Delete the re-read thrash hard stop (CL-6936)

reReadLimit 4 hard-stopped a worker for reading one path four times past
8 total tool calls, reported as thrash — a sticky hard block that refuses
identical re-dispatch. Read pressure only decayed when a product mutation
tool edited that exact path, so reading file A while editing file B, four
whole-file reads spread across a long task, and re-running a grep to
verify an edit all tripped it on healthy work.

The fingerprint period detector in stop-policy.ts already catches a
genuinely repeating read cycle, and catches it on the evidence that it
repeats rather than on a raw count. Re-read counting is strictly weaker
and its verdict is more severe, so this deletes it rather than retuning
the number.

- thrash.ts keeps only near-budget force-report plus the read/edit
  bookkeeping that requireEdit / requireEvidence consume; the edit-decay
  of read counts goes too, since an edit erasing read evidence could only
  ever weaken the requireEvidence check.
- "thrash" and "re-read-nudge" leave SubAgentStopReason/ForcedStopReason
  and the SubAgentDirector wiring; the Summary-substring classifier in
  brief-dispatch.ts is left for CL-6939.

Net -487 lines.

Author: TheGreatAxios

CHANGELOG.md

@@ -11,6 +11,19 @@ matching `## [X.Y.Z]` section (plus install instructions). Do not maintain
 parallel copies under `docs/` or `scripts/notes/`. At cut time: rename
 `## [Unreleased]` to `## [X.Y.Z] - YYYY-MM-DD`, then run the release script.
 
+## [Unreleased]
+
+### Agent
+
+- **Re-read pressure no longer stops a worker.** The `reReadLimit` thrash hard
+  stop and its soft `re-read-nudge` are removed: reading one file four times
+  while editing another, paging a large file, or re-running a grep to verify an
+  edit could all end a healthy worker with a sticky hard block that refused
+  re-dispatch. Fingerprint period detection already catches a genuinely
+  repeating read cycle, on the evidence that it repeats. `src/subagent/thrash.ts`
+  now only tracks read/edit evidence for the `intent=implement` and critique
+  completeness checks, plus the near-budget wrap-up nudge.
+
 ## [0.2.105] - 2026-08-23
 
 ### Agent

docs/ARCHITECTURE.md

@@ -106,8 +106,8 @@ In TUI chat mode there is no completion gate — the session stays open across t
 Two directors, selected by role:
 
