claude-turing 4.4.0 → 4.6.0

package/bin/cli.js

@@ -1,9 +1,25 @@
 #!/usr/bin/env node
 import { createRequire } from "module";
+import { realpathSync } from "fs";
+import { fileURLToPath } from "url";
 const require = createRequire(import.meta.url);
 const { Command } = require("commander");
 const pkg = require("../package.json");
 
+export function buildInitArgs(name, dir) {
+  return [name, dir].filter(Boolean);
+}
+
+function isDirectRun() {
+  if (!process.argv[1]) return false;
+
+  try {
+    return realpathSync(fileURLToPath(import.meta.url)) === realpathSync(process.argv[1]);
+  } catch {
+    return false;
+  }
+}
+
 const program = new Command();
 
 program
@@ -34,13 +50,16 @@ program
   .command("init [name] [dir]")
   .description("Scaffold ML project (CLI mode, non-Claude-Code usage)")
   .action(async (name, dir) => {
-    const { execSync } = await import("child_process");
+    const { spawnSync } = await import("child_process");
     const { dirname, join } = await import("path");
     const { fileURLToPath } = await import("url");
     const __dirname = dirname(fileURLToPath(import.meta.url));
     const script = join(__dirname, "turing-init.sh");
-    const args = [name, dir].filter(Boolean).join(" ");
-    execSync(`bash "${script}" ${args}`, { stdio: "inherit" });
+    const args = buildInitArgs(name, dir);
+    const result = spawnSync("bash", [script, ...args], { stdio: "inherit" });
+    process.exit(result.status ?? 1);
   });
 
-program.parse();
+if (isDirectRun()) {
+  program.parse();
+}

package/commands/doctor.md

@@ -21,6 +21,7 @@ Is Turing healthy? Check everything and get a score.
 - **Scripts:** train.py, prepare.py, evaluate.py exist and parse
 - **Disk space:** warn if <1GB free
 - **Git state:** uncommitted changes to critical files
+- **Claude hooks:** `.claude/settings.local.json` hook group schema; `--fix` migrates legacy bare command hooks
 
 ## Examples
 ```

package/commands/init.md

@@ -37,18 +37,36 @@ python3 <templates_dir>/scripts/scaffold.py \
 The scaffold script handles everything in a single atomic operation:
 - Copies all template files with placeholder substitution
 - Creates data/, experiments/, models/ directories
-- Sets up agent memory at `.claude/agent-memory/ml-researcher/MEMORY.md`
+- Sets up agent memory at `.claude/agent-memory/ml-researcher-{project_name}/MEMORY.md`
 - Configures Claude Code hooks in `.claude/settings.local.json`
 - Creates Python virtual environment and installs requirements
 - Verifies all placeholders were replaced (fails loudly if any remain)
 
 ## Locating Templates
 
-Find the templates directory using Glob:
+Use the installed command-pack templates directory first:
+```
+.claude/commands/turing/templates/
+~/.claude/commands/turing/templates/
+```
+Then fall back to plugin or npm locations:
 ```
 ~/.claude/plugins/*/templates/
+node_modules/claude-turing/templates/
+```
+
+Example command:
+
+```bash
+python3 ~/.claude/commands/turing/templates/scripts/scaffold.py \
+    --project-name "<project_name>" \
+    --target-metric "<target_metric>" \
+    --metric-direction "<metric_direction>" \
+    --task-description "<task_description>" \
+    --ml-dir "<ml_dir>" \
+    --data-source "<data_source>" \
+    --templates-dir ~/.claude/commands/turing/templates
 ```
-Or check if installed via npm by looking for `node_modules/claude-turing/templates/`.
 
 ## After Scaffolding
 

package/commands/turing.md

@@ -1,9 +1,17 @@
 ---
 name: turing
-description: Autonomous ML research harness. Thin router that detects ML training intent and dispatches to focused sub-commands. Each sub-command handles one phase of the experiment lifecycle.
+description: Autonomous ML research harness. Thin router that detects ML training intent and identifies the matching Turing sub-command execution path. Each sub-command handles one phase of the experiment lifecycle.
 ---
 
-You are the Turing ML research router. Detect the user's intent and route to the appropriate sub-command. Do not attempt to handle ML tasks directly — dispatch to the focused skill.
+You are the Turing ML research router. Detect the user's intent and identify the matching Turing sub-command execution path.
+
+## Execution Contract
+
+Turing sub-commands are explicit slash-command skills. Current sub-commands are `slash_only` and use `disable-model-invocation: true`, so router handling must not claim model dispatch into those skills.
