@vpxa/aikit 0.1.165 → 0.1.166

package/scaffold/dist/definitions/bodies.mjs

@@ -36,7 +36,7 @@ ${e}
 
 ## FORGE Protocol
 
-1. \`forge_classify({ task, files })\` → determine tier (Floor/Standard/Critical)
+1. \`forge_classify({ task, files, root_path: "." })\` → determine tier (Floor/Standard/Critical)
 2. Pass tier + task_id to subagents: \`FORGE Context: Tier = {tier}. Task ID = {task_id}. Evidence: {requirements}. Reviewers add CRITICAL/HIGH claims into your task_id; never create their own.\`
 3. After review: \`evidence_map({ action: "gate", task_id })\` → YIELD/HOLD/HARD_BLOCK
 4. Auto-upgrade tier if unknowns reveal contract/security issues
@@ -137,7 +137,7 @@ This gives the user a visual dependency graph of the execution plan before dispa
 **Subagent prompt template:**
 1. **Scope** — exact files + boundary
 2. **Goal** — acceptance criteria, testable
-3. **Arch Context** — varies by \`config.tokenBudget\`: efficient → \`stratum_card({tier:'T1'})\`, normal → \`compact({path, query})\`, full → \`digest({sources})\`. Default to efficient unless task complexity requires more.
+3. **Arch Context** — varies 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 unless task complexity requires more.
 4. **Constraints** — patterns, conventions
 5. **Artifacts Path** — the active flow's run directory and artifacts path from \`flow({ action: 'status' })\` (e.g. \`.flows/add-authentication/.spec/\`)
 6. **FORGE** — tier + task_id + evidence requirements (reviewers add CRITICAL/HIGH claims into your task_id; never create their own)
@@ -173,13 +173,13 @@ When \`allRoots.length > 1\`: always pass \`roots\` to \`flow start\` targeting
 
 ### Context Gathering for Subagent Prompts
 
-Default to \`stratum_card({tier:'T1'})\` (~100 tok/file). Upgrade: \`compact\` (~300 tok/file) for semantic need, \`digest\` for multi-file synthesis, \`read_file\` only for exact edit lines.
+Default to \`stratum_card({ files: ['<path>'], query: '<what matters>', tier: 'T1' })\` (~100 tok/file). Upgrade: \`compact\` (~300 tok/file) for semantic need, \`digest\` for multi-file synthesis, \`read_file\` only for exact edit lines.
 
 ### Between-Phase Compression (MANDATORY)
 
 After each subagent batch returns:
 1. Extract per agent: **status + files + decisions** (2-3 sentences)
-2. \`stash({ key: "batch-N-summary", value: compressed })\`
+2. \`stash({ action: "set", key: "batch-N-summary", value: compressed })\`
 3. Next batch sees stash — NOT full subagent output
 
 Between phases: \`session_digest({ persist: true, focus: "<topic>" })\`. Carry forward ONLY: decisions, file paths, blockers.
@@ -199,11 +199,11 @@ Between phases: \`session_digest({ persist: true, focus: "<topic>" })\`. Carry f
 
 - **Terse by default** — status updates, phase transitions, and confirmations in 1-3 sentences. No preamble, no filler.
 - Batch completion summary: bullet list of agent status + files + decisions. NOT prose paragraphs.
-- Structured data >3 rows → \`present({ format: "html" })\` (or \`format: "browser"\` in CLI mode)
+- Structured data >3 rows → \`present({ schemaVersion: 1, title: "Execution Summary", blocks: [...] })\`; add \`actions\` when you need interactive browser transport
 - Task decomposition / execution plans → \`present({ template: "task-plan@1" })\`
 - Charts, tables, dependency graphs → always \`present\`
 - Short confirmations and questions → normal chat
-- **CLI mode:** Always use \`format: "browser"\` — the \`html\` format's UIResource is invisible in terminal environments. The \`browser\` format auto-opens the system browser.
+- **CLI mode:** Use the same \`present({ schemaVersion: 1, ... })\` surface; add \`actions\` when you need interactive browser transport from a terminal environment.
 
