@vpxa/aikit 0.1.250 → 0.1.251

package/scaffold/dist/definitions/bodies.mjs

@@ -149,7 +149,7 @@ import{postTaskLesson as e,preTaskKnowledgeRecall as t}from"./protocols.mjs";con
   **Subagent prompt template:**
   1. **Scope** — exact files + boundary
   2. **Goal** — acceptance criteria, testable
-  3. **Arch Context** — pick by \`config.tokenBudget\`: efficient → \`stratum_card({ files: ['<path>'], query: '<what matters>', tier: 'T1' })\`, normal → \`compact({path, query})\`, full → \`digest({ sources: [...], query: '<what matters>' })\`. Default to efficient.
+  3. **Arch Context** — pick by \`config.tokenBudget\`: efficient → \`stratum_card({ files: ['<path>'], query: '<what matters>', tier: 'T1' })\`, normal → \`compact({path, query})\` or \`compact({ref, query?})\`, full → \`digest({ sources: [...], query: '<what matters>' })\`. Default to efficient.
   4. **Constraints** — patterns, conventions
   5. **Prior Knowledge** — Fetch topic-scoped knowledge: \`knowledge({ action: "lesson", subAction: "list-lessons", topic: "<2-3 task keywords>", minConfidence: 70 })\` + \`search({ query: "<task area>", category: "conventions", limit: 3 })\`. Include HIGH-confidence results (≥70) under \`## Prior Knowledge\`. Skip if none.
   6. **Artifacts Path** — the active flow's run directory and artifacts path from \`flow({ action: 'status' })\` (e.g. \`.flows/add-authentication/.spec/\`)
@@ -188,7 +188,7 @@ import{postTaskLesson as e,preTaskKnowledgeRecall as t}from"./protocols.mjs";con
 
   ### Context Gathering for Subagent Prompts
 
-  Default to \`stratum_card({ files: ['<path>'], query: '<what matters>', tier: 'T1' })\`; upgrade to \`compact\` or \`digest\`; use \`read_file\` only for exact edit lines.
+  Default to \`stratum_card({ files: ['<path>'], query: '<what matters>', tier: 'T1' })\`; upgrade to \`compact({ path, query })\`, \`compact({ ref, query? })\`, or \`digest\`; use \`read_file\` only for exact edit lines.
 
   **Knowledge injection (MANDATORY for Standard+ tier):** Before any subagent prompt, call:
   - \`knowledge({ action: "lesson", subAction: "list-lessons", topic: "<task keywords>", minConfidence: 70 })\`
@@ -415,7 +415,7 @@ import{postTaskLesson as e,preTaskKnowledgeRecall as t}from"./protocols.mjs";con
 ## Pre-Edit Checklist
 
 1. **Understand consumers** — \`graph({action:'find_nodes', name_pattern:'<target>'})\` → \`graph({action:'neighbors', node_id, direction:'incoming'})\`
-2. **Compress, don't raw-read** — \`file_summary\` then \`compact({path, query})\`; \`read_file\` only for exact edit lines
+2. **Compress, don't raw-read** — \`file_summary\` then \`compact({path, query})\` or \`compact({ref, query?})\`; \`read_file\` only for exact edit lines
 3. **Snapshot risky edits** — \`checkpoint({action:'save', label:'pre-<scope>'})\` before cross-cutting changes
 4. **Estimate blast radius** — run \`blast_radius\` before and after shared/public symbol changes
 5. **TDD when tests exist** — failing test first, then minimum code

package/scaffold/dist/definitions/flows.mjs

@@ -10,7 +10,7 @@ Follow \`multi-agents-development\` dispatch patterns:
 2. **Subagent Context**:
    - **Scope**: exact files + do NOT touch boundary
    - **Goal**: testable acceptance criteria
-   - **Arch Context**: code via \`compact()\`/\`digest()\`
+   - **Arch Context**: code via \`compact()\`/\`digest()\` or a cached ref via \`compact({ ref, query? })\`
    - **Constraints**: patterns, conventions, anti-patterns
    - **Self-Review**: checklist before DONE
 

package/scaffold/dist/definitions/protocols.mjs

@@ -52,6 +52,7 @@ Use AI Kit retrieval/compression first. Native tools are fallback only.
 | \`read_file\` to understand a file | \`file_summary({ path })\` | Structure first |
 | \`read_file\` to find code | \`compact({ path, query })\` | Focused extract |
 | Multiple \`read_file\` calls | \`digest({ sources, query: "<task description>" })\` | Compress multi-file context |
+| Cached ref to refocus prior output | \`compact({ ref, query? })\` | Reuse reversible text artifacts |
 | \`grep_search\` / \`semantic_search\` | \`search({ query })\` | Indexed search |
 | \`grep_search\` for a symbol | \`symbol({ name })\` | Def + refs |
 | \`run_in_terminal\` for tsc/lint | \`check({})\` | Narrow validation |
@@ -196,6 +197,7 @@ Use targeted searches before expensive work:
 | \`symbol({ name })\` | Definition + refs |
 | \`trace({ start, direction })\` | Call/data flow |
 | \`compact({ path, query })\` | Read specific section of a file |
+| \`compact({ ref, query? })\` | Reuse cached search/find/knowledge/compact output |
 | \`read_file\` | **ONLY** when you need exact lines for a pending edit |
 
 ### Step 4: Tool Discovery

package/scaffold/dist/definitions/skills/aikit.mjs

@@ -155,9 +155,9 @@ Every tool call passes through extractors that capture reusable facts:
 | **Research results** | \`web_search\`, \`web_fetch\`, \`search\`, \`find\` | Search findings, web content, code discoveries |
 | **Behavioral patterns** | ALL tools (ring buffer) | Tool preferences, search→edit sequences, error-fix cycles |
 
-**Retrieval:** Use \`enrich: true\` on any tool that supports it — the server automatically surfaces previously captured facts relevant to your query. Or search directly: \`search({ query: "...", origin: "curated" })\`
+**Retrieval:** Use \`enrich: true\` on any tool that supports it — the server automatically surfaces previously captured facts relevant to your query. Search/find/knowledge responses can also emit reusable refs; feed those into \`compact({ ref, query })\` instead of reopening the source.
 
-**Best practice:** Before re-reading a file you've already explored, try \`search({ query: "file-path-or-topic" })\` — auto-knowledge may already have what you need.
+**Best practice:** Before re-reading a file you've already explored, try \`search({ query: "file-path-or-topic" })\` — auto-knowledge may already have what you need, or reuse an existing \`ref\` with \`compact({ ref, query })\`.
 
 ### Retention & Tier Promotion
 - Memories start at **working** tier → promote on repeated access: episodic (2) → semantic (5) → procedural (10)