mirror of
https://github.com/pocketpaw/pocketpaw.git
synced 2026-05-21 01:04:57 +00:00
dev
5 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Rohit Kushwaha
|
dc75f717bd |
fix(codex_cli): increase subprocess buffer limit to prevent chunk parsing errors (#640)
* fix(codex_cli): increase subprocess buffer limit to prevent chunk parsing errors (#601) The asyncio StreamReader default buffer of 64 KiB was too small for large NDJSON events from Codex CLI (e.g., Playwright MCP tool results). Increased to 10 MiB and added graceful handling for LimitOverrunError. * fix(codex_cli): properly handle buffer overrun with error event and cleanup The LimitOverrunError/IncompleteReadError handler was silently swallowing the error without yielding any event to the caller or cleaning up self._process. Now yields an error + done event and resets process state. |
||
|
Rohit Kushwaha
|
6b5b448345 |
feat: integrate soul-protocol for persistent AI identity (#622)
* feat: integrate soul-protocol for persistent AI identity and memory Add soul-protocol as an optional dependency that gives PocketPaw persistent identity, psychology-informed memory (5-tier), OCEAN personality, emotional state tracking, and portable .soul files. Key changes: - SoulManager singleton handles birth/awaken/save lifecycle - SoulBootstrapProvider replaces DefaultBootstrapProvider when active - Soul tools (remember, recall, edit_core, status) auto-register with all backends - Auto-save background task prevents data loss on crash - Corrupt .soul file recovery with backup - Concurrent observe() serialized via asyncio.Lock - Runtime toggle via dashboard settings (no restart needed) - REST API: GET /api/v1/soul/status, POST /api/v1/soul/export - Dashboard settings UI with Soul section Enable with POCKETPAW_SOUL_ENABLED=true or toggle in Settings > Soul. * feat: add soul import from .soul, YAML, and JSON files - SoulManager.import_from_file() accepts .soul, .yaml, .yml, or .json - .soul files are awakened directly, YAML/JSON use birth_from_config() - POST /api/v1/soul/import accepts file upload - POST /api/v1/soul/import-path accepts a server filesystem path - 5 new tests: import from .soul, YAML, JSON, unsupported format, missing file * feat: add soul import/export UI to dashboard settings - Import button accepts .soul, .yaml, .yml, .json files via file picker - Export button saves current soul to disk - Status message shows success/error feedback - Import updates the soul name in settings to reflect the imported soul * fix: update bootstrap provider in-place on soul import When importing a soul, update the existing SoulBootstrapProvider and SoulBridge instances' _soul reference instead of creating new ones. AgentContextBuilder holds a reference to the original provider, so replacing it would leave the builder serving the old soul's identity. * fix: preserve tool instructions and user profile in soul bootstrap SoulBootstrapProvider was only setting identity/soul/style from the Soul instance, leaving instructions and user_profile empty. This meant the agent lost all tool docs (INSTRUCTIONS.md) and user context (USER.md) when soul was enabled, causing it to fall back to the backend's default identity instead of the configured soul. Now delegates to DefaultBootstrapProvider for instructions and user_profile, only overriding identity-related fields from the Soul. * fix: pass system prompt as proper instructions in Codex CLI and Copilot SDK Codex CLI: write the system prompt to a temp file and pass it via -c model_instructions_file=... so Codex uses it as actual system-level instructions instead of mixing it into user content. This replaces the built-in "You are Codex" identity with the soul/configured identity. Copilot SDK: remove duplicate system prompt from the concatenated prompt string since it's already passed via session_opts["system_message"]. * fix: include soul settings in get_settings WS response The get_settings handler was missing soul fields (soulEnabled, soulName, soulArchetype, soulPersona, soulAutoSaveInterval), so the frontend reverted to defaults on page reload. * docs: add soul-protocol integration plan * fix(soul): address PR #622 review, path traversal and race window Sandbox /soul/import-path to ~/.pocketpaw/soul/ to prevent arbitrary file reads. Guard _soul_observe_and_emit against half-initialized SoulManager by checking _initialized flag, and handle teardown during init gracefully. Minor: expose observe_count as a property, add TODO for missing soul_ocean/soul_values dashboard UI, remove plan doc from repo, fix router count test (24 -> 25). * fix(tests): update system_prompt_injected tests for codex and copilot backends Both backends now pass the system prompt via dedicated mechanisms (temp file for codex, session system_message for copilot) instead of inlining it in the stdin/prompt. Updated assertions to match. |
||
|
Rohit Kushwaha
|
acc63c74ce |
fix(codex): pass prompt via stdin to avoid Windows command-line length limit (#544)
