luminos

archeious/luminos

Fork 0

Commit graph

Author	SHA1	Message	Date
Jeff Smith	e942ecc34a	docs(plan): add Phase 2.5 context budget reliability (#44 ) #5 smoke test showed the dir loop exhausts the 126k context budget on a 13-file Python lib. Sequencing #44 between Phase 2 and Phase 3 so the foundation is solid before planning + external tools add more prompt and tool weight.	2026-04-06 21:59:01 -06:00
Jeff Smith	05fcaac755	docs(plan): note classifier rebuild (#42 ) in Phase 2 The filetype classifier is biased toward source code and would mislead the survey pass on non-code targets (mail, notebooks, ledgers). #5 ships with a prompt-level Band-Aid; #42 captures the real fix and is sequenced after the survey pass is observable end-to-end and before Phase 3 depends on survey output.	2026-04-06 21:47:49 -06:00
Jeff Smith	0a9afc96c9	chore: update CLAUDE.md for session 3	2026-04-06 21:15:27 -06:00

Author

SHA1

Message

Date

Jeff Smith

e942ecc34a

docs(plan): add Phase 2.5 context budget reliability (#44 )

#5 smoke test showed the dir loop exhausts the 126k context budget on
a 13-file Python lib. Sequencing #44 between Phase 2 and Phase 3 so
the foundation is solid before planning + external tools add more
prompt and tool weight.

2026-04-06 21:59:01 -06:00

Jeff Smith

05fcaac755

docs(plan): note classifier rebuild (#42 ) in Phase 2

The filetype classifier is biased toward source code and would mislead
the survey pass on non-code targets (mail, notebooks, ledgers). #5
ships with a prompt-level Band-Aid; #42 captures the real fix and is
sequenced after the survey pass is observable end-to-end and before
Phase 3 depends on survey output.

2026-04-06 21:47:49 -06:00

Jeff Smith

0a9afc96c9

chore: update CLAUDE.md for session 3

2026-04-06 21:15:27 -06:00

3 commits