@ai-dev-methodologies/rlp-desk 0.14.4 → 0.14.6

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-dev-methodologies/rlp-desk",
-  "version": "0.14.4",
+  "version": "0.14.6",
   "description": "Fresh-context iterative loops for Claude Code — autonomous task completion with independent verification",
   "scripts": {
     "postinstall": "node scripts/postinstall.js",

package/src/commands/rlp-desk.md

@@ -89,6 +89,14 @@ Ask about these items one by one (or in small groups):
    - **gpt-5.5:medium** — default recommendation (full context window, progressive upgrade handles harder US)
    - **spark:high** — only when US is small enough for spark's 100k context (single-file, AC count <= 4, simple logic). Do NOT use as primary recommendation — spark context window is too small for most tasks
 
+   **Context window behavior (claude models — v0.14.6+)**:
+   - All claude models default to **200K**. `sonnet` and `opus` aliases both run at the standard window.
+   - To request 1M, append the explicit `[1m]` suffix on the full model id:
+     - `claude-opus-4-7[1m]` — 1M attempted via `ANTHROPIC_BETA=context-1m-2025-08-07`. Works on most Claude Max accounts.
+     - `claude-sonnet-4-6[1m]` — 1M attempted, **but** requires the Anthropic "Extra usage" toggle at https://claude.ai/settings/usage. Without that toggle the worker fails at the first API call with `Extra usage is required for 1M context`.
+   - rlp-desk does NOT pre-check entitlement — the explicit `[1m]` is honored as-is. If the API rejects it, you will see the error immediately and can re-run with the standard alias or the opus 1M form.
+   - **Default recommendation when 1M is genuinely needed:** prefer `claude-opus-4-7[1m]` over `claude-sonnet-4-6[1m]` because opus 1M does not require a separate entitlement toggle.
+
    Present complexity score with evidence to the user, e.g.: "I rate this MEDIUM because: US count=4 (MEDIUM), file scope=2 (MEDIUM), logic=conditionals (MEDIUM), deps=none (LOW), impact=modify (MEDIUM). Highest=MEDIUM."
 
    **If codex IS installed** — say: "Codex is installed. I recommend cross-engine Worker for cost savings (Pro token pool separation) and cross-engine blind-spot coverage (claude Verifier catches issues codex Worker misses)."

package/src/node/cli/command-builder.mjs

@@ -1,5 +1,5 @@
 import { shellQuote } from '../util/shell-quote.mjs';
-import { OPUS_1M_BETA, isOpusModel } from '../constants.mjs';
+import { ONE_MILLION_BETA, wantsOneMillionContext } from '../constants.mjs';
 
 const CLAUDE_BIN = 'claude';
 const CODEX_BIN = 'codex';
@@ -32,12 +32,14 @@ function assertTuiMode(mode, builderName) {
 export function buildClaudeCmd(mode, model, options = {}) {
   assertTuiMode(mode, 'buildClaudeCmd');
 
-  // v5.7 §4.9: auto-enable 1M-token context for Opus models. Long campaigns
-  // no longer silently truncate at 200K. Header is benign for non-Opus calls
-  // but we omit it there to keep the cmdline tidy.
+  // v0.14.6: 1M context is opt-in only via the explicit '[1m]' suffix.
+  // opus / sonnet / claude-opus-4-7 (no suffix) all run at the standard
+  // 200K context. Adding '[1m]' on either opus or sonnet model id injects
+  // the ANTHROPIC_BETA header and attempts the 1M window — sonnet[1m] still
+  // requires Anthropic "Extra usage" entitlement at the API layer.
   const parts = ['DISABLE_OMC=1'];
-  if (isOpusModel(model)) {
-    parts.push(`ANTHROPIC_BETA=${shellQuote(OPUS_1M_BETA)}`);
+  if (wantsOneMillionContext(model)) {
+    parts.push(`ANTHROPIC_BETA=${shellQuote(ONE_MILLION_BETA)}`);
   }
   parts.push(
     CLAUDE_BIN,

package/src/node/constants.mjs

@@ -1,19 +1,21 @@
 // Shared runtime constants. Single-source for cross-module values.
 
