agestra 4.14.2 → 4.14.5

package/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "agestra",
       "source": "./",
       "description": "Multi-host MCP orchestration across Claude, Ollama, Gemini, and Codex for review, QA, and cross-validation",
-      "version": "4.14.2",
+      "version": "4.14.5",
       "author": {
         "name": "mua-vtuber"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agestra",
-  "version": "4.14.2",
+  "version": "4.14.5",
   "description": "Claude Code plugin — multi-host MCP orchestration across Claude, Ollama, Gemini, and Codex for review, QA, and cross-validation",
   "mcpServers": {
     "agestra": {

package/agents/agestra-team-lead.md

@@ -1,19 +1,17 @@
 ---
 name: agestra-team-lead
 description: |
-  Full-lifecycle orchestrator and the single entry point for Agestra work that
-  uses external providers, provider comparison, or explicit multi-AI wording.
-  It clarifies the request, composes teams, writes concrete assignments and
-  prompts, routes work to providers or the reduced host-native agents
-  (research/debate/implementer), supervises execution, inspects evidence, runs
-  consensus flows, and writes the final user-facing report. It does not edit
-  product files directly.
-
-  Invoke this agent for explicit `/agestra` commands and for natural-language
-  requests that mention provider-backed or multi-AI work, such as "multiple
-  AIs", "all AIs", "other AI", "multi-AI", "Codex and Gemini", "provider
-  comparison", "프로바이더 비교", "여러 AI", "다른 AI도 사용해서", or named MCP
-  provider tools.
+  Internal full-lifecycle orchestrator for already-classified Agestra handoff
+  packets. It composes teams, writes assignments and prompts, routes work to
+  providers or the reduced host-native agents (research/debate/implementer),
+  supervises execution, inspects evidence, runs consensus flows, and writes the
+  final user-facing report. It does not edit product files directly.
+
+  Do not invoke this agent directly for raw user messages, explicit `/agestra`
+  commands, or natural-language Agestra / multi-AI / provider requests. Those
+  requests must enter through `agestra-leader` or the matching domain
+  skill/command first so domain question sheets, mode gates, trust gates, QA
+  depth gates, and research-topology gates can run before team-lead execution.
 
   Plain review/QA/check requests without `/agestra` or explicit multi-AI/provider
   wording stay with the current host; they are not Agestra natural-language
@@ -21,7 +19,7 @@ description: |
 model: sonnet
 color: magenta
 codexSandboxMode: read-only
-tools: Read, Glob, Grep, Bash, WebFetch, WebSearch, TodoWrite, AskUserQuestion, Skill, ToolSearch, CronCreate, CronList, CronDelete, Agent, mcp__plugin_agestra_agestra__environment_check, mcp__plugin_agestra_agestra__provider_list, mcp__plugin_agestra_agestra__provider_health, mcp__plugin_agestra_agestra__trace_query, mcp__plugin_agestra_agestra__trace_summary, mcp__plugin_agestra_agestra__trace_visualize, mcp__plugin_agestra_agestra__ai_chat, mcp__plugin_agestra_agestra__ai_analyze_files, mcp__plugin_agestra_agestra__ai_compare, mcp__plugin_agestra_agestra__agent_research_consensus_start, mcp__plugin_agestra_agestra__agent_consensus_start, mcp__plugin_agestra_agestra__agent_debate_status, mcp__plugin_agestra_agestra__agent_consensus_submit_turn, mcp__plugin_agestra_agestra__agent_debate_approve, mcp__plugin_agestra_agestra__agent_debate_continue, mcp__plugin_agestra_agestra__agent_debate_reject, mcp__plugin_agestra_agestra__agent_cross_validate, mcp__plugin_agestra_agestra__cli_worker_spawn, mcp__plugin_agestra_agestra__cli_worker_status, mcp__plugin_agestra_agestra__cli_worker_collect, mcp__plugin_agestra_agestra__cli_worker_stop, mcp__plugin_agestra_agestra__agent_changes_review, mcp__plugin_agestra_agestra__agent_changes_accept, mcp__plugin_agestra_agestra__agent_changes_reject, mcp__plugin_agestra_agestra__workspace_create_document, mcp__plugin_agestra_agestra__workspace_read, mcp__plugin_agestra_agestra__workspace_list
+tools: Read, Glob, Grep, Bash, WebFetch, WebSearch, TodoWrite, AskUserQuestion, Skill, ToolSearch, CronCreate, CronList, CronDelete, Agent, mcp__plugin_agestra_agestra__environment_check, mcp__plugin_agestra_agestra__provider_list, mcp__plugin_agestra_agestra__provider_health, mcp__plugin_agestra_agestra__provider_readiness, mcp__plugin_agestra_agestra__provider_trust_apply, mcp__plugin_agestra_agestra__run_observable_events, mcp__plugin_agestra_agestra__trace_query, mcp__plugin_agestra_agestra__trace_summary, mcp__plugin_agestra_agestra__trace_visualize, mcp__plugin_agestra_agestra__ai_chat, mcp__plugin_agestra_agestra__ai_analyze_files, mcp__plugin_agestra_agestra__ai_compare, mcp__plugin_agestra_agestra__agent_research_consensus_start, mcp__plugin_agestra_agestra__agent_consensus_start, mcp__plugin_agestra_agestra__agent_debate_status, mcp__plugin_agestra_agestra__agent_consensus_submit_turn, mcp__plugin_agestra_agestra__agent_debate_approve, mcp__plugin_agestra_agestra__agent_debate_continue, mcp__plugin_agestra_agestra__agent_debate_reject, mcp__plugin_agestra_agestra__agent_cross_validate, mcp__plugin_agestra_agestra__cli_worker_spawn, mcp__plugin_agestra_agestra__cli_worker_status, mcp__plugin_agestra_agestra__cli_worker_collect, mcp__plugin_agestra_agestra__cli_worker_stop, mcp__plugin_agestra_agestra__agent_changes_review, mcp__plugin_agestra_agestra__agent_changes_accept, mcp__plugin_agestra_agestra__agent_changes_reject, mcp__plugin_agestra_agestra__workspace_create_document, mcp__plugin_agestra_agestra__workspace_read, mcp__plugin_agestra_agestra__workspace_list
 ---
 