+
+- If the user explicitly invokes `/turing:<cmd>`, Claude Code runtime handles that slash command.
+- If the user invokes `/turing` as a router and the detected command is `slash_only`, give the exact slash command to run.
+- If a command has a documented safe equivalent script, the assistant may execute those documented steps inline when safe and appropriate.
 
 ## Routing Table
 
@@ -86,82 +94,82 @@ You are the Turing ML research router. Detect the user's intent and route to the
 
 ## Sub-commands
 
-| Command | Purpose | Agent |
+| Command | Purpose | Invocation |
 |---|---|---|
-| `/turing:train [ml/project] [N]` | Run the autonomous experiment loop (auto-detects project from path or cwd) | @ml-researcher |
-| `/turing:status` | Show experiment status, best model, convergence | @ml-evaluator |
-| `/turing:compare <a> <b>` | Side-by-side experiment comparison | @ml-evaluator |
-| `/turing:sweep` | Generate and run hyperparameter sweep | @ml-researcher |
-| `/turing:try <hypothesis>` | Inject a hypothesis into the agent's queue | (inline) |
-| `/turing:brief` | Generate structured research intelligence report | @ml-evaluator |
-| `/turing:init` | Scaffold a new ML project | (inline) |
-| `/turing:validate` | Check metric stability, auto-fix if noisy | (inline) |
-| `/turing:seed [N] [--quick]` | Multi-seed study: mean/std/CI, flag seed-sensitive results | (inline) |
-| `/turing:reproduce <exp-id>` | Reproducibility verification with tolerance checking | (inline) |
-| `/turing:suggest` | Literature-grounded model architecture suggestions | (inline, uses WebSearch) |
-| `/turing:explore` | Tree-search hypothesis exploration via AB-MCTS | (inline) |
-| `/turing:design <hyp-id>` | Generate structured experiment design from hypothesis | (inline, uses WebSearch) |
-| `/turing:logbook` | HTML/markdown logbook with trajectory chart | (inline) |
-| `/turing:poster` | Single-page HTML research poster | (inline) |
-| `/turing:report` | Structured markdown research report | (inline) |
-| `/turing:mode <mode>` | Set research strategy (explore/exploit/replicate) | (inline) |
-| `/turing:preflight` | Pre-flight resource check (VRAM/RAM/disk) | (inline) |
-| `/turing:card` | Generate standardized model card (type, performance, data, limitations, contract) | (inline) |
-| `/turing:diagnose [exp-id]` | Error analysis: failure modes, confused pairs, feature-range bias | (inline) |
-| `/turing:ablate [--components]` | Ablation study: remove components, measure impact, flag dead weight | (inline) |
-| `/turing:frontier [--metrics]` | Pareto frontier: multi-objective tradeoff visualization | (inline) |
-| `/turing:lit <query>` | Literature search: papers, SOTA baselines, related work | (inline, uses WebSearch) |
-| `/turing:paper [--sections] [--format]` | Draft paper sections from experiment logs (setup, results, ablation, hyperparams) | (inline) |
-| `/turing:export [exp-id] [--format]` | Export model to production format with equivalence check + latency benchmark | (inline) |
-| `/turing:queue <action>` | Batch experiment scheduler: add, list, run, pause, clear | (inline) |
-| `/turing:retry <exp-id>` | Smart failure recovery: auto-diagnose crash, apply fix, re-run | (inline) |
-| `/turing:fork <exp-id> --branches` | Experiment branching: run parallel tracks, report winner | (inline) |
-| `/turing:profile [exp-id]` | Computational profiling: timing, memory, throughput, bottleneck detection | (inline) |
-| `/turing:checkpoint <action>` | Smart checkpoint management: list, prune (Pareto), average, resume, stats | (inline) |
-| `/turing:diff <exp-a> <exp-b>` | Deep experiment comparison: config diff, metric significance, per-class regressions, curve divergence | (inline) |
-| `/turing:watch [--analyze]` | Live training monitor with early-warning alerts (loss spike, NaN, overfitting, plateau) | (inline) |
-| `/turing:regress [--tolerance]` | Performance regression gate: re-run best experiment, verify metrics haven't degraded | (inline) |
-| `/turing:ensemble [--top-k] [--methods]` | Automated ensemble: voting, weighted voting, stacking, blending from top-K models | (inline) |
-| `/turing:stitch <action> [stage]` | Pipeline composition: show/swap/cache/run stages independently | (inline) |
-| `/turing:warm <exp-id>` | Warm-start from prior model: load checkpoint, freeze layers, adjust LR | (inline) |
-| `/turing:scale [--axis]` | Scaling law estimator: fit power law, predict full-scale performance | (inline) |
-| `/turing:budget <action>` | Compute budget manager: set limits, track allocation, auto-shift modes | (inline) |
