kolega-code 0.10.0__tar.gz → 0.11.0__tar.gz

{kolega_code-0.10.0 → kolega_code-0.11.0}/CHANGELOG.md

@@ -6,6 +6,19 @@ This project uses GitHub Releases for detailed generated release notes. This fil
 
 ## Unreleased
 
+## 0.11.0 - 2026-06-26
+
+### Added
+
+- Added queued follow-up messages in the TUI so users can submit additional
+  prompts while an active turn is still running.
+
+### Changed
+
+- Moved task-list status into the sidebar and refined sidebar presentation.
+- Updated documentation and positioning copy for gigacode and queued follow-up
+  messages.
+
 ## 0.10.0 - 2026-06-25
 
 ### Added

{kolega_code-0.10.0 → kolega_code-0.11.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: kolega-code
-Version: 0.10.0
-Summary: Local-first AI coding agent for the terminal
+Version: 0.11.0
+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
@@ -82,7 +82,7 @@ Description-Content-Type: text/markdown
 
 # Kolega Code
 
-**An AI coding agent that runs in your terminal — local-first, model-agnostic, plan-then-build.**
+**Multi-agent coding in the terminal.**
 
 [![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/)
@@ -92,41 +92,65 @@ Description-Content-Type: text/markdown
 [![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)
 
-Point Kolega Code at a project directory and it opens an interactive UI where you talk to an
-agent that can read and edit your code, run shell commands, search the codebase, browse the
-web, and dispatch specialized sub-agents to get work done.
-
-It's **local-first**: the agent operates on your actual filesystem and terminal, and your
-sessions, settings, and API keys stay on your own machine.
+Kolega Code is a local-first terminal coding agent built for work that is too wide
+for one loop: fan out specialized sub-agents with **Gigacode**, route different
+models to different jobs, search the web, drive a browser, and keep sessions,
+settings, permissions, and credentials on your machine.
 
 ![Kolega Code in action](docs/src/assets/demo.gif)
 
