The harness has no way to put an agent into a reduced-authority working state. The canonical feature that needs one is plan mode — the agent explores and designs under a read-only tool policy, produces a reviewable plan, and crosses back into full authority only through an explicit approval. [The extension cookbook](../../../cookbook/extension-cookbook.md) already reserves the row ("Plan mode — `tools/pre-execute` (deny writes) + a mode prompt section"), and [the ACP feature matrix](../../../../packages/ui/acp/acp-feature-support.md) records session modes as a known gap both reference adapters ship. Neither says where the mode STATE lives, how it survives resume and fork, or how its model-visible consequences stay honest with the session log.
Every shipped plan mode decomposes into the same five parts — a low-authority tool policy, a plan artifact, an approval moment, an execution-state switch, and durable state ([Prior art](#prior-art) carries the survey). Four of the five already exist here as gated infrastructure: what the model is TOLD it can do is shaped per step at [`system-prompt/assemble`](../../../../packages/core/system-prompt/README.md) and whatever ships is logged as `request/header*` events ([reconstructability](../../implemented/architecture/2026-07-05-reconstructable-requests.md)); what can RUN is gated at `tools/pre-execute` with typed decisions ([interception seams](../../implemented/feature/2026-06-30-interception-seams.md)); the approval moment is a human answer over the user-interaction seam ([`ctx.userInteraction`](../../../../packages/ui/user-interaction/README.md), the [ask-user precedent](../../implemented/feature/2026-06-25-ask-user-question.md)); durable per-agent facts are `SessionEventMap` members ([the `todo/write` precedent](../../implemented/feature/2026-06-29-todo-write-tool.md)). The missing fifth is the mode itself: a named, durable, per-agent policy state the policy listeners can read.
The deliverable is **plan mode**. It ships as the first **session mode** — a named, logged, per-agent policy state: mode definitions — which tools stay visible, what guidance section renders — are deployment config, and the mode IN FORCE for an agent is session state, folded from its log. One new product package, `@deepseek-ai/dsh-mode` at `packages/mode/mode/` (a new top-level group, the `packages/approval/` shape), owns the event vocabulary, a thin `ctx.modes` service, and every policy listener; the loop does not change. `plan` is the only shipped definition — the mode-shaped vocabulary exists so a second mode never renames durable event types, not because more modes ship now.
The state is one `SessionEventMap` member: **`mode/set`**, a log-only, non-surface event carrying `{ mode: string }` with whole-value-replace semantics, plus a pure `foldMode(events)` that returns the mode in force — the last `mode/set`, or the default mode when none exists. Because [the log is the fact channel](../../implemented/architecture/2026-06-30-event-domain-semantics.md), resume, fork, and compaction restore the mode with no extra machinery, and UIs read flips off `session/event`. The default mode is the absence of policy — no section, no filtering, no gate — so an agent that never sees a `mode/set` behaves byte-identically to a deployment that never loads `dsh-mode`, which keeps every existing snapshot golden stable and makes the plugin safe to compose unconditionally.
Enforcement is two layers that cover each other. The **soft** layer is a `system-prompt/assemble` listener that filters the tool schemas down to the mode's allowlist and appends the mode's guidance section — every transition therefore surfaces as an attributable `request/header` event on the next step (a delta when expressible, the full fallback snapshot otherwise), keeping the [reconstructability](../../implemented/architecture/2026-07-05-reconstructable-requests.md) invariant green by construction. The **hard** layer is a `tools/pre-execute` listener that denies, deny-by-default against the same allowlist, any call the mode does not permit — so a hallucinated call to a still-registered tool, or a schema re-widened by a foreign assemble listener, still cannot run.
The model leaves plan mode through the **`exit_plan_mode`** tool: its single argument is the plan text, which makes the plan a durable log artifact, and the tool conducts the review itself through the user-interaction seam — a question with options and a free-text channel, not a bare permission — so an approval flips the logged mode back to the default, and a rejection becomes the corrective error carrying the user's feedback verbatim, which keeps the model planning with direction. A user flips the mode from any surface through `ctx.modes.set()`; the flip is applied at the next turn boundary (session events are turn-enclosed) and narrated to the model once, only when the model-visible state actually changed.