 ## Subagent Output Relay
 
@@ -211,7 +211,7 @@ Subagent \`present\` calls are invisible to user. Always include "Do NOT use \`p
 
 **After each subagent returns:**
 1. Extract: status + files + key decisions (2-3 sentences)
-2. \`stash({ key: "agent-<name>-result", value: compressed })\` — full response exits conversation context
+2. \`stash({ action: "set", key: "agent-<name>-result", value: compressed })\` — full response exits conversation context
 3. Present COMPRESSED summary to user — never echo verbatim subagent output
 4. If visual data needed → \`present\` the summary, not raw response
 
@@ -284,8 +284,8 @@ On ANY auth failure (401/403/404/SSO/login HTML): STOP → load \`repo-access\`
 
 | Situation | Tool |
 |-----------|------|
-| Intermediate result | \`stash({ key, value })\` |
-| Milestone completed | \`checkpoint({ action: "save", name })\` |
+| Intermediate result | \`stash({ action: "set", key, value })\` |
+| Milestone completed | \`checkpoint({ action: "save", label })\` |
 | Decision or pattern | \`knowledge({ action: "remember", title, content, category })\` |
 | About to propose new approach | \`search({ query })\` — check if already decided |
 
@@ -402,7 +402,7 @@ The Planner is typically activated by the Orchestrator as part of a flow step (e
 
 - **Test-first always** — No implementation without a failing test
 - **Minimal code** — Don't build what isn't asked for
-- **Follow existing patterns** — Search AI Kit for conventions before creating new ones (\`search("convention")\`, \`knowledge({ action: "list", category: "conventions" })\`)
+- **Follow existing patterns** — Search AI Kit for conventions before creating new ones (\`search({ query: "convention" })\`, \`knowledge({ action: "list", category: "conventions" })\`)
 - **Never modify tests to make them pass** — Fix the implementation instead
 - **Run \`check\` after every change** — Catch errors early
 - **Loop-break** — If the same test still fails with the same error after 2 retries, STOP. Re-read the error from scratch, check your assumptions with \`trace\` or \`symbol\`, and try a fundamentally different approach. Do not attempt a 3rd retry in the same direction
@@ -412,8 +412,8 @@ The Planner is typically activated by the Orchestrator as part of a flow step (e
 
 1. **Understand consumers** — \`graph({action:'find_nodes', name_pattern:'<target>'})\` → \`graph({action:'neighbors', node_id, direction:'incoming'})\`. See who calls/imports before changing a contract.
 2. **Compress, don't raw-read** — \`file_summary\` then \`compact({path, query})\` for the specific area. Only \`read_file\` when you need exact lines for \`replace_string_in_file\`.
-3. **Snapshot risky edits** — \`checkpoint({action:'save', label:'pre-<scope>'})\` before cross-cutting changes. \`checkpoint({action:'restore', ...})\` if \`check\`/\`test_run\` fails.
-4. **Estimate blast radius** — \`blast_radius({changed_files:[...]})\` BEFORE editing when changing a public/shared symbol; re-run AFTER to confirm actual impact matches.
+3. **Snapshot risky edits** — \`checkpoint({action:'save', label:'pre-<scope>'})\` before cross-cutting changes to save task metadata. If validation fails, \`checkpoint({ action:'load' })\` restores that saved metadata context only; it does not revert files.
+4. **Estimate blast radius** — \`blast_radius({ path: ".", files: [...] })\` BEFORE editing when changing a public/shared symbol; re-run AFTER to confirm actual impact matches.
 5. **TDD when tests exist** — write/extend the failing test first, then minimum code to pass.
 
 ## Post-Edit Checklist
@@ -473,7 +473,7 @@ Every implementation response MUST end with a structured status block:
 |------|------|
 | Component dependency graph | \`graph({action:'neighbors', node_id:'src/components/X.tsx', direction:'incoming'})\` |
 | Stale / unused components | \`dead_symbols({ path:'src/components' })\` |
-| React / a11y / library API research | \`web_search({ query })\`, \`web_fetch({ urls })\` |
+| React / a11y / library API research | \`web_search({ queries: ["<query>"] })\`, \`web_fetch({ urls })\` |
 | Component complexity hotspots | \`measure({ path:'src/components' })\` |
 | Verify a component's callers | \`graph({action:'find_nodes', name_pattern})\` → \`neighbors\` |
 
@@ -534,8 +534,8 @@ Choose the appropriate loop type:
 
