pcode 0.1.1__tar.gz → 0.1.3__tar.gz

{pcode-0.1.1 → pcode-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: pcode
-Version: 0.1.1
+Version: 0.1.3
 Summary: Terminal-native AI coding agent with background jobs, parallel worktrees, forkable sessions, and multi-model support
 Project-URL: Homepage, https://github.com/cruxwell/pcode
 Project-URL: Documentation, https://cruxwell.github.io/pcode/
@@ -16,34 +16,38 @@ Classifier: Intended Audience :: Developers
 Classifier: Operating System :: MacOS
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 Classifier: Topic :: Software Development
-Requires-Python: >=3.11
-Requires-Dist: filelock<4,>=3.16
+Requires-Python: >=3.14
+Requires-Dist: filelock<5,>=4
 Requires-Dist: genai-prices<0.2,>=0.1.7
-Requires-Dist: httpx2<3,>=2.13
+Requires-Dist: httpx2<3,>=2.13.1
 Requires-Dist: prompt-toolkit==3.0.53
 Requires-Dist: psutil<8,>=6
-Requires-Dist: pydantic-ai-harness[codemode,coder,exa,playwright]<0.53,>=0.52.0
-Requires-Dist: pydantic-ai-slim[anthropic,bedrock,duckduckgo,google,groq,mcp,openai,web-fetch,xai]<3,>=2.52.0
-Requires-Dist: rich<15,>=14
+Requires-Dist: pydantic-ai-harness[codemode,coder,exa,playwright]<0.56,>=0.55.0
+Requires-Dist: pydantic-ai-slim[anthropic,bedrock,duckduckgo,google,groq,mcp,openai,web-fetch,xai]<3,>=2.55.0
+Requires-Dist: rich<16,>=15
 Requires-Dist: websockets<17,>=15.0.1
 Requires-Dist: yappi<2,>=1.7.6
 Provides-Extra: claude
-Requires-Dist: claude-agent-sdk<0.3,>=0.2.160; extra == 'claude'
+Requires-Dist: claude-agent-sdk<0.3,>=0.2.164; extra == 'claude'
 Description-Content-Type: text/markdown
 
-<img width="1512" height="947" alt="Screenshot 2026-10-06 at 7 23 29 PM" src="https://github.com/user-attachments/assets/a648fede-d703-44ef-8b52-895d3a0cd2af" />
-<img width="1360" alt="pcode fixing a bug: a word-level diff of the edit, then a worker sub-agent reviewing it with its own plan nested under the task list" src="https://raw.githubusercontent.com/cruxwell/pcode/master/docs/assets/screenshots/readme.png" />
+<img width="1392" height="1522" alt="pcode in a dark terminal" src="docs/assets/screenshots/tabs-dark.png" />
+
+<img width="1392" height="1522" alt="pcode in a light terminal" src="docs/assets/screenshots/tabs-light.png" />
 
 # pcode
 
-pcode is a terminal-native coding agent built for long-running and parallel
-work. Background commands wake the agent when they finish, every session can
-use its own git worktree, conversations can be rewound and forked, and every
-tool call stays inspectable.
+pcode is a terminal-native coding agent that lets you change what's visible in
+your scrollback, even after the work is done. Expand commands, output, and diffs
+when you need the details; hide them when you want to read the conversation.
+The same history, with the detail you choose.
+
+Long-running commands continue in the background and wake the agent when they
+finish. Run sessions in separate git worktrees, or rewind and branch a
+conversation to try another approach.
 
 - **Slow work doesn't block you.** Long commands become background jobs, and a
   finished job wakes the agent, so it can watch tests or CI and fix what fails.
@@ -51,8 +55,9 @@ tool call stays inspectable.
   on one repo at once.
 - **Rewind and fork.** `/tree` returns to any point in a conversation and
   branches from there. Every session is kept, so you can resume or search it.
-- **Nothing hidden.** `/tools` shows every command the agent ran and its full
-  output, and scrollback re-renders to show or fold every command and diff.
+- **Change your view, not your history.** Show or hide commands, output, and
+  diffs throughout the conversation. Hidden output stays available, and `/tools`
+  lets you inspect every tool call and its full output.
 
