@dzhechkov/harness-cli 0.3.252 → 0.3.254

package/.dz-manifest.json

@@ -9,7 +9,7 @@
       },
       {
         "path": "README.md",
-        "sha256": "ff1b1a2239a254f500c999c5c25ab9303561b433fb1cac420a2b28a7bd0d9fd6"
+        "sha256": "fc57c105e5031d2d6751ef08b64769dc463cd79c5cf7637b48bc8cb7190e5b3a"
       },
       {
         "path": "coverage/coverage-final.json",
@@ -41,15 +41,15 @@
       },
       {
         "path": "dist/cli.d.ts.map",
-        "sha256": "c9b415287eda0a7c2ad32dbb7cfc3ecce19aa3b90c96d3fbeedd62d20fe34bc7"
+        "sha256": "4268f56e38f72625c2c490add4b17ee12d7ff7db991a2090f426afbb026b98a9"
       },
       {
         "path": "dist/cli.js",
-        "sha256": "56b4da2639c1721180387f28166d84d065718a4002f556307a6598570d335809"
+        "sha256": "fe24568930cc226e0bad8b4ccba559e2f837bb4cb068c2cc37750b5a10c27a70"
       },
       {
         "path": "dist/cli.js.map",
-        "sha256": "4a172ba5384c9716fa48570979b7ffba969599ed5c639d7e7268a829d2b9b4e1"
+        "sha256": "4a0b554fab78cd50fc46cff653411b2003b7dd9a4df1b16af6e9f5a0e24379ff"
       },
       {
         "path": "dist/index.d.ts",
@@ -73,7 +73,7 @@
       },
       {
         "path": "package.json",
-        "sha256": "65e245ef567ccecdc382bb040f27dd98e01ce2c3a104935aa2dc0558b22220e2"
+        "sha256": "c6469d0f7539ce6c0a8176d0b795952a667df2b975c9f93c66e7cd6eba843383"
       },
       {
         "path": "src/bin.ts",
@@ -81,7 +81,7 @@
       },
       {
         "path": "src/cli.ts",
-        "sha256": "1aceceef391cac55d00f7872632d28c4116a82025b9235343b81398fc515f944"
+        "sha256": "13d3946992186e019310c1c8666fd724ce74880b8fda19850eeb8b6e0399e3d7"
       },
       {
         "path": "src/index.ts",
@@ -91,6 +91,10 @@
         "path": "test/cli.test.ts",
         "sha256": "7d6ba26ec1188db3b3ac89f50b015ba1f0c6117b5c30d99b22da41da10c96c12"
       },
+      {
+        "path": "test/epoch-replay-cli.test.ts",
+        "sha256": "a5a48585b565288ca1ea96030b02b2ccb37a621ef7b3cfe54cd7aaa7164d6904"
+      },
       {
         "path": "tsconfig.json",
         "sha256": "e80ef2911c3347a713dc3dca6a5f6034d91e938e58e71345ea920dd9833bcdbb"
@@ -101,5 +105,5 @@
       }
     ]
   },
-  "signature": "QkTucRDewQaD109O+GaZcrFfuzX3jp/bFPbLBYq5CmLT7BCzeHAGDdGfJogI8yZA81HE5oQLRzixyq6IdNPDCw=="
+  "signature": "lRzsYJCin4HX25rutyyh0Veo7d29P+AOTtJyKdgPcBrzIY44kdm7AHYRYCKcTrH5esXg8nVfhxd1Uw74PjtZAg=="
 }

package/README.md

@@ -132,7 +132,7 @@ point any tool at (a skill is just Markdown). Dedicated targets are on the [road
 
