claude-turing 4.7.0 → 4.8.1

package/skills/turing/watch/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: watch
 description: Live training monitor with early-warning alerts for loss spikes, NaN, overfitting, and metric plateaus.
-disable-model-invocation: true
 argument-hint: "[--alerts] [--interval 10] [--analyze run.log]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ Stream metrics during training with early-warning alerts. Catches problems mid-r
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -24,13 +23,13 @@ Stream metrics during training with early-warning alerts. Catches problems mid-r
 
 3. **For post-hoc analysis:**
    ```bash
-   python scripts/training_monitor.py --analyze run.log
+   uv run python scripts/training_monitor.py --analyze run.log
    ```
 
 4. **For live monitoring (inform user):**
    Live monitoring requires a running training process. Suggest the user run in a separate terminal:
    ```bash
-   python scripts/training_monitor.py --log run.log --interval 10
+   uv run python scripts/training_monitor.py --log run.log --interval 10
    ```
 
 5. **Alert types:**

package/skills/turing/whatif/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: whatif
 description: What-if analysis — answer hypotheticals from existing experiment data without running new experiments.
-disable-model-invocation: true
 argument-hint: "\"<question>\" [--json]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -9,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Answer "what if?" questions using existing experiment data. Routes to the right estimator automatically.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/whatif_engine.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/whatif_engine.py $ARGUMENTS`
 3. **Saved:** `experiments/whatif/`
 
 ## Supported question types

package/skills/turing/xray/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: xray
 description: Internal model diagnostics — gradient flow, dead neurons, activation stats, weight distributions, tree depth analysis.
-disable-model-invocation: true
 argument-hint: "[exp-id] [--layer encoder.layer.2] [--compare exp-a exp-b]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---
@@ -10,9 +9,9 @@ See inside the model. When it underperforms, the fix depends on *why*.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -23,7 +22,7 @@ See inside the model. When it underperforms, the fix depends on *why*.
 
 3. **Run model diagnostics:**
    ```bash
-   python scripts/model_xray.py $ARGUMENTS
+   uv run python scripts/model_xray.py $ARGUMENTS
    ```
 
 4. **Diagnostics by model type:**

package/src/command-registry.js

@@ -140,11 +140,13 @@ export async function getCommandNames(registryPath) {
   return registry.commandNames;
 }
 
+// Installed public layout under .claude/commands/turing.
 export async function getExpectedCommandPaths(registryPath) {
   const names = await getCommandNames(registryPath);
   return ['SKILL.md', ...names.map((name) => `${name}/SKILL.md`)];
 }
 
+// Editable repository source layout.
 export async function getExpectedSkillSourcePaths(registryPath) {
   const names = await getCommandNames(registryPath);
   return [
@@ -154,6 +156,16 @@ export async function getExpectedSkillSourcePaths(registryPath) {
   ];
 }
 
+// Generated repository compatibility layout.
+export async function getExpectedLegacyCommandCompatPaths(registryPath) {
+  const names = await getCommandNames(registryPath);
+  return [
+    'commands/turing.md',
+    ...names.map((name) => `commands/${name}.md`),
+    'commands/rules/loop-protocol.md',
+  ];
+}
+
 export async function getConfigFiles(registryPath) {
   const registry = await loadCommandRegistry(registryPath);
   return registry.configFiles;

package/src/install.js

@@ -18,6 +18,7 @@ import { getCommandNames, getConfigFiles } from "./command-registry.js";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const PLUGIN_ROOT = join(__dirname, "..");
+const SKILL_SOURCE_ROOT = join(PLUGIN_ROOT, "skills", "turing");
 
 
 export async function install(opts = {}) {
@@ -37,7 +38,7 @@ export async function install(opts = {}) {
 
   // Copy root command (router) as SKILL.md
   await copyFile(
-    join(PLUGIN_ROOT, "commands", "turing.md"),
+    join(SKILL_SOURCE_ROOT, "SKILL.md"),
     join(paths.commands, "SKILL.md"),
   );
   console.log("  Router -> SKILL.md");
@@ -45,7 +46,7 @@ export async function install(opts = {}) {
   // Copy sub-commands as <name>/SKILL.md
   for (const cmd of subCommands) {
     await copyFile(
-      join(PLUGIN_ROOT, "commands", `${cmd}.md`),
+      join(SKILL_SOURCE_ROOT, cmd, "SKILL.md"),
       join(paths.commands, cmd, "SKILL.md"),
     );
   }
@@ -53,7 +54,7 @@ export async function install(opts = {}) {
 