-| `/turing:distill <exp-id>` | Model compression: distill teacher into smaller student model | (inline) |
-| `/turing:transfer [--from]` | Cross-project knowledge transfer: find similar prior projects, surface what worked | (inline) |
-| `/turing:audit [--strict]` | Pre-submission methodology audit: data leakage, baselines, seeds, ablations, reproducibility | (inline) |
-| `/turing:sanity [--quick]` | Pre-training sanity checks: initial loss, overfit test, gradient flow, output validation | (inline) |
-| `/turing:baseline [--methods]` | Automatic baseline generation: random, majority/mean, linear, k-NN | (inline) |
-| `/turing:leak [--deep]` | Targeted leakage detection: single-feature tests, correlation, train/test overlap | (inline) |
-| `/turing:xray [exp-id]` | Internal model diagnostics: gradient flow, dead neurons, weight distributions, tree analysis | (inline) |
-| `/turing:sensitivity [exp-id]` | Hyperparameter sensitivity analysis: rank parameters by impact, detect non-monotonic responses | (inline) |
-| `/turing:calibrate [exp-id]` | Probability calibration: ECE/MCE, reliability diagrams, Platt/isotonic/temperature scaling | (inline) |
-| `/turing:feature [--method]` | Automated feature selection: multi-method consensus ranking, redundancy, interaction generation | (inline) |
-| `/turing:curriculum [exp-id]` | Training curriculum optimization: difficulty scoring, strategy comparison, impossible sample detection | (inline) |
-| `/turing:prune <exp-id>` | Weight pruning: magnitude/structured/lottery, sparsity sweep, knee point detection | (inline) |
-| `/turing:quantize <exp-id>` | Post-training quantization: FP16/INT8, accuracy-latency comparison, QAT suggestion | (inline) |
-| `/turing:merge <exp-ids...>` | Model merging: uniform/greedy soup, TIES, DARE — free accuracy, zero latency cost | (inline) |
-| `/turing:surgery <exp-id>` | Architecture modification: add/remove layer, widen/narrow, swap activation, skip connections | (inline) |
-| `/turing:trend` | Long-term trend analysis: improvement velocity, family ROI, diminishing returns detection | (inline) |
-| `/turing:flashback` | Session context restoration: "where was I?" after days away from the project | (inline) |
-| `/turing:archive` | Experiment lifecycle cleanup: compress old artifacts, prune checkpoints, summary index | (inline) |
-| `/turing:annotate <exp-id>` | Retrospective annotations: add human notes, tags, search by content | (inline) |
-| `/turing:search <query>` | Natural language experiment search with structured filters | (inline) |
-| `/turing:template <action>` | Experiment template library: save/list/apply reusable configs across projects | (inline) |
-| `/turing:replay <exp-id>` | Experiment replay: re-run old experiment with current infrastructure | (inline) |
-| `/turing:cite <action>` | Citation manager: add/list/check/bib for papers, datasets, methods | (inline) |
-| `/turing:present [--figures]` | Presentation figures: training curves, comparisons, ablation, Pareto, sensitivity | (inline) |
-| `/turing:changelog [--audience]` | Model changelog: version-grouped improvements for technical or stakeholder audiences | (inline) |
-| `/turing:onboard [--audience]` | Project onboarding: full walkthrough for new collaborators | (inline) |
-| `/turing:share <exp-ids...>` | Experiment packaging: portable archive with manifest and README | (inline) |
-| `/turing:review [--venue]` | Peer review simulation: weaknesses, questions, fix commands, score | (inline) |
-| `/turing:whatif "<question>"` | What-if analysis: route hypotheticals to existing estimators (scaling, ablation, sensitivity, ensemble, pruning) | (inline) |
-| `/turing:counterfactual <exp-id> --sample <index>` | Input-level counterfactual explanations: minimum input change to flip a prediction | (inline) |
-| `/turing:simulate [--configs] [--top-k]` | Experiment outcome prediction: pre-filter configs using surrogate model, save budget | (inline) |
-| `/turing:update <exp-id> --new-data <path>` | Incremental model update: add new data without full retraining, forgetting detection | (inline) |
-| `/turing:registry [list\|register\|promote\|demote\|history]` | Model registry: stage lifecycle (candidate → staging → production) with promotion gates | (inline) |
-| `/turing:postmortem [--window N]` | Failure postmortem: diagnose why experiments stopped improving (exhaustion, config error, data issue, ceiling, noise) | (inline) |
