oacp-cli 0.2.1__tar.gz → 0.2.2__tar.gz

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/CHANGELOG.md

@@ -5,6 +5,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.2] - 2026-04-17
+
+### Added
+
+- `oacp watch` — monitor-friendly inbox/outbox watcher with structured output and partial-progress preservation on errors
+
+### Changed
+
+- Docs: refreshed cross-runtime capability matrix and public-skill parity framing
+
 ## [0.2.1] - 2026-03-22
 
 ### Fixed
@@ -100,6 +110,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Checkout step in github-release workflow job (#19)
 - Pre-release audit fixes: SHA-pinned actions, dangling doc refs (#15, #16)
 
+[0.2.2]: https://github.com/kiloloop/oacp/compare/v0.2.1...v0.2.2
 [0.2.1]: https://github.com/kiloloop/oacp/compare/v0.2.0...v0.2.1
 [0.2.0]: https://github.com/kiloloop/oacp/compare/v0.1.9...v0.2.0
 [0.1.9]: https://github.com/kiloloop/oacp/compare/v0.1.2...v0.1.9

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oacp-cli
-Version: 0.2.1
+Version: 0.2.2
 Summary: Open Agent Coordination Protocol CLI for file-based multi-agent workflows
 Project-URL: Homepage, https://github.com/kiloloop/oacp
 Project-URL: Repository, https://github.com/kiloloop/oacp
@@ -54,6 +54,7 @@ When running inside a configured agent runtime, `--from` can be omitted — OACP
 - **Inbox/outbox messaging** — async YAML messages with threading, broadcast, and expiry
 - **Structured review loop** — severity-graded findings, quality gates, multi-round review
 - **Inbox CLI** — `oacp inbox` lists pending messages across agents with table or `--json` output
+- **Watch CLI** — `oacp watch` emits inbox delta events for Claude Monitor or shell loops
 - **Durable shared memory** — project facts, decisions, and known debt with active/archive split
 - **Agent safety defaults** — baseline rules for git, credentials, and scope discipline
 - **Runtime-agnostic** — works with any runtime that reads/writes files
@@ -150,6 +151,7 @@ uv tool install .
 | `oacp setup` | Generate runtime-specific config files (Claude, Codex, etc.) |
 | `oacp send` | Send a protocol-compliant inbox message (`--from` auto-inferred) |
 | `oacp inbox` | List pending messages across agents (table or `--json`) |
+| `oacp watch` | Emit inbox delta events for one agent across selected projects |
 | `oacp memory` | Archive or restore project memory files |
 | `oacp agent` | Manage global agent profiles (`init`, `show`, `list`) |
 | `oacp org-memory` | Initialize org-level memory at `$OACP_HOME/org-memory/` |
@@ -163,6 +165,8 @@ uv tool install .
 
 **`oacp send`**: `--in-reply-to`, `--expires`, `--body-file`, `--channel`, `--dry-run`, `--json`, `--quiet`
 
+**`oacp watch`**: `--agent`, repeatable `--project`, `--all-projects`, `--json`
+
 **`oacp doctor`**: `--fix` (auto-fix safe issues), `--json`, `-o/--output`
 
 **`oacp memory`**: `oacp memory archive <project> <file>`, `oacp memory restore <project> <file>`

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/README.md

@@ -28,6 +28,7 @@ When running inside a configured agent runtime, `--from` can be omitted — OACP
 - **Inbox/outbox messaging** — async YAML messages with threading, broadcast, and expiry
 - **Structured review loop** — severity-graded findings, quality gates, multi-round review
 - **Inbox CLI** — `oacp inbox` lists pending messages across agents with table or `--json` output
+- **Watch CLI** — `oacp watch` emits inbox delta events for Claude Monitor or shell loops
 - **Durable shared memory** — project facts, decisions, and known debt with active/archive split
 - **Agent safety defaults** — baseline rules for git, credentials, and scope discipline
 - **Runtime-agnostic** — works with any runtime that reads/writes files
@@ -124,6 +125,7 @@ uv tool install .
 | `oacp setup` | Generate runtime-specific config files (Claude, Codex, etc.) |
 | `oacp send` | Send a protocol-compliant inbox message (`--from` auto-inferred) |
 | `oacp inbox` | List pending messages across agents (table or `--json`) |
+| `oacp watch` | Emit inbox delta events for one agent across selected projects |
 | `oacp memory` | Archive or restore project memory files |
 | `oacp agent` | Manage global agent profiles (`init`, `show`, `list`) |
 | `oacp org-memory` | Initialize org-level memory at `$OACP_HOME/org-memory/` |
@@ -137,6 +139,8 @@ uv tool install .
 