 ## User Journey — from install to mastery
 
-All 43 commands mapped to a real workflow:
+All 62 commands mapped to a real workflow:
 
 ```
 DISCOVER → INSTALL → USE → CREATE → MAINTAIN → SHARE
@@ -236,6 +236,11 @@ dz workflow --task security-audit               # adversarial security scan
 
 # Cross-host state sync:
 dz roam --apply                                 # sync agent state across machines
+
+# Is the self-learning loop actually paying off?
+dz compounding                                  # readiness + payoff report (INSUFFICIENT_DATA is a real answer)
+dz epoch-replay --mock --n 24 --effect 0.9      # $0 dry run of the cold-vs-warm verdict math
+dz epoch-replay --emit                          # ready? emit the real cold-vs-warm work order
 ```
 
 ### Phase 6: Share (publish to the world)
@@ -464,6 +469,98 @@ The prompt queries that make replay possible stay on your machine: `.dz/recall-u
 git-ignored, entries are truncated at 200 chars and flagged when truncated (a prefix is not a prompt,
 so flagged rows never count as replayable).
 
+### Did the lessons actually change outcomes? — `dz epoch-replay`
+
+`dz compounding` says a cold-vs-warm replay **can** be run. `dz epoch-replay` **runs** it and reports
+what it found: Epoch 0 (cold — the prompt alone) vs Epoch 1 (warm — the same prompt plus exactly the
+lessons the apply leg injected), on the same instances, scored into a three-valued verdict.
+
+**The test is PAIRED.** Each instance is one judgment on one prompt, so the statistic is a single
+binomial over *decisive* pairs: `p̂ = warm wins / (warm wins + cold wins)`, with a `95%` Wilson
+interval reported on the **lift** scale `2p̂ − 1`. Ties carry no direction — they are excluded from
+the denominator and reported separately.
+
+**`SUPPORTED` only when the lift interval lies entirely above zero.** `FALSIFIED` only on **harm**
+(entirely below zero) or on a passed **non-superiority** test — the lift upper bound below a
+pre-registered margin, default `0.05`, at 10+ decisive pairs. Everything else is `INCONCLUSIVE`, a
+first-class honest outcome; below 5 decisive pairs there is no verdict at all.
+
+**A tie is under-powered, not refuted.** `6/12` gives a lift interval of `[-0.492, 0.492]` — that
+excludes nothing, so it reads `INCONCLUSIVE`. So does a *perfectly* even 500/500 over 1000 pairs
+(lift upper `0.0619`): the most uninformative result the protocol can produce must not be reported
+as a refutation. A refutation has to clear a bar too.
+
+**Try it at $0 first — `--mock` generates seeded synthetic outcomes at a TRUE effect you choose, and
+runs them through the real verdict math:**
+
+```
+$ dz epoch-replay --mock --n 24 --effect 0.9 --seed 20260729
+  COLD (epoch 0, no injected lessons): 1/24   CI95 [0.007, 0.202]
+  WARM (epoch 1, apply-leg lessons):   23/24  CI95 [0.798, 0.993]
+  VERDICT: SUPPORTED
+    warm 23/24 CI [0.798, 0.993] is DISJOINT above cold 1/24 CI [0.007, 0.202]
+
+$ dz epoch-replay --mock --n 24 --effect -0.9 --seed 20260729   # → FALSIFIED (harm)
+$ dz epoch-replay --mock --n 24 --effect 0.4  --seed 20260729   # → INCONCLUSIVE (neither separates nor excludes)
+$ dz epoch-replay --mock --n 12 --effect 0    --seed 7          # → INCONCLUSIVE (6/6 tie: under-powered, NOT refuted)
+```
+
+```
+$ dz epoch-replay --mock --n 24 --effect 0.9 --seed 20260729
+  SLICE: all · 24 scored instance(s) · 24 DECISIVE pair(s)
+  COLD (epoch 0, no injected lessons): 1/24 decisive   CI95 [0.007, 0.202]