   // Copy rules
   await copyFile(
-    join(PLUGIN_ROOT, "commands", "rules", "loop-protocol.md"),
+    join(SKILL_SOURCE_ROOT, "rules", "loop-protocol.md"),
     join(paths.commands, "rules", "loop-protocol.md"),
   );
   console.log("  Rules installed");

package/src/sync-commands-layout.js

@@ -0,0 +1,149 @@
+#!/usr/bin/env node
+/**
+ * Synchronize the legacy commands/ compatibility tree from skills/turing/.
+ *
+ * Usage:
+ *   node src/sync-commands-layout.js [--check]
+ */
+
+import { mkdir, readdir, readFile, rm, writeFile } from "fs/promises";
+import { dirname, join, relative } from "path";
+import { fileURLToPath } from "url";
+import { getCommandNames } from "./command-registry.js";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const PLUGIN_ROOT = join(__dirname, "..");
+const SKILLS_DIR = join(PLUGIN_ROOT, "skills", "turing");
+const COMMANDS_DIR = join(PLUGIN_ROOT, "commands");
+
+async function readUtf8(path) {
+  return readFile(path, "utf8");
+}
+
+async function copyTextFile(source, target) {
+  await mkdir(dirname(target), { recursive: true });
+  await writeFile(target, await readUtf8(source));
+}
+
+async function compatibilityEntries() {
+  const names = await getCommandNames();
+  return [
+    {
+      source: join(SKILLS_DIR, "SKILL.md"),
+      target: join(COMMANDS_DIR, "turing.md"),
+    },
+    ...names.map((name) => ({
+      source: join(SKILLS_DIR, name, "SKILL.md"),
+      target: join(COMMANDS_DIR, `${name}.md`),
+    })),
+    {
+      source: join(SKILLS_DIR, "rules", "loop-protocol.md"),
+      target: join(COMMANDS_DIR, "rules", "loop-protocol.md"),
+    },
+  ];
+}
+
+async function existingCompatibilityEntries(dir = COMMANDS_DIR) {
+  let entries;
+  try {
+    entries = await readdir(dir, { withFileTypes: true });
+  } catch (error) {
+    if (error.code === "ENOENT") {
+      return [];
+    }
+    throw error;
+  }
+
+  const paths = [];
+  for (const entry of entries) {
+    const path = join(dir, entry.name);
+    paths.push(path);
+    if (entry.isDirectory()) {
+      paths.push(...await existingCompatibilityEntries(path));
+    }
+  }
+  return paths;
+}
+
+async function findDrift() {
+  const entries = await compatibilityEntries();
+  const expectedTargets = new Set(entries.map(({ target }) => target));
+  const expectedPaths = new Set([COMMANDS_DIR]);
+  for (const target of expectedTargets) {
+    let current = target;
+    while (current.startsWith(COMMANDS_DIR)) {
+      expectedPaths.add(current);
+      if (current === COMMANDS_DIR) {
+        break;
+      }
+      current = dirname(current);
+    }
+  }
+  const issues = [];
+
+  for (const { source, target } of entries) {
+    let sourceText;
+    try {
+      sourceText = await readUtf8(source);
+    } catch (error) {
+      issues.push(`missing source ${relative(PLUGIN_ROOT, source)}: ${error.message}`);
+      continue;
+    }
+
+    let targetText;
+    try {
+      targetText = await readUtf8(target);
+    } catch (error) {
+      if (error.code === "ENOENT") {
+        issues.push(`missing compatibility file ${relative(PLUGIN_ROOT, target)}`);
+      } else {
+        issues.push(`cannot read compatibility file ${relative(PLUGIN_ROOT, target)}: ${error.message}`);
+      }
+      continue;
+    }
+
+    if (targetText !== sourceText) {
+      issues.push(`diverged compatibility file ${relative(PLUGIN_ROOT, target)}`);
+    }
+  }
+
+  for (const path of await existingCompatibilityEntries()) {
+    if (!expectedPaths.has(path)) {
+      issues.push(`stale compatibility path ${relative(PLUGIN_ROOT, path)}`);
+    }
+  }
+
+  return issues;
+}
+
+export async function syncCommandsLayout({ check = false } = {}) {
+  if (check) {
+    const issues = await findDrift();
+    if (issues.length > 0) {
+      for (const issue of issues) {
+        console.error(issue);
+      }
+      process.exitCode = 1;
+      return;
+    }
+    console.log("commands compatibility tree is in sync");
+    return;
+  }
+
+  await rm(COMMANDS_DIR, { recursive: true, force: true });
+  for (const { source, target } of await compatibilityEntries()) {
+    await copyTextFile(source, target);
+  }
+  console.log("commands compatibility tree synchronized");
+}
+
+const isDirectRun =
+  process.argv[1] &&
+  fileURLToPath(import.meta.url).endsWith(process.argv[1].replace(/^.*\//, ""));
+
+if (isDirectRun) {
+  syncCommandsLayout({ check: process.argv.includes("--check") }).catch((error) => {
+    console.error(error.message);
+    process.exitCode = 1;
+  });
+}

package/src/sync-skills-layout.js

@@ -1,148 +1,19 @@
 #!/usr/bin/env node
 /**
- * Synchronize the modern skills/turing package mirror from commands/.
+ * Backward-compatible wrapper for the flipped source layout.
  *
- * Usage:
- *   node src/sync-skills-layout.js [--check]
+ * The editable source is now skills/turing/, and sync generates commands/.
  */
 
-import { mkdir, readdir, readFile, rm, writeFile } from "fs/promises";
-import { dirname, join, relative } from "path";
 import { fileURLToPath } from "url";
-import { getCommandNames } from "./command-registry.js";
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const PLUGIN_ROOT = join(__dirname, "..");
-const COMMANDS_DIR = join(PLUGIN_ROOT, "commands");
-const SKILLS_DIR = join(PLUGIN_ROOT, "skills", "turing");
-
-async function readUtf8(path) {
-  return readFile(path, "utf8");
-}
-
-async function copyTextFile(source, target) {
-  await mkdir(dirname(target), { recursive: true });
-  await writeFile(target, await readUtf8(source));
-}
-
-async function mirrorEntries() {
-  const names = await getCommandNames();
-  return [
-    {
-      source: join(COMMANDS_DIR, "turing.md"),
-      target: join(SKILLS_DIR, "SKILL.md"),
-    },
-    ...names.map((name) => ({
-      source: join(COMMANDS_DIR, `${name}.md`),
-      target: join(SKILLS_DIR, name, "SKILL.md"),
-    })),
-    {
-      source: join(COMMANDS_DIR, "rules", "loop-protocol.md"),
-      target: join(SKILLS_DIR, "rules", "loop-protocol.md"),
-    },
-  ];
-}
-
-async function existingMirrorEntries(dir = SKILLS_DIR) {
-  let entries;
-  try {
-    entries = await readdir(dir, { withFileTypes: true });
-  } catch (error) {
-    if (error.code === "ENOENT") {
-      return [];
-    }
-    throw error;
-  }
-
-  const paths = [];
-  for (const entry of entries) {
-    const path = join(dir, entry.name);
-    paths.push(path);
-    if (entry.isDirectory()) {
-      paths.push(...await existingMirrorEntries(path));
-    }
-  }
-  return paths;
-}
-
-async function findDrift() {
-  const entries = await mirrorEntries();
-  const expectedTargets = new Set(entries.map(({ target }) => target));
-  const expectedPaths = new Set([SKILLS_DIR]);
-  for (const target of expectedTargets) {
-    let current = target;
-    while (current.startsWith(SKILLS_DIR)) {
-      expectedPaths.add(current);
-      if (current === SKILLS_DIR) {
-        break;
-      }
-      current = dirname(current);
-    }
-  }
-  const issues = [];
-
-  for (const { source, target } of entries) {
-    let sourceText;
-    try {
-      sourceText = await readUtf8(source);
-    } catch (error) {
-      issues.push(`missing source ${relative(PLUGIN_ROOT, source)}: ${error.message}`);
-      continue;
-    }
-
-    let targetText;
-    try {
-      targetText = await readUtf8(target);
-    } catch (error) {
-      if (error.code === "ENOENT") {
-        issues.push(`missing mirror ${relative(PLUGIN_ROOT, target)}`);
-      } else {
-        issues.push(`cannot read mirror ${relative(PLUGIN_ROOT, target)}: ${error.message}`);
-      }
-      continue;
-    }
-
-    if (targetText !== sourceText) {
-      issues.push(`diverged mirror ${relative(PLUGIN_ROOT, target)}`);
-    }
-  }
-
-  for (const path of await existingMirrorEntries()) {
-    if (!expectedPaths.has(path)) {
-      issues.push(`stale mirror ${relative(PLUGIN_ROOT, path)}`);
-    }
-  }
-
-  return issues;
-}
-
-export async function syncSkillsLayout({ check = false } = {}) {
-  if (check) {
-    const issues = await findDrift();
-    if (issues.length > 0) {
-      for (const issue of issues) {
-        console.error(issue);
-      }
-      process.exitCode = 1;
-      return;
-    }
-    console.log("skills/turing mirror is in sync");
-    return;
-  }
-
-  await rm(SKILLS_DIR, { recursive: true, force: true });
-  for (const { source, target } of await mirrorEntries()) {
-    await copyTextFile(source, target);
-  }
-  console.log("skills/turing mirror synchronized");
-}
+import { syncCommandsLayout } from "./sync-commands-layout.js";
 
 const isDirectRun =
   process.argv[1] &&
   fileURLToPath(import.meta.url).endsWith(process.argv[1].replace(/^.*\//, ""));
 
 if (isDirectRun) {
-  syncSkillsLayout({ check: process.argv.includes("--check") }).catch((error) => {
+  syncCommandsLayout({ check: process.argv.includes("--check") }).catch((error) => {
     console.error(error.message);
     process.exitCode = 1;
   });

package/templates/README.md

@@ -21,23 +21,21 @@ This separation is the invariant that makes experiment comparisons valid.
 
 ```bash
 # 1. Set up the environment
-python -m venv .venv
-source .venv/bin/activate
-pip install -r requirements.txt
+uv sync
 
 # 2. Add your training data to {{DATA_SOURCE}}
 
 # 3. Create train/val/test splits
-python prepare.py
+uv run python prepare.py
 
 # 4. Run training
-python train.py > run.log 2>&1
+uv run python train.py > run.log 2>&1
 
 # 5. Check results
 grep -A 10 "^---" run.log
 
 # 6. View experiment history
-python scripts/show_metrics.py
+uv run python scripts/show_metrics.py
 ```
 
 ## Using the Autoresearch Agent
@@ -88,6 +86,5 @@ For hands-off mode: `/loop 5m /turing:train`
 ## Running Tests
 
 ```bash
-source .venv/bin/activate
-python -m pytest tests/ -v
+uv run pytest tests/ -v
 ```

package/templates/program.md

@@ -54,11 +54,11 @@ Update it after each experiment with:
 
 For systematic hyperparameter search:
 1. Edit `sweep_config.yaml` with parameter ranges
-2. Generate queue: `python scripts/sweep.py`
-3. Check status: `python scripts/sweep.py --status`
-4. Get next: `python scripts/sweep.py --next`
+2. Generate queue: `uv run python scripts/sweep.py`
+3. Check status: `uv run python scripts/sweep.py --status`
+4. Get next: `uv run python scripts/sweep.py --next`
 5. Apply overrides, create branch, run training
-6. Mark done: `python scripts/sweep.py --mark <name> complete|failed`
+6. Mark done: `uv run python scripts/sweep.py --mark <name> complete|failed`
 
 ## THE LOOP
 
@@ -66,8 +66,8 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
 1. **OBSERVE** — Read recent results, check hypothesis queue, research plan, and review failed diffs:
    ```bash
-   python scripts/show_metrics.py --last 5
-   python scripts/manage_hypotheses.py next 2>/dev/null || echo "No queued hypotheses"
+   uv run python scripts/show_metrics.py --last 5
+   uv run python scripts/manage_hypotheses.py next 2>/dev/null || echo "No queued hypotheses"
    cat RESEARCH_PLAN.md 2>/dev/null || true
    ```
 
@@ -88,12 +88,12 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
    **If using a queued hypothesis:**
    ```bash
-   python scripts/manage_hypotheses.py mark hyp-NNN in-progress
+   uv run python scripts/manage_hypotheses.py mark hyp-NNN in-progress
    ```
 
    **If generating your own hypothesis**, register it with structured detail:
    ```bash
-   python scripts/manage_hypotheses.py add "your hypothesis description" \
+   uv run python scripts/manage_hypotheses.py add "your hypothesis description" \
      --priority medium --source agent \
      --model-type xgboost \
      --hyperparams '{"max_depth": 8, "n_estimators": 200}' \
@@ -101,7 +101,7 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
      --tags "depth,estimators" \
      --parent exp-NNN \
      --expected "deeper trees should capture feature interactions"
-   python scripts/manage_hypotheses.py mark hyp-NNN in-progress
+   uv run python scripts/manage_hypotheses.py mark hyp-NNN in-progress
    ```
 
    This creates both an index entry in `hypotheses.yaml` and a detailed file at `hypotheses/hyp-NNN.yaml` with full architecture, hyperparameters, expected outcome, and lineage.
@@ -110,7 +110,7 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
    To read a hypothesis's full detail:
    ```bash
-   python scripts/manage_hypotheses.py show hyp-NNN
+   uv run python scripts/manage_hypotheses.py show hyp-NNN
    ```
 
 3. **PREPARE** — Modify `config.yaml` for hyperparameter changes. Only modify `train.py` for structural code changes.
@@ -122,7 +122,7 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
 5. **EXECUTE** training:
    ```bash
-   source .venv/bin/activate && python train.py > run.log 2>&1
+   uv run python train.py > run.log 2>&1
    ```
 
 6. **MEASURE** — Parse metrics from run.log:
@@ -144,7 +144,7 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
 8. **RECORD** — Log the experiment (kept or discarded):
    ```bash
-   python scripts/log_experiment.py experiments/log.jsonl exp-NNN kept|discarded \
+   uv run python scripts/log_experiment.py experiments/log.jsonl exp-NNN kept|discarded \
      '{"{{TARGET_METRIC}}": X.XX, ...}' \
      '{"model_type": "xgboost", "hyperparams": {...}}' \
      models/model.joblib "Description of hypothesis and outcome"
@@ -152,7 +152,7 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
    Update the hypothesis status with result metrics:
    ```bash
-   python scripts/manage_hypotheses.py mark hyp-NNN tested \
+   uv run python scripts/manage_hypotheses.py mark hyp-NNN tested \
      --result exp-NNN \
      --metrics '{"{{TARGET_METRIC}}": X.XX, ...}' \
      --notes "Brief explanation of what happened and why"
@@ -162,7 +162,7 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
    Then synthesize a decision packet and auto-queue follow-ups:
    ```bash
-   python scripts/synthesize_decision.py --experiment exp-NNN --auto-queue
+   uv run python scripts/synthesize_decision.py --experiment exp-NNN --auto-queue
    ```
    This produces a verdict (promote/branch_followup/abandon/fix_and_retry) and automatically queues follow-up hypotheses for `branch_followup` and `fix_and_retry` outcomes.
 
@@ -172,7 +172,7 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
    - Report final best model and recommend next steps
    - **Before declaring final results**, run a seed study to verify robustness:
      ```bash
-     python scripts/seed_runner.py --quick
+     uv run python scripts/seed_runner.py --quick
      ```
      If CV > 5%, the result is seed-sensitive — report mean ± std, not a single-seed number.
 
@@ -180,9 +180,9 @@ The autoresearch experiment loop. Each iteration is one experiment — one hypot
 
 ## Execution Rules
 
-- **ALWAYS redirect output:** `python train.py > run.log 2>&1`
+- **ALWAYS redirect output:** `uv run python train.py > run.log 2>&1`
 - **ALWAYS parse with grep:** `grep -A 10 "^---" run.log | head -10`
-- **ALWAYS activate venv:** `source .venv/bin/activate`
+- **ALWAYS run Python through uv:** `uv run python ...`
 - **NEVER install packages** without human approval
 
 ## Strategy Escalation Protocol
@@ -219,5 +219,5 @@ Starting suggestions (ordered by expected impact):
 ## Comparing Runs
 
 ```bash
-python scripts/compare_runs.py exp-001 exp-002
+uv run python scripts/compare_runs.py exp-001 exp-002
 ```

package/templates/pyproject.toml

@@ -2,6 +2,16 @@
 name = "{{PROJECT_NAME}}-ml"
 version = "0.1.0"
 requires-python = ">=3.12"
+dependencies = [
+    "scikit-learn>=1.6",
+    "xgboost>=3.2",
+    "lightgbm>=4.6",
+    "pandas>=2.2",
+    "numpy>=2.0",
+    "joblib>=1.4",
+    "pyyaml>=6.0",
+    "pytest>=8.0",
+]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

package/templates/requirements.txt

@@ -1,3 +1,6 @@
+# Compatibility export only. pyproject.toml is canonical for dependencies.
+# Prefer: uv sync
+
 scikit-learn>=1.6
 xgboost>=3.2
 lightgbm>=4.6
@@ -8,5 +11,5 @@ pyyaml>=6.0
 pytest>=8.0
 
 # Optional: tree-search-guided hypothesis exploration
-# Install with: pip install "treequest[all]"
+# Install with: uv add "treequest[all]"
 # treequest>=0.1

package/templates/scripts/generate_onboarding.py

@@ -210,7 +210,7 @@ def format_onboarding_report(config, experiments, families, best, decisions,
         "5. `/turing:try \"your hypothesis\"` — inject ideas",
         "6. `/turing:train` — run next experiment",
     ], "engineer": [
-        "1. `pip install -r requirements.txt`",
+        "1. `uv sync`",
         "2. Review `config.yaml` for data paths",
         "3. `/turing:status` — where things stand",
         "4. Check `train.py` for current model",