-## Why Kolega Code
-
-- **Plans before it builds.** A read-only **Plan mode** produces a reviewable plan and a
-  shared task list before anything changes; **Build mode** implements it. Toggle with `Shift+Tab`.
-- **Orchestrates many agents.** For larger jobs, the main agent dispatches specialized
-  sub-agents (investigation, browser, coding, general) and can fan them out in parallel for
-  broad audits, large migrations, or implementing a plan's independent parts at once.
-- **Local-first by design.** It works on your real files and terminal; sessions, settings,
-  and credentials live on your machine, not in someone else's cloud.
-- **Bring your own model.** Talks to a range of providers and lets you assign different models
-  to different roles.
-
-## What it does
-
-- **Reads and edits your code.** Opens files, searches across the codebase, creates new files,
-  and applies precise edits.
-- **Runs commands.** Executes shell commands and watches their output in a dedicated terminal view.
-- **Plans before it builds.** Plan mode investigates and proposes; Build mode executes.
-- **Searches and browses the web.** The agent can search for relevant pages, fetch URLs
-  directly, or use the built-in browser agent (powered by Playwright) when a task needs
-  site interaction.
-- **Dispatches sub-agents.** Hands work off to specialized agents and tracks their activity live.
-- **Orchestrates workflows.** With [gigacode](https://kolega-ai.github.io/kolega-code/gigacode/),
-  it fans out many sub-agents in parallel.
-- **Works non-interactively too.** Run a single prompt with `kolega-code ask`, get JSON output,
-  and save or resume sessions.
+## Built for work one agent cannot cover
+
+Most terminal agents are strongest when one model can reason through one task at a
+time. Kolega Code keeps that familiar workflow, then adds orchestration for broad work:
+large audits, sweeping migrations, cross-file checks, adversarial reviews, and
+implementation plans whose pieces can run independently.
+
+With [Gigacode](https://kolega-ai.github.io/kolega-code/gigacode/), Kolega Code can:
+
+- **Fan out many sub-agents at once.** Split a wide codebase review by package,
+  assign independent implementation tasks, or run checks across many directories in
+  parallel.
+- **Use real workflow shapes.** The agent can generate parallel phases, pipelines,
+  loops, judge panels, and synthesis steps instead of only delegating one task at a
+  time.
+- **Keep orchestration visible.** Workflow phase headers and progress lines appear
+  in the transcript; the sub-agent inspector shows each agent's live trajectory.
+- **Save inspectable artifacts.** Each run keeps the generated workflow script,
+  result files, a Markdown transcript, raw JSONL, a resume journal, and debug
+  sub-agent transcripts under Kolega Code's state directory.
+- **Run in either mode.** In Plan mode, workflow sub-agents stay read-only for
+  parallel investigation. In Build mode, they can use the full coding toolset.
+- **Resume interrupted runs.** Finished workflow steps are journaled so a deliberate
+  resume does not have to restart the whole fan-out.
+
+Use normal chat for focused changes. Turn on Gigacode when the problem is broad
+enough that one serial agent pass would be the bottleneck.
+
+## Features
+
+- **Gigacode orchestration:** parallel, pipelined, looped, judged, and synthesized
+  multi-agent workflows with saved artifacts and resume support.
+- **Specialized sub-agents:** planning, building/coder, investigation, general, and
+  browser agents, with live activity tracking in the TUI.
+- **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.
+- **Plan/build workflow:** use read-only Plan mode for investigation and a reviewable
+  task list, then Build mode to implement.
+- **Web search and browsing:** DuckDuckGo works by default with no key; Firecrawl,
+  Tavily, and SearXNG are configurable search backends. Kolega Code can also fetch URLs
+  directly and use a Playwright-powered browser agent for interactive sites.
+- **Model routing:** choose provider/model combinations, set thinking effort, split
+  long-context/fast/thinking roles, and override models per agent role.
+- **Interactive or scriptable:** use the Textual TUI, queue follow-up prompts
+  while the agent is working, run `kolega-code ask`, request JSON output,
+  list/export/resume sessions, and diagnose setup with `doctor`.
+- **Extensibility:** add agent skills, override prompts with project templates, run
+  lifecycle hooks, and persist project permission rules.
+- **Local-first state:** sessions, settings, permissions, OAuth tokens, and API-key
+  settings stay on your machine with restrictive permissions where applicable.
 
 ## Quick start
 
@@ -155,8 +179,9 @@ kolega-code --version
 kolega-code .
 ```
 
-**3. Add a provider key.** Open the **Settings** tab to pick a provider and model and save your
-API key. Then press `Shift+Tab` anytime to switch between **Plan** and **Build** mode.
+**3. Add a provider key.** Open the **Settings** tab to pick a provider/model and
+save your API key. 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:
 
@@ -169,7 +194,7 @@ kolega-code . --resume <id>       # a specific thread or session
 
 | Mode | Command | Best for |
 | --- | --- | --- |
-| **Interactive TUI** | `kolega-code .` | Day-to-day development, exploration, pair-programming |
+| **Interactive TUI** | `kolega-code .` | Day-to-day development, exploration, orchestration |
 | **One-shot** | `kolega-code ask "…"` | Scripting, automation, quick questions, CI |
 
 There are also helper commands for managing sessions and checking your setup:
@@ -180,25 +205,60 @@ kolega-code sessions list --project .
 kolega-code doctor --project .
 ```
 
-## Bring your own model
+## Supported providers
+
+Kolega Code supports a broad model-provider catalog and lets you route models by
+role instead of forcing one model to do every job.
+
+Supported model providers:
+
+- Anthropic
+- OpenAI API
+- OpenAI via ChatGPT subscription sign-in
+- Google
+- Groq
+- Together.ai
+- Fireworks.ai
+- xAI / Grok
+- DashScope / Qwen
+- Moonshot / Kimi
+- DeepSeek
+- Z.AI / GLM Coding Plan
+- Kimi Coding Plan
+- Ollama Cloud
+- local Llama
+
+Supported web-search backends:
+
+- DuckDuckGo — default, no key required
+- Firecrawl
+- Tavily
+- SearXNG — self-hosted option
+
+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.
+
+## Model routing
 
