open-research-protocol 0.4.26 → 0.4.28

package/AGENT_INTEGRATION.md

@@ -40,20 +40,24 @@ If the agent only remembers one ORP loop, it should be this:
    ```bash
    orp status --json
    ```
-3. resolve the right secret
+3. classify dirty worktree state before expansion
+   ```bash
+   orp hygiene --json
+   ```
+4. resolve the right secret
    ```bash
    orp secrets ensure --alias <alias> --provider <provider> --current-project --json
    ```
-4. inspect the current frontier
+5. inspect the current frontier
    ```bash
    orp frontier state --json
    ```
-5. if the work feels confusing or too large, break it down before moving
+6. if the work feels confusing or too large, break it down before moving
    ```bash
    orp mode breakdown granular-breakdown --json
    ```
-6. do the next honest move
-7. checkpoint it honestly
+7. do the next honest move
+8. checkpoint it honestly
    ```bash
    orp checkpoint create -m "checkpoint note" --json
    ```
@@ -62,6 +66,7 @@ That is the ORP rhythm in one line:
 
 - recover continuity
 - inspect repo safety
+- classify dirty state and stop if anything is unowned
 - resolve access
 - inspect context
 - break down complexity when comprehension would help
@@ -98,6 +103,11 @@ artifact paths (code/data/proofs/logs/papers).
 - Treat **failed paths** as assets: record dead ends as a `Failed Path Record` with the blocking reason/counterexample and a
   next hook.
 - Resolve disputes by **verification or downgrade**, not argument.
+- Run `orp hygiene --json` before long delegation, after material writeback, before API/remote/paid compute, and when dirty
+  state grows unexpectedly.
+- Stop long-running expansion while hygiene reports `dirty_unclassified`; classify, refresh generated surfaces, canonicalize
+  useful scratch, or write a blocker before continuing.
+- Hygiene is non-destructive: never reset, checkout, or delete files merely to hide dirty state.
 
 ### How to work in an ORP repo
 

package/CHANGELOG.md

@@ -6,6 +6,62 @@ There was no prior in-repo changelog file, so the first formal entry starts
 with the currently shipped `v0.4.4` release and summarizes the full release
 delta reflected in this repo.
 
+## v0.4.28 - 2026-04-22
+
+This release tightens the ORP project-startup and research-spend loops, then
+refreshes the public README presentation with a mascot-led terminal animation.
+
+### Added
+
+- Added `orp init --project-startup` support for a fuller new-project ritual:
+  private GitHub remote setup, `main` workspace ledger tracking, Codex session
+  capture, bootstrap command storage, and optional Clawdad delegation setup.
+- Added local research spend guardrails for provider-backed research lanes:
+  per-secret daily spend cap metadata, dashboard limit notes, local spend
+  ledger records, and OpenAI preflight blocking when a lane would exceed the
+  configured cap.
+- Added a mascot-led ORP terminal animation that explains workspace ledgers,
+  secrets, research lanes, governance checkpoints, breakdown mode, and
+  agent-readable handoffs in simple language.
+
+### Changed
+
+- Promoted the refreshed terminal animation to the top of the README with a
+  short greeting and updated the walkthrough copy to match the current ORP
+  command surface.
+- Simplified generated animation scenes from a crowded command survey into a
+  cleaner seven-scene story with an expressive mascot and real CLI commands.
+
+## v0.4.27 - 2026-04-18
+
+This release adds a staged OpenAI research profile and default-on worktree
+hygiene for agent loops. ORP-initialized repos now teach agents when to stop,
+classify dirty paths, refresh generated surfaces, canonicalize scratch, or
+write a blocker instead of letting unowned worktree state become invisible.
+
+### Added
+
+- Added the built-in `deep-think-web-think-deep` research profile: Deep
+  Research, high-reasoning think, think plus web synthesis, high-reasoning
+  think, and a final Deep Research pass.
+- Added profile listing/show commands and MCP exposure so Codex-like clients
+  can discover staged research templates and fill project-specific fields.
+- Added `orp hygiene --json` and the `orp workspace hygiene --json` alias for
+  non-destructive worktree classification with dirty counts, categories,
+  unclassified and scratch counts, required action, and recommended next checks.
+- Added `orp/hygiene-policy.json` scaffolding during `orp init` so each project
+  can customize canonical surfaces, artifact roots, scratch paths, and
+  classification rules.
+
+### Changed
+
+- Updated ORP agent docs, generated handoffs, agent policy, project context,
+  home/about metadata, and workspace help to include the hygiene stop rule:
+  no long-running expansion while dirty paths are unclassified.
+- Research runs now persist generated lane prompts and can pass prior lane
+  outputs into later staged prompts while skipping live later-stage calls when
+  prerequisites are incomplete.
+
 ## v0.4.26 - 2026-04-17
 
 This release adds ORP-native project context and OpenAI research-loop support,

package/README.md

@@ -9,6 +9,12 @@ Maintained by SproutSeeds. Research stewardship: Fractal Research Group ([frg.ea
 [![license](https://img.shields.io/npm/l/open-research-protocol?color=111111&label=license)](./LICENSE)
 [![node](https://img.shields.io/node/v/open-research-protocol?color=111111&label=node)](https://www.npmjs.com/package/open-research-protocol)
 
+<p align="center">
+  <img src="https://raw.githubusercontent.com/SproutSeeds/orp/main/assets/terminal-demo.gif" alt="open-research-protocol mascot terminal demo">
+</p>
+
+<p align="center"><strong>Hello, researcher.</strong> Keep the loop open, recoverable, and kind.</p>
+
 > Agent-first CLI for workspace ledgers, operating agendas, local governance, secrets, scheduling, packets, reports, and research workflows.
 
 **Links:** [GitHub](https://github.com/SproutSeeds/orp) · [npm](https://www.npmjs.com/package/open-research-protocol) · [frg.earth](https://frg.earth)
@@ -38,24 +44,21 @@ checkpoint layer. See
 
 ## Watch It Run
 
-A short ORP command-family walkthrough:
-
-![open-research-protocol terminal demo](https://raw.githubusercontent.com/SproutSeeds/orp/main/assets/terminal-demo.gif)
+The current animation introduces a small protocol mascot for the ORP message:
+context before claims, saved threads before crashes, hidden keys before exposed
+secrets, dry-run research before spend, checkpoints before handoffs, and
+breakdowns before overwhelm. The terminal still uses real ORP command surfaces
+rather than a fabricated UI.
 
-The current animation intentionally uses the same human-facing command surfaces ORP prints in the terminal. It is not a fabricated UI layer. It currently shows ORP from multiple angles:
+It currently shows ORP from seven angles:
 
 - `home` for discovery and next actions
-- `hosted` for ideas, workspaces, runners, and the control plane
-- `secrets` for create-or-reuse plus local Keychain sync
-- `workspace` for the hosted + local saved workspace ledger and recovery commands
-- `agenda` for Codex-ranked actions and suggestions across current work
-- `connections` for service accounts, data sources, deploy targets, and research destinations
-- `opportunities` for contests, programs, grants, and other tracked openings
-- `schedule` for recurring Codex jobs
+- `workspace` for grouped project/session ledgers and recovery commands
+- `secrets` for local reusable credentials and spend policy metadata
+- `research` for dry-run-first research lanes with an OpenAI-ready provider path
 - `governance` for local checkpoints and repo safety
-- `planning` for frontier, compute, packet, and report surfaces
-- `synthesis` for discover, exchange, collaborate, and YouTube ingestion
-- `mode` for optional perspective-shift nudges
+- `breakdown` for broad-to-atomic comprehension loops
+- `publish` for agent-readable reports, handoffs, and open research messaging
 
 Maintainer asset generation:
 
