claude-turing 4.2.0 → 4.4.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "turing",
-  "version": "4.2.0",
-  "description": "Autonomous ML research harness — the autoresearch loop as a formal protocol. 69 commands, 2 specialized agents, what-if analysis (whatif + counterfactual + simulate), collaboration (onboard + share + review), research communication (cite + present + changelog), experiment archaeology (trend + flashback + archive + annotate + search + template + replay), model surgery (prune + quantize + merge + surgery), feature & training intelligence, model debugging, pre-training intelligence, meta-intelligence, scaling & efficiency, model composition, deep analysis, experiment orchestration, literature + paper, model export, profiling, checkpoints, experiment intelligence, statistical rigor, tree-search, cost-performance, model cards, hypothesis database, novelty guard, anti-cheating, taste-leverage loop. Inspired by Karpathy's autoresearch and the scientific method itself.",
+  "version": "4.4.0",
+  "description": "Autonomous ML research harness — the autoresearch loop as a formal protocol. 74 commands, 2 specialized agents, operational intelligence (postmortem + doctor + plan), model lifecycle (update + registry), what-if analysis (whatif + counterfactual + simulate), collaboration (onboard + share + review), research communication (cite + present + changelog), experiment archaeology (trend + flashback + archive + annotate + search + template + replay), model surgery (prune + quantize + merge + surgery), feature & training intelligence, model debugging, pre-training intelligence, meta-intelligence, scaling & efficiency, model composition, deep analysis, experiment orchestration, literature + paper, model export, profiling, checkpoints, experiment intelligence, statistical rigor, tree-search, cost-performance, model cards, hypothesis database, novelty guard, anti-cheating, taste-leverage loop. Inspired by Karpathy's autoresearch and the scientific method itself.",
   "author": {
     "name": "pragnition"
   },

package/README.md

@@ -380,6 +380,11 @@ The index (`hypotheses.yaml`) is the lightweight queue. The detail files (`hypot
 | `/turing:whatif "<question>"` | What-if analysis — answer hypotheticals from existing experiment data |
 | `/turing:counterfactual <exp-id>` | Counterfactual explanations — minimum input change to flip a prediction |
 | `/turing:simulate [--configs]` | Experiment outcome prediction — pre-filter configs, save budget |
+| `/turing:update <exp-id>` | Incremental model update — add new data without full retraining |
+| `/turing:registry [action]` | Model registry — track lifecycle from candidate to production with gates |
+| `/turing:postmortem` | Failure postmortem — diagnose why experiments stopped improving |
+| `/turing:doctor [--fix]` | Harness self-diagnosis — check environment, project, resources |
+| `/turing:plan [--budget N]` | Research planning — strategic experiment campaign by ROI |
 
 And for fully hands-off operation:
 
@@ -564,11 +569,11 @@ Each project gets independent config, data, experiments, models, and agent memor
 