-Kolega Code talks to a range of LLM providers — including Anthropic, OpenAI, Google, Moonshot,
-and DeepSeek — and lets you assign **different models to different roles**: a strong
-long-context model for coding, a fast cheap model for small utility calls, and one for extended
-"thinking". See [Providers & Models](https://kolega-ai.github.io/kolega-code/configuration/providers-and-models/).
+Kolega Code can assign different models to different operational roles: a strong
+long-context model for the main coding loop, a faster model for utility calls, and
+a dedicated model for extended thinking. You can also override models per agent
+role — planning, building, investigation, general, and browser — so wide workflows
+can use cheaper models where they fit and stronger models where they matter.
 
 ## Sign in with ChatGPT
 
-If you have a paid **ChatGPT** plan (Plus, Pro, or Business), you can use it to run OpenAI models
-instead of a separate API key. Run `/login chatgpt` in the TUI, complete the browser sign-in, and
-Kolega Code switches to the **OpenAI (ChatGPT subscription)** provider (default `gpt-5.5`). Tokens are
-stored locally (chmod `600`) and refreshed automatically; `/logout chatgpt` removes them. See
+If you have a paid **ChatGPT** plan (Plus, Pro, or Business), you can use it to run
+OpenAI models instead of a separate API key. Run `/login chatgpt` in the TUI,
+complete the browser sign-in, and Kolega Code switches to the **OpenAI (ChatGPT
+subscription)** provider (default `gpt-5.5`). Tokens are stored locally (chmod
+`600`) and refreshed automatically; `/logout chatgpt` removes them. See
 [Sign in with ChatGPT](https://kolega-ai.github.io/kolega-code/configuration/sign-in-with-chatgpt/).
 