 It runs on any model [Pydantic AI](https://ai.pydantic.dev/) supports, or on
 your Claude or ChatGPT subscription.
@@ -71,7 +76,7 @@ brew install cruxwell/pcode/pcode
 Or from [PyPI](https://pypi.org/project/pcode/) with [uv](https://docs.astral.sh/uv/):
 
 ```sh
-uv tool install 'pcode[claude]'
+uv tool install --python 3.14 'pcode[claude]'
 ```
 
 `brew install --HEAD` tracks `master` instead of the latest release.
@@ -79,23 +84,24 @@ uv tool install 'pcode[claude]'
 ## Quick start
 
 ```sh
-codex login                                  # or /login [claude|openai-codex] inside pcode, or export a provider API key
-pcode -m openai-codex:gpt-5.6-luna           # interactive; /model (Ctrl+L) saves a default
-pcode                                        # reuses the saved model, or opens the offline preview
+pcode -m claude:claude-sonnet-5              # Claude subscription; run /login claude if not signed in
+pcode -m openai-codex:gpt-5.6-luna           # ChatGPT subscription (/login openai-codex)
+pcode -m anthropic:claude-sonnet-5           # or any provider, with its API key set
+pcode                                        # reuses the model /model (Ctrl+L) saved; with none, an offline preview
 pcode -C /path/to/repo "Summarize the open TODOs"
 git diff | pcode -p --no-save                # non-interactive: reply to stdout
 pcode --continue                             # resume this directory's newest session
 pcode --theme-preview                        # offline sample output and the style gallery
 ```
 
-**Live mode edits files and runs shell commands with your permissions and no
+**The agent edits files and runs shell commands with your permissions and no
 approval prompt.** Read [tool permissions](https://cruxwell.github.io/pcode/tools/#tool-permissions)
 before pointing it at anything you care about.
 
 ## More
 
 - **Your subscription:** Claude runs through Anthropic's own Agent SDK and
-  Claude Code login, the way Anthropic supports, and ChatGPT through a Codex
+  Claude Code login (the route Anthropic supports), and ChatGPT through a Codex
   login. See [providers](https://cruxwell.github.io/pcode/providers/).
 - [Email remote control](https://cruxwell.github.io/pcode/email/): send a task
   from Gmail on your phone, reply to keep going, and take the session over at a
@@ -105,10 +111,10 @@ before pointing it at anything you care about.
   `jj` to leave insert mode.
 - `/btw` side questions, background sessions, recall of past sessions, a
   browser the agent can drive, and Python extensions.
-- Pydantic AI's Harness coder capabilities, with the rest of a finished agent
-  on top: MCP with OAuth and tool search, searchable sessions, jobs,
-  worktrees. Extensions are plain Pydantic AI capabilities. The conversation
-  tree follows [pi](https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/docs/tree.md)'s.
+- Built on Pydantic AI's Harness coder, with MCP (OAuth and tool search),
+  searchable sessions, jobs and worktrees on top. Extensions are plain
+  Pydantic AI capabilities. The conversation tree follows
+  [pi](https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/docs/tree.md)'s.
 
 See [PLAN.md](https://github.com/cruxwell/pcode/blob/master/PLAN.md) for the longer-term direction.
 
@@ -116,21 +122,23 @@ See [PLAN.md](https://github.com/cruxwell/pcode/blob/master/PLAN.md) for the lon
 
