kolega-code 0.30.1__tar.gz → 0.32.0__tar.gz

{kolega_code-0.30.1 → kolega_code-0.32.0}/CHANGELOG.md

@@ -6,6 +6,80 @@ This project uses GitHub Releases for detailed generated release notes. This fil
 
 ## Unreleased
 
+## 0.32.0 - 2026-08-24
+
+### Added
+
+- **Editor integration over the Agent Client Protocol (ACP).** `kolega-code acp`
+  serves the full Kolega Code agent — models, tools, permissions, skills,
+  plan/build modes, sub-agent fan-out — to editors over stdio; Zed hosts it
+  natively through an `agent_servers` entry, and the new Editor Integration
+  docs page covers setup and flags (`--permission-mode`, `--acp-log`,
+  `--debug`). Each editor thread is an ordinary persisted Kolega Code session
+  that replays in the TUI, `kolega-code sessions`, exports, and `/share`.
+  Over the wire the agent server provides: TUI-faithful plan/build session
+  modes with task-list checklist rendering in the plan view and mid-turn mode
+  switching; tool approvals prompted through the editor
+  (`session/request_permission`) plus a model select and auto-approve toggle
+  as session config options; sub-agent dispatch cards with live progress and
+  per-subagent transcripts (Zed's `subagent_session_info` convention);
+  compaction shown as a collapsible thought view; advertised slash commands;
+  user questions via client elicitation; file edits rendered as diffs;
+  streamed terminal output; context-usage updates; and session load/restore so
+  clients can reopen previous threads.
+- Added DeepSeek V4 Flash Vision (`deepseek-v4-flash-vision-exp`),
+  DeepSeek's first multimodal model (experimental): 1M-token context, image
+  input, hosted web search, and `none`/`low`/`high`/`max` reasoning effort on
+  the Responses API.
+
+### Changed
+
+- OpenRouter catalog refreshed from the 2026-08-24 snapshots: 274 tool-capable
+  models, 20 featured.
+
+### Fixed
+
+- Sub-agents launched by `dispatch_agent` now run in auto permission mode.
+  An ask-mode parent previously passed its approval callback down to the
+  sub-agent, which could hang a turn waiting for a prompt that ACP clients
+  cannot render for delegated work.
+- Streaming consumers now receive reasoning and response text as clean,
+  ordered segments: thinking is flushed the moment prose starts (and vice
+  versa) instead of interleaving at buffer boundaries, and a lower flush
+  threshold makes streaming feel more responsive in every frontend.
+
+## 0.31.0 - 2026-08-20
+
+### Added
+
+- Prompt history: submitted prompts are saved per project (capped at 100)
+  and persist across sessions. Press the up arrow in the composer to recall
+  previous prompts, even after restarting the app.
+
+### Changed
+
+- Kolega Code is now licensed under the Business Source License 1.1.
+- Bundled skills updated to v0.3.3.
+- Model catalogs refreshed: OpenRouter now lists 273 models, Tinker 26,
+  Ollama Cloud 19, and the Perplexity Agent catalog (45 models) is now
+  generated from live endpoints.
+- Bundled prompts are now stable across projects and no longer carry
+  open-source secrecy language.
+
+### Fixed
+
+- Cancelling a turn (Ctrl-C) while a terminal tool call (`exec_command` /
+  `write_stdin`) was in flight now stops the agent on the first press. The
+  command is still killed and its partial output is kept in the transcript,
+  but the agent no longer swallows the cancellation and continues with
+  another model request.
+- Tinker models reserve their full max output against the shared
+  input/output window, so a near-full prompt can no longer leave generation
+  with almost no room.
+- Skill invocations now appear in the transcript as a one-line "Activated
+  skill `/name`." label followed by the complete submitted command, instead
+  of dumping the skill's activation contents into the chat.
+
 ## 0.30.1 - 2026-08-17
 