-// Anthropic Claude API beta header that activates the 1M-token context window
-// for Opus models. Auto-prepended to every claude CLI invocation that uses
-// --model opus so long campaigns no longer silently truncate at 200K.
+// Anthropic Claude API beta header for the 1M-token context window. Injected
+// only when the user explicitly opts in via the '[1m]' suffix on the model
+// id — see wantsOneMillionContext() below.
 //
 // Docs: https://docs.anthropic.com/en/docs/build-with-claude/context-windows
 // (search "1M context") — header rotates with each beta phase.
-export const OPUS_1M_BETA = 'context-1m-2025-08-07';
+export const ONE_MILLION_BETA = 'context-1m-2025-08-07';
 
-// Model id that triggers Opus 1M auto-enable. Plain string match against the
-// --model value (post-shellQuote stripping). Bracketed form
-// 'claude-opus-4-7[1m]' is also Opus and benefits from this; pattern match
-// covers both.
-export function isOpusModel(model) {
+// v0.14.6: 1M context is opt-in only via the explicit '[1m]' suffix on the
+// model id. Previously rlp-desk auto-injected ANTHROPIC_BETA for any opus
+// model; in practice that produced surprising results (opus alias still
+// reported a 200K window in real CLI calls, and sonnet[1m] requires a
+// separate "Extra usage" entitlement). New rule: user is the source of
+// truth. Type the suffix to opt in; otherwise both opus and sonnet run at
+// the standard 200K context.
+export function wantsOneMillionContext(model) {
   if (!model) return false;
-  const m = String(model).toLowerCase();
-  return m === 'opus' || m.startsWith('claude-opus-');
+  return String(model).toLowerCase().endsWith('[1m]');
 }

package/src/node/runner/campaign-main-loop.mjs

@@ -7,7 +7,7 @@ import { promisify } from 'node:util';
 
 import { buildClaudeCmd, buildCodexCmd, parseModelFlag } from '../cli/command-builder.mjs';
 import { shellQuote } from '../util/shell-quote.mjs';
-import { OPUS_1M_BETA, isOpusModel } from '../constants.mjs';
+import { ONE_MILLION_BETA, wantsOneMillionContext } from '../constants.mjs';
 import { initCampaign } from '../init/campaign-initializer.mjs';
 import { LEGACY_DESK_REL, resolveDeskRoot } from '../util/desk-root.mjs';
 import { writeSentinelExclusive } from '../shared/fs.mjs';
@@ -933,9 +933,11 @@ async function runFinalSequentialVerify({
 const HOME_DESK_DIR = path.join(os.homedir(), '.claude', 'ralph-desk');
 
 function buildAutonomousClaudeCmd({ promptFile, model, rootDir, homeDeskDir = HOME_DESK_DIR }) {
-  // §4.9: ANTHROPIC_BETA prefix for Opus 1M context.
-  const betaPrefix = isOpusModel(model)
-    ? `ANTHROPIC_BETA=${shellQuote(OPUS_1M_BETA)} `
+  // v0.14.6: ANTHROPIC_BETA prefix injected only when the model id ends
+  // with explicit '[1m]' suffix. opus / sonnet / claude-opus-4-7 (no
+  // suffix) all run at the standard 200K context.
+  const betaPrefix = wantsOneMillionContext(model)
+    ? `ANTHROPIC_BETA=${shellQuote(ONE_MILLION_BETA)} `
     : '';
   // §4.11.a: --add-dir whitelist (home rlp-desk + campaign cwd) for true autonomy.
   const addDirParts = [];

