Repository navigation
Description
Summary
Production data from OpenCode 1.18.9 shows the Anthropic prompt cache bust bug (Issue #24841) is still active and causing significant financial waste.
Key findings:
- 5 sessions using Opus 5 max cost $38.35
- $24.45 (63.8%) of that was cache write charges
- 9 cache busts in a single 43-message session (22.5% bust rate)
- 5 consecutive cache busts in a row (messages Codex mini #34-38), each costing $1.63
- All 9 cache busts occurred immediately after tool-calls, confirming the root cause identified in Prompt loop DB reload breaks Anthropic cache after tool calls (63% of spend) #24841
Estimated waste: $14.82 (39% of total cost) could have been avoided if caching worked correctly.
Evidence
Session 1: ses_03563ecbdffe92x5KFrsYJRWnN ($18.66)
Title: Creating AGENTS.md for repository
Date: 2026-08-04
Messages: 43 (38 tool-calls, 2 stop)
Total tokens: 80 input / 48,028 output / 6,148,780 cache read / 2,301,161 cache write
Cost breakdown:
| Component | Tokens | Rate | Cost | % |
|---|---|---|---|---|
| Input | 80 | $5.00/M | $0.00 | 0% |
| Output | 48,028 | $25.00/M | $1.20 | 6.4% |
| Cache Read | 6,148,780 | $0.50/M | $3.07 | 16.5% |
| Cache Write | 2,301,161 | $6.25/M | $14.38 | 77.1% |
Cache bust pattern (all after tool-calls):
msg# cache_read cache_write cost prev_finish flag
1 0 84,195 $0.55 (start) CACHE RESET
21 0 233,523 $1.47 tool-calls CACHE RESET
29 0 255,794 $1.61 tool-calls CACHE RESET
30 0 256,289 $1.61 tool-calls CACHE RESET
34 0 259,313 $1.63 tool-calls CACHE RESET
35 0 259,498 $1.63 tool-calls CACHE RESET
36 0 259,734 $1.63 tool-calls CACHE RESET
37 0 260,018 $1.63 tool-calls CACHE RESET
38 0 260,207 $1.63 tool-calls CACHE RESET
Consecutive cache busts (#34-38): 5 in a row, wasting $8.15
Expected cost if cache worked: $5.84
Actual cost: $18.66
Waste: $12.82 (69%)
Session 2: ses_03861eca0ffeuobD3dLHqYq99p ($11.50)
Title: LLM速度对比与Agent配置优化建议
Date: 2026-08-03
Messages: 73 (67 tool-calls, 3 stop)
Cache busts: 2
Cache write: 523,712 tokens × $6.25/M = $3.27 (28.5% of cost)
Session 3: ses_0381fd091ffe4KS4TxsnTcsOFW ($7.51)
Title: Claude Code Max订阅与API token费用对比
Date: 2026-08-03
Messages: 45 (35 tool-calls, 5 stop)
Cache busts: 2
Cache write: 498,810 tokens × $6.25/M = $3.12 (41.5% of cost)
Comparison: DeepSeek V4 Pro (no cache write fee)
Session: ses_02b3612c6ffeOFnJw6eQrlTKW0 (2026-08-06)
Cost: $0.03
Cache write: 0 (DeepSeek does not charge for cache writes)
Cache read: grows steadily from 2K to 89K (no busts)
This demonstrates that the issue is specific to Anthropic's cache write pricing combined with the cache bust bug.
Root Cause
Matches Issue #24841 exactly:
- OpenCode's prompt loop reloads all messages from DB via
filterCompactedEffect()at the start of every iteration - Tool parts transition from
pending→completedwith output text between API calls toModelMessages()serializes the conversation with different bytes- Anthropic's prompt cache sees different content → cache invalidated from that position forward
- Entire conversation context (~250K tokens) re-written at cache-write pricing ($6.25/M)
Verified: All 9 cache busts in the $18.66 session occurred immediately after tool-calls finish type.
New Evidence Not in Previous Reports
-
Consecutive cache busts: 5 in a row (messages Codex mini #34-38), each costing $1.63. This suggests the cache is being invalidated on every single turn during heavy tool-use loops.
-
Cache bust rate: 22.5% (9/40 messages) in a real production session with only 43 messages.
-
Cost per bust: $1.46-$1.63 (250K tokens), lower than the $3.50 (560K) reported in Prompt loop DB reload breaks Anthropic cache after tool calls (63% of spend) #24841, but still significant at scale.
-
Production cost data: Real money wasted ($14.82 across 3 sessions) with exact per-message cost breakdown from OpenCode's SQLite database.