 ### Fixed

kolega_code-0.32.0/LICENSE

@@ -0,0 +1,115 @@
+# Business Source License 1.1
+
+## Parameters
+
+**Licensor:** KLG Tech Innovations Limited
+
+**Licensed Work:** Kolega Code — Multi-agent coding in the terminal
+([github.com/kolega-ai/kolega-code](https://github.com/kolega-ai/kolega-code)).
+The Licensed Work is (c) 2026 KLG Tech Innovations Limited.
+
+**Additional Use Grant:** You may make production use of the Licensed Work,
+provided Your use does not include offering the Licensed Work to third parties
+on a hosted or embedded basis in order to compete with KLG Tech Innovations
+Limited's paid version(s) of the Licensed Work. For purposes of this license:
+
+A "competitive offering" is a product or service that is offered to third
+parties on a paid basis, including through paid support arrangements, that
+significantly overlaps with the capabilities of KLG Tech Innovations Limited's
+paid version(s) of the Licensed Work. Products or services that are not
+offered to third parties, or that are offered free of charge, are not
+competitive.
+
+"Hosted basis" means making the capabilities of the Licensed Work available to
+third parties as a managed or remotely accessible service, such as a hosted or
+cloud-based coding-agent service.
+
+"Embedded" means including the source code or executable code of the Licensed
+Work in a competitive offering, or packaging the competitive offering in such
+a way that the Licensed Work must be accessed or downloaded for the
+competitive offering to operate.
+
+**Change Date:** 2030-08-12
+
+**Change License:** GNU Affero General Public License, Version 3.0 or later
+
+For information about alternative licensing arrangements for the Licensed
+Work, please contact the Licensor.
+
+## Notice
+
+The Business Source License (this document, or the "License") is not an Open
+Source license. However, the Licensed Work will eventually be made available
+under an Open Source License, as stated in this License.
+
+License text copyright (c) 2017 MariaDB Corporation Ab, All Rights Reserved.
+"Business Source License" is a trademark of MariaDB Corporation Ab.
+
+---
+
+## Terms
+
+The Licensor hereby grants you the right to copy, modify, create derivative
+works, redistribute, and make non-production use of the Licensed Work. The
+Licensor may make an Additional Use Grant, above, permitting limited
+production use.
+
+Effective on the Change Date, or the fourth anniversary of the first publicly
+available distribution of a specific version of the Licensed Work under this
+License, whichever comes first, the Licensor hereby grants you rights under
+the terms of the Change License, and the rights granted in the paragraph
+above terminate.
+
+If your use of the Licensed Work does not comply with the requirements
+currently in effect as described in this License, you must purchase a
+commercial license from the Licensor, its affiliated entities, or authorized
+resellers, or you must refrain from using the Licensed Work.
+
+All copies of the original and modified Licensed Work, and derivative works
+of the Licensed Work, are subject to this License. This License applies
+separately for each version of the Licensed Work and the Change Date may vary
+for each version of the Licensed Work released by Licensor.
+
+You must conspicuously display this License on each original or modified copy
+of the Licensed Work. If you receive the Licensed Work in original or
+modified form from a third party, the terms and conditions set forth in this
+License apply to your use of that work.
+
+Any use of the Licensed Work in violation of this License will automatically
+terminate your rights under this License for the current and all other
+versions of the Licensed Work.
+
+This License does not grant you any right in any trademark or logo of
+Licensor or its affiliates (provided that you may use a trademark or logo of
+Licensor as expressly required by this License).
+
+TO THE EXTENT PERMITTED BY APPLICABLE LAW, THE LICENSED WORK IS PROVIDED ON
+AN "AS IS" BASIS. LICENSOR HEREBY DISCLAIMS ALL WARRANTIES AND CONDITIONS,
+EXPRESS OR IMPLIED, INCLUDING (WITHOUT LIMITATION) WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, AND
+TITLE.
+
+MariaDB hereby grants you permission to use this License's text to license
+your works, and to refer to it using the trademark "Business Source License",
+as long as you comply with the Covenants of Licensor below.
+
+## Covenants of Licensor
+
+In consideration of the right to use this License's text and the "Business
+Source License" name and trademark, Licensor covenants to MariaDB, and to all
+other recipients of the licensed work to be provided by Licensor:
+
+1. To specify as the Change License the GPL Version 2.0 or any later version,
+   or a license that is compatible with GPL Version 2.0 or a later version,
+   where "compatible" means that software provided under the Change License
+   can be included in a program with software provided under GPL Version 2.0
+   or a later version. Licensor may specify additional Change Licenses
+   without limitation.
+
+2. To either: (a) specify an additional grant of rights to use that does not
+   impose any additional restriction on the right granted in this License, as
+   the Additional Use Grant; or (b) insert the text "None".
+
+3. To specify a Change Date.
+
+4. Not to modify this License in any other way.