The user switches the session to plan mode — the ACP mode picker or the stdio `/mode plan` — and from the next turn every request ships the filtered read-only toolset plus the plan-mode guidance section.
The model explores and designs with what remains — the bash tools included when the composition confines them: plan mode's `access: read-only` cap clamps every command to a read-only sandbox, so exploration runs for real; if the model attempts a write anyway, the gate denies with a reason naming the mode and pointing at `exit_plan_mode`, and the transcript keeps planning.
When ready, the model calls `exit_plan_mode` with the plan markdown as its argument; the UI renders the plan as the call card and the review question arrives through the user-interaction channel — approve, or keep planning, with free-text feedback welcome — so what the human reviews is exactly the logged artifact.
On approve, the tool flips the logged mode back to the default: the next step runs with the full toolset and the widening header event in the log, and execution tracking from there is already `todo_write`'s job. On keep-planning, the model receives a corrective error carrying the user's feedback text, revises, and re-presents.
Mode definitions are validated plugin Config — per repo convention, changeable from `cordis.yml` with no code edit. The shipped `plan` definition works with zero config; overriding it, or adding a mode, is a config entry:
`plan`'s shipped default allowlist is the read-only surface: `read`, `todo_write`, `web_search`/`web_fetch`, `ask_user_question`, `structured_output`, `exit_plan_mode` (the last three are the pure ask/report class), plus the bash trio under the `access: read-only` cap — CONDITIONAL on a confining executor ([the access cap](#the-access-cap-clamping-the-bash-resolution)); `subagent` stays excluded until mode inheritance lands. `default` is reserved (the absence of policy) and rejected as a key; an `access` outside the `SANDBOX_MODES` ladder fails validation at load; an unknown mode name fails loudly at `set()` time.
The stdio app gains `/mode` (print the current and available modes) and `/mode <name>` (switch + banner — a command line, never sent to the model, and reserved even while a question prompt is active: a command is never recorded as an answer). The exit review prompts right in the terminal with no new machinery: it is an ordinary user-interaction question, so it rides the stdio provider's one-prompt-owns-stdin queue that `ask_user_question` already uses.
The mode PICKER is this package's surface: `session/new`/`session/load` advertise `availableModes`/`currentModeId` from `ctx.modes` (consumed opportunistically via `ctx.get`, the `tool-bash` pattern), `session/set_mode` calls `set()` and notifies `current_mode_update` optimistically (the pending mode IS the user's selection; the logged `mode/set` follows at the boundary), and a `session/event` listener re-notifies on each logged flip that differs from the last sent. The exit tool's review needs no new ACP work at all — it rides the elicitation flow the user-interaction ACP provider already drives, beside the already-streamed plan card. Individual environment knobs — sandbox mode, approval policy, the model — are NOT modes and belong to `session/set_config_option` ([FAQ](#faq)).
`ctx.modes` is the whole programmatic surface: `list()` returns the configured definitions plus the synthetic `default` entry (for pickers), `get(agent)` returns the folded mode plus any pending intent, and `set(agent, mode)` validates the name against `list()`'s vocabulary and records the boundary-applied intent — `default` is always a valid target, so exiting a mode is the same call as entering one. A creator seeds a child's initial mode through `AgentOptions.mode` (`AgentOptions` is merge-extensible; `dsh-mode` declares the optional field). There is no live `agent/*` mirror to subscribe: UIs read `mode/set` off `session/event`, per [event-domain semantics](../../implemented/architecture/2026-06-30-event-domain-semantics.md).
