diff --git a/website/src/content/docs/learning-hub/building-custom-agents.md b/website/src/content/docs/learning-hub/building-custom-agents.md index 3ad3e7cb95..0f9586c7dc 100644 --- a/website/src/content/docs/learning-hub/building-custom-agents.md +++ b/website/src/content/docs/learning-hub/building-custom-agents.md @@ -267,7 +267,7 @@ The agent can then query your database, analyze query plans, and suggest optimiz |----------|-------------------| | Most demanding reasoning, security review | Claude Sonnet 5 *(v1.0.67+)* | | Complex reasoning, analysis | Claude Sonnet 4 | -| Code generation, tool-driven agentic work | GPT-5.6 *(v1.0.70+)* | +| Code generation, tool-driven agentic work | GPT-5.6 *(v1.0.70+)*, GPT-6 Astra *(v1.0.84+)* | | Code generation, refactoring | GPT-4.1 | | Code-specialized tasks, large context | kimi-k2.7-code *(v1.0.68+)*, kimi-k3 *(v1.0.79+)* | | Quick analysis, simple tasks | Claude Haiku or GPT-4.1-mini | diff --git a/website/src/content/docs/learning-hub/copilot-configuration-basics.md b/website/src/content/docs/learning-hub/copilot-configuration-basics.md index 57474e417d..ea4bf9f1ab 100644 --- a/website/src/content/docs/learning-hub/copilot-configuration-basics.md +++ b/website/src/content/docs/learning-hub/copilot-configuration-basics.md @@ -457,7 +457,7 @@ The model picker opens in a **full-screen view** with inline reasoning effort ad **Auto mode and server-side model routing** (v1.0.43+): When you select **Auto** as your model, the CLI uses server-side model routing for real-time model selection. Instead of locking in a single model at session start, Auto mode evaluates each request and routes it to the most appropriate model dynamically. This means straightforward questions can be handled by a faster model while complex reasoning tasks are automatically escalated — without you needing to switch models manually. -**Model family aliases** (v1.0.64+): Instead of typing a full model name, you can use short family aliases in the model setting: `opus`, `sonnet`, `haiku` (Anthropic), and `gpt`, `gemini` (Google/OpenAI). The CLI resolves the alias to the latest available model in that family. This is especially useful in scripts or configuration files where you want to track the best model in a family without hardcoding a version string. Recent models available include **Claude Opus 5** (v1.0.75+), the latest in Anthropic's Opus family for the most demanding tasks, **Grok 4.5** (v1.0.76+) from xAI, **Gemini 3.7 Flash** (v1.0.81+), and **Claude Fable 5.1** (v1.0.83+). **Grok 4.6** (v1.0.81+) also gains support for the `xhigh` reasoning effort level, one step above `high`, for the most demanding reasoning tasks. The `/model picker` also periodically retires older models no longer worth recommending — a recent cleanup removed several deprecated Claude and Gemini entries (v1.0.83+), so don't be surprised if a model you previously pinned disappears from the list. +**Model family aliases** (v1.0.64+): Instead of typing a full model name, you can use short family aliases in the model setting: `opus`, `sonnet`, `haiku` (Anthropic), and `gpt`, `gemini` (Google/OpenAI). The CLI resolves the alias to the latest available model in that family. This is especially useful in scripts or configuration files where you want to track the best model in a family without hardcoding a version string. Recent models available include **Claude Opus 5** (v1.0.75+), the latest in Anthropic's Opus family for the most demanding tasks, **Grok 4.5** (v1.0.76+) from xAI, **Gemini 3.7 Flash** (v1.0.81+), **Claude Fable 5.1** (v1.0.83+), and **GPT-6 Astra** (v1.0.84+) from OpenAI. **Grok 4.6** (v1.0.81+) also gains support for the `xhigh` reasoning effort level, one step above `high`, for the most demanding reasoning tasks. The `/model picker` also periodically retires older models no longer worth recommending — a recent cleanup removed several deprecated Claude and Gemini entries (v1.0.83+), so don't be surprised if a model you previously pinned disappears from the list. **Model fallback lists** *(v1.0.83+)*: Custom agents can set `model` to a list of several models instead of a single name. Copilot tries each one in order until it finds one available to your account — useful when your preferred model is temporarily rate-limited or not enrolled. Pair this with `model-policy: required` to keep the agent restricted to that list even if you try to switch models mid-session. See [Building Custom Agents](../building-custom-agents/) for the frontmatter syntax. @@ -687,6 +687,8 @@ Use `/diagnose` when a session is behaving unexpectedly — it inspects session **Worktree switch reliability (v1.0.82+)**: If you start typing a new message while `/worktree` or `/move` is preparing a worktree switch, that message is no longer dropped when the switch completes. +**Vim mode for everyone** *(v1.0.84+)*: Modal editing in the composer is now available to all users. Turn it on with `/vim`, or set `editorMode` to `vim` in your configuration to enable it by default for every session. The current mode (normal or insert) is shown while you type, so you always know which mode is active. + The `/ask` command lets you ask a quick question without affecting your conversation history. The current session context is preserved, so you can use it for one-off lookups without derailing an ongoing task. Responses are rendered as full markdown, including tables and formatted links: ``` diff --git a/website/src/content/docs/learning-hub/creating-effective-skills.md b/website/src/content/docs/learning-hub/creating-effective-skills.md index d9ba88a4ce..c1f0f63bdc 100644 --- a/website/src/content/docs/learning-hub/creating-effective-skills.md +++ b/website/src/content/docs/learning-hub/creating-effective-skills.md @@ -379,10 +379,14 @@ copilot skill list # list all currently loaded skills copilot skill add ./my-skill/ # add a skill from a local directory copilot skill add https://example.com/skill.zip # add a skill from a URL copilot skill remove my-skill # remove an installed skill by name +copilot skill enable my-skill # re-enable a disabled skill (v1.0.84+) +copilot skill disable my-skill # disable a skill without removing it (v1.0.84+) ``` You can also run `/skill` (or the existing `/skills`) inside an interactive session to see what's loaded. The `copilot skill` subcommand is the recommended way to install skills that aren't packaged inside a plugin. +> **Command restructuring (v1.0.84+)**: `copilot skill add [--project]` replaces the older `copilot plugins install --skill [--scope project]` syntax — the `--scope` spelling is gone. Enabling and disabling a skill now happens directly on `copilot skill enable`/`disable` instead of the retired cross-kind `copilot plugins enable/disable --skill`. + **Q: How are skills different from prompts?** A: Skills replace the older prompt file (`*.prompt.md`) format. Skills offer agent discovery (prompts were manual-only), bundled assets (prompts were single files), and cross-platform portability via the Agent Skills specification. If you have existing prompts, consider migrating them to skills. diff --git a/website/src/content/docs/learning-hub/installing-and-using-plugins.md b/website/src/content/docs/learning-hub/installing-and-using-plugins.md index 9c4956e11c..1338b5ac2d 100644 --- a/website/src/content/docs/learning-hub/installing-and-using-plugins.md +++ b/website/src/content/docs/learning-hub/installing-and-using-plugins.md @@ -255,6 +255,8 @@ This opens an interactive list where each installed plugin and its components ar > **Dashboard available to everyone (v1.0.81+)**: The plugins dashboard (`/plugin`, `/mcp`, and `/skills`) is now on for all users by default. If you need to opt out, set `PLUGINS_DASHBOARD=false`, which also restores the legacy `copilot plugins` command. This opt-out was later removed in the same release, along with the legacy skills picker it kept alive — `/skills`, bare `/mcp`, and `/mcp show` (with no server name) always open the dashboard now, and `/mcp config` opens the dedicated MCP wizard. +> **CLI command split by kind (v1.0.84+)**: The cross-kind `copilot plugins` subcommand family has been split into dedicated per-kind commands. Use `copilot instruction list` and `copilot lsp list` instead of `copilot plugins list --kind instruction` / `--kind lsp`; use `copilot skill add [--project]` instead of `copilot plugins install --skill [--scope project]`; and use `enable`/`disable` directly on `copilot plugin`, `copilot mcp`, and `copilot skill` instead of `copilot plugins enable/disable --plugin|--mcp|--skill`. The cross-kind `--kind`, `--scope`, `--mcp`, and `--skill` flags have been removed from `copilot plugins`. `copilot plugins list` is now a plain alias for `copilot plugin list` — it reports only plugins, not MCP servers, skills, instructions, or LSP servers — and with `--json` it emits a flat array instead of the old `{ plugins, errors }` object, so scripts reading `.plugins` need updating. `copilot plugin list`, `copilot plugin marketplace list`, and `copilot plugin marketplace browse` all gained a `--json` flag for scripting. + ### Loading Plugins from a Local Directory You can load plugins directly from a local directory without installing them from a marketplace, using the `--plugin-dir` flag when starting Copilot: