ultra-builder-pro-cli 0.25.0 → 0.26.0

package/skills/ultra-doctor/SKILL.md

@@ -1,41 +0,0 @@
----
-name: ultra-doctor
-description: Diagnose and mechanically recover Ultra schema, projection, session, archive, hook, and installed-asset faults. Use when authority is degraded, contradictory, or unavailable.
----
-
-# Diagnose before repair
-
-Doctor owns deterministic health and supported recovery. It cannot choose product
-scope, invent evidence, accept a baseline, resolve a user decision, or declare
-semantic work complete.
-
-## Diagnose
-
-Call `ultra.doctor { repair: false }` and inspect:
-
-- SQLite integrity, schema, backups, WAL/SHM, and migration state;
-- artifact ownership, digest freshness, edges, orphans, and duplicate authority;
-- team-checkpoint ancestry and real concurrent record conflicts;
-- projection jobs, sessions, leases, worktrees, and recovery journals;
-- installed plugin assets, MCP startup, and hook paths.
-
-An expected workflow pause, editable draft, semantic warning, or awaiting owner
-decision is not corruption.
-
-## Repair
-
-With explicit repair authority, call `ultra.doctor { repair: true }`. It may apply
-backup-first schema migration, regenerate local projections, recover supported
-journals, reconcile orphan sessions, and repair installed mechanical assets.
-
-It may not manufacture semantic evidence, import or publish a team checkpoint, replace
-a healthy baseline, resolve decisions, edit application code, or force a draft to
-accepted. Use `ultra.sync` for reviewed checkpoint import/publish. Doctor never changes
-semantic checkpoint acceptance or Change intent.
-
-Preserve corrupt DB/WAL/SHM and dirty worktrees. Never patch plugin cache files by
-hand; reinstall through `ubp` and verify the installed manifest and hook targets.
-
-Rerun doctor read-only after repair. Report health, exact failed checks, backups,
-repairs, preserved recovery paths, and remaining owner or semantic work. Do not invoke
-another capability automatically.

package/skills/ultra-plan/references/semantic-preflight.md

@@ -1,20 +0,0 @@
-# Semantic planning preflight
-
-Before task decomposition, read the normalized Change Contract and the current
-change-bound research records.
-
-1. Resolve every blocking `unresolved_decision` or return to `ultra-change`.
-2. When research is recorded, verify one completed run has the same mode and selected
-   step set. Re-run stale or missing evidence through `ultra-research`.
-3. Build a coverage ledger from Change acceptance ids to task acceptance ids.
-4. Bind every task to an accepted id, semantic record id, semantic source ref, or real
-   Markdown anchor through `trace_to`.
-5. Check that every task reaches a public consumer and owns its error, documentation,
-   verification, and recovery obligations.
-6. Validate dependencies. A `quick` profile normally has one vertical task, but the
-   model may use the smallest evidence-backed graph that satisfies the accepted Change.
-
-Treat the MCP result as a persistence receipt plus typed diagnostics. Structural,
-digest, path, concurrency, and exact topology conflicts must be repaired. The model
-owns semantic completeness, acceptance coverage, research sufficiency, and whether a
-warning requires another planning revision before execution.