The payload carries no reason/provenance field: a tool-driven flip sits next to its `tool/call` in the log and a user flip sits at its turn boundary, so the cause is log-adjacent — the same "narrative fields are derivable" call the [reconstructability RFC](../../implemented/architecture/2026-07-05-reconstructable-requests.md) made for header deltas (the in-flight `env/state` event carries a `source` precisely because its drift variant has NO log-adjacent cause — a contrast, not a conflict). Mode names are config-declared vocabulary, not opaque cross-boundary ids, so they stay bare strings (no `Branded<B>`).
The allowlist is deliberately the degenerate form of a future per-tool decision map (`allow | deny | ask`): execution-phase ask policies (an every-write-asks "guarded" mode) stay deferred until the approval seam grows durable grants (`allow_always` — its own open question), and the config shape must not need a migration when they arrive.
`foldMode(events)` is pure (exported for reconstructors and tests); the service tracks it per session with a lazy cursor in a `WeakMap<Session, { cursor, mode }>` — O(new events) per read, never invalidated, because the log is append-only and `mode/set` is not a surface node (compaction cannot rewrite it). `set(agent, mode)` validates the name against `list()`'s vocabulary — the configured definitions plus the reserved `default`, which is rejected as a config KEY but always accepted as a `set()` TARGET (a picker's exit-to-default must be a valid write) — drops a no-op (target equals pending ?? current), and otherwise records the intent in a `WeakMap<Session, string>` — it cannot append immediately, because [every session event is turn-enclosed](../../implemented/architecture/2026-06-15-turn-enclosure-invariant.md) and an idle agent has no open turn.
A contained `session/event` listener ([defensive patterns](../../../defensive-patterns.md): a policy plugin must not kill the feed) flushes the pending intent as a `mode/set` append on the next `turn/start` or `step/end` — both sit outside the step's tool-execution window, so the executions of a step always run under the mode its assembly folded — and, when the flushed mode differs from the fold at the last `request/header`, appends one coalesced `context/message` notice in the same frame ("The user switched this session to plan mode."); the user-visible narration cases are enumerated in the [FAQ](#faq). Seeding rides `agent/created`: `AgentOptions.mode` becomes a pending intent, so explicit options beat the logged baseline on create AND resume — the same precedence the call-config seed follows.
A `system-prompt/assemble` waterfall listener reads the calling agent's mode (the `AssembleContext` carries `agent`) and, in a non-default mode, filters `assembly.tools` down to the mode's allowlist and appends the mode's guidance section. The loop already renders per step and logs the result: entering or leaving a mode surfaces on the next step as a `request/header-delta` — or as the full `request/header` fallback snapshot when the change is inexpressible in the delta encoding (adding `exit_plan_mode` resorts the canonical tool list, and a pure reordering has no delta form) — so every mode transition is an attributable log fact. The section is static per mode and the plan itself stays in the conversation (messages and tool args, already in context), so a mode does not add per-step prompt churn — re-injecting plan state into every request ([Prior art](#prior-art)'s compaction-survival hack) is unnecessary and would only burn prefix cache.
The guidance section is an ordinary registered section, `{ name: 'mode:policy', order: 50, text: context => … }` — order 50 sits after the persona (0) and before tool guidance (100–199); it resolves to the folded mode's configured text and to `''` (dropped at render) for the default mode or an agent-less assembly. The tool filter wraps with `prepend: true`: it awaits `next()` and filters the RETURNED assembly's `tools`, so additions made anywhere inside its wrap — including every append-registered listener's post-`next()` mutation, regardless of load order — are covered. `run_code` survives the filter in every mode: under the registry's Code Mode it is the only wire tool (filtering it would strip the model of everything, the exit included), and it is a transport, not a capability — each bridged sub-call re-enters the hard gate individually. Code Mode's soft surface is the `tools:sdk` section rather than the wire schemas, and section text resolves in assemble's base, so the same wrapper re-renders that section under the mode's visibility rule — the prompt documents exactly the callable bindings, never one the gate would deny. The default mode re-renders it too, hiding only the exit binding: that keeps a default-mode Code Mode assembly byte-identical to a deployment that never loaded `dsh-mode` (whose registry never saw the tool), instead of advertising a binding that can only error. The filter enforces one rule in every mode: `exit_plan_mode` is visible IFF the agent's folded mode is `plan` — which is also what keeps a default-mode assembly byte-identical to a no-`dsh-mode` deployment even though the tool is always registered. In a non-default mode it additionally intersects with the mode's allowlist.