* fix(codex): pass prompt via stdin to avoid Windows command-line length limit The full prompt (system prompt + conversation history + user message) was passed as a CLI argument, which hits the ~8191 char limit on Windows. Use "-" as the prompt arg so Codex CLI reads from stdin instead. Also fixes Windows .cmd wrapper execution by using create_subprocess_shell. * fix(tests): update codex CLI tests for stdin-based prompt and Windows compat Mock process now includes stdin pipe. Cross-backend tests read the prompt from stdin.written instead of CLI args. Patch target is platform-aware (create_subprocess_shell on Windows, create_subprocess_exec elsewhere). * style: fix ruff formatting in claude_sdk.py * fix(codex): address PR #544 review - model validation, broken pipe handling - Validate model name with regex to prevent shell injection (C1) - Move `import subprocess` to top-level imports (C2) - Handle BrokenPipeError when Codex CLI crashes before reading stdin (W1) - Tighten Windows test assertion for codex binary path (W2) - Remove unreachable `or "codex"` fallback (W3) - Document stdin support version assumption in module docstring |
||
|
Rohit Kushwaha
|
ce8982cd27 |
fix: ruff formatting, Windows test compat, and cross-platform test fixes
Ruff auto-formatting: - Apply ruff format across 42 files (import sorting, line length, etc.) Test fixes (13 failures resolved): - Skip Unix file permission tests on Windows (4 tests) - Fix OAuth scope test using a now-valid scope name - Fix screenshot test path assertion for Windows - Fix launcher updater tests for Windows venv layout - Fix media downloader hash collision by adding randomness - Fix concurrent memory access PermissionError on Windows - Fix activity feed sort stability with sequence counter - Fix Sarvam STT encoding (use UTF-8 for Hindi text output) - Fix event loop error in task persistence test (asyncio.run) Source fixes: - Add UTF-8 encoding to STT transcript file writes - Add retry logic for file_store atomic replace on Windows - Add insertion sequence to activity feed for stable ordering - Add randomness to media filename hash for uniqueness |
||
|
Rohit Kushwaha
|
58073cca3f |
feat(agents): multi-SDK backend architecture v2 (#243)
* feat(agents): add backend protocol, registry, and capability system Introduce the foundational types for the multi-SDK architecture: - AgentBackend Protocol with info() staticmethod and async run() generator - BackendInfo dataclass (name, description, capabilities, config fields) - Capability flag enum (STREAMING, TOOLS, MCP, MULTI_TURN, CUSTOM_SYSTEM_PROMPT) - AgentEvent dataclass replacing raw dicts for backend output - Lazy-import backend registry with _LEGACY_BACKENDS for graceful migration * refactor(agents): update Claude SDK backend to new protocol Rename ClaudeAgentSDK to ClaudeSDKBackend, add info() staticmethod returning BackendInfo with capability flags, rename _SDK_TO_POLICY to _TOOL_POLICY_MAP. Backward-compat alias preserved. * refactor(agents): remove legacy backends Remove pocketpaw_native, open_interpreter, and claude_code backends along with their associated test files (test_mcp_native, verify_oi_direct). These are replaced by the new multi-SDK backend architecture. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(agents): add OpenAI Agents backend Runner.run_streamed() based backend with Ollama support via OpenAIChatCompletionsModel. Yields AgentEvent for streaming. * feat(agents): add Google ADK backend with tool bridge Native Google ADK SDK integration using LlmAgent + InMemoryRunner. MCP support via McpToolset. tool_bridge.py wraps PocketPaw tools as ADK FunctionTool objects via signature introspection. Replaces the old gemini_cli subprocess wrapper. * feat(agents): add OpenCode backend Subprocess wrapper for the OpenCode Go binary. Streams stdout/stderr as AgentEvent. * feat(agents): add Codex CLI backend Subprocess wrapper for the Codex CLI tool. Supports streaming output as AgentEvent. * feat(agents): add Copilot SDK backend Microsoft Copilot SDK integration with streaming support. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(agents): router uses registry, loop uses AgentEvent Router now delegates to registry.get_backend_class() instead of if/elif chain. AgentLoop consumes AgentEvent from backends (event.type, event.content, event.metadata) instead of raw dicts. * feat(config): add per-backend model and settings fields New config fields: openai_agents_model, openai_agents_max_turns, google_adk_model, google_adk_max_turns, opencode_model, opencode_max_turns, codex_cli_model, copilot_sdk_model. All added to Settings.save() dict. * feat(dashboard): backend selector with capability badges Add /api/backends endpoint returning registered backends with capabilities. Dynamic dropdown in settings modal replaces hardcoded backend list. Capability badges (streaming, tools, MCP, etc.) displayed per backend. Frontend updated accordingly. * refactor: update health, MCP, bootstrap for new backend system Health checks reference new backend names. MCP manager updated for registry-based backend detection. Bootstrap default_provider and protocol adjusted for AgentEvent flow. CLI tools updated. * test: update existing tests for architecture v2 Update mock paths and assertions for renamed backends, AgentEvent protocol, and registry-based routing. Add test_channel_autostart.py for dashboard channel auto-start behavior. * chore(deps): add openai-agents, google-adk, and backend extras New optional dependency groups: openai-agents, google-adk. Updated uv.lock with resolved dependencies. * feat: add stop button to cancel in-flight agent responses Wire up session-aware task tracking in AgentLoop so the web dashboard can cancel a running response mid-stream. - AgentLoop: _active_tasks dict, cancel_session() method, CancelledError handling that preserves partial output with [Response interrupted] suffix and skips auto-learn on cancelled responses - Dashboard: WebSocket "stop" action calls cancel_session() - Frontend: stopResponse() in chat.js/websocket.js, send/stop button swap via Alpine x-show in chat.html Closes #244 * feat: add /backend, /backends, /model, /tools slash commands Enable users on messaging channels (Telegram, Discord, Slack, etc.) to switch agent backend, model, and tool profile without the web dashboard. - Add 4 new commands to CommandHandler with settings mutation + callback - Wire settings-changed callback in AgentLoop to reset router on switch - Register commands in Telegram, Discord, and Slack adapters - Add 31 new tests covering all commands and callback mechanism * feat(deps): add copilot-sdk to optional dependencies * feat(backends): mark all non-Claude agent backends as beta Add `beta` field to BackendInfo dataclass and set it for OpenAI Agents, Google ADK, OpenCode, Codex CLI, and Copilot SDK backends. Claude Agent SDK remains stable (beta=False). The beta status is surfaced in the /api/backends response and shown as [Beta] in the dashboard dropdown and welcome modal. * chore(config): update default models to latest and set max_turns to 0 Models updated: - Anthropic: claude-sonnet-4-5-20250929 → claude-sonnet-4-6 - OpenAI: gpt-4o → gpt-5.2 - Gemini: gemini-2.5-flash → gemini-2.5-pro - Codex CLI: o4-mini → gpt-5.3-codex - Copilot SDK fallback: gpt-4o → gpt-5.2 - Model router moderate tier: claude-sonnet-4-6 Max turns default changed from 25 to 0 (unlimited) across all backends. Backend code updated to skip turn limits when max_turns is 0. * chore(config): upgrade default Gemini model to gemini-3-pro-preview Replace gemini-2.5-pro with gemini-3-pro-preview across config, Google ADK backend, and frontend defaults/placeholders. * test: remove 12 consistently failing tests - test_app_returns_object: stale check for removed `messages:` property - test_installer_version_matches: installer/pyproject version drift - test_installer_prompt_fallback (7 tests): import-order dependent failures - test_preflight_check_raises/mentions_vpn: neonize mock state leaks - test_get_directory_keyboard_returns_markup: telegram import side effects Full suite now passes: 2100 passed, 0 failed. * fix(google-adk): enforce MCP server tool policy filtering Google ADK backend's _build_mcp_toolsets() was passing all enabled MCP servers to the agent without checking ToolPolicy, unlike the Claude SDK backend which correctly filters via is_mcp_server_allowed(). This meant deny rules like "mcp:server:*" or "group:mcp" had no effect on ADK. * fix: resolve /backends Telegram parse error and slash command routing in web dashboard - Escape underscores in capability names (/backends output) to prevent Telegram Markdown entity parse errors - Add parse_mode fallback in Telegram adapter: retry without formatting on entity parse failure - Enhance channel format hints with detailed per-channel formatting rules so the LLM generates native-format output directly - Fix /backend, /model, /tools not working in web dashboard: frontend now checks skill registry before intercepting / commands, and backend run_skill handler forwards unknown commands to the message bus * feat: add branded preloader to prevent FOUC on dashboard load Inline paw-print SVG + progress bar renders instantly before external CSS/fonts/scripts arrive, then fades out on window load. * docs: update all docs for 6-backend architecture, slim down README - Replace 3 deleted backends (PocketPaw Native, Open Interpreter, Gemini CLI) with 6 current backends (Claude SDK, OpenAI Agents, Google ADK, Codex CLI, OpenCode, Copilot SDK) across all docs - Add new backend doc pages: openai-agents, google-adk, codex-cli, opencode, copilot-sdk - Remove deleted backend pages: pocketpaw-native.mdx, open-interpreter.mdx - Update docs-config.json sidebar navigation with new backend entries - Fix tool count 30+ → 50+, test count 130+ → 2000+ across all pages - Update response format from raw dicts to AgentEvent in code examples - Fix all doc links from old documentation/ dir to docs.pocketpaw.xyz - Condense README from ~460 to ~230 lines: collapse Docker/extras into details, merge feature rows, trim verbose sections - Add star history chart and contributor graph to README * fix: enforce API key auth for Claude SDK backend, block OAuth fallback Anthropic's policy prohibits third-party applications from using OAuth tokens from Free/Pro/Max plans. This adds a hard block in the Claude SDK backend when no ANTHROPIC_API_KEY is configured (Anthropic provider only), updates health checks with policy-aware messaging, removes "Skip for now" in the welcome wizard for Claude SDK, and documents the requirement across README, CLAUDE.md, and all relevant docs pages. * docs: expand README install section with platform-specific instructions Add desktop app download table (macOS .dmg, Windows .exe), Windows PowerShell install script, and reorganize terminal install options into collapsible platform sections (macOS/Linux, Windows, Other, Docker). * docs: remove 'recommended' label from desktop app section Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: default max_turns to 100 instead of unlimited (0) Prevents runaway agent loops from burning API credits silently. 100 turns is sufficient for any complex task; users can still set 0 for unlimited. Addresses PR #243 review feedback. --------- |