 ## Architecture of Turing Itself
 
-69 commands, 2 agents, 10 config files, 88 template scripts, model registry, artifact contract, cost-performance frontier, model cards, tree-search exploration, statistical rigor, experiment intelligence, performance profiling, smart checkpoints, production model export, literature integration, paper section drafting, experiment orchestration (queue + retry + fork), deep analysis (diff + watch + regress), model composition (ensemble + stitch + warm), scaling & efficiency (scale + budget + distill), meta-intelligence (transfer + audit), pre-training intelligence (sanity + baseline + leak), model debugging (xray + sensitivity + calibrate), feature & training intelligence (feature + curriculum), model surgery (prune + quantize + merge + surgery), experiment archaeology (trend + flashback + archive + annotate + search + template + replay), research communication (cite + present + changelog), collaboration (onboard + share + review), what-if analysis (whatif + counterfactual + simulate), 16 ADRs. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full codemap.
+74 commands, 2 agents, 10 config files, 93 template scripts, model registry, artifact contract, cost-performance frontier, model cards, tree-search exploration, statistical rigor, experiment intelligence, performance profiling, smart checkpoints, production model export, literature integration, paper section drafting, experiment orchestration (queue + retry + fork), deep analysis (diff + watch + regress), model composition (ensemble + stitch + warm), scaling & efficiency (scale + budget + distill), meta-intelligence (transfer + audit), pre-training intelligence (sanity + baseline + leak), model debugging (xray + sensitivity + calibrate), feature & training intelligence (feature + curriculum), model surgery (prune + quantize + merge + surgery), experiment archaeology (trend + flashback + archive + annotate + search + template + replay), research communication (cite + present + changelog), collaboration (onboard + share + review), what-if analysis (whatif + counterfactual + simulate), model lifecycle (update + registry), operational intelligence (postmortem + doctor + plan), 16 ADRs. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full codemap.
 
 ```
 turing/
-├── commands/              65 skill files (core + taste-leverage + reporting + exploration + statistical rigor + experiment intelligence + performance + deployment + research workflow + orchestration + deep analysis + model composition + scaling & efficiency + meta-intelligence + pre-training intelligence + model debugging + feature & training intelligence + model surgery + experiment archaeology + research communication + what-if analysis)
+├── commands/              70 skill files (core + taste-leverage + reporting + exploration + statistical rigor + experiment intelligence + performance + deployment + research workflow + orchestration + deep analysis + model composition + scaling & efficiency + meta-intelligence + pre-training intelligence + model debugging + feature & training intelligence + model surgery + experiment archaeology + research communication + what-if analysis + model lifecycle + operational intelligence)
 ├── agents/                2 agents (researcher: read/write, evaluator: read-only)
 ├── config/                8 files (lifecycle, taxonomy, archetypes, novelty aliases)
 ├── templates/             Scaffolded into user projects by /turing:init

package/commands/doctor.md

@@ -0,0 +1,30 @@
+---
+name: doctor
+description: Harness self-diagnosis — check environment, project, resources, and git state. Auto-fix common issues.
+disable-model-invocation: true
+argument-hint: "[--fix] [--verbose]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Is Turing healthy? Check everything and get a score.
+
+## Steps
+1. `source .venv/bin/activate`
+2. `python scripts/harness_doctor.py $ARGUMENTS`
+3. **Saved:** `experiments/doctor/`
+
+## Checks
+- **Environment:** Python version, venv status
+- **Dependencies:** all required packages importable
+- **Config:** config.yaml valid with required fields
+- **Experiment log:** JSONL integrity, corrupt line detection
+- **Scripts:** train.py, prepare.py, evaluate.py exist and parse
+- **Disk space:** warn if <1GB free
+- **Git state:** uncommitted changes to critical files
+
+## Examples
+```
+/turing:doctor
+/turing:doctor --fix
+/turing:doctor --verbose --json
+```

package/commands/plan.md

@@ -0,0 +1,27 @@
+---
+name: plan
+description: Research planning assistant — design a strategic experiment campaign with budget-aware ROI allocation.
+disable-model-invocation: true
+argument-hint: "[--budget 20] [--goal \"maximize F1 for production\"]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Design the next N experiments strategically, not randomly. Allocates budget by expected ROI.
+
+## Steps
+1. `source .venv/bin/activate`
+2. `python scripts/research_planner.py $ARGUMENTS`
+3. **Saved:** `experiments/plans/`
+
+## How it works
+- Analyzes experiment history to compute per-family ROI
+- Adjusts strategy priorities based on project state and goal
+- Allocates budget across: feature engineering, model search, ensemble, calibration, verification
+- Generates phased plan with specific experiment descriptions
+
+## Examples
+```
+/turing:plan --budget 20
+/turing:plan --budget 10 --goal "maximize F1 for production deployment"
+/turing:plan --budget 30 --json
+```

package/commands/postmortem.md

@@ -0,0 +1,28 @@
