You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
**Deduplication** — Identifies repeated tool calls (e.g., reading the same file multiple times) and keeps only the most recent output. Runs automatically on every request with zero LLM cost.
29
29
30
-
**Prune Thinking Blocks** — Removes LLM thinking/reasoning blocks from the conversation history.
31
-
32
30
**On Idle Analysis** — Uses a language model to semantically analyze conversation context during idle periods and identify tool outputs that are no longer relevant.
33
31
34
32
**Prune Tool** — Exposes a `prune` tool that the AI can call to manually trigger pruning when it determines context cleanup is needed.
35
33
34
+
*More strategies coming soon.*
35
+
36
36
Your session history is never modified. DCP replaces pruned outputs with a placeholder before sending requests to your LLM.
37
37
38
38
## Impact on Prompt Caching
@@ -66,10 +66,6 @@ DCP uses its own config file (`~/.config/opencode/dcp.jsonc` or `.opencode/dcp.j
66
66
// Additional tools to protect from pruning
67
67
"protectedTools": []
68
68
},
69
-
// Remove thinking/reasoning LLM blocks
70
-
"pruneThinkingBlocks": {
71
-
"enabled":false
72
-
},
73
69
// Exposes a prune tool to your LLM to call when it determines pruning is necessary
0 commit comments