package/src/scripts/lib_ralph_desk.zsh

@@ -46,17 +46,19 @@ build_claude_cmd() {
   # Defends against bracketed model ids like 'claude-opus-4-7[1m]' (zsh char-class glob),
   # spaces, embedded quotes, etc. Plain "$model" would let zsh expand brackets as glob.
   #
-  # v5.7 §4.9: auto-enable Opus 1M context window via ANTHROPIC_BETA env. Mirror
-  # of src/node/constants.mjs OPUS_1M_BETA. Update both on header rotation.
-  local _opus_beta=""
+  # v0.14.6: ANTHROPIC_BETA injected only when the model id ends with the
+  # explicit '[1m]' suffix. opus / sonnet / claude-opus-4-7 (no suffix) all
+  # run at the standard 200K context. Mirror of src/node/constants.mjs
+  # ONE_MILLION_BETA + wantsOneMillionContext(). Update both on rotation.
+  local _onem_beta=""
   case "$model" in
-    opus|claude-opus-*) _opus_beta="ANTHROPIC_BETA='context-1m-2025-08-07' " ;;
+    *\[1m\]) _onem_beta="ANTHROPIC_BETA='context-1m-2025-08-07' " ;;
   esac
   # v5.7 §4.11.a: --add-dir whitelist for autonomous mode. ROOT (campaign cwd)
   # plus home rlp-desk tree authorized for read/write without TUI prompts.
   local _home_desk="$HOME/.claude/ralph-desk"
   local _add_dirs="--add-dir ${(qq)_home_desk} --add-dir ${(qq)ROOT}"
-  local base="DISABLE_OMC=1 ${_opus_beta}$CLAUDE_BIN --model ${(qq)model} --mcp-config '{\"mcpServers\":{}}' --strict-mcp-config --dangerously-skip-permissions ${_add_dirs}"
+  local base="DISABLE_OMC=1 ${_onem_beta}$CLAUDE_BIN --model ${(qq)model} --mcp-config '{\"mcpServers\":{}}' --strict-mcp-config --dangerously-skip-permissions ${_add_dirs}"
   if [[ -n "$effort" ]]; then
     base="$base --effort $effort"
   fi

package/src/scripts/run_ralph_desk.zsh

@@ -1508,6 +1508,28 @@ _verifier_pane_has_verdict() {
   return 1
 }
 
+# v0.14.5 Bug Report #6 Fix-M (worker mirror of Fix-A/Fix-D):
+# Worker (claude sonnet 1m) writes commit + iter-signal.json verify signal
+# then claude CLI parks at its idle prompt. check_no_progress observes
+# byte-stasis on the worker pane and would BLOCK after 600s even though
+# the signal is on disk. When the pane is the worker pane AND a valid
+# iter-signal is on disk, defer to the harvest step (poll_for_signal in
+# run_single_worker) instead of escalating BLOCKED.
+_worker_pane_has_signal() {
+  local pane_id="$1"
+  [[ -n "${WORKER_PANE:-}" && "$pane_id" == "${WORKER_PANE}" ]] || return 1
+  [[ -n "${SIGNAL_FILE:-}" && -s "$SIGNAL_FILE" ]] || return 1
+  jq -e . "$SIGNAL_FILE" >/dev/null 2>&1 || return 1
+  local iter_field us_field status_field
+  iter_field=$(jq -r '.iteration // empty' "$SIGNAL_FILE" 2>/dev/null)
+  us_field=$(jq -r '.us_id // empty' "$SIGNAL_FILE" 2>/dev/null)
+  status_field=$(jq -r '.status // empty' "$SIGNAL_FILE" 2>/dev/null)
+  [[ "$iter_field" =~ ^[0-9]+$ ]] || return 1
+  [[ -n "$us_field" ]] || return 1
+  [[ "$status_field" == "verify" || "$status_field" == "verify_partial" ]] || return 1
+  return 0
+}
+
 # v5.7 §4.17 (codex Critic HIGH): generic no-progress timeout — independent
 # of prompt detection. Closes the gap where an undetected prompt or alive-
 # but-frozen Worker can bypass Layer 4 and infinite-wait.
@@ -1534,6 +1556,16 @@ check_no_progress() {
     PANE_LAST_CHANGE_TS[$pane_id]=$now
     return 0
   fi
+  # v0.14.5 Bug Report #6 Fix-M: claude worker finishes (commit + iter-signal
+  # write) then parks at its idle prompt. byte-stasis would BLOCK after 600s
+  # even though the signal is on disk. Worker mirror of the verifier branch
+  # above — defer to poll_for_signal harvest when SIGNAL_FILE is valid.
+  if _worker_pane_has_signal "$pane_id"; then
+    PANE_LAST_CONTENT_FOR_PROGRESS[$pane_id]="$capture"
+    PANE_LAST_CHANGE_TS[$pane_id]=$now
+    log_debug "[GOV] iter=${ITERATION:-0} worker_progress_check=signal_present pane=$pane_id signal=${SIGNAL_FILE}"
+    return 0
+  fi
   # v0.14.2: root-cause tracing for Bug Report #4. When the watcher is
   # examining a verifier pane that does NOT have a verdict yet, log once
   # per byte-stasis transition so post-mortem can tell whether the