 - **ChatDirector** (interactive, `src/agent/director.ts`) — Extends `DefaultDirector` with task list tracking, workflow nudges, LSP auto-activation, and multi-turn chat semantics. It never terminates the session: operator declines are surfaced as replies and the reactor stays alive for the next message. Auto mode is toggled by CLI flags (`--auto` / `--no-auto`); there is currently no in-session key to toggle it (default on; constrained envelope — workspace writes and unconstrained shell auto-allow; installs, recursive rm, force/uncontained worktree changes, sensitive-path and opaque-wrapper shell still ask; contained non-force `git worktree add`/`remove`/`prune` and `list` auto-allow; shell file-mutation denied). It is not a separate edit/plan mode.
-- **SubAgentDirector** (delegated work, `src/subagent/index.ts`) — Drives a dispatched worker until a turn arrives with no tool calls, then replies with the final assistant text and ends the run. A tool-less turn **after tools** completes only with the four-heading envelope (Summary, Findings, Blockers, Paths); a missing envelope nudges once then salvages as **incomplete-report**. A tool-less completion with **zero tool calls in the entire run** is returned as a **never-acted** salvage report (not a successful implement). When `task(intent="implement")` is set, a tool-using run that never wrote/edited/deleted a file is returned as **never-edited** instead of complete — so a pure-explore "plan" cannot look shipped to the parent (tracked via `thrashState.editedPaths` from `edit_file` / `write_file` / `delete_file`). Explore/read-only workers that used tools then replied with findings remain normal completes. Hard stops also fire after 5 consecutive identical tool-call fingerprints (**no-progress**, mirroring the director-level `IDENTICAL_REPEAT_MIN` threshold), on progressive re-read pressure (**thrash** — the same path re-read past a limit amid enough tool volume, tracked by `src/subagent/thrash.ts`), or after the leaf turn budget (**turn-budget**, default 30, overridable via `task(maxTurns)`, agent profile `maxTurns`, or `settings.subagentMaxTurns`; floor ≥1, no hard upper cap), each returning a structured salvage report (reason, partial findings, blockers) so a thrashing child cannot burn tokens indefinitely. Before hard thrash, a one-shot **re-read-nudge** fires when re-read pressure crosses a soft threshold (default 3 same-path reads with enough tool volume, still below the hard re-read limit of 4): the director injects an ephemeral redirect — implement leaves are asked to edit or wrap up; explore leaves are asked to expand findings / change approach / report, never forced into edit — then keeps running so hard thrash remains reachable if the leaf ignores it. A fourth hard stop, **repetition**, is detected outside the director entirely:
-  `runSubAgent`'s stream sink watches the streamed text of the in-flight cycle for degenerate token loops (`src/subagent/repetition.ts`) — format chars (ZWSP, BOM, bidi marks, soft hyphen, …) stripped then whitespace-collapsed raw text, a smallest-period KMP check over the probe tail, default window >= 16 chars repeated >= 8 times, evaluated every 256 streamed chars — and on a hit aborts the run controller mid-cycle, returning a `repetition` salvage report that leads with the looped window and warns the parent against re-dispatching the identical brief. `inference.thinking.delta` is sampled the same way on its own buffer, but with digit runs folded to one placeholder and a shorter window (>= 4 chars repeated >= 32 times), gated to periods <= 16 chars once folded: thinking is never rendered to the user, so a monotonic counter (e.g. `0/1 1/2 2/3 …`, which stays non-periodic and escapes the raw-text check) can be caught, but folding still erases real information — a healthy templated enumeration line becomes byte-identical to its neighbors once digits are erased, so the period-length cap only lets counter-shaped folded periods (a handful of chars) through and refuses the much longer periods a folded prose line produces. Because directors only see completed turns, this is the only stop that can catch a loop inside a single turn that never finishes. A one-shot **report-forced** signal fires a few turns before the cap while the leaf is still tooling — it is not a stop: the director injects a wrap-up nudge and lets the leaf finish on its own, so turn-budget stays reachable for a leaf still making progress. When both report-forced and re-read-nudge apply, report-forced wins (near-budget wrap-up is more urgent than a mid-run redirect). Operator/parent cancel after any progress likewise returns a **cancelled** salvage report (partial findings + tool activity) instead of a bare cancel string; cancel before progress still surfaces as cancelled-by-operator.
+- **SubAgentDirector** (delegated work, `src/subagent/index.ts`) — Drives a dispatched worker until a turn arrives with no tool calls, then replies with the final assistant text and ends the run. A tool-less turn **after tools** completes only with the four-heading envelope (Summary, Findings, Blockers, Paths); a missing envelope nudges once then salvages as **incomplete-report**. A tool-less completion with **zero tool calls in the entire run** is returned as a **never-acted** salvage report (not a successful implement). When `task(intent="implement")` is set, a tool-using run that never wrote/edited/deleted a file is returned as **never-edited** instead of complete — so a pure-explore "plan" cannot look shipped to the parent (tracked via `thrashState.editedPaths` from `edit_file` / `write_file` / `delete_file`). Explore/read-only workers that used tools then replied with findings remain normal completes. Hard stops also fire after 5 consecutive identical tool-call fingerprints (**no-progress**, mirroring the director-level `IDENTICAL_REPEAT_MIN` threshold) or after the leaf turn budget (**turn-budget**, default 30, overridable via `task(maxTurns)`, agent profile `maxTurns`, or `settings.subagentMaxTurns`; floor ≥1, no hard upper cap), each returning a structured salvage report (reason, partial findings, blockers) so a looping child cannot burn tokens indefinitely. Re-read counts are **not** a stop signal: `src/subagent/thrash.ts` keeps read/edit bookkeeping only to serve the `requireEdit` / `requireEvidence` checks above, because the fingerprint period detector already catches a genuinely repeating read cycle on the evidence that it repeats, while a raw count cannot separate four reads across real progress from four reads in a loop (CL-6936). A third hard stop, **repetition**, is detected outside the director entirely:
+  `runSubAgent`'s stream sink watches the streamed text of the in-flight cycle for degenerate token loops (`src/subagent/repetition.ts`) — format chars (ZWSP, BOM, bidi marks, soft hyphen, …) stripped then whitespace-collapsed raw text, a smallest-period KMP check over the probe tail, default window >= 16 chars repeated >= 8 times, evaluated every 256 streamed chars — and on a hit aborts the run controller mid-cycle, returning a `repetition` salvage report that leads with the looped window and warns the parent against re-dispatching the identical brief. `inference.thinking.delta` is sampled the same way on its own buffer, but with digit runs folded to one placeholder and a shorter window (>= 4 chars repeated >= 32 times), gated to periods <= 16 chars once folded: thinking is never rendered to the user, so a monotonic counter (e.g. `0/1 1/2 2/3 …`, which stays non-periodic and escapes the raw-text check) can be caught, but folding still erases real information — a healthy templated enumeration line becomes byte-identical to its neighbors once digits are erased, so the period-length cap only lets counter-shaped folded periods (a handful of chars) through and refuses the much longer periods a folded prose line produces. Because directors only see completed turns, this is the only stop that can catch a loop inside a single turn that never finishes. A one-shot **report-forced** signal fires a few turns before the cap while the leaf is still tooling — it is not a stop: the director injects a wrap-up nudge and lets the leaf finish on its own, so turn-budget stays reachable for a leaf still making progress. Operator/parent cancel after any progress likewise returns a **cancelled** salvage report (partial findings + tool activity) instead of a bare cancel string; cancel before progress still surfaces as cancelled-by-operator.
   Optional `task(tier=)` (`fast` | `standard` | `clever`) overrides profile inference, profile tier, and the parent provider for that spawn only, and fails closed when the tier is unconfigured. The parent `task` tool keeps a session-scoped brief-dispatch ledger (`src/subagent/brief-dispatch.ts`): fingerprints cover prompt + agent + intent + success_criteria + do_not (not maxTurns/description/tier). After thrash / no-progress / repetition / never-acted / never-edited salvage, an identical re-dispatch is hard-blocked for the rest of the parent chat; change at least one fingerprint field to force a re-run. Turn-budget salvage still invites a higher maxTurns for a few same-brief retries without a successful complete, then flips the parent hint to stop and change approach (soft — further identical dispatches are still admitted). A successful complete resets the same-brief retry budget.
 