The gate denies, with a mode-naming reason that steers the model back to planning, any call outside the mode's allowlist. This layer is not redundant with the filter: [`ToolRegistry.execute()`](../../../../packages/core/tools/README.md) dispatches any registered tool by name, so a model hallucinating a filtered-out (or MCP-registered) tool would still run it without the gate. Deny-by-default against the allowlist also means the two layers cover each other — a peer `assemble` listener that re-widens the schema set cannot make the widened tools executable.
The gate folds the LOGGED mode only, never the pending intent — enforcement judges by the same state the request's header shipped under. The gate never returns `{ kind: 'ask' }`: the exit review is a question with options and feedback, not a permission, so it lives inside the tool's own execution over the user-interaction seam and the registry's `ask` vocabulary stays free for genuine permission gating. A call to `exit_plan_mode` outside plan mode reaches the tool only from the default mode (any other mode's allowlist excludes it), and the tool's own folded-mode recheck rejects it there.
A definition's `access` is the widest sandbox access shell commands run under while the mode is in force — the `SANDBOX_MODES` ladder from `dsh-bash` (`read-only` | `workspace-write` | `danger-full-access`); the built-in `plan` ships `access: 'read-only'`. The cap is made real on the bash seam's own resolution point: `BashExecutor.resolveMode(session)` computes `session override ?? executor default` and dispatches it through the **`bash/resolve-mode` waterfall** (declared in `dsh-bash`; consulted by `dsh-tool-bash` at both its stamping site and its escalation baseline), and `dsh-mode` registers the clamp listener — `min(await next(), access)` on the ladder, per call.
The composition is read-time over two independent log folds. The session's sandbox knob (`bash/sandbox-mode` events, the sandbox RFC) is never written by the mode: a knob flipped during plan stays logged but capped, exiting plan uncovers it unchanged, the two switch in any order without interference, and there is no restore step for a crash to strand. Attribution stays log-adjacent on both axes — a clamped call's width is explained by the standing `mode/set`, a knob change by its own `bash/sandbox-mode` event.
Two rules ride with a declared cap. The bash trio (`bash`/`bash_output`/`bash_kill`) is CONDITIONAL: both policy layers admit it only while a confining executor is mounted (`ctx.get('bash')?.sandboxMode` set) — an unconfinable shell cannot honor the cap, so under `dsh-bash-local` the trio is hidden by the filter and denied by the gate exactly like a non-allowlisted tool. And sandbox ESCALATION is denied at the gate: a `bash` call carrying `sandbox_permissions` in a capped mode gets a deny that points the model at putting the widened step in the plan — without this rule the clamped resolution would read as a legitimate escalation baseline and one approval prompt could pierce the cap mid-mode. A mode that allowlists `bash` WITHOUT `access` is the deployment's explicit uncapped choice; neither rule applies.
`defineTool` with one required `plan: string` argument — the plan is thereby a durable, replayable log artifact riding the ordinary `tool/call` event. `execute` rejects an agent-less call (the [`todo_write` precedent](../../implemented/feature/2026-06-29-todo-write-tool.md)), re-checks the folded mode as defense in depth, then conducts the review: one single-select `ctx.userInteraction.ask()` question — approve, or keep planning — with the free-text channel open for feedback. Approve records the switch back to `default` as a SILENT boundary-applied pending intent (flushed at this step's end, still in-turn) and returns a short confirmation; the gate therefore stays plan-mode for every remaining call of the SAME assistant response — a same-batch `exit_plan_mode` + `write` pair cannot smuggle the write past a request assembled under the plan header — and the next step's assembly restores the full toolset and logs the widening header event. Every other outcome — keep-planning (the user's feedback text carried verbatim), an aborted question, a missing provider — returns the corrective `isError` that tells the model to revise and re-present, and the mode stays `plan`.