 | Page | What it covers |
 | --- | --- |
-| [Getting started](https://cruxwell.github.io/pcode/getting-started/) | Homebrew and source installs, `-C`, `--print`, shell completion |
+| [Getting started](https://cruxwell.github.io/pcode/getting-started/) | Homebrew, uv and source installs, signing in, `--print`, shell completion |
 | [Scrollback and transparency](https://cruxwell.github.io/pcode/guide/scrollback/) | Guide: what goes into scrollback, `/tools`, `/diffs` |
 | [A shell for long-running work](https://cruxwell.github.io/pcode/guide/shell/) | Guide: background jobs, watching CI |
 | [Parallel agents](https://cruxwell.github.io/pcode/guide/parallel/) | Guide: worktrees, parallel sub-agents, `/agents` |
 | [Extending pcode](https://cruxwell.github.io/pcode/guide/extending/) | Guide: extensions, skills, settings |
-| [Providers and models](https://cruxwell.github.io/pcode/providers/) | Authentication, supported providers, the model picker, reasoning effort, Claude Code, Meridian, proxies |
+| [Providers and models](https://cruxwell.github.io/pcode/providers/) | Authentication, supported providers, the model picker, reasoning effort, Claude Code, proxies |
 | [Configuration](https://cruxwell.github.io/pcode/configuration/) | `pcode config`, per-repository overrides, trusting repository code, the settings table, syntax styles |
 | [Commands and keys](https://cruxwell.github.io/pcode/commands/) | Slash commands, key bindings, vi mode, tmux newlines, status line, `!command`, the diff and tool inspectors |
 | [Keybindings](https://cruxwell.github.io/pcode/keybindings/) | Custom command mappings with `/bind`, Ctrl shortcuts, vi editing, a normal-mode leader, and custom escape sequences such as `jj` |
+| [Terminal setup](https://cruxwell.github.io/pcode/terminal/) | Tab titles, the progress bar, iTerm2 and tmux settings |
 | [Tools](https://cruxwell.github.io/pcode/tools/) | Tool permissions, web search, the browser, code mode |
 | [MCP servers](https://cruxwell.github.io/pcode/mcp/) | Opt-in MCP configuration, OAuth sign-in, deferred tool search |
 | [Working in a repository](https://cruxwell.github.io/pcode/workspace/) | `AGENTS.md`/`CLAUDE.md`, skills as slash commands, one worktree per session |
 | [Sessions and recovery](https://cruxwell.github.io/pcode/sessions/) | Saving, resuming, recalling earlier sessions, checkpoints, retries |
 | [Context, limits and caching](https://cruxwell.github.io/pcode/context/) | Prompt overhead, compaction, output limits, prompt cache notices |
 | [The transcript](https://cruxwell.github.io/pcode/transcript/) | What lands in scrollback: diffs, thinking, errors, command output, `/redraw` |
+| [Email remote control](https://cruxwell.github.io/pcode/email/) | Driving a session from Gmail, the remote profile |
 | [Conversation tree](https://cruxwell.github.io/pcode/conversation-tree/) | `/tree`: rewinding and forking a conversation |
 | [Side questions](https://cruxwell.github.io/pcode/side-questions/) | `/btw`: asking about the running turn without interrupting it |
 

{pcode-0.1.1 → pcode-0.1.3}/README.md

@@ -1,12 +1,17 @@
-<img width="1512" height="947" alt="Screenshot 2026-10-06 at 7 23 29 PM" src="https://github.com/user-attachments/assets/a648fede-d703-44ef-8b52-895d3a0cd2af" />
-<img width="1360" alt="pcode fixing a bug: a word-level diff of the edit, then a worker sub-agent reviewing it with its own plan nested under the task list" src="https://raw.githubusercontent.com/cruxwell/pcode/master/docs/assets/screenshots/readme.png" />
+<img width="1392" height="1522" alt="pcode in a dark terminal" src="docs/assets/screenshots/tabs-dark.png" />
+
+<img width="1392" height="1522" alt="pcode in a light terminal" src="docs/assets/screenshots/tabs-light.png" />
 
 # pcode
 
-pcode is a terminal-native coding agent built for long-running and parallel
-work. Background commands wake the agent when they finish, every session can
-use its own git worktree, conversations can be rewound and forked, and every
-tool call stays inspectable.
+pcode is a terminal-native coding agent that lets you change what's visible in
+your scrollback, even after the work is done. Expand commands, output, and diffs
+when you need the details; hide them when you want to read the conversation.
+The same history, with the detail you choose.
+
+Long-running commands continue in the background and wake the agent when they
+finish. Run sessions in separate git worktrees, or rewind and branch a
+conversation to try another approach.
 