 ## Configuration
 
-Set your provider, model, and API keys from the **Settings** tab in the UI, or via environment
-variables and flags for non-interactive use:
+Set your provider, model, and API keys from the **Settings** tab in the UI, or via
+environment variables and flags for non-interactive use:
 
 ```bash
 export KOLEGA_CODE_PROVIDER=deepseek
@@ -206,27 +266,28 @@ 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/model explicitly or save one in
-Settings. Local session state lives under your platform's state directory unless
-`KOLEGA_CODE_STATE_DIR` is set. See the
+API key variables only provide credentials — pick a provider/model explicitly or
+save one 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.
 
-The `web_search` tool uses DuckDuckGo by default without a key. To choose another backend,
-set it in **Settings** or export `KOLEGA_CODE_WEB_SEARCH_BACKEND` as `firecrawl`, `tavily`,
-or `searxng`; use `FIRECRAWL_API_KEY`, `TAVILY_API_KEY`, or `SEARXNG_BASE_URL` as needed.
+The `web_search` tool uses DuckDuckGo by default without a key. To choose another
+backend, set it in **Settings** or export `KOLEGA_CODE_WEB_SEARCH_BACKEND` as
+`firecrawl`, `tavily`, or `searxng`; use `FIRECRAWL_API_KEY`, `TAVILY_API_KEY`, or
+`SEARXNG_BASE_URL` as needed.
 
-Projects can also override Kolega Code's base prompts with uppercase Markdown templates in
-`.kolega/prompts/`. Generate editable starters with Jinja replacement tags using `/prompts dump`
-in the TUI or `kolega-code prompts dump --project .` in a terminal. To dump only selected
-starters, pass prompt names such as `coder`, `planning`, or `compaction` (filename aliases
-like `CODER.md` work too). Validate existing overrides with `/prompts validate` or
-`kolega-code prompts validate --project .`.
+Projects can override Kolega Code's base prompts with uppercase Markdown templates
+in `.kolega/prompts/`. Generate editable starters with Jinja replacement tags using
+`/prompts dump` in the TUI or `kolega-code prompts dump --project .` in a terminal.
+To dump only selected starters, pass prompt names such as `coder`, `planning`, or
+`compaction` (filename aliases like `CODER.md` work too). Validate existing
+overrides with `/prompts validate` or `kolega-code prompts validate --project .`.
 
 ## Requirements
 
 - **Python 3.11+**
-- An **API key** for at least one supported provider
+- 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
@@ -249,9 +310,9 @@ Full documentation lives at **[kolega-ai.github.io/kolega-code](https://kolega-a
 
 ## 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).
+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).
 
 ## License
 

kolega_code-0.11.0/README.md

@@ -0,0 +1,237 @@
+# Kolega Code
+
+**Multi-agent coding in the terminal.**
+
+[![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: MIT](https://img.shields.io/badge/license-MIT-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/)
+[![Changelog](https://img.shields.io/badge/changelog-keep%20up-blue)](CHANGELOG.md)
+
+Kolega Code is a local-first terminal coding agent built for work that is too wide
+for one loop: fan out specialized sub-agents with **Gigacode**, route different
+models to different jobs, search the web, drive a browser, and keep sessions,
+settings, permissions, and credentials on your machine.
+
+![Kolega Code in action](docs/src/assets/demo.gif)
+
+## Built for work one agent cannot cover
+
+Most terminal agents are strongest when one model can reason through one task at a
+time. Kolega Code keeps that familiar workflow, then adds orchestration for broad work:
+large audits, sweeping migrations, cross-file checks, adversarial reviews, and
+implementation plans whose pieces can run independently.
+
+With [Gigacode](https://kolega-ai.github.io/kolega-code/gigacode/), Kolega Code can:
+
+- **Fan out many sub-agents at once.** Split a wide codebase review by package,
+  assign independent implementation tasks, or run checks across many directories in
+  parallel.
+- **Use real workflow shapes.** The agent can generate parallel phases, pipelines,
+  loops, judge panels, and synthesis steps instead of only delegating one task at a
+  time.
+- **Keep orchestration visible.** Workflow phase headers and progress lines appear
+  in the transcript; the sub-agent inspector shows each agent's live trajectory.
+- **Save inspectable artifacts.** Each run keeps the generated workflow script,