Its [render intent](../../implemented/architecture/2026-07-02-tool-render-intent-union.md), decided up front: `presentCall` is a `generic` card titled by the plan's first heading with the plan markdown as content, plus a `generic` result card — the review question arrives beside this already-streamed card, so what the human reviews is exactly the logged artifact. The seam is consumed opportunistically (`ctx.get('userInteraction')`), so `dsh-mode` composes without it and degrades to the manual exit pinned in the [FAQ](#faq).
`dsh-mode` is one product package, not a capability-seam trio ([Alternatives considered](#alternatives-considered)): it peers on `cordis`, `dsh-session`, `dsh-agent`, `dsh-tools`, `dsh-system-prompt`, and `dsh-bash` (the `SANDBOX_MODES` vocabulary and the `bash/resolve-mode` clamp listener; the executor itself is read opportunistically via `ctx.get('bash')`, so the composition works without one), injects `['tools', 'systemPrompt']`, reads `ctx.userInteraction` opportunistically at execute time (a type-only peer edge on `dsh-user-interaction`), and depends on no UI package. Beyond the `ctx.modes` call surface everything participates through listeners, so dropping the package gracefully removes modes rather than breaking a consumer. The stdio app adds a `/mode [name]` line-handler branch — the exit review needs nothing there, because the stdio user-interaction provider already owns the prompt queue. The ACP wire mapping is pinned in [High-level API](#over-acp); package-wise the bridge takes a type-only peer edge on `dsh-mode` and reads the service opportunistically, so a bridge without the plugin behaves exactly as today.
`input.json` gains one step op, `{ "op": "setMode", "modeId": "plan" }`, driven through the real `session/set_mode` RPC, and a scripted `elicitationAnswers` queue (FIFO, consumed by the harness client's elicitation callback — the review question's answer). The `plan-mode` scenario: initialize → newSession → setMode(plan) → a prompt the model answers by running a real `cat` through the bash tool INSIDE plan (executed under the clamped read-only sandbox on replay — Seatbelt on macOS, bwrap on Linux CI) and presenting the plan via `exit_plan_mode` → a scripted approve → the same turn's next step writes for real under the restored toolset. Because the mode is set before turn 1, the FIRST `request/header` snapshot is already in plan shape (filtered tools + section, reason `initial`) — the widening header event appears at the exit; the scenario pins both, plus the `mode/set` pair. A sibling `plan-mode-reject` scenario scripts the keep-planning answer with feedback text and pins the corrective result. Both need a with-key recording session; the deny/reject texts — and the sandbox-denial marker, whose recorded stderr would be the backend's dialect and replay only where it was recorded — are pinned at the unit tier.
No new cordis event is declared IN `dsh-mode` (`mode/set` rides `session/event`; the policy listeners attach to existing waterfalls) — the one new event, the `bash/resolve-mode` waterfall the access cap clamps, lives in `dsh-bash` where the resolution it wraps lives. Regenerated in the same change: the events catalog (`bash/resolve-mode`), the persistence log catalog (`mode/set`), the services catalog (`ctx.modes`, JSDoc-complete), the config catalog (`ModeConfig`), the tool catalog (`exit_plan_mode`), the producer/consumer map and doc graphs, and the module graph. Repo plumbing: a root tsconfig `paths` entry, the new group's README plus a [packages map](../../../../packages/README.md) row (a new top-level group is the deliberate act that table names), an `architecture.md` capability-services row for `ctx.modes` (budget-checked), and the cookbook row upgrade.