 - **Slow work doesn't block you.** Long commands become background jobs, and a
   finished job wakes the agent, so it can watch tests or CI and fix what fails.
@@ -14,8 +19,9 @@ tool call stays inspectable.
   on one repo at once.
 - **Rewind and fork.** `/tree` returns to any point in a conversation and
   branches from there. Every session is kept, so you can resume or search it.
-- **Nothing hidden.** `/tools` shows every command the agent ran and its full
-  output, and scrollback re-renders to show or fold every command and diff.
+- **Change your view, not your history.** Show or hide commands, output, and
+  diffs throughout the conversation. Hidden output stays available, and `/tools`
+  lets you inspect every tool call and its full output.
 
 It runs on any model [Pydantic AI](https://ai.pydantic.dev/) supports, or on
 your Claude or ChatGPT subscription.
@@ -34,7 +40,7 @@ brew install cruxwell/pcode/pcode
 Or from [PyPI](https://pypi.org/project/pcode/) with [uv](https://docs.astral.sh/uv/):
 
 ```sh
-uv tool install 'pcode[claude]'
+uv tool install --python 3.14 'pcode[claude]'
 ```
 
 `brew install --HEAD` tracks `master` instead of the latest release.
@@ -42,23 +48,24 @@ uv tool install 'pcode[claude]'
 ## Quick start
 
 ```sh
-codex login                                  # or /login [claude|openai-codex] inside pcode, or export a provider API key
-pcode -m openai-codex:gpt-5.6-luna           # interactive; /model (Ctrl+L) saves a default
-pcode                                        # reuses the saved model, or opens the offline preview
+pcode -m claude:claude-sonnet-5              # Claude subscription; run /login claude if not signed in
+pcode -m openai-codex:gpt-5.6-luna           # ChatGPT subscription (/login openai-codex)
+pcode -m anthropic:claude-sonnet-5           # or any provider, with its API key set
+pcode                                        # reuses the model /model (Ctrl+L) saved; with none, an offline preview
 pcode -C /path/to/repo "Summarize the open TODOs"
 git diff | pcode -p --no-save                # non-interactive: reply to stdout
 pcode --continue                             # resume this directory's newest session
 pcode --theme-preview                        # offline sample output and the style gallery
 ```
 
-**Live mode edits files and runs shell commands with your permissions and no
+**The agent edits files and runs shell commands with your permissions and no
 approval prompt.** Read [tool permissions](https://cruxwell.github.io/pcode/tools/#tool-permissions)
 before pointing it at anything you care about.
 
 ## More
 
 - **Your subscription:** Claude runs through Anthropic's own Agent SDK and
-  Claude Code login, the way Anthropic supports, and ChatGPT through a Codex
+  Claude Code login (the route Anthropic supports), and ChatGPT through a Codex
   login. See [providers](https://cruxwell.github.io/pcode/providers/).
 - [Email remote control](https://cruxwell.github.io/pcode/email/): send a task
   from Gmail on your phone, reply to keep going, and take the session over at a
@@ -68,10 +75,10 @@ before pointing it at anything you care about.
   `jj` to leave insert mode.
 - `/btw` side questions, background sessions, recall of past sessions, a
   browser the agent can drive, and Python extensions.
-- Pydantic AI's Harness coder capabilities, with the rest of a finished agent
-  on top: MCP with OAuth and tool search, searchable sessions, jobs,
-  worktrees. Extensions are plain Pydantic AI capabilities. The conversation
-  tree follows [pi](https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/docs/tree.md)'s.
+- Built on Pydantic AI's Harness coder, with MCP (OAuth and tool search),
+  searchable sessions, jobs and worktrees on top. Extensions are plain
+  Pydantic AI capabilities. The conversation tree follows
+  [pi](https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/docs/tree.md)'s.
 
 See [PLAN.md](https://github.com/cruxwell/pcode/blob/master/PLAN.md) for the longer-term direction.
 
