Skip to content

feat(clone): classify autolens_assistant's free-tier chat surface #189

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Jammy2211 merged 1 commit into from
Aug 3, 2026
Merged

feat(clone): classify autolens_assistant's free-tier chat surface #189

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion agents/conductors/clone/_clone.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,9 @@
"AGENTS.md", "CLAUDE.md", "LICENSE", ".gitignore", ".gitattributes",
"Makefile", "__init__.py", "activate.sh", "version.txt",
"AI_POLICY.md", "CITATIONS.md", "CODE_OF_CONDUCT.md", "CONTRIBUTING.md",
"AGENTS_CHAT.md", # chat-mode counterpart of AGENTS.md: the same
# skeleton with the shell-dependent rules cut,
# so it clones on the same terms as AGENTS.md
"modes/*", # Teacher/Assistant mode machinery
"skills/_style.md", "skills/_bootstrap_skill.md", "skills/README.md",
"skills/start-new-project*", "skills/contribute-upstream*",
Expand Down Expand Up @@ -87,6 +90,10 @@

_SHARED_MIXED = [
"llms.txt", "llms-full.txt",
"llms-chat.txt", # generated paste bundle: same seam as llms.txt
"FREE_TIER_SETUP.md", # per-platform chat setup — the platform
# mechanics clone verbatim, the worked prompts
# and dataset names are domain
"config/*",
"benchmarks/README.md", # protocol generic, benchmark table domain
]
Expand Down Expand Up @@ -117,10 +124,15 @@
"wiki/literature/*", # a shipped lensing paper corpus
"paper/*", # this assistant's own JOSS paper
"scripts/*.py", # bundled science scripts (a named lens)
# Generated chat knowledge pack: concatenated al_* skill bodies +
# wiki/core pages + a snapshot of the lensing stack's API surface.
# Every input is domain, so a newborn regenerates it from its own
# content (`make chat-bundle`) rather than copying this one.
"chat_pack/*",
*_SHARED_DOMAIN,
],
"mixed": _SHARED_MIXED,
"scaffold_dirs": ["wiki/core", "wiki/literature", "dataset", "hpc"],
"scaffold_dirs": ["wiki/core", "wiki/literature", "dataset", "hpc", "chat_pack"],
},
# The domain-agnostic base: `af_*` inference skills and the *statistics*
# `wiki/core/` are GENERIC infrastructure kept verbatim; only the example
Expand Down