+  result files, a Markdown transcript, raw JSONL, a resume journal, and debug
+  sub-agent transcripts under Kolega Code's state directory.
+- **Run in either mode.** In Plan mode, workflow sub-agents stay read-only for
+  parallel investigation. In Build mode, they can use the full coding toolset.
+- **Resume interrupted runs.** Finished workflow steps are journaled so a deliberate
+  resume does not have to restart the whole fan-out.
+
+Use normal chat for focused changes. Turn on Gigacode when the problem is broad
+enough that one serial agent pass would be the bottleneck.
+
+## Features
+
+- **Gigacode orchestration:** parallel, pipelined, looped, judged, and synthesized
+  multi-agent workflows with saved artifacts and resume support.
+- **Specialized sub-agents:** planning, building/coder, investigation, general, and
+  browser agents, with live activity tracking in the TUI.
+- **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.
+- **Plan/build workflow:** use read-only Plan mode for investigation and a reviewable
+  task list, then Build mode to implement.
+- **Web search and browsing:** DuckDuckGo works by default with no key; Firecrawl,
+  Tavily, and SearXNG are configurable search backends. Kolega Code can also fetch URLs
+  directly and use a Playwright-powered browser agent for interactive sites.
+- **Model routing:** choose provider/model combinations, set thinking effort, split
+  long-context/fast/thinking roles, and override models per agent role.
+- **Interactive or scriptable:** use the Textual TUI, queue follow-up prompts
+  while the agent is working, run `kolega-code ask`, request JSON output,
+  list/export/resume sessions, and diagnose setup with `doctor`.
+- **Extensibility:** add agent skills, override prompts with project templates, run
+  lifecycle hooks, and persist project permission rules.
+- **Local-first state:** sessions, settings, permissions, OAuth tokens, and API-key
+  settings stay on your machine with restrictive permissions where applicable.
+
+## 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. Add a provider key.** Open the **Settings** tab to pick a provider/model and
+save your API key. 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 thread or session
+```
+
+## 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 |
+
+There are also helper commands for managing sessions and checking your setup:
+
+```bash
+kolega-code ask "summarize this repository" --project .
+kolega-code sessions list --project .
+kolega-code doctor --project .
+```
+
+## Supported providers
+
+Kolega Code supports a broad model-provider catalog and lets you route models by
+role instead of forcing one model to do every job.
+
+Supported model providers:
+
+- Anthropic
+- OpenAI API
+- OpenAI via ChatGPT subscription sign-in
+- Google
+- Groq
+- Together.ai
+- Fireworks.ai
+- xAI / Grok
+- DashScope / Qwen
+- Moonshot / Kimi
+- DeepSeek
+- Z.AI / GLM Coding Plan
+- Kimi Coding Plan
+- Ollama Cloud
+- local Llama
+
+Supported web-search backends:
+
+- DuckDuckGo — default, no key required
+- Firecrawl
+- Tavily
+- SearXNG — self-hosted option
+
+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.
+
+## Model routing
+
+Kolega Code can assign different models to different operational roles: a strong
+long-context model for the main coding loop, a faster model for utility calls, and
+a dedicated model for extended thinking. You can also override models per agent
+role — planning, building, investigation, general, and browser — so wide workflows
+can use cheaper models where they fit and stronger models where they matter.
+
+## Sign in with ChatGPT
+
+If you have a paid **ChatGPT** plan (Plus, Pro, or Business), you can use it to run
+OpenAI models instead of a separate API key. Run `/login chatgpt` in the TUI,
+complete the browser sign-in, and Kolega Code switches to the **OpenAI (ChatGPT
+subscription)** provider (default `gpt-5.5`). Tokens are stored locally (chmod
+`600`) and refreshed automatically; `/logout chatgpt` removes them. See
+[Sign in with ChatGPT](https://kolega-ai.github.io/kolega-code/configuration/sign-in-with-chatgpt/).
+
+## Configuration
+
+Set your provider, model, and API keys from the **Settings** tab in the UI, 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/model explicitly or
+save one 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.
+
+The `web_search` tool uses DuckDuckGo by default without a key. To choose another
