thaloco/pyro-mcp
1
Fork 0
Code Pull requests Releases Packages Activity Actions

Make workspace-core the default MCP profile

Browse source 
Flip bare pyro mcp serve, create_server(), and Pyro.create_server() to default to workspace-core in 4.0.0 while keeping workspace-full as the explicit advanced opt-in surface.

Rewrite the MCP-facing docs and host-specific examples around the bare default command, update package and catalog compatibility to 4.x, and move the public-contract wording from 3.x compatibility guidance to the new stable default.

Adjust the server, API, and contract tests so bare server creation now asserts the workspace-core tool set, while explicit workspace-full coverage continues to prove shells, services, snapshots, and disk tools remain available.

Validation: uv lock; .venv/bin/pytest --no-cov tests/test_cli.py tests/test_api.py tests/test_server.py tests/test_public_contract.py; UV_CACHE_DIR=.uv-cache make check; UV_CACHE_DIR=.uv-cache make dist-check; real guest-backed smoke for bare Pyro.create_server() plus explicit profile="workspace-full".
This commit is contained in:
Thales Maciel 2026-03-13 14:14:15 -03:00
parent 68d8e875e0
commit c00c699a9f
25 changed files with 170 additions and 121 deletions
Download patch file Download diff file Expand all files Collapse all files

16
docs/roadmap/llm-chat-ergonomics.md
View file

@ -6,7 +6,7 @@ goal:
make the core agent-workspace use cases feel trivial from a chat-driven LLM
interface.
Current baseline is `3.11.0`:
Current baseline is `4.0.0`:
- the stable workspace contract exists across CLI, SDK, and MCP
- one-shot `pyro run` still exists as the narrow entrypoint
@ -35,10 +35,7 @@ More concretely, the model should not need to:
The remaining UX friction for a technically strong new user is now narrower:
- the generic MCP guidance is strong, but Codex and OpenCode still ask the user
to translate the generic config into host-specific setup steps
- `workspace-core` is clearly the recommended profile, but `pyro mcp serve` and
`create_server()` still default to `workspace-full` for `3.x` compatibility
- no major chat-host ergonomics gaps remain in the current roadmap
## Locked Decisions
@ -64,7 +61,7 @@ The remaining UX friction for a technically strong new user is now narrower:
8. [`3.9.0` Content-Only Reads And Human Output Polish](llm-chat-ergonomics/3.9.0-content-only-reads-and-human-output-polish.md) - Done
9. [`3.10.0` Use-Case Smoke Trust And Recipe Fidelity](llm-chat-ergonomics/3.10.0-use-case-smoke-trust-and-recipe-fidelity.md) - Done
10. [`3.11.0` Host-Specific MCP Onramps](llm-chat-ergonomics/3.11.0-host-specific-mcp-onramps.md) - Done
11. [`4.0.0` Workspace-Core Default Profile](llm-chat-ergonomics/4.0.0-workspace-core-default-profile.md)
11. [`4.0.0` Workspace-Core Default Profile](llm-chat-ergonomics/4.0.0-workspace-core-default-profile.md) - Done
Completed so far:
@ -93,13 +90,12 @@ Completed so far:
- `3.11.0` added exact host-specific MCP onramps for Claude Code, Codex, and OpenCode so new
chat-host users can copy one known-good setup example instead of translating the generic MCP
config manually.
- `4.0.0` flipped the default MCP/server profile to `workspace-core`, so the bare entrypoint now
matches the recommended narrow chat-host profile across CLI, SDK, and package-level factories.
Planned next:
- `4.0.0` flips the default MCP profile from `workspace-full` to
`workspace-core` so the no-flag server entrypoint finally matches the
recommended docs path, while keeping explicit opt-in access to the full
advanced surface.
- no further chat-ergonomics milestones are currently planned in this roadmap.
## Expected Outcome