 **`oacp send`**: `--in-reply-to`, `--expires`, `--body-file`, `--channel`, `--dry-run`, `--json`, `--quiet`
 
+**`oacp watch`**: `--agent`, repeatable `--project`, `--all-projects`, `--json`
+
 **`oacp doctor`**: `--fix` (auto-fix safe issues), `--json`, `-o/--output`
 
 **`oacp memory`**: `oacp memory archive <project> <file>`, `oacp memory restore <project> <file>`

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/docs/guides/runtime_capability_matrix.md

@@ -1,8 +1,10 @@
 # Cross-Runtime Parity Matrix
 
-**Date**: 2026-03-16
+**Date**: 2026-04-17
 
-This is a capability comparison across 3 agent runtimes (Claude Code, Codex, Gemini), compiled from each runtime's self-report. Use this as a reference when deciding which agent to assign for a given task.
+This is a capability comparison across 3 agent runtimes (Claude Code, Codex, Gemini), compiled from each runtime's self-report and current runtime changelogs. Use this as a reference when deciding which agent to assign for a given task.
+
+Codex was last checked against the official Codex changelog entries for app update `26.415` (2026-04-16) and `Codex CLI 0.121.0` (2026-04-15).
 
 ---
 
@@ -13,15 +15,15 @@ This is a capability comparison across 3 agent runtimes (Claude Code, Codex, Gem
 | Spawn background tasks | Yes — Task tool + Bash `run_in_background`                                 | Yes — shell background processes                                                               | Yes — `run_command` async mode                                        |
 | Spawn subagents        | Yes — typed agents (Explore, Plan, general-purpose, code-reviewer, etc.)   | Yes — native `spawn_agent` lifecycle with `default`, `explorer`, and `worker` agents          | Partial — `browser_subagent` only                                     |
 | Parallel agent teams   | Yes — TeamCreate, task lists, SendMessage, broadcast                       | Partial — parallel spawned agents are supported, but there is no team/task-list primitive      | No — parallel tool calls but no independent agent instances           |
-| MCP tools              | Yes — extensible via MCP servers                                           | Partial — APIs available, no servers configured                                                | Yes — MCP server support                                              |
+| MCP tools              | Yes — extensible via MCP servers                                           | Yes — MCP/plugin support depends on configured servers and marketplaces                        | Yes — MCP server support                                              |
 | Web search             | Yes — native WebSearch tool                                                | Yes — web search/fetch tools                                                                   | Yes — native `search_web` tool                                        |
-| Browser interaction    | Partial — WebFetch (read-only, HTML→markdown)                              | Partial — web fetch/open/click flow, not full automation                                       | Yes — full browser control (click, type, navigate, screenshot, video) |
+| Browser interaction    | Partial — WebFetch (read-only, HTML→markdown)                              | Partial — web tools plus early in-app browser for local/public pages without sign-in           | Yes — full browser control (click, type, navigate, screenshot, video) |
 | File system access     | Sandboxed — configurable read/write allowlists                             | Policy-dependent per session                                                                   | Full — unrestricted                                                   |
 | Git operations         | Yes — via Bash (may need sandbox configuration)                            | Yes — native                                                                                   | Yes — via shell                                                       |
 | GitHub CLI (gh)        | Yes — via Bash (may need sandbox configuration)                            | Yes — authenticated                                                                            | Yes — native                                                          |
-| Session memory         | Strong — auto-loaded MEMORY.md + optional MCP memory                       | Partial — conversation context + manual file-based memory; no built-in persistent memory layer | Partial — Knowledge Items (not directly writable), conversation logs  |
+| Session memory         | Strong — auto-loaded MEMORY.md + optional MCP memory                       | Partial — app memories where available plus OACP file memory; app memories are not protocol SSOT | Partial — Knowledge Items (not directly writable), conversation logs  |
 | Interactive mode       | Yes — CLI chat with permissions, plan mode                                 | Yes — desktop app                                                                              | Yes — chat with task UI, artifacts                                    |
-| Context window         | ~200k (auto-compaction extends indefinitely)                               | Not directly exposed; practically finite                                                       | ~1M tokens                                                            |
+| Context window         | ~1M with Opus 4.7 (auto-compaction extends indefinitely)                   | Not directly exposed; practically finite                                                       | ~1M tokens                                                            |
 | Cost model             | Token-based, visible in statusline                                         | Not surfaced in runtime                                                                        | Token-based                                                           |
 | Sandbox restrictions   | Yes — configurable allowlists                                              | Session-dependent                                                                              | None — full system access                                             |
 
