mode-economics: add an ASF-scoped LLMAO section
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 70/100
- Issue type
- Documentation
- Clarity
- Mostly clear
- Activity status
- Active
- Domain
- build-system, documentation
Research direction
Start with docs/mode-economics.md and inspect the generated block and the existing organization-specific pattern under organizations/ASF/. Use #1261 for the LLMAO measurements and verify the section is ASF-only, dated, and outside the general tables. Run check-doc-sync and the token-count hook; done means both pass and the general tables remain unchanged.
Written by the indexing model from the issue text.
Description
Follow-up to #1260 and #1261.
What
Give docs/mode-economics.md an ASF-scoped section carrying the LLMAO measurements from #1261, rather than folding those numbers into the page's main tables.
Why scoped rather than inline
LLMAO is available to ASF committers only. Numbers that most readers of a public page cannot act on do not belong in the tables they read first — they invite the reasonable-but-wrong conclusion that these are costs anyone can obtain.
Magpie already solves this shape elsewhere: the framework is organisation-agnostic and carries organisation-specific material in clearly-marked sections, with organizations/ASF/ as the ASF instance of it. This should follow the same pattern rather than inventing a new one.
The page's own Long-term: the ASF inference endpoint section already anticipates this content:
As pilot adopters accumulate real usage data, this page will be updated with observed ranges rather than theoretical estimates, so the endpoint sizing argument rests on evidence.
So this is filling an existing promise, not adding a new claim.
Shape
- An ASF-scoped section, marked as such, holding per-skill token and wall-clock figures per LLMAO model.
- Explicit that access requires an ASF committer PAT, so a reader outside the ASF knows immediately whether this applies to them.
- Figures labelled with the date and model version measured. These are pilot numbers on a service under active capacity work; an undated figure will be quietly wrong within weeks.
- The main tables stay vendor-comparable and untouched.
Done when
- The section exists, is populated from #1261, and is unambiguously marked ASF-only.
- Nothing in the general tables implies LLMAO numbers apply to a non-ASF reader.
check-doc-syncand the token-count hook pass — this page is partly generated, so hand-edits must land outside the generated block.
- Dominant language
- Python
- Stars
- 96
- Forks
- 92
- Avg merge
- 13h 23m
- Merged PRs (30d)
- 163
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from apache/magpie
-
enhancement
Difficulty 2/5 1-2 days Newbie friendliness 64/100
-
capability:triage family:pr-management good first issue kind:dx kind:perf mode:Triage
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
family:security kind:policy question
Difficulty 4/5 3-5 days Newbie friendliness 48/100
-
family:security mode:cross-cutting question
Difficulty 4/5 3-5 days Newbie friendliness 48/100
-
documentation kind:perf mode:cross-cutting
Difficulty 5/5 Over a week Newbie friendliness 35/100
Similar issues
-
area/auth bug comp/agent P3 platform/discord type/security
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
NousResearch/hermes-agent#117848 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
bancolombia/sentinel#23 ·
-
test md OpenCI
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
-
integration:quickjs org:external priority:backlog topic:code-interpreter topic:middleware type:feature
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
langchain-ai/deepagents#6450 ·
-
bug client
Difficulty 2/5 1-3 hours Newbie friendliness 88/100