Enable DeepSeek prompt caching on OpenCode gateway
Cluster 24617 · agent. Data as of
1 open item. Fix merged in #75886 on 1 Aug 2026. Check it covers your case.
The short answer
- Known?
- Yes. 4 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #75886. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #75886. That is separate from the fix event. - Still open
- 0 issues and 1 PR.
Multiple related contributions adding DeepSeek models to the cache_control whitelist or enabling prompt caching support for DeepSeek via OpenCode gateways. The members appear to address the same feature from different angles or implementations.
Open issues0
Open PRs1
- PR#24639feat(cache): enable Anthropic cache_control for DeepSeek on OpenCode (#24617)
Fixes on record
-
#75886 feat(cache): enable prompt caching for DeepSeek models on OpenCode gateways
files:
agent/agent_runtime_helpers.py,tests/run_agent/test_anthropic_prompt_cache_policy.py
1 PR closed without merging
From the close comments: merged via another change 1
-
#74832 feat(cache): enable DeepSeek caching on OpenCode · merged via another change →
#75886,#24617,#24639
Closed issues · 1
- Closed#24617Prompt caching: add DeepSeek models to cache_control whitelist for OpenCode Go
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.50: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- agent
- Merged PRs
- #75886
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 1 Aug 2026