Each behind its own decision: subagent mode inheritance via a forwarded `AgentOptions.mode` (the option field itself ships), per-tool `ask` policies inside mode definitions (an OpenCode-style "bash asks in plan mode"), preset modes beyond `plan` (read-only, accept-edits), effects self-declaration on tool definitions (so the conditional-tool rule generalizes past the hardcoded bash trio — the MCP `ToolAnnotations` vocabulary is the natural template), and the idle-record primitive if pending-intent loss proves real.
The recorded snapshot scenarios are landed: `plan-mode` (the pinned-header arc — plan-shaped initial header, scripted elicitation approve, the boundary-flushed flip and widened fallback header, a real edit) and `plan-mode-reject` (keep-planning feedback carried verbatim in the corrective `isError`), beside the keyless `modes-advertise` wire golden. The gate's deny path stays pinned at the unit tier — the recorded model never calls a filtered tool, which is the behavior the soft layer exists to produce.
Behavioral clarifications of the chosen design; rejected designs live in [Alternatives considered](#alternatives-considered), accepted costs in [Consequences](#consequences).
**When does a user's mode flip take effect?** At the next turn boundary: `set()` records a pending intent, the service flushes it as the first append after the next `turn/start`, and the loop assembles the prompt after the turn opens and before each step — so step 1 already folds it. A mid-turn flip lands at the next boundary and takes effect on the following step. This is the "applies to subsequent requests" semantics every product in [Prior art](#prior-art) ships.
**When is a mode change narrated to the model?** Only when the model-visible state actually changed: the flush compares the flushed mode against the fold at the last `request/header` and narrates once, coalesced. A net-zero flip sequence (plan then back, all before the boundary) narrates nothing; a tool-driven exit narrates through its own tool result instead; a mode set before the first turn narrates nothing — the section is the state statement. The principle is the in-flight env-state proposal's boundary narration: a silently flipped prompt surface leaves the transcript arguing from a state the header no longer has.
**What happens on resume when the config no longer defines the folded mode?** One read-path rule closes the gap: a folded mode name the current config no longer defines behaves as the default mode plus one boundary notice naming the dropped definition — never a silent substitute restriction, never a bricked session. `set()`'s loud validation covers only the write path; a resumed log answers to the config it finds.
**What if a deployment composes no user-interaction provider?** Plan mode stays safe but manual: `ctx.userInteraction.ask()` throws `NO_PROVIDER` (and an absent seam never resolves at all), the tool returns the corrective `isError`, and the exit degrades to the user toggling modes — never to an unreviewed exit. The mode section tells the model to present its plan through `exit_plan_mode` — and to ask the user in prose if that fails — so it never thrashes against the gate.
**Do subagents inherit the parent's mode?** A fork child inherits for free — the parent's `mode/set` is inside the seeded prefix. A spawn child starts in the default mode unless its creator seeds `AgentOptions.mode`; automatic forwarding by subagent providers is deferred ([Deferred](#deferred)).
**How does plan mode's read-only relate to the sandbox knob's read-only?** They are two independent folds over the same log with different owners: the knob (`bash/sandbox-mode`, [the sandbox RFC](2026-07-06-sandbox.md)) is the session's standing choice, the mode's `access` is a cap that rides the mode — and the cap is a clamp, never a write. `resolveMode` folds `override ?? default` and the clamp takes the ladder minimum at read time, per call, so the two switch in any order without interference: a knob flipped during plan stays logged but capped, exiting plan uncovers it unchanged, and there is no restore step for a crash to strand. The log attributes each axis to its own event — a clamped call's width to the standing `mode/set`, a knob change to its `bash/sandbox-mode` event.
**Why aren't sandbox mode, approval policy, or the model themselves modes?** They are individual environment knobs and belong to ACP's `session/set_config_option`; the division this proposal pins is picker-to-modes / knobs-to-config-options. The in-flight sandbox branch already ships both knobs as config-option selects and its feature-matrix stance records session modes as deliberately unmodeled — the one overlap between the two stacks; landing the picker supersedes that stance, and whichever side lands second amends the matrix rows. A mode definition may later bundle env facts (applied through `ctx.envState` where mounted) so a Codex-style preset stays a single mode; fusing approval policy into the mode CONCEPT itself is rejected in [Alternatives considered](#alternatives-considered).