+backend, set it in **Settings** or export `KOLEGA_CODE_WEB_SEARCH_BACKEND` as
+`firecrawl`, `tavily`, or `searxng`; use `FIRECRAWL_API_KEY`, `TAVILY_API_KEY`, or
+`SEARXNG_BASE_URL` as needed.
+
+Projects can override Kolega Code's base prompts with uppercase Markdown templates
+in `.kolega/prompts/`. Generate editable starters with Jinja replacement tags using
+`/prompts dump` in the TUI or `kolega-code prompts dump --project .` in a terminal.
+To dump only selected starters, pass prompt names such as `coder`, `planning`, or
+`compaction` (filename aliases like `CODER.md` work too). Validate existing
+overrides with `/prompts validate` or `kolega-code prompts validate --project .`.
+
+## 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
+
+Full documentation lives at **[kolega-ai.github.io/kolega-code](https://kolega-ai.github.io/kolega-code/)**:
+
+- [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)
+
+## 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).
+
+## License
+
+Released under the [MIT License](LICENSE).

{kolega_code-0.10.0 → kolega_code-0.11.0}/docs/astro.config.mjs

@@ -13,8 +13,8 @@ export default defineConfig({
     starlight({
       title: "Kolega Code",
       description:
-        "A local-first, terminal AI coding agent. Plan, build, and ship from your CLI.",
-      // The Kolega "</>" mark, alongside the "Kolega Code" wordmark in the nav.
+        "Multi-agent terminal coding with local state, model routing, web search, and browser automation.",
+      // The company "</>" mark, alongside the "Kolega Code" wordmark in the nav.
       logo: {
         light: "./src/assets/kolega-light.svg",
         dark: "./src/assets/kolega-dark.svg",

{kolega_code-0.10.0 → kolega_code-0.11.0}/docs/src/assets/coverage.svg

@@ -1 +1 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="114" height="20" role="img" aria-label="coverage: 80.49%"><title>coverage: 80.49%</title><filter id="blur"><feGaussianBlur stdDeviation="16"/></filter><linearGradient id="s" x2="0" y2="100%"><stop offset="0" stop-color="#bbb" stop-opacity=".1"/><stop offset="1" stop-opacity=".1"/></linearGradient><clipPath id="r"><rect width="114" height="20" rx="3"/></clipPath><g clip-path="url(#r)"><rect width="61" height="20" fill="#555"/><rect x="61" width="53" height="20" fill="#67ac09"/><rect width="114" height="20" fill="url(#s)"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="110"><g transform="scale(.1)"><g aria-hidden="true" fill="#010101"><text x="315" y="150" fill-opacity=".8" filter="url(#blur)" textLength="510">coverage</text><text x="315" y="150" fill-opacity=".3" textLength="510">coverage</text></g><text x="315" y="140" textLength="510">coverage</text></g><g transform="scale(.1)"><g aria-hidden="true" fill="#010101"><text x="865" y="150" fill-opacity=".8" filter="url(#blur)" textLength="430">80.49%</text><text x="865" y="150" fill-opacity=".3" textLength="430">80.49%</text></g><text x="865" y="140" textLength="430">80.49%</text></g></g></svg>
+<svg xmlns="http://www.w3.org/2000/svg" width="114" height="20" role="img" aria-label="coverage: 80.66%"><title>coverage: 80.66%</title><filter id="blur"><feGaussianBlur stdDeviation="16"/></filter><linearGradient id="s" x2="0" y2="100%"><stop offset="0" stop-color="#bbb" stop-opacity=".1"/><stop offset="1" stop-opacity=".1"/></linearGradient><clipPath id="r"><rect width="114" height="20" rx="3"/></clipPath><g clip-path="url(#r)"><rect width="61" height="20" fill="#555"/><rect x="61" width="53" height="20" fill="#67ac09"/><rect width="114" height="20" fill="url(#s)"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="110"><g transform="scale(.1)"><g aria-hidden="true" fill="#010101"><text x="315" y="150" fill-opacity=".8" filter="url(#blur)" textLength="510">coverage</text><text x="315" y="150" fill-opacity=".3" textLength="510">coverage</text></g><text x="315" y="140" textLength="510">coverage</text></g><g transform="scale(.1)"><g aria-hidden="true" fill="#010101"><text x="865" y="150" fill-opacity=".8" filter="url(#blur)" textLength="430">80.66%</text><text x="865" y="150" fill-opacity=".3" textLength="430">80.66%</text></g><text x="865" y="140" textLength="430">80.66%</text></g></g></svg>

{kolega_code-0.10.0 → kolega_code-0.11.0}/docs/src/content/docs/concepts/how-it-works.md

@@ -3,9 +3,13 @@ title: Architecture
 description: A high-level look at how Kolega Code works under the hood.
 ---
 
-You don't need to know the internals to use Kolega Code, but a mental model helps
