Thales Maciel
22d284b1f5
Make the human workspace read commands easier to use in chat transcripts and shell pipelines by adding CLI-only --content-only to workspace file read and workspace disk read. Keep JSON, SDK, and MCP behavior unchanged while fixing the default human rendering so content without a trailing newline is cleanly separated from the summary footer. Update the 3.9.0 docs and roadmap status, and add CLI regression coverage plus a real guest-backed smoke for live and stopped-disk reads.
102 lines
5.2 KiB
Markdown
102 lines
5.2 KiB
Markdown
# LLM Chat Ergonomics Roadmap
|
|
|
|
This roadmap picks up after the completed workspace GA plan and focuses on one
|
|
goal:
|
|
|
|
make the core agent-workspace use cases feel trivial from a chat-driven LLM
|
|
interface.
|
|
|
|
Current baseline is `3.9.0`:
|
|
|
|
- the stable workspace contract exists across CLI, SDK, and MCP
|
|
- one-shot `pyro run` still exists as the narrow entrypoint
|
|
- workspaces already support seeding, sync push, exec, export, diff, snapshots,
|
|
reset, services, PTY shells, secrets, network policy, and published ports
|
|
- stopped-workspace disk tools now exist, but remain explicitly secondary
|
|
|
|
## What "Trivial In Chat" Means
|
|
|
|
The roadmap is done only when a chat-driven LLM can cover the main use cases
|
|
without awkward shell choreography or hidden host-side glue:
|
|
|
|
- cold-start repo validation
|
|
- repro plus fix loops
|
|
- parallel isolated workspaces for multiple issues or PRs
|
|
- unsafe or untrusted code inspection
|
|
- review and evaluation workflows
|
|
|
|
More concretely, the model should not need to:
|
|
|
|
- patch files through shell-escaped `printf` or heredoc tricks
|
|
- rely on opaque workspace IDs without a discovery surface
|
|
- consume raw terminal control sequences as normal shell output
|
|
- choose from an unnecessarily large tool surface when a smaller profile would
|
|
work
|
|
|
|
The remaining UX friction for a technically strong new user is now narrower:
|
|
|
|
- the recommended chat-host onramp is now explicit, but human-mode file reads
|
|
still need final transcript polish for copy-paste and chat logs
|
|
|
|
## Locked Decisions
|
|
|
|
- keep the workspace product identity central; do not drift toward CI, queue,
|
|
or runner abstractions
|
|
- keep disk tools secondary and do not make them the main chat-facing surface
|
|
- prefer narrow tool profiles and structured outputs over more raw shell calls
|
|
- capability milestones should update CLI, SDK, and MCP together
|
|
- CLI-only ergonomics are allowed when the SDK and MCP surfaces already have the
|
|
structured behavior natively
|
|
- every milestone below must also update docs, help text, runnable examples,
|
|
and at least one real smoke scenario
|
|
|
|
## Milestones
|
|
|
|
1. [`3.2.0` Model-Native Workspace File Ops](llm-chat-ergonomics/3.2.0-model-native-workspace-file-ops.md) - Done
|
|
2. [`3.3.0` Workspace Naming And Discovery](llm-chat-ergonomics/3.3.0-workspace-naming-and-discovery.md) - Done
|
|
3. [`3.4.0` Tool Profiles And Canonical Chat Flows](llm-chat-ergonomics/3.4.0-tool-profiles-and-canonical-chat-flows.md) - Done
|
|
4. [`3.5.0` Chat-Friendly Shell Output](llm-chat-ergonomics/3.5.0-chat-friendly-shell-output.md) - Done
|
|
5. [`3.6.0` Use-Case Recipes And Smoke Packs](llm-chat-ergonomics/3.6.0-use-case-recipes-and-smoke-packs.md) - Done
|
|
6. [`3.7.0` Handoff Shortcuts And File Input Sources](llm-chat-ergonomics/3.7.0-handoff-shortcuts-and-file-input-sources.md) - Done
|
|
7. [`3.8.0` Chat-Host Onramp And Recommended Defaults](llm-chat-ergonomics/3.8.0-chat-host-onramp-and-recommended-defaults.md) - Done
|
|
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
|
|
|
|
Completed so far:
|
|
|
|
- `3.2.0` added model-native `workspace file *` and `workspace patch apply` so chat-driven agents
|
|
can inspect and edit `/workspace` without shell-escaped file mutation flows.
|
|
- `3.3.0` added workspace names, key/value labels, `workspace list`, `workspace update`, and
|
|
`last_activity_at` tracking so humans and chat-driven agents can rediscover and resume the right
|
|
workspace without external notes.
|
|
- `3.4.0` added stable MCP/server tool profiles with `vm-run`, `workspace-core`, and
|
|
`workspace-full`, plus canonical profile-based OpenAI and MCP examples so chat hosts can start
|
|
narrow and widen only when needed.
|
|
- `3.5.0` added chat-friendly shell reads with plain-text rendering and idle batching so PTY
|
|
sessions are readable enough to feed directly back into a chat model.
|
|
- `3.6.0` added recipe docs and real guest-backed smoke packs for the five core workspace use
|
|
cases so the stable product is now demonstrated as repeatable end-to-end stories instead of
|
|
only isolated feature surfaces.
|
|
- `3.7.0` removed the remaining shell glue from canonical CLI workspace flows with `--id-only`,
|
|
`--text-file`, and `--patch-file`, so the shortest handoff path no longer depends on `python -c`
|
|
extraction or `$(cat ...)` expansion.
|
|
- `3.8.0` made `workspace-core` the obvious first MCP/chat-host profile from the first help and
|
|
docs pass while keeping `workspace-full` as the 3.x compatibility default.
|
|
- `3.9.0` added content-only workspace file and disk reads plus cleaner default human-mode
|
|
transcript separation for files that do not end with a trailing newline.
|
|
|
|
## Expected Outcome
|
|
|
|
After this roadmap, the product should still look like an agent workspace, not
|
|
like a CI runner with more isolation.
|
|
|
|
The intended model-facing shape is:
|
|
|
|
- one-shot work starts with `vm_run`
|
|
- persistent work moves to a small workspace-first contract
|
|
- file edits are structured and model-native
|
|
- workspace discovery is human and model-friendly
|
|
- shells are readable in chat
|
|
- CLI handoff paths do not depend on ad hoc shell parsing
|
|
- the recommended chat-host profile is obvious from the first MCP example
|
|
- human-mode content reads are copy-paste safe
|
|
- the five core use cases are documented and smoke-tested end to end
|