-| `/turing:doctor [--fix]` | Harness self-diagnosis: environment, dependencies, config, log integrity, scripts, disk, git state | (inline) |
-| `/turing:plan [--budget N] [--goal]` | Research planning assistant: strategic campaign design with budget-aware ROI allocation | (inline) |
+| `/turing:train [ml/project] [N]` | Run the autonomous experiment loop (auto-detects project from path or cwd) | slash_only |
+| `/turing:status` | Show experiment status, best model, convergence | slash_only |
+| `/turing:compare <a> <b>` | Side-by-side experiment comparison | slash_only |
+| `/turing:sweep` | Generate and run hyperparameter sweep | slash_only |
+| `/turing:try <hypothesis>` | Inject a hypothesis into the agent's queue | slash_only |
+| `/turing:brief` | Generate structured research intelligence report | slash_only |
+| `/turing:init` | Scaffold a new ML project | slash_only |
+| `/turing:validate` | Check metric stability, auto-fix if noisy | slash_only |
+| `/turing:seed [N] [--quick]` | Multi-seed study: mean/std/CI, flag seed-sensitive results | slash_only |
+| `/turing:reproduce <exp-id>` | Reproducibility verification with tolerance checking | slash_only |
+| `/turing:suggest` | Literature-grounded model architecture suggestions | slash_only |
+| `/turing:explore` | Tree-search hypothesis exploration via AB-MCTS | slash_only |
+| `/turing:design <hyp-id>` | Generate structured experiment design from hypothesis | slash_only |
+| `/turing:logbook` | HTML/markdown logbook with trajectory chart | slash_only |
+| `/turing:poster` | Single-page HTML research poster | slash_only |
+| `/turing:report` | Structured markdown research report | slash_only |
+| `/turing:mode <mode>` | Set research strategy (explore/exploit/replicate) | slash_only |
+| `/turing:preflight` | Pre-flight resource check (VRAM/RAM/disk) | slash_only |
+| `/turing:card` | Generate standardized model card (type, performance, data, limitations, contract) | slash_only |
+| `/turing:diagnose [exp-id]` | Error analysis: failure modes, confused pairs, feature-range bias | slash_only |
+| `/turing:ablate [--components]` | Ablation study: remove components, measure impact, flag dead weight | slash_only |
+| `/turing:frontier [--metrics]` | Pareto frontier: multi-objective tradeoff visualization | slash_only |
+| `/turing:lit <query>` | Literature search: papers, SOTA baselines, related work | slash_only |
+| `/turing:paper [--sections] [--format]` | Draft paper sections from experiment logs (setup, results, ablation, hyperparams) | slash_only |
+| `/turing:export [exp-id] [--format]` | Export model to production format with equivalence check + latency benchmark | slash_only |
+| `/turing:queue <action>` | Batch experiment scheduler: add, list, run, pause, clear | slash_only |
+| `/turing:retry <exp-id>` | Smart failure recovery: auto-diagnose crash, apply fix, re-run | slash_only |
+| `/turing:fork <exp-id> --branches` | Experiment branching: run parallel tracks, report winner | slash_only |
+| `/turing:profile [exp-id]` | Computational profiling: timing, memory, throughput, bottleneck detection | slash_only |
+| `/turing:checkpoint <action>` | Smart checkpoint management: list, prune (Pareto), average, resume, stats | slash_only |
+| `/turing:diff <exp-a> <exp-b>` | Deep experiment comparison: config diff, metric significance, per-class regressions, curve divergence | slash_only |
+| `/turing:watch [--analyze]` | Live training monitor with early-warning alerts (loss spike, NaN, overfitting, plateau) | slash_only |
+| `/turing:regress [--tolerance]` | Performance regression gate: re-run best experiment, verify metrics haven't degraded | slash_only |
+| `/turing:ensemble [--top-k] [--methods]` | Automated ensemble: voting, weighted voting, stacking, blending from top-K models | slash_only |
+| `/turing:stitch <action> [stage]` | Pipeline composition: show/swap/cache/run stages independently | slash_only |
+| `/turing:warm <exp-id>` | Warm-start from prior model: load checkpoint, freeze layers, adjust LR | slash_only |
+| `/turing:scale [--axis]` | Scaling law estimator: fit power law, predict full-scale performance | slash_only |
+| `/turing:budget <action>` | Compute budget manager: set limits, track allocation, auto-shift modes | slash_only |
+| `/turing:distill <exp-id>` | Model compression: distill teacher into smaller student model | slash_only |
+| `/turing:transfer [--from]` | Cross-project knowledge transfer: find similar prior projects, surface what worked | slash_only |