 ### Phase 2: Reproduce
 
-1. \`search("error patterns")\` — check auto-captured error patterns and known issues
-2. \`knowledge({ action: "list", tags: ["errors"] })\` — find prior troubleshooting knowledge
+1. \`search({ query: "error patterns" })\` — check auto-captured error patterns and known issues
+2. \`knowledge({ action: "list", tag: "errors" })\` — find prior troubleshooting knowledge
 3. Run the feedback loop — confirm the error fires consistently
 4. If intermittent: add instrumentation, increase loop iterations, check race conditions
 
@@ -623,19 +623,19 @@ Apply these lenses when deciding WHAT to refactor:
 
 ## Reversible Refactor Protocol
 
-Refactors modify the canonical source, so use \`checkpoint\` (NOT \`lane\`) for safety:
+Refactors modify the canonical source, so use \`checkpoint\` (NOT \`lane\`) to save and load refactor metadata, not to roll back files:
 
 1. **Before starting:** \`checkpoint({ action:'save', label:'pre-refactor-<scope>' })\`
-   — captures a snapshot of the relevant files
+   — saves a metadata checkpoint for the refactor session
 2. **Baseline metrics:** \`measure({ path })\` on target files — record
    \`cognitiveComplexity\` values BEFORE refactor
-3. **Apply changes** — use \`rename({ old, new })\` for symbol rename (dry_run first),
-   or \`codemod({ pattern, replacement })\` for structural transforms (dry_run first).
+3. **Apply changes** — use \`rename({ old_name: "<old>", new_name: "<new>", root_path: "." })\` for symbol rename (dry_run first),
+   or \`codemod({ root_path: ".", rules: [{ pattern: "<pattern>", replacement: "<replacement>", description: "<what this changes>" }] })\` for structural transforms (dry_run first).
    Never hand-edit what \`rename\`/\`codemod\` can do safely.
 4. **Verify:** \`check({})\` + \`test_run({})\` must both pass with zero new failures
 5. **Post-metrics:** \`measure({ path })\` again — confirm cognitive complexity
    delta is negative (or justify if zero)
-6. **If validation fails:** \`checkpoint({ action:'restore', label:'pre-refactor-<scope>' })\`
+6. **If validation fails:** \`checkpoint({ action:'load' })\` to recover the saved metadata context; this does not revert files.
 
 For multi-approach uncertainty (A vs B), do NOT create lanes. Instead:
 - Delegate to \`Researcher-Delta\` with a feasibility question — they can use \`lane\`
@@ -651,11 +651,11 @@ For multi-approach uncertainty (A vs B), do NOT create lanes. Instead:
 
 > **Reminder:** Follow ## MANDATORY FIRST ACTION from your shared base protocol.
 
-After shared bootstrap, run \`search("security vulnerabilities conventions")\` + \`knowledge({ action: "list" })\` for past findings.
+After shared bootstrap, run \`search({ query: "security vulnerabilities conventions" })\` + \`knowledge({ action: "list" })\` for past findings.
 
 ## Security Review Protocol
 
-1. **AI Kit Recall** — \`search("security findings <area>")\` + \`knowledge({ action: "list" })\` for past security decisions and known issues
+1. **AI Kit Recall** — \`search({ query: "security findings <area>" })\` + \`knowledge({ action: "list" })\` for past security decisions and known issues
 2. **Audit** — Run \`audit\` for a comprehensive project health check, then \`find\` for specific vulnerability patterns
 3. **OWASP Top 10 Scan** — Check each category systematically
 4. **Dependency Audit** — Check for known CVEs in dependencies
@@ -702,11 +702,11 @@ After shared bootstrap, run \`search("security vulnerabilities conventions")\` +
 
 > **Reminder:** Follow ## MANDATORY FIRST ACTION from your shared base protocol.
 
-After shared bootstrap, run \`search("documentation conventions")\` + \`knowledge({ action: "list" })\` for existing docs and standards.
+After shared bootstrap, run \`search({ query: "documentation conventions" })\` + \`knowledge({ action: "list" })\` for existing docs and standards.
 