@@ -42,27 +44,23 @@ This is a capability comparison across 3 agent runtimes (Claude Code, Codex, Gem
 | Code outline navigation          | Gemini        | `view_file_outline`, `view_code_item` for structured exploration             |
 | PTY / terminal stdin             | Codex, Gemini | Codex: native PTY; Gemini: `send_command_input` (Claude lacks stdin support) |
 | `apply_patch` editing            | Codex         | Grammar-based file edits                                                     |
-| Automation scheduling            | Codex         | Desktop app can schedule tasks (with user request)                           |
+| App-level computer use           | Codex         | macOS app, simulator, and GUI-only workflows; unavailable in EEA, UK, and Switzerland at launch |
+| App-level artifact review        | Codex         | Sidebar preview for generated PDFs, spreadsheets, documents, and presentations |
+| App-level PR review              | Codex         | PR sidebar can inspect changed files, review comments, and follow-up fixes   |
 
 ---
 
-## 3. Installed Skills/Workflows Comparison
-
-| Skill                  | Claude  | Codex    | Gemini               |
-| ---------------------- | ------- | -------- | -------------------- |
-| `review-loop-reviewer` | Working | Working  | Working              |
-| `review-loop-author`   | Working | Untested | Working              |
-| `check-inbox`          | Working | Working  | Working (convention) |
-| `debrief`              | Working | Working  | Working              |
-| `sync`                 | Working | Untested | N/A                  |
-| `blitz`                | Working | N/A      | N/A                  |
-| `team-stats`           | Working | N/A      | N/A                  |
-| `worktree-workflow`    | Working | N/A      | N/A                  |
-| `send-message`         | Working | N/A      | N/A                  |
-| `claude-mem` skills    | Working | N/A      | N/A                  |
-| `gh-address-comments`  | N/A     | Untested | N/A                  |
-| `lint-and-validate`    | N/A     | Untested | N/A                  |
-| `beads`                | N/A     | Untested | N/A                  |
+## 3. Public OACP Skills Coverage
+
+Scope: skills shipped in [`kiloloop/oacp-skills`](https://github.com/kiloloop/oacp-skills). Private/local skills (debrief, sync, blitz, team-stats, worktree-workflow, send-message, etc.) are intentionally not tracked here — this table is meant as a cross-runtime parity signal for distributable skills only.
+
+| Skill                  | Claude  | Codex    | Gemini       |
+| ---------------------- | ------- | -------- | ------------ |
+| `check-inbox`          | Working | Working  | Not packaged |
+| `doctor`               | Working | Working  | Not packaged |
+| `review-loop-reviewer` | Working | Working  | Not packaged |
+| `review-loop-author`   | Working | Working  | Not packaged |
+| `self-improve`         | Working | Working  | Not packaged |
 
 ---
 
@@ -70,8 +68,8 @@ This is a capability comparison across 3 agent runtimes (Claude Code, Codex, Gem
 
 | Dimension       | Claude                                                                 | Codex                                                                   | Gemini                                                               |
 | --------------- | ---------------------------------------------------------------------- | ----------------------------------------------------------------------- | -------------------------------------------------------------------- |
-| Best at         | Orchestration, multi-agent teams, persistent memory, plan-then-execute | Terminal-native execution, fast iterative patching, protocol discipline | Web research, browser automation, visual verification, large context |
-| Ideal task type | Team coordination, complex multi-file refactors, long-running sessions | Shell-heavy workflows, targeted file edits, deterministic scripts       | External research, UI testing, document review, MCP integrations     |
+| Best at         | Orchestration, multi-agent teams, persistent memory, plan-then-execute | Terminal-native execution, fast iterative patching, app-assisted PR/artifact review, protocol discipline | Web research, browser automation, visual verification, large context |
+| Ideal task type | Team coordination, complex multi-file refactors, long-running sessions | Shell-heavy workflows, targeted file edits, deterministic scripts, PR follow-up, artifact review | External research, UI testing, document review, MCP integrations     |
 | Cost profile    | Flexible (haiku subagents for cheap tasks, opus for complex)           | Not directly visible                                                    | Token-based, web search has additional costs                         |
 