package/skills/ultra-verify/SKILL.md

@@ -1,46 +0,0 @@
----
-name: ultra-verify
-description: Run independent two-model verification with the current host as primary and one installed read-only advisor, then verify and synthesize both evidence sets. Use only when the user explicitly requests cross-model verification.
----
-
-# Run independent cross-model verification
-
-Keep the current host responsible for scope, evidence, edits, verification, and the
-final answer. Use one installed collaboration companion that invokes a different CLI;
-never recurse into the current host or treat advisor output as authority.
-
-## Modes
-
-- `decision`: one consequential architecture or product choice;
-- `diagnose`: independent root-cause hypotheses;
-- `audit`: evidence-backed findings over a bounded scope;
-- `estimate`: an estimate with explicit assumptions and uncertainty.
-
-## Workflow
-
-1. Define the workspace, question, evidence standard, and response shape. Confirm the
-   selected advisor CLI and authentication. Exclude secrets and unrelated files.
-2. Create `.ultra/.runtime/collab/<session-id>/` and write the current host's independent,
-   evidence-backed analysis to `host-analysis.md` before reading advisor output.
-   Treat the directory as working scratch, not Ultra authority.
-3. Follow the installed collaboration companion's read-only invocation contract. Give
-   the advisor the same bounded question and evidence, without the primary conclusion
-   when independence matters. Store its result as `advisor-output.md` and diagnostics
-   as `advisor-error.log`.
-4. Run `scripts/verify_wait.py <session-path> --advisor advisor --output
-   advisor-output.md` from this skill directory. Use a yielded shell session and poll
-   in bounded intervals; do not hold one blocking tool call longer than one minute.
-5. Read advisor output only after the waiter reports a complete, non-empty file.
-6. Verify consequential claims against the current checkout, tests, runtime, or
-   primary documentation. Explain scope, version, evidence, and assumption differences
-   before resolving disagreement.
-7. Write `metadata.json` and `synthesis.md`, then return one host-owned conclusion.
-   Promote only verified conclusions into the invoking DB-bound workflow artifact or
-   report; files under `.ultra/.runtime/collab/` remain non-authoritative.
-
-Read `references/cross-verify-modes.md` for mode-specific evidence and
-`references/evidence-status.md` when the synthesis needs an evidence status. Model agreement
-never overrides failing tests or authoritative runtime evidence.
-
-Advisor failure degrades to the primary analysis with a single-source warning. It
-never blocks the user's underlying task.

package/skills/ultra-verify/evals/evals.json

@@ -1,46 +0,0 @@
-{
-  "skill_name": "ultra-verify",
-  "evals": [
-    {
-      "id": "explicit-decision",
-      "prompt": "Run independent cross-model verification on the database choice, with the current host writing its view before the advisor.",
-      "should_trigger": true,
-      "assertions": [
-        "Writes the primary analysis before reading advisor output",
-        "Launches the advisor in a read-only sandbox",
-        "Uses a bounded session directory and completion waiter",
-        "Verifies consequential claims against authoritative evidence",
-        "Returns one host-owned synthesis"
-      ]
-    },
-    {
-      "id": "explicit-diagnosis",
-      "prompt": "Use two independent models to diagnose the intermittent 500 response and reconcile their hypotheses with discriminating checks.",
-      "should_trigger": true,
-      "assertions": [
-        "Keeps both initial hypotheses independent",
-        "Deduplicates by root cause after both outputs complete",
-        "Orders verification by evidence and diagnostic value",
-        "Does not decide by model vote"
-      ]
-    },
-    {
-      "id": "ordinary-analysis-negative",
-      "prompt": "Should this service use PostgreSQL or MongoDB?",
-      "should_trigger": false,
-      "assertions": [
-        "Answers with the ordinary analysis workflow",
-        "Does not launch an external advisor without explicit cross-model intent"
-      ]
-    },
-    {
-      "id": "ordinary-review-negative",
-      "prompt": "Review these changes before I commit.",
-      "should_trigger": false,
-      "assertions": [
-        "Uses the standard review workflow",
-        "Does not substitute cross-model verification for native review"
-      ]
-    }
-  ]
-}

package/skills/ultra-verify/references/cross-verify-modes.md

@@ -1,28 +0,0 @@
-# Ultra Verify Modes
-
-All four modes compare an independently written primary analysis with one read-only external
-advisor. Agreement is useful corroboration, not proof; evidence decides the final result.
-
-## 1. Decision (`decision`)
-
-Give both analyses the same decision context, constraints, and options. Compare recommendation,
-trade-offs, risks, and assumptions. When they differ, identify the assumption or evidence that
-caused the split and resolve it before recommending an option.
-
-## 2. Diagnose (`diagnose`)
-
-Provide symptoms, exact errors, relevant code, and recent changes. Each analysis should rank its
-root-cause hypotheses and provide discriminating checks. Merge duplicate hypotheses, retain useful
-unique ones, and order investigation by evidence strength and verification cost.
-
-## 3. Audit (`audit`)
-
-Use the same code scope and severity model for both analyses. Deduplicate findings by root cause,
-verify every location against the current checkout, and retain a single-model finding when source
-evidence confirms it. Never derive severity from model agreement alone.
-
-## 4. Estimate (`estimate`)
-
-Require a breakdown, assumptions, dependencies, and risk range from both analyses. Explain large
-differences by locating mismatched scope or assumptions. Return a range supported by the reconciled
-work breakdown rather than averaging estimates mechanically.