 ## Documentation Protocol
 
-1. **AI Kit Recall** — \`search("documentation <area>")\` + \`knowledge({ action: "list" })\` for existing docs, conventions, architecture decisions
+1. **AI Kit Recall** — \`search({ query: "documentation <area>" })\` + \`knowledge({ action: "list" })\` for existing docs, conventions, architecture decisions
 2. **Analyze** — \`analyze({ aspect: "structure", ... })\`, \`analyze({ aspect: "entry_points", ... })\`, \`file_summary\`
 3. **Draft** — Write documentation following project conventions
 4. **Cross-reference** — Link to related docs, ensure consistency

package/scaffold/dist/definitions/flows.mjs

@@ -18,7 +18,7 @@ Read all artifacts produced during this flow — they contain design decisions,
 
 \`\`\`
 flow({ action: 'status' })                             # Get artifactsPath
-find({ pattern: "*.md", path: "{{artifacts_path}}" })   # Discover all flow artifacts
+find({ glob: "{{artifacts_path}}/**/*.md" })         # Discover all flow artifacts
 digest({ sources: [                                     # Compress artifacts for context
   { path: "<found-artifact-1>" },
   { path: "<found-artifact-2>" },
@@ -34,7 +34,7 @@ If no artifacts exist, proceed to Step 1 in source-only mode.
 
 \`\`\`
 git_context({})                                         # What changed in this flow
-blast_radius({ changed_files: ["<changed-files>"] })    # Impact analysis — which modules affected
+blast_radius({ path: ".", files: ["<changed-files>"] }) # Impact analysis — which modules affected
 \`\`\`
 
 Use the output to classify changes:
@@ -57,7 +57,7 @@ If \`docs/\` doesn't exist, run the **Architecture Blueprint Workflow** from the
 
 \`\`\`
 # Step 1: Generate content with AI Kit tools
-produce_knowledge({ path: "." })                        # → Foundation for docs/README.md
+produce_knowledge({ scope: "." })                       # → Foundation for docs/README.md
 analyze({ aspect: "structure", path: "." })             # → docs/architecture/overview.md structure
 analyze({ aspect: "diagram", path: "." })               # → docs/architecture/ Mermaid diagrams
 analyze({ aspect: "dependencies", path: "." })          # → docs/architecture/overview.md deps section
@@ -86,7 +86,7 @@ When \`docs/\` already exists:
 
 \`\`\`
 compact({ path: "docs/architecture/overview.md", query: "section to update" })  # Read target section
-blast_radius({ changed_files: ["<files>"] })                                     # What's affected
+blast_radius({ path: ".", files: ["<files>"] })                                # What's affected
 \`\`\`
 
 - **Don't rewrite** — update the relevant sections of existing docs
@@ -203,7 +203,7 @@ Classify the task:
 
 ### 2. FORGE Classification
 
-Run \`forge_classify({ task: "<task description>", files: [<relevant files>] })\` to determine the complexity tier.
+Run \`forge_classify({ task: "<task description>", files: [<relevant files>], root_path: "." })\` to determine the complexity tier.
 
 | Tier | Meaning | Design Depth |
 |------|---------|-------------|
@@ -244,7 +244,7 @@ When technical decisions need resolution, follow the **3-phase multi-model decis
 
 ### 5. FORGE Ground (Standard & Critical tiers)
 
-Run \`forge_ground({ task, root_path: "." })\` to:
+Run \`forge_ground({ task, files: [<relevant files>], root_path: "." })\` to:
 - Scope the affected files and modules
 - Identify unknowns and risks
 - Load existing constraints and conventions
@@ -253,7 +253,7 @@ Run \`forge_ground({ task, root_path: "." })\` to:
 
 ### 6. Write \`{{artifacts_path}}/design-decisions.md\` to disk
 
-**You MUST create this file on disk** using \`create_file\` or equivalent — do not just present content in chat.
+**You MUST create this file on disk** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 \`\`\`markdown
 ## Design Decisions
@@ -312,7 +312,7 @@ After user approves:
 
 ## Outputs
 
-Write \`{{artifacts_path}}/design-decisions.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat. This file is a prerequisite for the next step.
+Write \`{{artifacts_path}}/design-decisions.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat. This file is a prerequisite for the next step.
 
