about summary refs log tree commit diff
path: root/test/python/test_openapi.py
diff options
context:
space:
mode:
authorPjotr <wrk@bosa.lan>2026-11-14 12:41:57 +0000
committerPjotr <wrk@bosa.lan>2026-11-14 12:41:57 +0000
commit56bb6214aef7aba1b3ad01d334553c8a62deacdf (patch)
tree2437b499370dbf46bc984098791ee858bbc0b766 /test/python/test_openapi.py
parent7ff1543f8649b4e04d6ccfd012ae8d2403f2e0a7 (diff)
downloadgenenetwork4-56bb6214aef7aba1b3ad01d334553c8a62deacdf.tar.gz
docs: always offer one sentence of what to do next, unless disabled
The API already computes every reply's options -- `next` are GETs that answer
200, `actions` are the POSTs to run next -- and a caller that reads them
learned nothing extra from being told "you could now do X" in prose. What was
missing was the instruction: an answer that stops at the result leaves the
reader to work out the graph.

docs/www/SKILL.md gains "Always offer the next step": end every answer with
ONE sentence built from that reply's own next/actions -- after a compute run, a
lookup, a plot, an upload, a basket edit. Prefer the action href over a
hand-built call. A refusal is an answer too: its next or detail names the
alternative (bulklmm for a GEMMA permutation, /compute/gemma for a covariate
fit). Do not stack suggestions; one next plus at most one genuinely different
alternative. "Skip the suggestions" / "just the result" turns it off for the
session -- it is the sentence that is disabled, not the content. And never
propose a step the API cannot do: if nothing in next/actions fits, say so.

README states the same bargain where the next-link promise is described: the
server's half is that the suggestion is always reachable, the assistant's half
is that it is one sentence and it is a link the reply actually carries.
Diffstat (limited to 'test/python/test_openapi.py')
0 files changed, 0 insertions, 0 deletions