package/skills/ultra-verify/references/evidence-status.md

@@ -1,21 +0,0 @@
-# Evidence Status
-
-Cross-model agreement is a signal, not an authority. Classify the synthesis only after checking
-consequential claims against source code, tests, runtime output, or primary documentation.
-
-## Levels
-
-- **Verified agreement**: both analyses agree and the consequential claims have authoritative
-  supporting evidence.
-- **Resolved dissent**: the analyses differ, but current evidence supports one position and explains
-  the disagreement.
-- **Unresolved**: available evidence cannot distinguish the positions or key assumptions remain
-  untested.
-- **Single source**: the advisor failed or returned no usable output; no cross-model corroboration is
-  available.
-
-## Reporting
-
-Record which claims were verified, the evidence used, useful dissent, unsupported assertions, and
-remaining uncertainty. Model agreement never upgrades a claim contradicted by tests or runtime
-evidence, and a uniquely reported finding remains valid when independently verified.

package/skills/ultra-verify/scripts/verify_wait.py

@@ -1,94 +0,0 @@
-#!/usr/bin/env python3
-"""Wait for one named advisor output file to become non-empty and stable."""
-
-import argparse
-import json
-import re
-import sys
-import time
-from pathlib import Path
-
-POLL_INTERVAL = 3
-DEFAULT_TIMEOUT = 1200
-SAFE_ADVISOR = re.compile(r"^[a-zA-Z0-9_-]+$")
-
-
-def _file_size(path: Path) -> int:
-    try:
-        return path.stat().st_size
-    except (FileNotFoundError, OSError):
-        return -1
-
-
-def _safe_output(value: str) -> Path:
-    result = Path(value)
-    if result.is_absolute() or len(result.parts) != 1 or result.name in {"", ".", ".."}:
-        raise argparse.ArgumentTypeError("--output must be one file name inside the session directory")
-    return result
-
-
-def _arguments():
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument("session_path", type=Path)
-    parser.add_argument("--advisor", default="advisor")
-    parser.add_argument("--output", type=_safe_output, default=Path("advisor-output.md"))
-    parser.add_argument("--timeout", type=int, default=DEFAULT_TIMEOUT)
-    args = parser.parse_args()
-    if not SAFE_ADVISOR.fullmatch(args.advisor):
-        parser.error("--advisor must use letters, numbers, underscore, or hyphen")
-    if args.timeout < 0:
-        parser.error("--timeout must be non-negative")
-    if not args.session_path.is_dir():
-        parser.error(f"session directory not found: {args.session_path}")
-    return args
-
-
-def _status(session_path: Path, advisor: str, output_name: Path) -> dict:
-    output = session_path / output_name
-    if _file_size(output) > 0:
-        return {"name": advisor, "status": "complete", "file": str(output)}
-    return {"name": advisor, "status": "pending", "file": None}
-
-
-def _timeout_status(session_path: Path, advisor: str, output_name: Path) -> dict:
-    output = session_path / output_name
-    error = session_path / f"{advisor}-error.log"
-    output_size = _file_size(output)
-    if output_size > 0:
-        return {"name": advisor, "status": "complete", "file": str(output)}
-    if _file_size(error) > 0:
-        return {"name": advisor, "status": "failed", "file": str(error)}
-    if output_size == 0:
-        return {"name": advisor, "status": "empty", "file": str(output)}
-    return {"name": advisor, "status": "pending", "file": None}
-
-
-def main() -> None:
-    args = _arguments()
-    output = args.session_path / args.output
-    deadline = time.monotonic() + args.timeout
-    previous_size = _file_size(output)
-    while time.monotonic() < deadline:
-        current_size = _file_size(output)
-        advisor = _status(args.session_path, args.advisor, args.output)
-        if advisor["status"] == "complete" and current_size == previous_size:
-            elapsed = int(args.timeout - (deadline - time.monotonic()))
-            print(json.dumps({
-                "status": "complete", "advisor": advisor, "elapsed_seconds": elapsed,
-            }))
-            return
-        state = "stabilizing" if advisor["status"] == "complete" else "waiting"
-        remaining = max(0, int(deadline - time.monotonic()))
-        sys.stderr.write(f"\r  [0/1] {args.advisor}:{state} ({remaining}s remaining)  ")
-        sys.stderr.flush()
-        previous_size = current_size
-        time.sleep(POLL_INTERVAL)
-
-    advisor = _timeout_status(args.session_path, args.advisor, args.output)
-    print(json.dumps({
-        "status": "timeout", "advisor": advisor, "elapsed_seconds": args.timeout,
-    }))
-
-
-if __name__ == "__main__":
-    main()