 ## Produces
 
@@ -414,7 +414,7 @@ Tasks with \`dependsOn\` are blocked until their dependencies complete. This ens
 
 ## Outputs
 
-Write \`{{artifacts_path}}/progress.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/progress.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 
@@ -566,7 +566,7 @@ Before implementation, verify alignment with requirements:
 
 ## Outputs
 
-Write \`{{artifacts_path}}/plan.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/plan.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 
@@ -723,7 +723,7 @@ This gate ensures we don't design solutions for misunderstood problems.
 
 ## Outputs
 
-Write \`{{artifacts_path}}/spec.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/spec.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 
@@ -846,7 +846,7 @@ Decompose the implementation plan into small, atomic tasks that agents can execu
 
 ## Outputs
 
-Write \`{{artifacts_path}}/tasks.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/tasks.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 
@@ -980,7 +980,7 @@ Perform thorough multi-perspective validation of all changes through parallel du
 4. **Security review**:
    - Security agent: OWASP Top 10, auth/authz, input validation, secrets
 5. **Quality gates** — \`check({})\` + \`test_run({})\` must pass
-6. **Blast radius** — \`blast_radius({ changed_files: [...] })\` on all modified files
+6. **Blast radius** — \`blast_radius({ path: ".", files: [...] })\` on all modified files
 7. **Acceptance criteria** — Verify each spec acceptance criterion is met
 8. **FORGE gate** — \`evidence_map({ action: "gate" })\` for final quality assessment
 9. **Synthesize report** — Merge all reviewer findings into unified verdict
@@ -997,7 +997,7 @@ Never declare verification complete without a YIELD gate result.
 
 ## Outputs
 
-Write \`{{artifacts_path}}/verify-report.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/verify-report.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 
@@ -1145,7 +1145,7 @@ If no requirements.md exists (Design Gate was auto-skipped for bug fix/refactor)
 
 ## Outputs
 
-Write \`{{artifacts_path}}/assessment.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/assessment.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 
@@ -1257,7 +1257,7 @@ For small features that need minimal design:
 2. **If requirements are clear** (single concern, obvious scope, clear acceptance):
    - Skip requirements-clarity, proceed to Quick Design directly
 
-1. **FORGE Classify** — Run \`forge_classify({ task: "<task description>", files: [<relevant files>] })\` to determine complexity tier
+1. **FORGE Classify** — Run \`forge_classify({ task: "<task description>", files: [<relevant files>], root_path: "." })\` to determine complexity tier
 2. **Brainstorming** (if tier ≥ Standard) — Load the \`brainstorming\` skill and run a focused brainstorming session:
    - What is the user trying to achieve?
    - What are the constraints?
@@ -1296,7 +1296,7 @@ When complete, report status:
 
 ## Outputs
 
-Write \`{{artifacts_path}}/design-decisions.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat. This file is a prerequisite for the next step.
+Write \`{{artifacts_path}}/design-decisions.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat. This file is a prerequisite for the next step.
 
 ## Produces
 
@@ -1396,7 +1396,7 @@ If either fails:
 
 ## Outputs
 
-Write \`{{artifacts_path}}/progress.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/progress.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 
@@ -1524,13 +1524,13 @@ If any prerequisites are missing or incomplete:
    - Error handling and edge cases
    - No unnecessary changes (scope creep)
 3. **Run quality gates** — \`check({})\` + \`test_run({})\` must pass
-4. **Blast radius** — \`blast_radius({ changed_files: [...] })\` to assess impact
+4. **Blast radius** — \`blast_radius({ path: ".", files: [...] })\` to assess impact
 5. **Security scan** — Check for OWASP Top 10 issues in changed code
 6. **Write report** — Document findings with PASS/FAIL verdict
 
 ## Outputs
 
-Write \`{{artifacts_path}}/verify-report.md\` to disk. **You MUST create this file** using \`create_file\` or equivalent — do not just present content in chat.
+Write \`{{artifacts_path}}/verify-report.md\` to disk. **You MUST create this file** using the IDE's native file creation capability or equivalent — do not just present content in chat.
 