+| `/turing:audit [--strict]` | Pre-submission methodology audit: data leakage, baselines, seeds, ablations, reproducibility | slash_only |
+| `/turing:sanity [--quick]` | Pre-training sanity checks: initial loss, overfit test, gradient flow, output validation | slash_only |
+| `/turing:baseline [--methods]` | Automatic baseline generation: random, majority/mean, linear, k-NN | slash_only |
+| `/turing:leak [--deep]` | Targeted leakage detection: single-feature tests, correlation, train/test overlap | slash_only |
+| `/turing:xray [exp-id]` | Internal model diagnostics: gradient flow, dead neurons, weight distributions, tree analysis | slash_only |
+| `/turing:sensitivity [exp-id]` | Hyperparameter sensitivity analysis: rank parameters by impact, detect non-monotonic responses | slash_only |
+| `/turing:calibrate [exp-id]` | Probability calibration: ECE/MCE, reliability diagrams, Platt/isotonic/temperature scaling | slash_only |
+| `/turing:feature [--method]` | Automated feature selection: multi-method consensus ranking, redundancy, interaction generation | slash_only |
+| `/turing:curriculum [exp-id]` | Training curriculum optimization: difficulty scoring, strategy comparison, impossible sample detection | slash_only |
+| `/turing:prune <exp-id>` | Weight pruning: magnitude/structured/lottery, sparsity sweep, knee point detection | slash_only |
+| `/turing:quantize <exp-id>` | Post-training quantization: FP16/INT8, accuracy-latency comparison, QAT suggestion | slash_only |
+| `/turing:merge <exp-ids...>` | Model merging: uniform/greedy soup, TIES, DARE — free accuracy, zero latency cost | slash_only |
+| `/turing:surgery <exp-id>` | Architecture modification: add/remove layer, widen/narrow, swap activation, skip connections | slash_only |
+| `/turing:trend` | Long-term trend analysis: improvement velocity, family ROI, diminishing returns detection | slash_only |
+| `/turing:flashback` | Session context restoration: "where was I?" after days away from the project | slash_only |
+| `/turing:archive` | Experiment lifecycle cleanup: compress old artifacts, prune checkpoints, summary index | slash_only |
+| `/turing:annotate <exp-id>` | Retrospective annotations: add human notes, tags, search by content | slash_only |
+| `/turing:search <query>` | Natural language experiment search with structured filters | slash_only |
+| `/turing:template <action>` | Experiment template library: save/list/apply reusable configs across projects | slash_only |
+| `/turing:replay <exp-id>` | Experiment replay: re-run old experiment with current infrastructure | slash_only |
+| `/turing:cite <action>` | Citation manager: add/list/check/bib for papers, datasets, methods | slash_only |
+| `/turing:present [--figures]` | Presentation figures: training curves, comparisons, ablation, Pareto, sensitivity | slash_only |
+| `/turing:changelog [--audience]` | Model changelog: version-grouped improvements for technical or stakeholder audiences | slash_only |
+| `/turing:onboard [--audience]` | Project onboarding: full walkthrough for new collaborators | slash_only |
+| `/turing:share <exp-ids...>` | Experiment packaging: portable archive with manifest and README | slash_only |
+| `/turing:review [--venue]` | Peer review simulation: weaknesses, questions, fix commands, score | slash_only |
+| `/turing:whatif "<question>"` | What-if analysis: route hypotheticals to existing estimators (scaling, ablation, sensitivity, ensemble, pruning) | slash_only |
+| `/turing:counterfactual <exp-id> --sample <index>` | Input-level counterfactual explanations: minimum input change to flip a prediction | slash_only |
+| `/turing:simulate [--configs] [--top-k]` | Experiment outcome prediction: pre-filter configs using surrogate model, save budget | slash_only |
+| `/turing:update <exp-id> --new-data <path>` | Incremental model update: add new data without full retraining, forgetting detection | slash_only |
+| `/turing:registry [list\|register\|promote\|demote\|history]` | Model registry: stage lifecycle (candidate → staging → production) with promotion gates | slash_only |
+| `/turing:postmortem [--window N]` | Failure postmortem: diagnose why experiments stopped improving (exhaustion, config error, data issue, ceiling, noise) | slash_only |
+| `/turing:doctor [--fix]` | Harness self-diagnosis: environment, dependencies, config, log integrity, scripts, disk, git state, Claude hooks | slash_only |
+| `/turing:plan [--budget N] [--goal]` | Research planning assistant: strategic campaign design with budget-aware ROI allocation | slash_only |
 
 ## Proactive Detection