kolega_code-0.32.0/PKG-INFO

@@ -0,0 +1,343 @@
+Metadata-Version: 2.4
+Name: kolega-code
+Version: 0.32.0
+Summary: Multi-agent coding in the terminal
+Project-URL: Homepage, https://kolega-ai.github.io/kolega-code/
+Project-URL: Documentation, https://kolega-ai.github.io/kolega-code/
+Project-URL: Repository, https://github.com/kolega-ai/kolega-code
+Project-URL: Issues, https://github.com/kolega-ai/kolega-code/issues
+Project-URL: Changelog, https://github.com/kolega-ai/kolega-code/blob/main/CHANGELOG.md
+Project-URL: Contributing, https://github.com/kolega-ai/kolega-code/blob/main/CONTRIBUTING.md
+Project-URL: Releases, https://github.com/kolega-ai/kolega-code/releases
+Project-URL: Security, https://github.com/kolega-ai/kolega-code/security/policy
+Author: Kolega Team
+License-Expression: BUSL-1.1
+License-File: LICENSE
+Keywords: agent,ai,cli,coding-agent,developer-tools
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+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: Topic :: Software Development
+Classifier: Topic :: Utilities
+Requires-Python: >=3.11
+Requires-Dist: agent-client-protocol==0.12.0
+Requires-Dist: anthropic==0.101.0
+Requires-Dist: atif==1.7.0
+Requires-Dist: beautifulsoup4==4.14.3
+Requires-Dist: cryptography==48.0.1; sys_platform == 'darwin' and platform_machine == 'x86_64'
+Requires-Dist: cryptography==50.0.0; sys_platform != 'darwin' or platform_machine != 'x86_64'
+Requires-Dist: ddgs==9.14.4
+Requires-Dist: fastapi==0.139.2
+Requires-Dist: filelock==3.20.3
+Requires-Dist: firecrawl-py==4.28.2
+Requires-Dist: google-genai==2.12.1
+Requires-Dist: httpx==0.28.1
+Requires-Dist: idna==3.18
+Requires-Dist: jinja2==3.1.6
+Requires-Dist: langfuse==3.14.5
+Requires-Dist: lxml-html-clean==0.4.5
+Requires-Dist: markdownify==1.2.3
+Requires-Dist: markitdown[docx,pdf,pptx,xls,xlsx]==0.1.6
+Requires-Dist: mcp==1.28.1
+Requires-Dist: nest-asyncio==1.6.0
+Requires-Dist: onnxruntime==1.27.0; python_version >= '3.14' and sys_platform != 'win32'
+Requires-Dist: openai==2.46.0
+Requires-Dist: packaging==25.0
+Requires-Dist: pathspec==1.1.1
+Requires-Dist: pillow==12.3.0
+Requires-Dist: playwright==1.59.0
+Requires-Dist: psutil==7.2.2
+Requires-Dist: pydantic==2.13.4
+Requires-Dist: pygments==2.20.0
+Requires-Dist: python-dotenv==1.2.2
+Requires-Dist: pyyaml==6.0.3
+Requires-Dist: readability-lxml==0.8.4.1
+Requires-Dist: tavily-python==0.7.26
+Requires-Dist: tenacity==9.1.4
+Requires-Dist: textual==8.2.5
+Requires-Dist: tiktoken==0.12.0
+Requires-Dist: trafilatura==2.0.0
+Requires-Dist: uvicorn==0.49.0
+Requires-Dist: websockets==16.0
+Provides-Extra: cli
+Provides-Extra: dev
+Requires-Dist: genbadge[coverage]==1.1.3; extra == 'dev'
+Requires-Dist: pre-commit==4.6.0; extra == 'dev'
+Requires-Dist: pyright==1.1.411; extra == 'dev'
+Requires-Dist: pytest-asyncio==1.3.0; extra == 'dev'
+Requires-Dist: pytest-cov==7.0.0; extra == 'dev'
+Requires-Dist: pytest-xdist==3.8.0; extra == 'dev'
+Requires-Dist: pytest==9.0.3; extra == 'dev'
+Requires-Dist: ruff==0.15.12; extra == 'dev'
+Requires-Dist: twine==6.2.0; extra == 'dev'
+Provides-Extra: tinker
+Requires-Dist: tinker-cookbook==0.5.4; extra == 'tinker'
+Requires-Dist: tinker==0.25.0; extra == 'tinker'
+Requires-Dist: tml-renderers==0.1.0; extra == 'tinker'
+Description-Content-Type: text/markdown
+
+# Kolega Code
+
+**A terminal coding agent where the model writes its own multi-agent workflows.**
+
+[![PyPI version](https://img.shields.io/pypi/v/kolega-code)](https://pypi.org/project/kolega-code/)