@@ -79,21 +86,23 @@ See [PLAN.md](https://github.com/cruxwell/pcode/blob/master/PLAN.md) for the lon
 
 | Page | What it covers |
 | --- | --- |
-| [Getting started](https://cruxwell.github.io/pcode/getting-started/) | Homebrew and source installs, `-C`, `--print`, shell completion |
+| [Getting started](https://cruxwell.github.io/pcode/getting-started/) | Homebrew, uv and source installs, signing in, `--print`, shell completion |
 | [Scrollback and transparency](https://cruxwell.github.io/pcode/guide/scrollback/) | Guide: what goes into scrollback, `/tools`, `/diffs` |
 | [A shell for long-running work](https://cruxwell.github.io/pcode/guide/shell/) | Guide: background jobs, watching CI |
 | [Parallel agents](https://cruxwell.github.io/pcode/guide/parallel/) | Guide: worktrees, parallel sub-agents, `/agents` |
 | [Extending pcode](https://cruxwell.github.io/pcode/guide/extending/) | Guide: extensions, skills, settings |
-| [Providers and models](https://cruxwell.github.io/pcode/providers/) | Authentication, supported providers, the model picker, reasoning effort, Claude Code, Meridian, proxies |
+| [Providers and models](https://cruxwell.github.io/pcode/providers/) | Authentication, supported providers, the model picker, reasoning effort, Claude Code, proxies |
 | [Configuration](https://cruxwell.github.io/pcode/configuration/) | `pcode config`, per-repository overrides, trusting repository code, the settings table, syntax styles |
 | [Commands and keys](https://cruxwell.github.io/pcode/commands/) | Slash commands, key bindings, vi mode, tmux newlines, status line, `!command`, the diff and tool inspectors |
 | [Keybindings](https://cruxwell.github.io/pcode/keybindings/) | Custom command mappings with `/bind`, Ctrl shortcuts, vi editing, a normal-mode leader, and custom escape sequences such as `jj` |
+| [Terminal setup](https://cruxwell.github.io/pcode/terminal/) | Tab titles, the progress bar, iTerm2 and tmux settings |
 | [Tools](https://cruxwell.github.io/pcode/tools/) | Tool permissions, web search, the browser, code mode |
 | [MCP servers](https://cruxwell.github.io/pcode/mcp/) | Opt-in MCP configuration, OAuth sign-in, deferred tool search |
 | [Working in a repository](https://cruxwell.github.io/pcode/workspace/) | `AGENTS.md`/`CLAUDE.md`, skills as slash commands, one worktree per session |
 | [Sessions and recovery](https://cruxwell.github.io/pcode/sessions/) | Saving, resuming, recalling earlier sessions, checkpoints, retries |
 | [Context, limits and caching](https://cruxwell.github.io/pcode/context/) | Prompt overhead, compaction, output limits, prompt cache notices |
 | [The transcript](https://cruxwell.github.io/pcode/transcript/) | What lands in scrollback: diffs, thinking, errors, command output, `/redraw` |
+| [Email remote control](https://cruxwell.github.io/pcode/email/) | Driving a session from Gmail, the remote profile |
 | [Conversation tree](https://cruxwell.github.io/pcode/conversation-tree/) | `/tree`: rewinding and forking a conversation |
 | [Side questions](https://cruxwell.github.io/pcode/side-questions/) | `/btw`: asking about the running turn without interrupting it |
 

