opencode-hive 1.2.0 → 1.3.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +83 -2
- package/dist/agents/custom-agents.d.ts +18 -0
- package/dist/agents/forager.d.ts +1 -1
- package/dist/agents/hive.d.ts +1 -1
- package/dist/agents/scout.d.ts +1 -7
- package/dist/agents/swarm.d.ts +1 -1
- package/dist/hooks/system-hook.d.ts +8 -0
- package/dist/hooks/variant-hook.d.ts +0 -33
- package/dist/index.js +1171 -684
- package/dist/utils/compaction-prompt.d.ts +1 -0
- package/package.json +1 -1
- package/skills/dispatching-parallel-agents/SKILL.md +3 -3
- package/skills/executing-plans/SKILL.md +1 -1
- package/skills/parallel-exploration/SKILL.md +2 -2
|
@@ -0,0 +1 @@
|
|
|
1
|
+
export declare function buildCompactionPrompt(): string;
|
package/package.json
CHANGED
|
@@ -78,9 +78,9 @@ Each agent gets:
|
|
|
78
78
|
|
|
79
79
|
```typescript
|
|
80
80
|
// Using Hive tools for parallel execution
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
81
|
+
hive_worktree_start({ task: "01-fix-abort-tests" })
|
|
82
|
+
hive_worktree_start({ task: "02-fix-batch-tests" })
|
|
83
|
+
hive_worktree_start({ task: "03-fix-race-condition-tests" })
|
|
84
84
|
// All three run concurrently in isolated worktrees
|
|
85
85
|
```
|
|
86
86
|
|
|
@@ -36,7 +36,7 @@ Only `done` satisfies dependencies (not `blocked`, `failed`, `partial`, `cancell
|
|
|
36
36
|
### Step 3: Execute Batch
|
|
37
37
|
|
|
38
38
|
For each task in the batch:
|
|
39
|
-
1. Mark as in_progress via `
|
|
39
|
+
1. Mark as in_progress via `hive_worktree_start()`
|
|
40
40
|
2. Follow each step exactly (plan has bite-sized steps)
|
|
41
41
|
3. Run verifications as specified
|
|
42
42
|
4. Mark as completed
|
|
@@ -13,7 +13,7 @@ When you need to answer "where/how does X work?" across multiple domains (codeba
|
|
|
13
13
|
|
|
14
14
|
**Safe in Planning mode:** This is read-only exploration. It is OK to use during exploratory research even when there is no feature, no plan, and no approved tasks.
|
|
15
15
|
|
|
16
|
-
**This skill is for read-only research.** For parallel implementation work, use `hive_skill("dispatching-parallel-agents")` with `
|
|
16
|
+
**This skill is for read-only research.** For parallel implementation work, use `hive_skill("dispatching-parallel-agents")` with `hive_worktree_start`.
|
|
17
17
|
|
|
18
18
|
## When to Use
|
|
19
19
|
|
|
@@ -24,7 +24,7 @@ When you need to answer "where/how does X work?" across multiple domains (codeba
|
|
|
24
24
|
- Questions are independent (answer to A doesn't affect B)
|
|
25
25
|
- User asks **3+ independent questions** (often as a numbered list or separate bullets)
|
|
26
26
|
- No edits needed (read-only exploration)
|
|
27
|
-
- User asks for an
|
|
27
|
+
- User asks for an exploration that likely spans multiple files/packages
|
|
28
28
|
- The work is read-only and the questions can be investigated independently
|
|
29
29
|
|
|
30
30
|
**Only skip this skill when:**
|