Source
14-day usage_log.md analysis (2026-04-18 CLI session), cross-checked against project_state.md self-reports.
Pattern
The scaffold's own reports understate this. project_state.md says "Haiku dominance 26.8%" but the actual usage_log data shows:
| Date |
Haiku % |
Opus count |
Haiku count |
| Apr 10 |
0% |
19 |
0 |
| Apr 11 |
0% |
20 |
0 |
| Apr 12 |
0% |
18 |
0 |
| Apr 13 |
10% |
18 |
2 |
| Apr 14 |
100% |
0 |
13 |
| Apr 15 |
100% |
0 |
14 |
| Apr 16 |
100% |
0 |
15 |
| Apr 17 |
100% |
0 |
12 |
Opus flipped off at 2026-04-13T20:51Z and has not returned over 96+ hours. This is not a partial rate-limit — it's total and persistent. Every claude -p --model opus invocation is being served by Haiku.
Why it matters (cost, not just reliability)
Per-turn cost comparison from the same window:
| Workflow |
Opus $/turn |
Haiku $/turn |
Haiku premium |
| analyze |
$0.039 |
$0.041 |
+5% |
| evolve |
$0.039 |
$0.042 |
+8% |
| watcher |
$0.041 |
$0.050 |
+22% |
Haiku is NOT cheaper per turn on these workloads. And because Haiku takes more turns to reach the same conclusion (cf. coder #173: Haiku hit 41/40 max-turns for $4.22 on a task Opus would likely have finished), total cost rises.
The assumption "fallback saves money" baked into current pipeline reasoning is empirically wrong on this repo's workload.
Proposed investigation
- Check account rate-limit status: is Opus 4.6 genuinely quota-capped, or is the
claude -p --model opus request resolving to opus → Haiku via some alias/routing issue?
- Check
CLAUDE_CODE_OAUTH_TOKEN — has it been downgraded to a Haiku-only plan, or expired and silently replaced?
- Inspect one recent "Opus" run's raw API response. The usage_log reports
model:claude-haiku-4-5-20251001 from modelUsage keys — confirm this is the actual inference model, not a fallback flag.
- If it IS a persistent rate-limit: raise the question of whether current cron cadence is structurally incompatible with available Opus quota. Either reduce cadence further or upgrade the account.
Proposed action
Once root cause is known, one of:
- Restore Opus access (account/billing fix) → immediate 5-22% per-turn cost reduction
- Explicitly pin workflows to Haiku where acceptable, and acknowledge cost-per-quality tradeoff
- Document in CLAUDE.md that "Opus" is effectively aliased to Haiku at this account tier
Risk of leaving it
- Cost reporting across the scaffold is misleading (baseline assumes Opus)
- Complex tasks like coder on 11-file changes keep failing at max-turns because Haiku needs more turns
- Future evolve findings that recommend Opus-based features (prompt caching tuning, extended context) are unactionable
Evidence artifacts
- state/usage_log.md (full 14d window)
- state/agent_log.md (reports "rate-limit" events Apr 14-15 ~25h, but never attributes the subsequent permanent switch)
Needs-human
Requires account-level investigation (billing, tokens, plan tier) that the coder agent cannot perform.
Surfaced from 14-day retrospective CLI session 2026-04-18.
Source
14-day usage_log.md analysis (2026-04-18 CLI session), cross-checked against project_state.md self-reports.
Pattern
The scaffold's own reports understate this. project_state.md says "Haiku dominance 26.8%" but the actual usage_log data shows:
Opus flipped off at
2026-04-13T20:51Zand has not returned over 96+ hours. This is not a partial rate-limit — it's total and persistent. Everyclaude -p --model opusinvocation is being served by Haiku.Why it matters (cost, not just reliability)
Per-turn cost comparison from the same window:
Haiku is NOT cheaper per turn on these workloads. And because Haiku takes more turns to reach the same conclusion (cf. coder #173: Haiku hit 41/40 max-turns for $4.22 on a task Opus would likely have finished), total cost rises.
The assumption "fallback saves money" baked into current pipeline reasoning is empirically wrong on this repo's workload.
Proposed investigation
claude -p --model opusrequest resolving toopus→ Haiku via some alias/routing issue?CLAUDE_CODE_OAUTH_TOKEN— has it been downgraded to a Haiku-only plan, or expired and silently replaced?model:claude-haiku-4-5-20251001frommodelUsagekeys — confirm this is the actual inference model, not a fallback flag.Proposed action
Once root cause is known, one of:
Risk of leaving it
Evidence artifacts
Needs-human
Requires account-level investigation (billing, tokens, plan tier) that the coder agent cannot perform.
Surfaced from 14-day retrospective CLI session 2026-04-18.