+[![Python versions](https://img.shields.io/pypi/pyversions/kolega-code)](https://pypi.org/project/kolega-code/)
+[![CI](https://github.com/kolega-ai/kolega-code/actions/workflows/ci.yml/badge.svg)](https://github.com/kolega-ai/kolega-code/actions/workflows/ci.yml)
+[![Coverage](docs/src/assets/coverage.svg)](https://github.com/kolega-ai/kolega-code/actions/workflows/ci.yml)
+[![Docs](https://img.shields.io/badge/docs-kolega--ai.github.io-blue)](https://kolega-ai.github.io/kolega-code/)
+[![Changelog](https://img.shields.io/badge/changelog-keep%20up-blue)](CHANGELOG.md)
+
+Kolega Code is a local-first terminal coding agent. For work that is too broad
+for one agent loop, its **Gigacode** engine has the model write a Python program
+that orchestrates multiple sub-agents. The runtime then executes that program.
+
+![Kolega Code in action](docs/src/assets/demo.gif)
+
+## Gigacode: model-authored orchestration
+
+For a repo-wide review, a migration, or a plan with independent workstreams, the
+model writes an orchestration program instead of delegating workers one at a
+time. The program can combine parallel phases, pipelines, adversarial
+verification, judge panels, and synthesis gates to fit the task. The runtime
+saves the script so it can be inspected and run again.
+
+Claude Code uses the same model-authored approach for its dynamic workflows
+(ultracode). Kolega Code provides an open, provider-agnostic implementation
+whose runtime source is available in this repository.
+
+The runtime journals each completed agent call to disk. Resume is content-keyed
+rather than positional: when you use `resume_from_run_id`, calls with unchanged
+semantic inputs replay from the journal at zero token cost. This still works if
+the script was edited or reordered, and it works across sessions and process
+restarts.
+
+Read [how gigacode works](how-gigacode-works.md) for the architecture, or an
+[unedited model-authored workflow](examples/parallel-code-review.py) with its
+full provenance and execution record.
+
+## How it works
+
+The model investigates your repo, then writes a Python program against a small
+runtime API (`agent`, `parallel`, `pipeline`, `phase`, `budget`). The runtime
+enforces concurrency caps, an agent-count backstop, and token-budget accounting.
+It dispatches typed sub-agents, including read-only investigators, coders, and
+browser agents, whose activity streams into the TUI's sub-agent inspector.
+
+As the run progresses, the runtime writes the script, per-call results,
+transcripts, and final result to disk. An interrupted or budget-capped run keeps
+its journal and can be resumed, with unchanged calls replaying free. The
+mechanics, guarantees, and limitations are documented in
+[how-gigacode-works.md](how-gigacode-works.md).
+
+## The rest of the agent
+
+Gigacode is off by default. Enable it with `/gigacode on`. For focused changes,
+use Kolega Code as an ordinary terminal coding agent:
+
+- **Plan/Build modes:** read-only Plan mode for investigation and a reviewable
+  task list, Build mode to implement (`Shift+Tab` to switch). In Plan mode,
+  workflow sub-agents are forced read-only too.
+- **Repo tools:** read and search code, create files, apply precise edits, and
+  inspect session changes/diffs.
+- **Terminal execution:** run shell commands with streamed output and
+  project-level permission controls.
+- **Web search and browsing:** DuckDuckGo by default with no key; Firecrawl,
+  Tavily, and SearXNG configurable; direct URL fetch; a Playwright-powered
+  browser agent for interactive sites.