package/spec/cli-protocol.md

@@ -1,102 +0,0 @@
-# `ultra-tools` CLI protocol
-
-`ultra-tools` is the maintenance and degraded-mode client for the same seven-tool
-kernel exposed through MCP. It does not publish the retired lifecycle families as
-model-facing tools and it does not contain a second semantic workflow engine.
-
-Authority boundary: [`docs/DECISIONS.md`](../docs/DECISIONS.md).
-
-## Invocation
-
-```text
-ultra-tools ultra <verb> [--json '<object>']
-```
-
-The supported verbs map exactly to the public MCP contract. JSON input uses the
-corresponding `input_schema` in `spec/mcp-tools.yaml`. Large inputs may use
-`--json-file <path>`.
-
-Maintenance-only commands such as installation diagnostics, explicit backup
-restore, schema migration, and runtime inspection remain available under their
-documented non-MCP command groups. They are operator surfaces, not hidden model
-tools.
-
-## Output
-
-The final stdout line is always one JSON envelope:
-
-```json
-{ "ok": true, "data": {} }
-```
-
-or:
-
-```json
-{
-  "ok": false,
-  "error": {
-    "code": "ERROR_CODE",
-    "message": "What failed",
-    "retriable": false
-  }
-}
-```
-
-Human-readable progress may precede the envelope. Structured logs go to stderr.
-Exit code `0` means success, `1` means invalid user input, `2` means a mechanical
-runtime or I/O failure, `3` means a lease conflict, `4` means a schema mismatch,
-and `5` means timeout.
-
-## Public tool mapping
-
-The table is checked against `spec/mcp-tools.yaml` at gate time.
-
-| MCP tool | CLI subcommand | Phase | Writer |
-|---|---|---:|---|
-| `ultra.context` | `ultra context` | 24 | mcp |
-| `ultra.record` | `ultra record` | 24 | mcp |
-| `ultra.checkpoint` | `ultra checkpoint` | 24 | mcp |
-| `ultra.sync` | `ultra sync` | 24 | mcp |
-| `ultra.session` | `ultra session` | 24 | mcp |
-| `ultra.archive` | `ultra archive` | 24 | mcp |
-| `ultra.doctor` | `ultra doctor` | 24 | mcp |
-
-The retired `task.*`, `change.*`, `decision.*`, `workflow.*`, `artifact.*`,
-`plan.*`, `session.*`, `baseline.*`, and `system.doctor` names are historical
-migration vocabulary only. They are neither returned by `tools/list` nor accepted
-by the MCP call handler.
-
-## Behavioral boundary
-
-- `ultra.context` is read-only and returns one canonical Context Envelope.
-- `ultra.record` appends typed facts or revises mutable drafts. Semantic
-  diagnostics are returned as data.
-- `ultra.checkpoint` attempts an immutable stage checkpoint. An unsuccessful
-  attempt remains a revisable draft.
-- `ultra.sync` imports, publishes, inspects, or migrates the Git team ledger.
-- `ultra.session` owns only leases, Worker Packets, heartbeats, and terminal
-  session transitions.
-- `ultra.archive` is the recoverable filesystem and database commit boundary.
-- `ultra.doctor` reports mechanical health and performs only explicit,
-  backup-first deterministic repairs.
-
-Skills own adaptive workflow prose and host-native user interaction. Hooks observe
-lifecycle events and inject bounded context. Neither surface may silently write
-semantic authority.
-
-## Orchestrator
-
-`ubp-orchestrator` consumes an accepted Plan checkpoint and a task-specific
-Worker Packet. It may schedule independent tasks but may not infer missing owner
-decisions, rewrite a Change contract, or bypass a rejected checkpoint.
-
-Every worker result must echo the exact `packet_digest`. A zero exit code is
-execution evidence, not automatic semantic completion; the responsible Skill
-records the outcome and attempts the appropriate checkpoint.
-
-## Versioning
-
-The CLI follows the `version` in `spec/mcp-tools.yaml`. Public tool removal,
-renaming, or incompatible envelope changes require a major contract revision and
-a migration note. Adding an optional field or a new typed record action requires
-a minor contract revision.