@@ -451,6 +454,7 @@ Local desk and automation:
 orp workspace create mac-main --machine-label "Mac Studio"
 orp workspace list
 orp workspace tabs main
+orp init --project-startup --github-repo owner/repo --current-codex
 orp workspace add-tab main --path /absolute/path/to/project --remote-url git@github.com:org/project.git --bootstrap-command "npm install" --resume-command "codex resume <id>"
 orp workspace add-tab main --path /absolute/path/to/project --title "second active thread" --resume-tool claude --resume-session-id <id> --append
 orp workspace remove-tab main --path /absolute/path/to/project
@@ -570,6 +574,7 @@ Stable artifact paths:
 1. Copy this folder into a new project directory.
 2. If you keep projects under one umbrella directory, run `orp agents root set /absolute/path/to/projects` once from anywhere.
 3. Run `orp init` immediately so the repo starts ORP-governed, scaffolds or updates `AGENTS.md` and `CLAUDE.md`, and creates `orp/project.json`.
+   For the fuller new-project ritual, run `orp init --project-startup --github-repo owner/repo --current-codex`; ORP will create a private GitHub remote through `gh`, save the path/session in workspace `main`, and register Clawdad delegation when `clawdad` is installed. Use `--startup-dry-run --json` first when you want to inspect the planned external commands.
 4. Edit `PROTOCOL.md` to define your canonical paths and claim labels.
 5. Run `orp project refresh --json` whenever the directory gains new roadmap, spec, docs, manifest, or command-surface files.
 6. Run `orp agents audit` to confirm the repo-level agent files are aligned and still preserving human notes.
@@ -769,3 +774,7 @@ python3 scripts/orp-pack-render.py --pack packs/erdos-open-problems --template s
 python3 scripts/orp-pack-render.py --pack packs/erdos-open-problems --template erdos_problems_catalog_sync \
   --var TARGET_REPO_ROOT=/path/to/repo --var ORP_REPO_ROOT=/path/to/orp --out /path/to/repo/orp.erdos-catalog-sync.yml
 ```
+
+## Support
+
+Everything here is released for public use. If ORP saved you time or you want to keep the work moving, you can [support public FRG releases](https://frg.earth/support?utm_source=readme&utm_medium=repo&utm_campaign=public_work_support&package=open-research-protocol).

package/bin/orp.js

@@ -36,24 +36,14 @@ async function runWorkspace(args) {
   process.exit(code == null ? 0 : code);
 }
 
-async function main() {
-  if (argv[0] === "compute") {
-    await runCompute(argv.slice(1));
-    return;
-  }
-  if (argv[0] === "workspace") {
-    await runWorkspace(argv.slice(1));
-    return;
-  }
-
-  const captureOutput = isTopLevelHelp(argv);
+function runPythonCli(args, { captureOutput }) {
   let lastErr = null;
 
   for (const py of candidates) {
-    const args = py === "py" ? ["-3", cliPath, ...argv] : [cliPath, ...argv];
+    const pyArgs = py === "py" ? ["-3", cliPath, ...args] : [cliPath, ...args];
     const result = spawnSync(
       py,
-      args,
+      pyArgs,
       captureOutput
         ? { encoding: "utf8" }
         : { stdio: "inherit" },
@@ -68,7 +58,7 @@ async function main() {
           process.stderr.write(result.stderr);
         }
         if (result.status === 0) {
-          process.stdout.write("\nAdditional wrapper surface:\n  orp compute -h\n  orp workspace tabs -h\n");
+          process.stdout.write("\nAdditional wrapper surface:\n  orp compute -h\n  orp workspace tabs -h\n  orp workspace hygiene --json\n");
         }
       }
       process.exit(result.status == null ? 1 : result.status);
@@ -88,6 +78,23 @@ async function main() {
   process.exit(1);
 }
 
+async function main() {
+  if (argv[0] === "compute") {
+    await runCompute(argv.slice(1));
+    return;
+  }
+  if (argv[0] === "workspace" && argv[1] === "hygiene") {
+    runPythonCli(["hygiene", ...argv.slice(2)], { captureOutput: false });
+    return;
+  }
+  if (argv[0] === "workspace") {
+    await runWorkspace(argv.slice(1));
+    return;
+  }
+
+  runPythonCli(argv, { captureOutput: isTopLevelHelp(argv) });
+}
+
 main().catch((error) => {
   console.error(String(error && error.stack ? error.stack : error));
   process.exit(1);