+  WARM (epoch 1, apply-leg lessons):   23/24 decisive  CI95 [0.798, 0.993]
+  LIFT (paired, 2p−1 over decisive pairs): +0.917  [0.595, 0.985]
+  VERDICT: SUPPORTED — the lift interval lies ENTIRELY above zero
+```
+
+Every mock run prints `SYNTHETIC … it is NOT evidence about the learning loop`, and the same seed
+gives byte-identical output — a demo is a reproducer.
+
+**Real mode: the runner ORCHESTRATES and SCORES — it never calls a model.** Generation and judging
+happen out of band, so the core stays pure, offline and reproducible:
+
+```
+$ dz epoch-replay --emit                   # → .dz/epoch-replay/work-order.json  (git-ignored: raw prompts)
+     25 instance(s) · seed 20260729 · blind A/B assignment PRE-REGISTERED
+  # 1. have an agent fill coldPlan / warmPlan for each item (symmetric length, same task)
+$ dz epoch-replay --judge .dz/epoch-replay/work-order.json     # → blind judge prompts
+  # 2. have an EXTERNAL, cross-model judge answer them → [{ "id": …, "winner": "A|B|TIE" }]
+$ dz epoch-replay --score judgments.json --work-order .dz/epoch-replay/work-order.json --slice task
+```
+
+Three things make that blind real rather than decorative:
+
+- **The judge sees `{id, prompt}` and nothing else.** No assignment, no arm names, no slice label,
+  not even a path back to the work order. The judge file is byte-identical whichever way the
+  assignment fell, so it cannot be decoded. (Skipped items are reported on stdout, not in the file —
+  their reasons name arms.)
+- **The work order is integrity-checked.** It carries a sha256 digest over its pre-registered core
+  (version, seed, margin, corpus fingerprint, every `[id, warmIsA]`); `--judge` and `--score`
+  recompute it *and* re-derive every assignment from the stated seed, refusing on any mismatch. A
+  hand-written order does not buy a verdict.
+  > **Honest scope:** this is an integrity check against accidental corruption and mismatch — **not
+  > a cryptographic commitment.** The hash is self-contained, so a determined operator can re-forge
+  > it (seed-searching a matching assignment at n=12 takes a few thousand tries). The threat model
+  > is *you making a mistake*: a hand-edited file, a stale order paired with fresh judgments. The
+  > honest-use contract is procedural — emit once, then judge, and keep the emitted file. `--emit`
+  > records `emittedAt` + a corpus fingerprint and `--score` prints the digest, seed and margin, so
+  > a reviewer can ask for the original and compare three numbers.
+- **The non-superiority margin is pre-registered.** `--margin` is accepted only at `--emit`, is
+  stored in the work order and covered by the digest, and `--score` **refuses** a `--margin` flag —
+  a margin chosen once you can see the counts is not a pre-registration, and `--margin 99` at
+  scoring time would simply buy `FALSIFIED`. Out of range (outside `(0, 0.5]`) is refused, not
+  clamped.
+- **Corrupt input is refused, not measured.** Duplicate judgement ids exit 1 rather than counting
+  one opinion N times. Unknown ids and unparseable winners are skipped **with a reason**, never
+  guessed.
+
+The warm arm's only delta is the injected lessons: no gold answers, no verdicts, no outcome labels
+ever enter a work order.
+
+**When to use:** after `dz compounding` reports the replay as READY; before claiming that recall
+"works"; and any time you want the claim re-checked as the corpus grows.
+
 ### Usage estimates you can act on — `dz usage`
 
