docs(trekresearch): deep-research engine is operator-only from CC 2.1.218; document the real window

Claude Code 2.1.218 changed /deep-research to start only when invoked
manually; from there the Skill tool refuses a model invocation outright
with `disable-model-invocation` (measured in a real `--engine deep-research`
run 2026-09-01 18:32Z - the SC3 fallback to swarm held). The engine was
built against 2.1.196 and the prose still promised a path Claude Code has
removed ("requires Claude Code 2.1.154+").

The flag is KEPT as an additive opt-in that never hard-fails. Prose only:
no lib/ change, no adapter-contract change, no default change, no version
bump.

- commands/trekresearch.md: flag bullet states the closed window
  `2.1.154 <= CC < 2.1.218`; the pre-gate gained an UPPER ceiling (still a
  numeric comparison, not a string one) that skips straight to the fallback
  with reason `disable-model-invocation`; step 3 names the Skill-tool
  refusal as a known failure manifestation; step 4 lists the reason tokens.
- docs/command-modes.md + README.md: same window, one sentence each, on the
  reference row itself.
- CHANGELOG.md: Unreleased/Docs entry.

Tests first (Iron Law): tests/lib/doc-consistency.test.mjs gained a pin
requiring 2.1.218 + disable-model-invocation on all three surfaces, on both
reference rows, and in both load-bearing regions of the command (flag
bullet + pre-gate). Seen red on all three surfaces before the prose change.
tests/commands/trekresearch-engine.test.mjs unchanged and green.

New baseline: 1024 tests, 1022 pass / 0 fail / 2 skip (was 1023: 1021/0/2).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

commands/trekresearch.md

@@ -87,9 +87,14 @@ Supported flags:
    behavior). `swarm` runs Voyage's own external-research agent swarm;
    `deep-research` delegates the external phase to Claude Code's built-in
    `/deep-research` dynamic workflow and adapts its report into the research-brief
-   schema (requires Claude Code 2.1.154+ and dynamic workflows enabled; falls back
-   to `swarm` and notes the fallback if unavailable — never hard-fails). Orthogonal
-   to `--profile`/`phase_signals`; only affects the external phase. Set
+   schema. **The delegation only works inside a closed version window:
+   `2.1.154 <= CC < 2.1.218`** (dynamic workflows enabled). From Claude Code
+   **2.1.218** `/deep-research` starts only when the operator invokes it, and the
+   Skill tool refuses a model invocation outright (`disable-model-invocation`), so
+   on 2.1.218 or newer the engine **always** falls back to `swarm`. The flag is
+   kept as an additive opt-in and **never hard-fails**: outside the window it
+   degrades to `swarm` and logs the reason. Orthogonal to
+   `--profile`/`phase_signals`; only affects the external phase. Set
    **engine = {swarm|deep-research}** (the *requested* engine).
 
 Flags can be combined:
@@ -328,9 +333,13 @@ changes nothing (SC1). Keep the native-swarm anchors intact ("in parallel",
 
 1. **Coarse pre-gate (best-effort, NOT a trust signal).** `Bash: claude --version`;
    parse the leading `X.Y.Z` (e.g. from `2.1.196 (Claude Code)`) and compare
-   numerically against `2.1.154` — split each on `.` and compare major, then minor,
+   numerically against **both ends** of the supported window
+   `2.1.154 <= version < 2.1.218` — split each on `.` and compare major, then minor,
    then patch as integers (do NOT string-compare; lexical comparison mis-orders
-   multi-digit patch numbers). If the version is `< 2.1.154`, OR if
+   multi-digit patch numbers). If the version is `< 2.1.154` (below the
+   dynamic-workflows floor), OR `>= 2.1.218` (the ceiling: `/deep-research` starts
+   only when the operator invokes it, and the Skill tool refuses a model invocation
+   with `disable-model-invocation` — see step 4's reason token), OR if
    `disableWorkflows: true` / `CLAUDE_CODE_DISABLE_WORKFLOWS=1` is set, skip to the
    fallback (step 4). **If `claude` is not on PATH inside the Bash tool (possible
    under `claude -p`) or the version cannot be parsed, treat the pre-gate as
@@ -347,14 +356,18 @@ changes nothing (SC1). Keep the native-swarm anchors intact ("in parallel",
    `/deep-research` report actually landed in context — substantive findings with
    citations, not an empty/denied/errored turn and not bare error text. This check
    must be **robust to all failure manifestations** (workflow disabled, approval
-   denied, runtime error, empty output), because the disabled-headless behavior is
-   undocumented: no recognizable cited report in context → fall back, regardless of
-   how the failure surfaces.
+   denied, runtime error, empty output, or the Skill tool refusing with
+   `disable-model-invocation` on CC 2.1.218+), because the disabled-headless
+   behavior is undocumented: no recognizable cited report in context → fall back,
+   regardless of how the failure surfaces.
 
 4. **On no real report (fallback):** set `effective_engine = swarm`, run the swarm
    blocks below, and **log the fallback at this decision point** — print
    `Engine: deep-research → swarm (fallback: <reason>)` and carry the reason into the
-   Phase-8 Present summary and the brief's `## Executive Summary`. **NEVER fabricate
+   Phase-8 Present summary and the brief's `## Executive Summary`. Known reason
+   tokens: `disable-model-invocation` (CC >= 2.1.218 — the expected reason on any
+   current Claude Code), `version-below-floor`, `workflows-disabled`,
+   `no-cited-report`. **NEVER fabricate
    or synthesize a substitute report** — a structurally-valid-but-invented brief
    passes the structure-only validator and silently poisons `/trekplan`; that is the
    worst outcome of this feature.