Status: Formulate -> Analyze (tree at 3bad07b probed).
11 findings (A1-A11), 5/6 open Qs resolved (Q-C4 deferred to baseline):
A1. broker.chat_stream surface clean — usage capture via closure-local
+ on_delta("usage") emission after curl.post_sse returns.
A2. 7 caller sites for opts.category threading (probe / norris /
summarize / main / delegate x2 / memory_summarize).
A3. build_request signature widens to (model_cfg, msgs, stream, opts)
to absorb tools / max_tokens / include_usage / stream_options
without further positional growth.
A4. Q-C3 RESOLVED: free-form categories (caller decides); matches
Phase 6 helpers/skills convention.
A5. Q-C5 RESOLVED: warn fires on the call that crossed (no NEXT-call
delay).
A6. Q-C6 RESOLVED: :reset does NOT clear cost_warn_fired; only
:cost reset clears.
A7. Norris call-graph rewires (commit 955bd82) — secrets streaming
rehydrator wraps only "text" kind; new "usage" kind passes
through unchanged. No new entanglement.
A8. ctx.usage_totals survives :reset (R8 parity with memory_items,
project).
A9. Session JSONL inherits the new field automatically (dkjson
opaque encoding).
A10. Q-C1 PARTIAL: defensive silent skip when provider omits usage.
Real probe required for local model — baseline action.
A11. Q-C4 deferred to baseline (real broker probe).
§2 build_request row updated to mention the A3 refactor.
§11 Open Qs table now shows all 6 with resolutions; only Q-C4
remains as a baseline-time probe.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
marfrit
f0bccdec48