 `dz usage` estimates how much of your Claude session (5h block) and week you have spent, from local
@@ -672,7 +769,7 @@ Each pack is an npm package — click through for the **full per-skill documenta
 | [@dzhechkov/skills-book-digitizer](https://www.npmjs.com/package/@dzhechkov/skills-book-digitizer) | 8 | *dz-original* — book → installable methodology pack: `digitize-book` (orchestrator) + ingest/extract/distill/pack/kb-index + `book-brain-register` (CP6 promote → cross-project brain) + `source-brain-ingest` (repo sibling). Verified provenance, IP-safe, resumable (`dz init --select digitize-book`) ([ADR-001](https://github.com/djd1m/dz-harness-hub/blob/main/features/book-knowledge-digitizer/03_adr/001-book-to-skillpack-pipeline.md)) |
 | [@dzhechkov/skills-12factor](https://www.npmjs.com/package/@dzhechkov/skills-12factor) | 12 | *generated by the digitizer, CC BY 4.0* — The Twelve-Factor App distilled into 12 decision-moment skills (one per factor). The first PUBLIC digitized-book pack; paraphrased (shingling-gated), routing-gated (every factor carries triggers), attributed (`NOTICE`) (`dz init --select 12factor-config-in-environment,…`) |
 
-### Available Presets (13)
+### Available Presets (14)
 
 | Preset | Skills | Description |
 |--------|--------|-------------|
@@ -726,7 +823,7 @@ Get the whole set with `dz init --target claude-code --preset meta`, or pick one
 
 > **A skill and its npx toolkit are not duplicates — they're a graduation.** Several skills (e.g. `feature-adr`, `design-thinking`) exist BOTH as a skill inside a `dz` preset AND as a standalone `npx` package. The preset's SKILL.md is **fully functional on its own** (the whole methodology — modules + references — travels with it, and it auto-activates by description), and it's the only way to compile that capability to the **non-Claude platforms** (Codex/OpenCode/Hermes/OpenClaude) via `dz`. The npx package adds **project-level runtime governance** around the same skill: a slash command, governance rules, a context shard, and (for feature-adr) reward-learning + `/harvest`. So: pick the **skill/preset** for a working capability across platforms; pick the **npx toolkit** when you want it as a governed, command-driven fixture of one project.
 