+- **MCP servers:** connect `streamable_http`, `sse`, and `stdio` MCP servers
+  (including OAuth-enabled HTTP servers) as permission-gated tools.
+- **Interactive or scriptable:** Textual TUI with queued follow-ups, one-shot
+  `kolega-code ask` with JSON output, session list/export/resume, `doctor`.
+- **Editor integration:** drive the full agent from Zed or VS Code over the
+  Agent Client Protocol — streamed responses, tool cards, diffs, permission
+  prompts, plan/build approval, session restore, slash commands, and sub-agent
+  transcripts ([docs](https://kolega-ai.github.io/kolega-code/editor-integration/)).
+- **Extensibility:** agent skills, project prompt-template overrides
+  ([docs](https://kolega-ai.github.io/kolega-code/configuration/prompt-overrides/)),
+  lifecycle hooks, persistent project permission rules.
+- **Local-first state:** sessions, settings, permissions, OAuth tokens, and
+  API-key settings stay on your machine with restrictive permissions where
+  applicable.
+
+## Editor integration (ACP)
+
+`kolega-code acp` serves the Agent Client Protocol, so Zed and VS Code can host
+the full agent — including permissions, plan/build modes, and sub-agent
+transcripts. Configure Zed with:
+
+```json
+{
+  "agent_servers": {
+    "Kolega Code": {
+      "command": "/absolute/path/to/bin/kolega-code",
+      "args": ["acp", "--permission-mode", "ask"]
+    }
+  }
+}
+```
+
+Use an absolute binary path: a bare `kolega-code` resolves to whatever is on the
+editor's `PATH`, so an installed release can shadow a dev checkout. Full setup
+for Zed, VS Code, and other ACP clients is in the
+[editor integration docs](https://kolega-ai.github.io/kolega-code/editor-integration/).
+
+## Quick start
+
+**1. Install** with the script:
+
+```bash
+curl -fsSL https://kolega.dev/install-kolega-code.sh | sh
+```
+
+Or with [uv](https://docs.astral.sh/uv/) (or `pip`):
+
+```bash
+uv tool install kolega-code
+# or: pip install kolega-code
+```
+
+Verify the install:
+
+```bash
+kolega-code --version
+```
+
+**2. Start a session** in your project:
+
+```bash
+kolega-code .
+```
+
+**3. Connect a model.** Complete the first-run wizard with ChatGPT sign-in or an
+API key. Later, open Settings from the sidebar or with `/settings`. Use
+`Shift+Tab` to switch between **Plan** and **Build** mode, or run `/gigacode on`
+when a task is broad enough for fan-out.
+
+Resume a previous conversation:
+
+```bash
+kolega-code . --resume            # latest session
+kolega-code . --resume <id>       # a specific Resume ID from `sessions list`
+```
+
+## Two ways to use it
+
+| Mode | Command | Best for |
+| --- | --- | --- |
+| **Interactive TUI** | `kolega-code .` | Day-to-day development, exploration, orchestration |
+| **One-shot** | `kolega-code ask "…"` | Scripting, automation, quick questions, CI |
+
+Helper commands for sessions and setup:
+
+```bash
+kolega-code ask "summarize this repository" --project .
+kolega-code sessions list --project .
+kolega-code doctor --project .
+```
+
+## Models and routing
+
+Kolega Code can route models by role. You can use a strong long-context model
+for the main loop, a faster model for utility calls, and a dedicated model for
+extended thinking. Per-agent-role overrides are available for planning,
+building, investigation, general, and browser agents. A Gigacode workflow can
+also pin cheaper models to individual calls with `model_override`, allowing one
+model to write the orchestration while cheaper models run its agents.
+
+Supported model providers:
+
+- Anthropic
+- OpenAI API