+---
+name: postmortem
+description: Failure postmortem — diagnose why experiments stopped improving and get actionable next steps.
+disable-model-invocation: true
+argument-hint: "[--window 10] [--auto-trigger 5]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+When experiments stop improving, find out why. Diagnoses search space exhaustion, config errors, data issues, metric ceilings, and noise floors.
+
+## Steps
+1. `source .venv/bin/activate`
+2. `python scripts/failure_postmortem.py $ARGUMENTS`
+3. **Saved:** `experiments/postmortems/`
+
+## Diagnosis categories
+- **Search space exhaustion:** micro-tuning params that don't matter
+- **Systematic config error:** all experiments share a bad common config
+- **Data issue:** all model types fail similarly
+- **Metric ceiling:** near theoretical maximum
+- **Noise floor:** improvements within seed variance
+
+## Examples
+```
+/turing:postmortem
+/turing:postmortem --window 15
+/turing:postmortem --json
+```

package/commands/registry.md

@@ -0,0 +1,31 @@
+---
+name: registry
+description: Model registry — track, promote, and govern the model lifecycle from candidate to production.
+disable-model-invocation: true
+argument-hint: "[list|register|promote|demote|archive|history] [exp-id] [stage]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Track which model is production, staging, candidate, or archived. Promotion requires passing gates.
+
+## Steps
+1. `source .venv/bin/activate`
+2. `python scripts/model_lifecycle.py $ARGUMENTS`
+3. **Registry:** `experiments/registry.yaml`
+
+## Promotion gates
+- **candidate → staging:** regression check + seed study must PASS
+- **staging → production:** audit + calibration check must PASS
+- Use `--force` to skip gate checks
+
+## Examples
+```
+/turing:registry list
+/turing:registry register exp-095 --version v4.1
+/turing:registry promote exp-089 staging
+/turing:registry promote exp-089 production --force
+/turing:registry demote exp-078 staging --reason "latency regression"
+/turing:registry archive exp-042 --reason "superseded by v4"
+/turing:registry history
+/turing:registry history exp-089
+```

package/commands/turing.md

@@ -78,6 +78,11 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | "what if", "what-if", "hypothetical", "estimate impact", "would it help" | `/turing:whatif` | Analyze |
 | "counterfactual", "flip prediction", "why this prediction", "minimum change", "explanation" | `/turing:counterfactual` | Explain |
 | "simulate", "predict outcome", "pre-filter", "which configs will work", "forecast" | `/turing:simulate` | Predict |
+| "update", "incremental", "new data", "add data", "fine-tune existing", "partial update" | `/turing:update` | Update |
+| "registry", "promote", "demote", "staging", "production", "which model is deployed", "model lifecycle" | `/turing:registry` | Govern |
+| "postmortem", "why failing", "failure streak", "why no improvement", "what went wrong" | `/turing:postmortem` | Diagnose |
+| "doctor", "health check", "is it broken", "diagnose harness", "self-check" | `/turing:doctor` | Check |
+| "plan", "research plan", "campaign", "what next", "allocate budget", "strategic plan" | `/turing:plan` | Plan |
 
 ## Sub-commands
 
@@ -152,6 +157,11 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | `/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) |
 
 ## Proactive Detection
 

package/commands/update.md

@@ -0,0 +1,27 @@
+---
+name: update
+description: Incremental model update — add new data without full retraining, with forgetting detection.
+disable-model-invocation: true
+argument-hint: "<exp-id> --new-data <path> [--replay-ratio 0.1] [--tolerance 0.005]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Add new data to an existing model without starting from scratch. Detects catastrophic forgetting.
+
+## Steps
+1. `source .venv/bin/activate`
+2. `python scripts/incremental_update.py $ARGUMENTS`
+3. **Saved:** `experiments/updates/`
+
+## Model-specific strategies
+- **XGBoost/LightGBM:** continued boosting with additional rounds
+- **Neural networks:** fine-tune with reduced LR + replay buffer from old data
+- **scikit-learn:** partial_fit() or warm_start=True
+
+## Examples
+```
+/turing:update exp-089 --new-data data/new_batch.csv
+/turing:update exp-089 --new-data data/new.csv --replay-ratio 0.2
+/turing:update exp-089 --new-data data/new.csv --tolerance 0.01
+/turing:update exp-089 --new-data data/new.csv --json
+```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-turing",
-  "version": "4.2.0",
+  "version": "4.4.0",
   "type": "module",
   "description": "Autonomous ML research harness for Claude Code. The autoresearch loop as a formal protocol — iteratively trains, evaluates, and improves ML models with structured experiment tracking, convergence detection, immutable evaluation infrastructure, and safety guardrails.",
   "bin": {

package/src/install.js

@@ -37,6 +37,8 @@ const SUB_COMMANDS = [
   "cite", "present", "changelog",
   "onboard", "share", "review",
   "whatif", "counterfactual", "simulate",
+  "update", "registry",
+  "postmortem", "doctor", "plan",
 ];
 
 export async function install(opts = {}) {

package/src/verify.js

@@ -83,6 +83,11 @@ const EXPECTED_COMMANDS = [
   "whatif/SKILL.md",
   "counterfactual/SKILL.md",
   "simulate/SKILL.md",
+  "update/SKILL.md",
+  "registry/SKILL.md",
+  "postmortem/SKILL.md",
+  "doctor/SKILL.md",
+  "plan/SKILL.md",
 ];
 
 const EXPECTED_AGENTS = ["ml-researcher.md", "ml-evaluator.md"];