A survey of shipped plan modes (Claude Code, Cursor, Copilot, OpenCode, Gemini CLI, Cline, Windsurf, Codex) shows the same five parts everywhere — the low-authority tool policy, plan artifact, approval moment, execution-state switch, and durable state that [Problem](#problem) builds on.
The mode surface is a LIST everywhere it is advertised, never a boolean: Claude Code's picker offers `plan` beside `acceptEdits` (plus an auto-mode entry into plan), and Codex — whose plan feature itself is `/plan` — fills its list with its approval presets (read-only / agent / full-access). This is the surface [the ACP feature matrix](../../../../packages/ui/acp/acp-feature-support.md) records as the gap, and what sizes the vocabulary as named modes rather than a flag.
The ecosystems that leave modes to convention show the failure shapes to avoid. Pi-style mode extensions fight over a last-wins global active-tool list, enforce "read-only" by prompt text alone (a hallucinated call to a still-registered tool executes), and re-inject plan state into every request to survive compaction. Each hole closes structurally here, but only because the mode is logged session state rather than plugin-private memory: per-agent folded state replaces the contested global list, the hard gate closes the prompt-only hole, and a log-only non-surface event that compaction cannot shadow makes the re-injection hack unnecessary.
**Permission modes as the concept (the Claude Code shape).** One `permissionMode` fusing approval policy and tool policy. Here those are two axes with two owners: the approval seam owns "who answers this question", modes own "what surface does the model get". ACP models them as related but distinct (a mode may select an approval policy later — a mode definition gains a field, not a merger).
**A capability-seam trio.** Interface/implementation/consumer fits a swappable backend; a mode's variable parts are config values, not implementations. Splitting would manufacture an empty implementation package — the same "don't split preemptively" call the approval seam and [`todo/`](../../implemented/feature/2026-06-29-todo-write-tool.md) made.
**Loop-owned mode state.** Rejected on the standing rule (plugins, not loop changes): every hook the feature needs — assemble, pre-execute, turn boundaries, session events — is already a documented seam, so a loop edit would buy nothing but coupling.
**Prompt-only plan mode (no hard gate).** The Pi failure shape ([Prior art](#prior-art)): filtering schemas (or asking nicely) does not stop a dispatch of a still-registered tool. The pre-execute gate is the enforcement layer; the filter is UX and cache hygiene.
**Runtime-only mode (UI- or bridge-local, unlogged).** Resume and fork would silently drop the mode, and the header deltas a mode causes would have no attributable cause in the log. Logged state is what makes the mode auditable and restorable for free.
**Mode flips as `context/message` via `agent.inject()`.** Reuses an existing turn-enclosure path, but puts policy state into the model transcript — the model does not need to be told twice (the section already tells it), and a log-only fact should not occupy surface.
**A plan-file store (`.plans/` directory).** A second durable home for what the log already carries replayably; a deployment wanting files can add a tool that writes them. One home per fact.
**A boolean `planMode` instead of named modes.** Too narrow for the surface the repo already tracks: ACP advertises a mode LIST and the shipped pickers fill it with more than plan ([Prior art](#prior-art)); generalizing later would rename durable event vocabulary. The string-shaped mechanism costs nothing extra now; only `plan` ships as a definition.
**A tool-policy-stack service (the Pi-critique remedy).** A dedicated composition service for tool policies is premature: waterfall listeners compose by construction, and the deny-by-default hard gate makes filter-order races non-exploitable. Formalize only if real conflicts appear.