 ---
@@ -81,9 +79,9 @@ This is a capability comparison across 3 agent runtimes (Claude Code, Codex, Gem
 | Limitation                    | Claude                        | Codex                                                          | Gemini                 |
 | ----------------------------- | ----------------------------- | -------------------------------------------------------------- | ---------------------- |
 | No subagents                  | —                             | Yes                                                            | Partial (browser only) |
-| No browser automation         | Yes (read-only)               | Partial                                                        | —                      |
+| No browser automation         | Yes (read-only)               | Partial (in-app browser is not full automation and excludes sign-in flows) | —                      |
 | No image generation           | Yes                           | Yes                                                            | —                      |
-| No persistent writable memory | —                             | Partial (no built-in persistent memory, file-based workaround) | Yes                    |
+| No persistent writable memory | —                             | Partial (app memories are not a replacement for OACP durable memory) | Yes                    |
 | Sandbox friction              | Yes (configurable)            | Session-dependent                                              | —                      |
 | No team primitive             | —                             | Yes                                                            | Yes                    |
 | Context limits                | Auto-compaction mitigates     | Yes (no compaction)                                            | Large but finite       |
@@ -101,9 +99,9 @@ These are the highest-impact gaps where one runtime's limitation blocks effectiv
 | No team orchestration       | Codex, Gemini                      | Cannot run parallel agent teams                                    | Agent cards — let runtimes discover and delegate to capable peers              |
 | Memory asymmetry            | Codex (partial), Gemini (KIs only) | Cross-session context degrades without MEMORY.md equivalent        | Standardize memory protocol; each runtime implements its own persistence layer |
 | Sandbox blocks git/gh       | Claude                             | Every git/gh call needs sandbox configuration                      | Configure sandbox allowlists or disable sandbox for specific commands          |
-| No browser for Claude/Codex | Claude, Codex                      | Cannot visually verify UIs or do browser-based testing             | Delegate browser tasks to Gemini; or add MCP browser server                    |
+| Full browser automation gap | Claude, Codex                      | Claude is read-only; Codex has early browser review but not full automation or sign-in flows | Delegate full browser tasks to Gemini; use Codex in-app browser for local/public page review |
 | Reviewer cost               | All (especially Claude)            | High cost for single PR review with polling pattern                | Stateless reviewer rounds — one round per invocation                           |
-| Skill parity                | Codex, Gemini                      | Many skills are Claude-only (blitz, team-stats, worktree-workflow) | Unified skill spec + install guide per runtime                                 |
+| Public skill coverage       | Gemini                             | `kiloloop/oacp-skills` ships `claude/` and `codex/` variants for all 5 public skills; no `gemini/` variants — Gemini users must rely on convention-based adoption | Add `gemini/` variants to each public skill, or document the convention-based pattern as a first-class install path |
 
 ---
 
@@ -113,15 +111,16 @@ These are the highest-impact gaps where one runtime's limitation blocks effectiv
 | ---------------------------- | -------------------------------- | ------------------------------------------ | --------------------------------------------- |
 | Max parallel tool calls      | ~10+                             | Yes (parallel independent calls)           | ~10 (practical)                               |
 | Hooks system                 | Yes (pre/post tool call hooks)   | No                                         | No                                            |
+| Automation scheduling        | Yes (`CronCreate`, `ScheduleWakeup`, `/loop`, `/schedule` skills) | Yes (desktop app thread automations wake a thread on a schedule, with user request) | No                                            |
 | Notebook editing             | Yes (NotebookEdit tool)          | No                                         | No                                            |
 | PDF reading                  | Yes (max 20 pages/request)       | No native tool                             | Via `read_url_content`                        |
 | Image reading (multimodal)   | Yes                              | Yes (desktop app local image/view support) | Yes                                           |
-| Artifact system              | No                               | No                                         | Yes (task.md, implementation plans)           |
+| Artifact system              | No                               | Yes (sidebar preview for generated files) | Yes (task.md, implementation plans)           |
 | Video recording              | No                               | No                                         | Yes (WebP via browser)                        |
 | Multi-file editing primitive | Edit tool (one file at a time)   | `apply_patch` (one file)                   | `multi_replace_file_content` (non-contiguous) |
 | Workflow file format         | SKILL.md with YAML frontmatter   | SKILL.md with YAML frontmatter             | Markdown with YAML frontmatter                |
 | Policy visibility at runtime | Partial (sandbox config visible) | Yes (session policy in system context)     | Yes (`SafeToAutoRun` flags)                   |
-| Long-running shell sessions  | Bash tool (no stdin)             | Yes (PTY + stdin)                          | Yes (`send_command_input`)                    |
+| Long-running shell sessions  | Bash tool (no stdin)             | Yes (PTY + stdin; multiple terminals in app) | Yes (`send_command_input`)                    |
 