-## All Commands (61)
+## All Commands (62)
 
 ```
 dz setup             --target <name> [--preset <name>] [--select id,id,...] [--skills-dir <dir>] [--memory agentdb] [--no-memory] [--no-hooks] [--install-driver] [--force]
@@ -784,6 +881,10 @@ dz discrimination-check --test <f[,f]> [--base <ref>] [--name <filter>] [--runne
 dz delivery-check --slug <slug> [--context-only] [--findings <f.json>] [--strict] [--author <model>] [--json]   # portable Step-10 Delivery Gate: the `manual` form that travels to every shell target — prints the 4-plane review brief (regressions ‖ security ‖ code-quality ‖ product-honesty) + artifact probes; --findings classifies a fed-back review into a fail-closed ready|blocked hand-off (only cross-validated BLOCKER/HIGH count) and writes features/<slug>/10_delivery_review.md; --strict exits 1 on blocked
 dz skills-verify     [--dir <project>] [--expect a,b] [--static] [--strict] [--timeout <s>] [--json]   # does .claude/skills/ actually REGISTER? --static = instant layout scan (CI-safe, no session): flags dirs that can never register; default also starts a real session and reads the authoritative system/init listing. exit 0 pass / 1 fail / 2 inconclusive — an unobservable registration is NEVER a pass
 dz compounding       [--project <dir>] [--json]   # honest learning-loop payoff report: pool write-only ratio, guard repeat-violation trajectory (rate per audit-half), cold-vs-warm replay readiness over unique untruncated prompt events, apply-leg staleness — a gate without enough data says INSUFFICIENT_DATA, never a verdict
+dz epoch-replay --mock  [--n <N>] [--effect <-1..1>] [--tie-rate <0..1>] [--seed <N>] [--slice <name>] [--margin <0..0.5>] [--json]   # $0 synthetic run through the REAL verdict math; labelled SYNTHETIC, same seed = byte-identical
+dz epoch-replay --emit  [--project <dir>] [--limit <N>] [--seed <N>] [--margin <0..0.5>] [--out <file>] [--json]   # cold-vs-warm work order: replayable instances + PRE-REGISTERED blind A/B assignment + the PRE-REGISTERED non-superiority margin + a sha256 integrity digest + emittedAt/corpus fingerprint (raw prompts — defaults into the git-ignored .dz/epoch-replay/)
+dz epoch-replay --judge <filled-work-order.json> [--out <file>] [--json]   # blind judge prompts from the filled plans — the file carries {id, prompt} ONLY (no assignment, no arm names); refuses an order whose digest or seed-derived assignment does not check out; half-pairs skipped WITH A REASON, on stdout
+dz epoch-replay --score <judgments.json> --work-order <file> [--slice <name>] [--json]   # un-blind against the VERIFIED pre-registered assignment; ONE paired binomial over DECISIVE pairs (ties excluded, reported) → SUPPORTED only when the lift interval (2p−1) lies entirely above zero; FALSIFIED only on harm or a passed non-superiority test (lift upper bound below the margin PRE-REGISTERED in the work order, default 0.05, at 10+ decisive pairs); else INCONCLUSIVE (min 5 decisive pairs). Refuses a forged work order, a --margin flag, or duplicate judgement ids; the verdict is data, not an exit code
 dz score             --slug <feature> [--project <dir>] [--json]   # process scorecard for ONE feature-adr run, from its artifacts: ADR confirmation, discrimination proof, cross-model QE grade, live verification, README-first, learning loop, amendments — DESCRIPTIVE-ONLY (a low score exits 0); evidence lines are shown so the reader judges the heuristics
 dz backlog <sub>     add "<idea>" | list | show <id> | goals [--validate] | roulette [--seed n] [--commit <id>] | enrich <id> | jira <id> | harmonize [--apply]   # brain-backed idea backlog: capture an idea → semantic dedup against past ideas/features via the REUSED agentdb vector engine (DUPLICATE≥0.92 / RELATED / NEW) + GoalMap alignment ("map+compass") → weighted seeded roulette picks one to work on → enrich STAGES an idea2prd hand-off → jira writes an auditable outbox via a configurable MCP adapter seam (jira-mcp|copilot-mcp|none). No 2nd vector store; without agentdb it degrades to exact-text dedup (honest)
 dz sign --init --out <path>  |  --pack <dir> --key <path>   # --init: generate the Ed25519 keypair (private OUTSIDE the repo, prints the public key for keys/dz.pub); else sign a pack's manifest + CycloneDX SBOM

package/dist/cli.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"cli.d.ts","sourceRoot":"","sources":["../src/cli.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAkUH,2EAA2E;AAC3E,MAAM,WAAW,KAAK;IACpB,QAAQ,CAAC,GAAG,CAAC,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,CAAC;IACxC;;;;OAIG;IACH,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;OAKG;IACH,QAAQ,CAAC,aAAa,CAAC,EAAE,iBAAiB,CAAC;CAC5C;AAED,yFAAyF;AACzF,MAAM,MAAM,iBAAiB,GAAG,CAC9B,GAAG,EAAE,MAAM,EACX,IAAI,EAAE;IAAE,QAAQ,CAAC,GAAG,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAA;CAAE,KACvD;IAAE,QAAQ,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,EAAE,OAAO,CAAA;CAAE,CAAC;AAg2M9E,wBAAsB,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,GAAE,KAAU,GAAG,OAAO,CAAC,MAAM,CAAC,CA0J5E"}
+{"version":3,"file":"cli.d.ts","sourceRoot":"","sources":["../src/cli.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAwVH,2EAA2E;AAC3E,MAAM,WAAW,KAAK;IACpB,QAAQ,CAAC,GAAG,CAAC,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,CAAC;IACxC;;;;OAIG;IACH,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;OAKG;IACH,QAAQ,CAAC,aAAa,CAAC,EAAE,iBAAiB,CAAC;CAC5C;AAED,yFAAyF;AACzF,MAAM,MAAM,iBAAiB,GAAG,CAC9B,GAAG,EAAE,MAAM,EACX,IAAI,EAAE;IAAE,QAAQ,CAAC,GAAG,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAA;CAAE,KACvD;IAAE,QAAQ,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,EAAE,OAAO,CAAA;CAAE,CAAC;AAopN9E,wBAAsB,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,GAAE,KAAU,GAAG,OAAO,CAAC,MAAM,CAAC,CA4J5E"}