os-sdlc: behavior-verifier cannot read its brief when the diff is large (brief truncated at tool display limit) #993
Labels
No labels
P0
P1
P2
P3
bug
category/code-change
category/cross-repo
category/eval-run
category/investigation
category/no-test-target
category/owner-ruling
category/prose-artifact
category/recurring-chore
category/structure
category/umbrella
crc-refactor
create
delete
enhancement
filed-by/agent
filed-by/user
frozen
lint-rule
needs-info
needs-triage
next
plugin/cc-architect
plugin/os
plugin/os-adr
plugin/os-aidd-lint
plugin/os-backlog
plugin/os-context
plugin/os-doc-hygiene
plugin/os-sdlc
plugin/os-vault
project/cc-os
ready-for-agent
ready-for-human
recurring
review
rule-proposal
update
waiting
wayfinder:grilling
wayfinder:map
wayfinder:map
wayfinder:research
wayfinder:task
wayfinder:task
wontfix
worklist/deviations
worklist/lint-rule
worklist/new-implement-build
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set
Reference
jared/cc-os#993
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Discovered
Project: n8n-api (github:jaredswanson/n8n-api), ticket #6, implementation 10, dispatch 85. Session 8aec61c5-c50b-4af4-a1da-ba023682b07e.
What happened
os-sdlc-brief --dispatch-id 85printed 34.5 KB (the diff moved ~20 files). The agent's Bash tool saved it to a file and showed a 2 KB preview that ended in the Approach section. The verifier never saw the acceptance criteria orcode_changes; reading the saved file withcatis outside its charter and was truncated the same way. It returned verdicterror(MISSING: ticket_brief, code_changes), and the Runner ended the run asimplementation_failed. A fresh run would hit the same limit.Expected
A verifier can read the whole brief for any diff size (e.g. paged brief sections, or a diff summary/stat in place of full rename hunks).
Also observed in the same session (no ticket yet)
misfit).unexpected_passat test-writer because production work is already present. Both happened on n8n-api #4 and #6, and the fix was a reroute each time.Workaround used
The orchestrator verified #6 by deterministic checks (full suite,
Loader.eager_load, required-work greps, programmer lint gate) and committed by hand.