: OS-enforced sandbox (read-only / workspace-write / danger-full-access, deployment default read-only), deny-by-default, denial surfaced as an actionable result fact ("[sandbox: file access denied under ] ... [sandbox: escalation available — retry this exact command once with sandbox_permissions + justification; the approval prompt asks the user]"), escalation = model-requested + one-shot user approval (allowed-once | rejected | cancelled | unavailable; no answerer → fail closed; approval policy is just ask/never; no remembered rules). Zero LLM gate machinery.
CodeWhale's #5353 guardian adds real autonomy dsh doesn't offer, but the scaffolding around the single LLM consult is measurable overhead (4 new concepts + a config flag + third audit event on top of a 3-enum cascade). Verdict: keep the ONE fail-closed LLM consult; cut the scaffolding.
Simplify #5353 — the 8 exact cuts (~170–200 lines, 2 state vars)
Merge safety_floor into deterministic_fallback with a floor: bool for the honest message — engine.rs:5350-5362
Delete AutoReviewRule.action (redundant with Vec membership) — auto_review.rs:255-261
Merge auto_review_plan_decision into _in_workspace; move write-bounding into evaluate() via a workspace field on the context (kills a double context rebuild)
ReviewerLedger: drop the 50-window; consecutive-only (3 → abort) or a cap-10 window
Collapse the ConsultReviewer handler into one Result<(), ToolError> helper; unify the 3 audit emitters into one gate-tagged event
Drop the reviewer_enabled config flag — derive from ApprovalMode::Auto alone
No secondary advisory LLM paths in the gate
Invariant preserved: deterministic blocks stay non-bypassable; no LLM override of a floor block; failure = deny.
Adopt / adapt list (with effort)
ADOPT (S) — dsh denial/escalation language in Auto mode: on sandbox deny, tell the model exactly how to retry (narrowest sufficient mode + justification), stamp approved escalations (CodeWhale has RetryWithPolicy plumbing already)
ADOPT (S) — model-visible "approval prompts disabled — do not request escalation" notice (dsh ApprovalPolicy::never parity)
DeepSeek Harness (dsh, 0.1.0-rc.5) harvest for CodeWhale v0.9.8 — read-only research of /Volumes/VIXinSSD/CW/dsh, filed as the action list for the v0.9.8 cycle.
Core finding on Auto-Review (answers the "too much machinery" feedback)
dsh has NO LLM reviewer, guardian agent, or auto-review tier at all. Its model: OS-enforced sandbox (read-only / workspace-write / danger-full-access, deployment default read-only), deny-by-default, denial surfaced as an actionable result fact ("[sandbox: file access denied under ] ... [sandbox: escalation available — retry this exact command once with sandbox_permissions + justification; the approval prompt asks the user]"), escalation = model-requested + one-shot user approval (
allowed-once | rejected | cancelled | unavailable; no answerer → fail closed; approval policy is just ask/never; no remembered rules). Zero LLM gate machinery.CodeWhale's #5353 guardian adds real autonomy dsh doesn't offer, but the scaffolding around the single LLM consult is measurable overhead (4 new concepts + a config flag + third audit event on top of a 3-enum cascade). Verdict: keep the ONE fail-closed LLM consult; cut the scaffolding.
Simplify #5353 — the 8 exact cuts (~170–200 lines, 2 state vars)
floor: boolfor the honest message — engine.rs:5350-5362Invariant preserved: deterministic blocks stay non-bypassable; no LLM override of a floor block; failure = deny.
Adopt / adapt list (with effort)
Not present in dsh (searched)
No TUI (CLI launcher + web UI), no prompt versioning, no reviewer/guardian machinery.