 ---
 

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/docs/protocol/dispatch_states.yaml

@@ -206,7 +206,7 @@ agent_transitions:
 dispatcher_states:
   sent:
     description: "Dispatch message written to agent inbox"
-    trigger: "send_inbox_message.py completes"
+    trigger: "`oacp send` completes"
 
   ackd:
     description: "Agent acknowledged receipt"

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/oacp/cli.py

@@ -23,6 +23,7 @@ Commands:
   add-agent      Add an agent to an existing project workspace
   agent          Manage global agent profiles (init, show, list)
   inbox          List pending inbox messages
+  watch          Emit inbox delta events for Monitor-friendly polling
   memory         Archive or restore project memory files
   setup          Generate runtime-specific config files in a repo
   send           Send a protocol-compliant inbox message
@@ -36,6 +37,7 @@ Examples:
   oacp init my-project --agents claude,codex
   oacp add-agent my-project alice --runtime claude
   oacp inbox my-project --agent claude
+  oacp watch --agent claude --project my-project --json
   oacp memory archive my-project research_notes.md
   oacp setup claude --project my-project
   oacp send my-project --to iris --type notification --subject "Done" --body "Completed"
@@ -50,6 +52,7 @@ SCRIPT_NAMES = {
     "add-agent": "add_agent.py",
     "agent": "agent_profile.py",
     "inbox": "oacp_inbox.py",
+    "watch": "oacp_watch.py",
     "memory": "memory_cli.py",
     "setup": "setup_runtime.py",
     "send": "send_inbox_message.py",

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "oacp-cli"
-version = "0.2.1"
+version = "0.2.2"
 description = "Open Agent Coordination Protocol CLI for file-based multi-agent workflows"
 readme = "README.md"
 license = "Apache-2.0"
@@ -61,6 +61,7 @@ packages = ["oacp"]
 "scripts/add_agent.py" = "oacp/_scripts/add_agent.py"
 "scripts/agent_profile.py" = "oacp/_scripts/agent_profile.py"
 "scripts/oacp_inbox.py" = "oacp/_scripts/oacp_inbox.py"
+"scripts/oacp_watch.py" = "oacp/_scripts/oacp_watch.py"
 "scripts/memory_cli.py" = "oacp/_scripts/memory_cli.py"
 "scripts/memory_archive_common.py" = "oacp/_scripts/memory_archive_common.py"
 "scripts/promote_to_archive.py" = "oacp/_scripts/promote_to_archive.py"

{oacp_cli-0.2.1 → oacp_cli-0.2.2}/scripts/codex_session_init.py

@@ -91,9 +91,9 @@ def _project_name_from_workspace_marker(cwd: Path, name: str) -> Optional[str]:
 
 def _detect_project_name(cwd: Path) -> Optional[str]:
     for resolver in (
-        lambda: _project_name_from_agent_hub(cwd),
         lambda: _project_name_from_workspace_marker(cwd, "workspace.json"),
         lambda: _project_name_from_workspace_marker(cwd, ".oacp"),
+        lambda: _project_name_from_agent_hub(cwd),
     ):
         project = resolver()
         if project:
@@ -285,7 +285,7 @@ def run_session_init(
         for name in MEMORY_FILES:
             memory_results[name] = {"path": "", "state": "skipped", "bytes": 0}
         status_result = {"path": "", "state": "no-project"}
-        warnings.append("no project detected from .agent-hub, workspace.json, .oacp, and --project not provided")
+        warnings.append("no project detected from workspace.json, .oacp, .agent-hub, and --project not provided")
 
     for name in PROTOCOL_FILES:
         state = protocol_results[name]["state"]