 #### Model-family policy (`src/agent/model-family-policy.ts`)
@@ -152,7 +152,7 @@ Because the operator explicitly wants long autonomous runs to keep going, reachi
 
 `SubAgentDirector` tracks `lastActivityAt`, updated on every real `inference.done` and `tool.done`. Directors are pure `decide(event, ...)` functions with no timer of their own and the reactor has no proactive "idle" event, so a genuinely silent leaf (e.g. parked on a long-running background command with nothing else to do) produces no event for the director to react to. `runSubAgent` (`src/subagent/index.ts`) arms an external interval, at `subAgentStallTimeoutMs`, that pings the same content-less continuation channel the compaction governor uses to re-enter an idle reactor (`requestContinuation`). The director only acts on a ping if the elapsed time since `lastActivityAt` has crossed the timeout — a ping delivered while a tool call is still executing simply queues until that cycle finishes, so "no pending harness-tracked work" falls out of when the check can run at all rather than needing separate bookkeeping. The first stall past the timeout gets one continuation nudge (asking the leaf to check on the background work or report status); a second **consecutive** stall (no activity since that nudge) escalates to the existing salvage path, returning a `stalled` `forcedStopReport` with the same structured shape (summary/findings/blockers) as `no-progress` / `turn-budget` / `thrash` / `never-acted` / `never-edited`. Any real activity between pings resets the streak, so a leaf that is genuinely working through a slow single turn is never penalized.
 