**Exit approval through the approval seam (a `{ kind: 'ask' }` gate decision).** The original sketch, natural while the approval seam was the only asking machinery in flight — but it seats a review in a permission chair: the seam's outcome vocabulary is deliberately closed and one-shot (`allowed-once`/`rejected`), so a rejection carries no feedback and an approval can never grow options (approve-and-accept-edits). The exit moment is a question, not a permission — the user-interaction seam gives it options plus the free-text channel, and the rejection feedback reaches the model verbatim. The approval seam remains the right seat for genuine permission gates (the sandbox escalation), and the registry's `ask` vocabulary stays available to deployments that want one there.
**Exit by prose or steering instead of a tool.** No artifact and no approval moment — the tool's argument IS the reviewable plan, and its review question is what gives the human a structured yes/no attached to the exact transition.
- The mode in force is a pure function of the session log: resume and fork restore it with no extra machinery, and a `mode/set` is followed by the matching `request/header` event (delta or fallback snapshot) on the next step with the dev invariant green throughout.
- A user-driven flip narrates exactly once at the next boundary and a net-zero flip sequence narrates nothing; a tool-driven exit narrates only through its tool result.
- In the default mode the plugin is invisible: assemblies are byte-identical with and without `dsh-mode` loaded, and every pre-existing snapshot golden is unchanged.
- In plan mode the filtered schemas and mode section reach both the wire request and the logged header; a call to a registered-but-filtered mutating tool is denied at `tools/pre-execute` with the mode-naming reason.
- Under a confining executor the bash trio stays available in plan mode with every call's sandbox resolution clamped to `read-only` (the `bash/resolve-mode` waterfall); the session's sandbox knob is never written by the mode and re-emerges intact on exit; a `sandbox_permissions` escalation inside a capped mode is denied at the gate. Without a confining executor the trio is hidden and denied.
- Mode definitions (allowlist, section text, `access` cap) are changeable from `cordis.yml` with no code edit; an unknown mode name fails validation loudly at `set()` time.
-`exit_plan_mode`'s approve path flips the mode and restores the full toolset on the next step; the keep-planning path returns the corrective `isError` carrying the user's feedback and stays in plan mode; the ACP `session/set_mode` round-trip updates `current_mode_update`, and the exit review prompts through each surface's user-interaction provider.
- The docs tail shipped with the landing: READMEs, regenerated catalogs (persistence log, config, cordis services, tools), the packages map and architecture rows, and the cookbook row.
The accepted costs: a pending user flip set while idle is lost if the process dies before the next turn (the UI re-applies; the idle-record primitive is the escape hatch if this bites in practice). Every mode transition is a logged header change and therefore a prefix-cache reset at the provider — inherent, visible in per-step usage, and an argument against mode-flapping UIs, not against the design. The mode filter prepends, so only a listener that ALSO prepends after `dsh-mode` loads can wrap outside it and re-widen filtered schemas — the one shipped instance is the structured runtime's per-spawn final-assembly wrapper, whose `structured_output` is on the plan allowlist precisely so the filter, that wrapper, and the gate agree; for any future such listener the hard gate keeps a re-widened tool non-executable, and the residual cost is cosmetic (the model sees a tool it cannot use), accepted rather than mechanized. Plan mode's bash power is exactly as real as the composition: under `dsh-bash-local` (or no executor) the trio is withheld in plan — hidden and denied, because an unhonorable cap must not be offered — and `subagent` stays excluded until mode inheritance lands; a deployment that accepts the risk can still define an uncapped mode that allowlists bash. The conditional-trio rule names the three bash tools rather than deriving them from tool metadata — the generalization is the effects self-declaration item in [Deferred](#deferred). The ACP mode surface carries both this stack's picker and the sandbox stack's config options under the picker-to-modes / knobs-to-config-options division pinned in the [FAQ](#faq), recorded in [the feature matrix](../../../../packages/ui/acp/acp-feature-support.md). The ACP spec's draft v2 direction reportedly slates session modes for removal in favor of config options; if that lands, the picker migrates to a config-option select mechanically — the mode state and both enforcement layers are wire-agnostic — accepted.