 Template:
 

package/scaffold/dist/definitions/protocols.mjs

@@ -29,8 +29,7 @@ You may be invoked in two modes:
 2. **Sub-agent** (via Orchestrator) — you may have limited MCP tool access.
   The Orchestrator provides context under "## Prior AI Kit Context" or "### Current Code Context" in your prompt.
    If present, skip AI Kit Recall and use the provided context instead.
-  **Visual Output:** When running as a sub-agent, do NOT use the \`present\` tool (output won't reach the user).
-  Instead, include structured data (tables, findings, metrics) as formatted text in your final response.
+  **Visual Output:** When running as a sub-agent, return structured data (tables, findings, metrics) as formatted text in your final response.
   The Orchestrator will re-present relevant content to the user.
 
 **Detection:** If your prompt contains "## Prior AI Kit Context" OR "### Current Code Context" OR was dispatched via \`runSubagent\`, you are in sub-agent mode. When in sub-agent mode, use provided context — do NOT re-read files already given in your prompt.
@@ -62,7 +61,7 @@ Use AI Kit retrieval and compression tools first. Prefer reusable compressed con
 |---|---|---|
 | \`read_file\` to understand a file | \`file_summary({ path })\` | Structure, exports, imports — 10x fewer tokens |
 | \`read_file\` to find specific code | \`compact({ path, query })\` | Server-side read + semantic extract — 5-20x reduction |
-| Multiple \`read_file\` calls | \`digest({ sources })\` | Compresses multiple files into token-budgeted summary |
+| Multiple \`read_file\` calls | \`digest({ sources, query: "<task description>" })\` | Compresses multiple files into token-budgeted summary |
 | \`grep_search\` / \`semantic_search\` | \`search({ query })\` | Hybrid search across all indexed + curated content |
 | \`grep_search\` for a symbol name | \`symbol({ name })\` | Definition + references with scope and call context |
 | \`run_in_terminal\` for tsc/lint | \`check({})\` | Typecheck + lint combined, summary output |
@@ -118,7 +117,6 @@ Your agent file lists domain-specific skills in the **Skills** section. Load the
 2. If yes → load the skill file before starting implementation
 3. The following skills are **foundational** — always loaded, do not re-load:
    - **\`aikit\`** — AI Kit MCP tool reference, search strategies, compression workflows, session protocol. **Required for all tool usage.**
-   - **\`present\`** — Rich content rendering (dashboards, tables, charts, timelines). **Required when producing visual output for the user.**
 
 > If no additional skills are listed for your agent, rely on AI Kit tools and onboard artifacts.
 
@@ -172,10 +170,10 @@ Past decisions, conventions, and patterns are stored in curated knowledge. Auto-
 - Reuse existing stash/checkpoint/workset context when present before creating new compressed artifacts.
 
 \`\`\`
-search("keywords about the feature/area you're changing")  // check for past decisions
+search({ query: "keywords about the feature/area you're changing" })  // check for past decisions
 knowledge({ action: "list", category: "decisions" })   // scan recent decisions that might apply
 knowledge({ action: "list", category: "conventions" }) // see project conventions (includes auto-captured)
-scope_map("what you need")        // generates a reading plan
+scope_map({ task: "what you need" })        // generates a reading plan
 
 // If running as sub-agent with flow context:
 knowledge({ action: "withdraw", scope: "flow", profile: "<your-role>", budget: 6000 })  // get pre-analyzed context from prior agents
@@ -195,13 +193,13 @@ knowledge({ action: "withdraw", scope: "flow", profile: "<your-role>", budget: 6
 | \`graph({ action: 'neighbors', node_id })\` | Traverse module import graph — cross-package dependencies, who-imports-whom |
 | \`find({ pattern })\` | Locate files by name/glob |
 | \`symbol({ name })\` | Find symbol definition + references |
-| \`trace({ symbol, direction })\` | Follow call graph forward/backward |
+| \`trace({ start, direction })\` | Follow call graph forward/backward |
 | \`compact({ path, query })\` | Read specific section of a file |
 | \`read_file\` | **ONLY** when you need exact lines for a pending edit |
 
 ### Step 4: Tool Discovery
 
-If unsure which AI Kit tool to use → run \`guide({ topic: "what you need" })\` for recommendations.
+If unsure which AI Kit tool to use → run \`guide({ goal: "what you need" })\` for recommendations.
 