{pcode-0.1.1 → pcode-0.1.3}/pyproject.toml

@@ -14,16 +14,15 @@ classifiers = [
     "Operating System :: MacOS",
     "Operating System :: POSIX :: Linux",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: 3.15",
     "Topic :: Software Development",
 ]
-requires-python = ">=3.11"
+requires-python = ">=3.14"
 dependencies = [
-    "filelock>=3.16,<4",
+    "filelock>=4,<5",
     "genai-prices>=0.1.7,<0.2",
-    "httpx2>=2.13,<3",
+    "httpx2>=2.13.1,<3",
     # Exact: pcode relies on prompt_toolkit internals, and point releases
     # change them. Bump on purpose after tests/test_prompt_toolkit_internals.py
     # and make test-all pass on the new version.
@@ -34,13 +33,14 @@ dependencies = [
     # itself is downloaded on first use, not at install.
     # Harness ships from the pydantic-ai repo with every Pydantic AI release and
     # pins pydantic-ai-slim to the same minor; bump both together.
-    "pydantic-ai-harness[exa,coder,codemode,playwright]>=0.52.0,<0.53",
+    "pydantic-ai-harness[exa,coder,codemode,playwright]>=0.55.0,<0.56",
     # duckduckgo and web-fetch back the bundled web_research extension when no
     # provider-native search or Exa key is available.
     # google covers both google and google-cloud providers; bedrock pulls boto3.
-    "pydantic-ai-slim[anthropic,bedrock,duckduckgo,google,groq,mcp,openai,web-fetch,xai]>=2.52.0,<3",
-    "rich>=14,<15",
+    "pydantic-ai-slim[anthropic,bedrock,duckduckgo,google,groq,mcp,openai,web-fetch,xai]>=2.55.0,<3",
+    "rich>=15,<16",
     # FastMCP 4.x OAuth callback server selects Uvicorn's websockets-sansio protocol.
+    # Capped below 17 by google-genai (still <17 as of 2.29), not by pcode.
     "websockets>=15.0.1,<17",
 ]
 
@@ -49,7 +49,7 @@ dependencies = [
 # (about 95 MB to download, 215 MB installed); the sdist would run whatever
 # `claude` is on PATH instead of the CLI version pcode was verified against.
 claude = [
-    "claude-agent-sdk>=0.2.160,<0.3",
+    "claude-agent-sdk>=0.2.164,<0.3",
 ]
 
 [project.urls]

{pcode-0.1.1 → pcode-0.1.3}/src/pcode/agent.py

@@ -32,6 +32,7 @@ from pydantic_ai_harness.subagents import ModelOption, SubAgent
 from pydantic_ai_harness.tool_output_limits import ToolOutputLimits
 
 from pcode import remote_profile
+from pcode.background_delegation import BackgroundDelegation
 from pcode.cache_settings import ProviderCacheSettings, model_settings
 from pcode.cache_warnings import CacheBustReporting
 from pcode.claude_sdk import ClaudeWorkspace
@@ -359,8 +360,10 @@ def create_coder(
     """
     workspace = workspace.resolve()
     _ensure_bundled_rg()
-    # Delegation is pcode's own `WorkspaceSubAgents`, added below.
-    coder = Coder(sub_agents=False)
+    # Delegation is pcode's own `WorkspaceSubAgents`, added below. Caching is
+    # `ProviderCacheSettings`' per-provider choice: Coder's default `cache=True`
+    # would also reach Meridian and OpenAI's explicit-breakpoint models.
+    coder = Coder(sub_agents=False, caching=False)
     output_limits = create_tool_output_limits()
     # Keep Coder's tool selection, including its persistent shell (as a
     # `JobShell`). File display and repository discovery remain local adapters;
@@ -402,6 +405,8 @@ def create_coder(
     capabilities.append(
         _delegation(workspace, worker, subagents, extensions, output_limits, cache_notices)
     )
+    # Steering mid-delegation reaches the parent; the child keeps working.
+    capabilities.append(BackgroundDelegation())
     # Summarize evidence before discarding it; pcode owns compaction.
     return CombinedCapability([c for c in capabilities if not isinstance(c, ClearToolResults)])
 

{pcode-0.1.1 → pcode-0.1.3}/src/pcode/anthropic_oauth.py

@@ -403,7 +403,7 @@ async def _receive_code(port: int, state: str, timeout: float) -> str:
                 + body
             )
             await writer.drain()
-        except (OSError, asyncio.TimeoutError, UnicodeError):
+        except OSError, asyncio.TimeoutError, UnicodeError:
             code = ""
         finally:
             writer.close()