+- OpenAI via ChatGPT subscription sign-in
+- Google
+- Groq
+- Together.ai
+- Fireworks.ai
+- xAI / Grok
+- DashScope / Qwen
+- OpenRouter (gateway to 250+ tool-capable models)
+- Moonshot / Kimi
+- DeepSeek
+- Z.AI / GLM Coding Plan
+- Kimi Coding Plan
+- Ollama Cloud
+- local Llama
+
+With a paid **ChatGPT** plan (Plus, Pro, or Business), `/login chatgpt` runs
+OpenAI models without a separate API key; tokens are stored locally (chmod `600`)
+and refreshed automatically. See
+[Sign in with ChatGPT](https://kolega-ai.github.io/kolega-code/configuration/sign-in-with-chatgpt/).
+
+Web search backends include DuckDuckGo (the default, with no key), Firecrawl,
+Tavily, and self-hosted SearXNG. Choose one in Settings or with
+`KOLEGA_CODE_WEB_SEARCH_BACKEND`.
+See [Providers & Models](https://kolega-ai.github.io/kolega-code/configuration/providers-and-models/)
+for model IDs, role configuration, API-key variables, and thinking-effort options.
+
+## Configuration
+
+Set provider, model, and API keys from onboarding or the Settings editor, or via
+environment variables and flags for non-interactive use:
+
+```bash
+export KOLEGA_CODE_PROVIDER=deepseek
+export DEEPSEEK_API_KEY=...
+kolega-code ask "summarize this repository" --project . --provider deepseek --model deepseek-v4-pro
+```
+
+API key variables only provide credentials. Pick a provider and model explicitly
+or save them in Settings. Local session state lives under your platform's state
+directory unless `KOLEGA_CODE_STATE_DIR` is set. See the
+[Configuration docs](https://kolega-ai.github.io/kolega-code/configuration/settings-and-api-keys/)
+for the full story.
+
+## Requirements
+
+- **Python 3.11+**
+- An **API key**, ChatGPT sign-in, or local model for at least one supported model provider
+- A terminal that supports a modern TUI (most do)
+
+## Documentation
+
+This repo includes the [Gigacode architecture document](how-gigacode-works.md)
+and an [unedited model-authored example workflow](examples/parallel-code-review.py).
+
+Full documentation lives at **[kolega-ai.github.io/kolega-code](https://kolega-ai.github.io/kolega-code/)**:
+
+- [Gigacode user guide](https://kolega-ai.github.io/kolega-code/gigacode/)
+- [Quick Start](https://kolega-ai.github.io/kolega-code/getting-started/quick-start/)
+- [CLI overview](https://kolega-ai.github.io/kolega-code/cli/overview/)
+- [How it works & concepts](https://kolega-ai.github.io/kolega-code/concepts/how-it-works/)
+- [Configuration](https://kolega-ai.github.io/kolega-code/configuration/settings-and-api-keys/)
+
+## Project resources
+
+- [Documentation](https://kolega-ai.github.io/kolega-code/)
+- [Releases](https://github.com/kolega-ai/kolega-code/releases)
+- [Changelog](CHANGELOG.md)
+- [Contributing](CONTRIBUTING.md)
+- [Security policy](SECURITY.md)
+- [Issue tracker](https://github.com/kolega-ai/kolega-code/issues)
+- [Discord community](https://discord.gg/kaS8PKKp4)
+
+## Contributing
+
+Contributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for local setup,
+running the test suite, and building the docs site. Please report security issues
+privately per [SECURITY.md](SECURITY.md).
+
+## Join the community
+
+Building something with Kolega Code, hit a rough edge, or want to shape where
+Gigacode goes next? Come talk to us.
+
+[![Join our Discord](https://img.shields.io/badge/Discord-join%20the%20community-5865F2?logo=discord&logoColor=white)](https://discord.gg/kaS8PKKp4)
+
+**→ [Join the Kolega Code Discord](https://discord.gg/kaS8PKKp4)** — share workflows,
+get help, and hear about releases first.