-**Precedence**: stall detection sits **below** no-progress, thrash, and turn-budget — those are evaluated from real `inference.done` turns inside `evaluateSubAgentStop` and always take priority; the stall check only ever fires on a continuation ping that inference/tool-result handling did not already consume that cycle. Report-forced (near-budget wrap-up) and re-read-nudge (mid-run soft re-read redirect) are independent one-shot signals that can both fire across a run — one is turn-count driven, the other re-read-pressure driven — but neither is a competing stop reason in the sense no-progress/thrash/turn-budget are. Stall nudging is wall-clock driven and likewise independent of both.
+**Precedence**: stall detection sits **below** no-progress and turn-budget — those are evaluated from real `inference.done` turns inside `evaluateSubAgentStop` and always take priority; the stall check only ever fires on a continuation ping that inference/tool-result handling did not already consume that cycle. Report-forced (near-budget wrap-up) is an independent one-shot, turn-count-driven signal, not a competing stop reason in the sense no-progress/turn-budget are. Stall nudging is wall-clock driven and likewise independent of both.
 
 The reactor only persists a response turn to `turns.jsonl` on `inference.done`, so a cycle that is cancelled, aborted, errors, or is otherwise interrupted mid-stream would leave nothing behind. A cycle-text recorder (`src/session/stream-journal.ts`) closes that gap by buffering the in-flight cycle's streamed text in memory — no writes on the happy path — and appending one JSON record (`{reason, chars, text}`) to `partial.jsonl`, alongside `turns.jsonl` in the session context dir, on abnormal cycle end. It is wired into the sub-agent run loop, the exec runner (flushed on failed sends), and the TUI runner (flushed on interrupt and on session rotation, before the context dir is repointed).
 

docs/PRODUCT.md

@@ -159,7 +159,7 @@ Corbits Code fans work out to short-lived **sub-agents** — child agents with t
 - **Tasks** are checklist items owned by one agent via `manage_tasks`.
 - **Sub-agents** are spawned with the `task` tool (wire name kept; meaning is "spawn a child agent," not "add a checklist item").
 
-Dispatch uses a structured brief (context / goal / optional goals seed) and returns a structured report. The TUI Agents strip and fleet board show who is running; live tool progress updates the status bar without dumping the child transcript into the parent chat. Workers hard-stop after 2 consecutive identical tool calls, when their inference-turn budget is exhausted (default 30; parent can pass `maxTurns` per dispatch; profiles and global settings can raise the default; no hard upper cap), when they finish without ever using tools (never-acted salvage — planning/prose only is not a successful implement), or when `intent=implement` finishes after tools but without any file write/edit/delete (never-edited salvage — a pure-explore plan is not a successful implement). Progressive re-read thrash also hard-stops a worker that keeps re-reading the same path (or the same grep) past a limit. Look _volume_ is not a stop — an implement may read hundreds of files before the first edit. Before a hard stop, a soft mid-run nudge asks implement workers to edit or wrap up (explore workers: expand findings / change approach — never forced to edit). Each hard stop returns a salvage report so a runaway or idle child cannot quietly burn a large token budget or look done after prose alone.
+Dispatch uses a structured brief (context / goal / optional goals seed) and returns a structured report. The TUI Agents strip and fleet board show who is running; live tool progress updates the status bar without dumping the child transcript into the parent chat. Workers hard-stop after 2 consecutive identical tool calls, when their inference-turn budget is exhausted (default 30; parent can pass `maxTurns` per dispatch; profiles and global settings can raise the default; no hard upper cap), when they finish without ever using tools (never-acted salvage — planning/prose only is not a successful implement), or when `intent=implement` finishes after tools but without any file write/edit/delete (never-edited salvage — a pure-explore plan is not a successful implement). Re-read counts never hard-stop a worker, and look _volume_ is not a stop either — an implement may read hundreds of files before the first edit, and a repeating read cycle is caught by fingerprint detection instead. Near the turn budget a one-shot nudge asks the worker to wrap up and write its report. Each hard stop returns a salvage report so a runaway or idle child cannot quietly burn a large token budget or look done after prose alone.
 The parent tracks same-brief fingerprints for the session (`src/subagent/brief-dispatch.ts`): after thrash / no-progress / repetition / never-acted / never-edited salvage, an identical re-dispatch is refused — change prompt, agent, intent, success_criteria, and/or do_not to unlock a new run (`maxTurns` or tier alone does not). Turn-budget salvage still allows a few same-brief retries with a higher `maxTurns`, then flips the parent hint to stop and change approach; a successful complete resets the same-brief retry budget.
 
 ## Roadmap (planned, not yet shipped)