-when you're debugging behavior or extending it. This is a light overview — not an
-API reference.
+A terminal agent loop with tools is the baseline. Kolega Code keeps that loop, then
+adds the pieces that matter for wider work: mode boundaries, evented local
+execution, specialized sub-agent dispatch, role-specific models, and
+[Gigacode](../../gigacode/) workflow orchestration.
+
+You don't need the internals for everyday use, but this mental model helps when
+you're debugging behavior, choosing models, or deciding when a task should fan out.
 
 ## The agent loop
 
@@ -38,6 +42,20 @@ work — investigating the codebase, driving a browser, or handling a self-conta
 coding task — and track their progress. Different agent types expose different
 toolsets. See [Agents](../agents/).
 
+Sub-agents are useful one at a time, but they become more powerful when a task can
+be split across independent workstreams. That's what Gigacode automates.
+
+## Gigacode workflows
+
+With [Gigacode](../../gigacode/) enabled, Kolega Code can write a small workflow that
+launches many sub-agents, organizes them into phases, and synthesizes their
+results. Workflows can run broad audits, migration checks, implementation batches,
+or review panels without forcing one model to do every step serially.
+
+Workflow runs are evented like normal agent work, so the TUI can show phase
+progress and sub-agent activity. They also save artifacts — result files,
+transcripts, raw JSONL, and a resume journal — under Kolega Code's state directory.
+
 ## Models per role
 
 A single turn may use more than one model. The main reasoning runs on the
@@ -45,6 +63,11 @@ A single turn may use more than one model. The main reasoning runs on the
 reasoning uses the **thinking** model. You control each independently — see
 [Providers & Models](../../configuration/providers-and-models/).
 
+Kolega Code can also override models per agent role: planning, building, investigation,
+general, and browser. This lets wide workflows put cheaper or faster models on
+routine investigation while reserving stronger models for implementation or
+synthesis.
+
 ## Local execution
 
 Kolega Code runs against your real environment:
@@ -53,5 +76,6 @@ Kolega Code runs against your real environment:
 - **Terminal** — runs shell commands and streams their output.
 - **Browser** — automates a real browser (via Playwright) for web tasks.
 
-Sessions and settings are persisted locally. This local-first design is what makes
-the agent useful for real development work rather than a sandboxed demo.
+Sessions, settings, permissions, and credentials are persisted locally. That local
+state is what lets Kolega Code operate on a real development workspace while preserving
+resumable sessions and project-specific controls.

{kolega_code-0.10.0 → kolega_code-0.11.0}/docs/src/content/docs/configuration/providers-and-models.mdx

@@ -8,6 +8,10 @@ import { Aside, Steps } from '@astrojs/starlight/components';
 Kolega Code is provider-agnostic. You choose which LLM provider to use and which
 model to use for each of several **roles**.
 
+Provider breadth is table stakes; Kolega Code's extra control is assigning models by
+operational role and by agent role, so cheap/fast models can investigate while
+stronger models plan, build, or think.
+
 ## Supported providers
 
 The agent runtime recognizes these providers:
@@ -51,7 +55,7 @@ with thinking effort `auto` (enabled) requests route to **K2.7 Code**, and with
 OpenAI-compatible API at `https://ollama.com/v1` with `OLLAMA_API_KEY`. Kolega
 Code uses the direct API model IDs returned by Ollama, such as **`glm-5.2`** and
 **`gpt-oss:120b`**, rather than local Ollama aliases such as `:cloud` or
-`-cloud`. Ollama may deprecate or retire older cloud models, so the supported
+`-cloud`. Ollama may deprecate or retire older cloud models, so Kolega Code's supported
 model catalog should be refreshed periodically from Ollama's model library/API.
 </Aside>
 
@@ -165,7 +169,7 @@ Thinking effort is model-specific. Kolega Code validates the selected value
 against the active model and resets it to the new model's default when you switch
 models in the TUI.
 
-| Provider/model | Values | Kolega default |
+| Provider/model | Values | Kolega Code default |
 | --- | --- | --- |
 | Anthropic `claude-opus-4-7` | `low`, `medium`, `high`, `xhigh`, `max` | `medium` |
 | DeepSeek `deepseek-v4-pro` | `none`, `high`, `max` | `high` |