{kolega_code-0.30.1 → kolega_code-0.32.0}/README.md

@@ -4,7 +4,6 @@
 
 [![PyPI version](https://img.shields.io/pypi/v/kolega-code)](https://pypi.org/project/kolega-code/)
 [![Python versions](https://img.shields.io/pypi/pyversions/kolega-code)](https://pypi.org/project/kolega-code/)
-[![License: Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)
 [![CI](https://github.com/kolega-ai/kolega-code/actions/workflows/ci.yml/badge.svg)](https://github.com/kolega-ai/kolega-code/actions/workflows/ci.yml)
 [![Coverage](docs/src/assets/coverage.svg)](https://github.com/kolega-ai/kolega-code/actions/workflows/ci.yml)
 [![Docs](https://img.shields.io/badge/docs-kolega--ai.github.io-blue)](https://kolega-ai.github.io/kolega-code/)
@@ -71,6 +70,10 @@ use Kolega Code as an ordinary terminal coding agent:
   (including OAuth-enabled HTTP servers) as permission-gated tools.
 - **Interactive or scriptable:** Textual TUI with queued follow-ups, one-shot
   `kolega-code ask` with JSON output, session list/export/resume, `doctor`.
+- **Editor integration:** drive the full agent from Zed or VS Code over the
+  Agent Client Protocol — streamed responses, tool cards, diffs, permission
+  prompts, plan/build approval, session restore, slash commands, and sub-agent
+  transcripts ([docs](https://kolega-ai.github.io/kolega-code/editor-integration/)).
 - **Extensibility:** agent skills, project prompt-template overrides
   ([docs](https://kolega-ai.github.io/kolega-code/configuration/prompt-overrides/)),
   lifecycle hooks, persistent project permission rules.
@@ -78,6 +81,28 @@ use Kolega Code as an ordinary terminal coding agent:
   API-key settings stay on your machine with restrictive permissions where
   applicable.
 
+## Editor integration (ACP)
+
+`kolega-code acp` serves the Agent Client Protocol, so Zed and VS Code can host
+the full agent — including permissions, plan/build modes, and sub-agent
+transcripts. Configure Zed with:
+
+```json
+{
+  "agent_servers": {
+    "Kolega Code": {
+      "command": "/absolute/path/to/bin/kolega-code",
+      "args": ["acp", "--permission-mode", "ask"]
+    }
+  }
+}
+```
+
+Use an absolute binary path: a bare `kolega-code` resolves to whatever is on the
+editor's `PATH`, so an installed release can shadow a dev checkout. Full setup
+for Zed, VS Code, and other ACP clients is in the
+[editor integration docs](https://kolega-ai.github.io/kolega-code/editor-integration/).
+
 ## Quick start
 
 **1. Install** with the script:
@@ -223,10 +248,6 @@ Contributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for local setu
 running the test suite, and building the docs site. Please report security issues
 privately per [SECURITY.md](SECURITY.md).
 