Database Queries
Query 1: Session-level cache stats
SELECT
id,
cost,
tokens_input,
tokens_output,
tokens_cache_read,
tokens_cache_write
FROM session
WHERE id = 'ses_03563ecbdffe92x5KFrsYJRWnN';Query 2: Message-level cache pattern
SELECT
json_extract(data, '$.finish') as finish,
json_extract(data, '$.tokens.cache.read') as cache_r,
json_extract(data, '$.tokens.cache.write') as cache_w,
json_extract(data, '$.cost') as cost
FROM message
WHERE session_id = 'ses_03563ecbdffe92x5KFrsYJRWnN'
AND json_extract(data, '$.role') = 'assistant'
ORDER BY json_extract(data, '$.time.created');Query 3: Verify cache busts after tool-calls
WITH msg_list AS (
SELECT
json_extract(data, '$.finish') as finish,
json_extract(data, '$.tokens.cache.read') as cache_r,
json_extract(data, '$.tokens.cache.write') as cache_w,
ROW_NUMBER() OVER (ORDER BY json_extract(data, '$.time.created')) as rn
FROM message
WHERE session_id = 'ses_03563ecbdffe92x5KFrsYJRWnN'
AND json_extract(data, '$.role') = 'assistant'
)
SELECT
m1.rn,
m1.cache_r,
m1.cache_w,
m2.finish as prev_finish
FROM msg_list m1
LEFT JOIN msg_list m2 ON m1.rn = m2.rn + 1
WHERE m1.cache_r = 0 AND m1.cache_w > 0;Impact
- Financial: $14.82 wasted across 3 sessions (39% of total Opus 5 spend)
- User trust: Users expect prompt caching to work as advertised; silent cache busts at 12.5x read cost are unacceptable
- Model choice: Forces users to avoid Anthropic models on Zen for tool-heavy workloads, limiting model selection
Request
- Reopen Issue Prompt loop DB reload breaks Anthropic cache after tool calls (63% of spend) #24841 or create a new issue with this evidence
- Prioritize PR fix(session): cache messages across prompt loop to preserve prompt cache byte-identity #36852 (or equivalent fix) to cache messages across prompt loop iterations
- Add cache bust detection/logging so users can see when this is happening
- Consider a cost warning when cache bust rate exceeds a threshold
Environment
- OpenCode: 1.18.9
- OS: macOS (darwin)
- Provider: OpenCode Zen (
opencode/claude-opus-5) - Variant: max
- Agent: Sisyphus - ultraworker (via oh-my-openagent)
Additional Data
Full session data available upon request (can export from ~/.local/share/opencode/opencode.db). Per-message cost breakdown available. Can provide additional sessions if needed.
Activity
Arrowyi commentedon Aug 14, 2026
Adding new evidence that was not in the original report and addressing the byte-identity point raised in #31525.
Consecutive cache busts (not previously reported)
The most expensive session (
ses_03563ecbdffe92x5KFrsYJRWnN, $18.66, 43 messages) shows 5 consecutive cache busts across messages #34-38. Each turn re-wrote ~260K tokens at cache-write pricing ($6.25/M), costing $1.63 per turn:Five consecutive turns, $8.15, zero cache reads. This is not a one-off invalidation; the cache is being re-written on every turn during a tool-use loop.
Full bust pattern (all 9 after tool-calls)
9 of 9 busts immediately follow a
tool-callsfinish. The correlation is deterministic, not incidental.On the byte-identity framing (#31525)
I understand the objection that Anthropic caching is keyed on content, not object identity. The data here does not depend on that framing. The observable fact is that
cache_read = 0andcache_write > 0on turns immediately after tool-calls, andcache_writescales with full context size (~260K tokens), not with the incremental delta. Whatever the exact mechanism, the effect is that the entire conversation is re-serialized into the cache on each tool-turn, and Anthropic charges cache-write rates for it.Reproducible from the database
No API introspection required. Anyone can verify from
~/.local/share/opencode/opencode.db:Scope and limitations
This is production evidence from OpenCode 1.18.9 with
opencode/claude-opus-5(max), running the Sisyphus ultraworker agent. Total waste across 3 sessions is $14.82 (39% of spend). I have since switched these workloads to DeepSeek, whose sessions show steady cache-read growth and zero cache-write charges, which isolates the issue to Anthropic's cache-write pricing combined with this behavior.I am not asking for a specific implementation, only that this be looked at with the deterministic 9/9 tool-call correlation and the 5-consecutive-bust sequence on record. If a fix lands in #14743 or elsewhere, happy to re-run the same workload and provide before/after numbers.
cn4750 commentedon Sep 3, 2026
I also see this issue.
rijnhard commentedon Sep 7, 2026
This was actually included in a published article. https://thenewstack.io/agent-harness-token-costs/
the actual source: https://www.eishanlawrence.com/blog/harness-efficiency-bench
Basically using OpenCode at the moment can have a severe financial impact.
thdxr commentedon Oct 11, 2026
Thanks for the report! OpenCode 2.0 is now out and development is focused on V2, so we're closing issues filed against OpenCode 1. Please upgrade (
opencode upgrade --major, details: https://anoma.ly/notes/opencode-2-0), and if this is still relevant on 2.0, reopen this issue or open a new one with your 2.0 version.— from 𝕺𝖕𝖊𝖓𝕮𝖔𝖉𝖊