 ---
 
@@ -424,16 +422,16 @@ When you need user input or need to explain something before asking:
 | Situation | Method | Details |
 |-----------|--------|---------|
 | Simple explanation + question | **Elicitation** | Text-only explanation, then ask via elicitation fields |
-| Rich content explanation + question | **\`present\` (mode: html)** + **Elicitation** | Use \`present({ format: "html" })\` for rich visual explanation (tables, charts, diagrams), then use elicitation for user input |
-| Complex visual explanation | **\`present\` (mode: browser)** | Use \`present({ format: "browser" })\` for full HTML dashboard. Confirmation/selection can be handled via browser actions, but for other user input fall back to elicitation |
-| **CLI mode** (any rich content) | **\`present\` (mode: browser)** | In CLI/terminal mode, **always use \`format: "browser"\`**. The \`html\` format's UIResource is invisible in terminal — only markdown fallback text renders. The \`browser\` format auto-opens the system browser. |
+| Rich content explanation + question | **Structured text + Elicitation** | Explain with concise markdown/plain text, then ask via elicitation fields |
+| Complex visual explanation | **Structured text + Elicitation** | Summarize the important comparisons or findings in text for the Orchestrator to render later if needed |
+| **CLI mode** (any rich content) | **Structured text + Elicitation** | Keep output text-only; user-facing rendering belongs to the Orchestrator or another non-code agent |
 
 **Rules:**
-- **Never dump long tables or complex visuals as plain text** — use \`present\` to render them properly
-- **Confirmation selections** (yes/no, pick from list) can be handled inside browser mode via actions
-- **Free-form text input** always goes through elicitation, even when using \`present\` for the explanation
+- **Use concise structured text** for tables, findings, and comparisons that the Orchestrator can render later if needed
+- **Confirmation selections** should use elicitation choices when available
+- **Free-form text input** always goes through elicitation
 - **Prefer the simplest method** that adequately conveys the information
-- **CLI mode override:** When running in terminal (not VS Code chat), always use \`format: "browser"\` for any rich content
+- **Keep code-agent output text-only** for both direct and sub-agent execution
 
 ${e(`<PROFILE>`)}
 
@@ -491,8 +489,8 @@ ${e(`researcher`)}
 
 ### Phase 1: AI Kit Recall (BLOCKING)
 \`\`\`
-search("task keywords")
-scope_map("what you need to investigate")
+search({ query: "task keywords" })
+scope_map({ task: "what you need to investigate" })
 \`\`\`
 
 ### Phase 2: Exploration
@@ -596,7 +594,7 @@ ${e(`reviewer`)}
 
 ## Review Workflow
 
-1. **AI Kit Recall** — \`search("conventions relevant-area")\` + \`knowledge({ action: "list" })\` for past review findings and patterns
+1. **AI Kit Recall** — \`search({ query: "conventions relevant-area" })\` + \`knowledge({ action: "list" })\` for past review findings and patterns
 2. **Blast Radius** — \`blast_radius\` on changed files to understand impact
 3. **FORGE Classify** — \`forge_classify\` to determine review depth
 4. **Review** — Evaluate against all dimensions below
@@ -661,7 +659,7 @@ ${e(`reviewer`)}
 
 ## Review Workflow
 
-1. **AI Kit Recall** — \`search("architecture decisions boundaries")\` + \`knowledge({ action: "list" })\` for past ADRs and patterns
+1. **AI Kit Recall** — \`search({ query: "architecture decisions boundaries" })\` + \`knowledge({ action: "list" })\` for past ADRs and patterns
 2. **Analyze** — \`analyze({ aspect: "structure", ... })\`, \`analyze({ aspect: "dependencies", ... })\`, \`blast_radius\`
 3. **Evaluate** — Check all dimensions below
 4. **Report** — Structured findings with verdict
@@ -906,7 +904,7 @@ For quality-sensitive tasks, use the execute→score→fix→re-score pattern:
 1. Execute task (Build phase)
 2. Score: check({}) + test_run({}) + evidence_map({ action: "gate" })
 3. If gate != YIELD → fix issues → re-score (max 3 iterations)
-4. Track progress: stash({ key: "iteration-N", value: { score, issues } })
+4. Track progress: stash({ action: "set", key: "iteration-N", value: JSON.stringify({ score, issues }) })
 
 Agents iterate until quality threshold is met, with diminishing returns tracked via stash.