-## License
-
-Released under the [Apache License 2.0](LICENSE).
-
 ## Join the community
 
 Building something with Kolega Code, hit a rough edge, or want to shape where

{kolega_code-0.30.1 → kolega_code-0.32.0}/kolega_code/__init__.py

@@ -174,4 +174,4 @@ __all__ = [
     "parse_git_status_output",
 ]
 
-__version__ = "0.30.1"
+__version__ = "0.32.0"

{kolega_code-0.30.1 → kolega_code-0.32.0}/kolega_code/_bundled_skills/manifest.json

@@ -154,7 +154,7 @@
     },
     {
       "path": "skills/review/SKILL.md",
-      "sha256": "c1075593eea35e27d744c7180636210fab6092059d6e08b3faa1bf1e45e97a67"
+      "sha256": "8f533bfb1a4471eeba3ed3b95ad02c43270e89d24d151ea81eb3ccc3afe3a3ae"
     },
     {
       "path": "skills/review/references/github-publishing.md",
@@ -217,8 +217,8 @@
     "xlsx"
   ],
   "source": {
-    "commit": "2de7491964d92e3dc78f13290d875c800ac6e22d",
+    "commit": "0d8188f00af97c4f98c58dc2ebe090099481e216",
     "repository": "https://github.com/kolega-ai/kolega-skills",
-    "tag": "v0.3.2"
+    "tag": "v0.3.3"
   }
 }

{kolega_code-0.30.1 → kolega_code-0.32.0}/kolega_code/_bundled_skills/skills/review/SKILL.md

@@ -91,9 +91,10 @@ output and collect:
 - base/head names and full object IDs;
 - changed paths and the complete patch.
 
-Stop without reviewing when the PR is not open, is a draft, has no effective changes, or
-cannot be read. Give the reason. Do not exclude a change merely because automation authored
-it.
+Review PRs in any state: open, draft, closed, or merged. Stop without reviewing only when
+the PR cannot be read or has no effective changes; give the reason. Note the state and draft
+status in the report when the PR is not open. Do not exclude a change merely because
+automation authored it.
 
 Reject a PR URL whose host is not GitHub before retrieval. Explain that local and branch
 review remain available for changes hosted elsewhere.

kolega_code-0.32.0/kolega_code/acp/__init__.py

@@ -0,0 +1,38 @@
+"""ACP agent side for kolega-code.
+
+Makes kolega-code usable from ACP clients (Zed, JetBrains, VS Code via
+extensions, Neovim, Emacs) by serving the Agent Client Protocol v1 over
+stdio. The client spawns this process and owns its lifecycle.
+
+stdout carries only ACP JSON-RPC frames (owned by the SDK transport); all
+diagnostics go to stderr. See ``acp-implementation-plan.md`` (repo root) for
+the full design and phases.
+"""
+
+from __future__ import annotations
+
+from kolega_code.acp.agent_factory import ACP_AGENT_MODE, ACP_PERMISSION_MODE, MODE_BUILD, MODE_PLAN, AgentFactory
+from kolega_code.acp.bridge import TOOL_KINDS, AcpBridge
+from kolega_code.acp.diffs import AcpDiffProvider
+from kolega_code.acp.permissions import AcpPermissionBroker
+from kolega_code.acp.plans import task_entries_from_markdown
+from kolega_code.acp.server import AcpAgent
+from kolega_code.acp.session import AcpSession
+from kolega_code.acp.usage import build_usage_update, context_window_for
+
+__all__ = [
+    "ACP_AGENT_MODE",
+    "ACP_PERMISSION_MODE",
+    "MODE_BUILD",
+    "MODE_PLAN",
+    "AcpAgent",
+    "AcpBridge",
+    "AcpDiffProvider",
+    "AcpPermissionBroker",
+    "AcpSession",
+    "AgentFactory",
+    "TOOL_KINDS",
+    "build_usage_update",
+    "context_window_for",
+    "task_entries_from_markdown",
+]