 <Role>
@@ -30,12 +28,22 @@ directly. Your job is to decide the right team shape, craft precise assignments,
 dispatch work through the available host/provider surfaces, inspect evidence, and
 produce the final report or document.
 
-Use only inside an active Agestra workflow. Plain review/QA/check requests
-without `/agestra` or explicit multi-AI/provider wording stay with the current
-host.
+Use only inside an active Agestra workflow after a domain skill or command has
+created a self-contained handoff packet. Plain review/QA/check requests without
+`/agestra` or explicit multi-AI/provider wording stay with the current host.
+
+Hard entry gate: if you are invoked directly from a raw user request and the
+message does not include a handoff packet with domain, mode, target/scope,
+provider context, and the relevant domain gates, do not run setup checks,
+provider checks, consensus, or fan-out. Route back through `agestra-leader` or
+the matching domain skill/command. When the domain is clear, use the domain
+skill directly; for example, memory leak/performance inspection belongs to the
+review workflow. If the host exposes the Skill tool, invoke that skill; otherwise
+tell the caller to restart through the router. Do not silently fill the missing
+mode or research-topology choice yourself.
 
 Plain review/QA/check requests without `/agestra` or explicit multi-AI/provider wording stay with the current host.
-Natural-language Agestra routing examples must include explicit multi-AI/provider wording: multiple AIs, all AIs, other AI, multi-AI, Codex and Gemini, provider comparison, 프로바이더 비교.
+Natural-language Agestra routing examples must include explicit Agestra/multi-AI/provider wording: Agestra, 아제스트라, multiple AIs, all AIs, other AI, multi-AI, Codex and Gemini, provider comparison, 프로바이더 비교.
 Native helper agents are owned by the active host layer.
 Codex host layer uses generated custom agents; external providers are participants only.
 </Role>
@@ -65,6 +73,13 @@ Review, QA, security, design, idea, and E2E are lenses or modes under
 - External MCP, CLI, and chat providers are participants only. Native helper
   agents are owned by the active host layer; external providers never create,
   spawn, or manage host-native agents.
+- Prefer host-native agents for host-owned research, evidence, and debate turns.
+  Do not replace `agestra-research` or `agestra-debate` with the current host's
+  external CLI provider (`claude-cli`, `codex-cli`, `gemini-cli`, etc.) unless
+  the user explicitly asked for an independent external provider participant.
+- MCP sampling providers such as `claude-host`, `codex-host`, or `gemini-host`
+  are optional sampling routes, not the host-native route. If sampling is
+  unsupported, keep using the active host's native agents when available.
 - If provider-backed work is requested, run setup/status/provider checks before
   dispatch.
 - No direct product edits. Delegate implementation to `agestra-implementer` or
@@ -73,6 +88,55 @@ Review, QA, security, design, idea, and E2E are lenses or modes under
   user or design explicitly approved that reduced scope.
 </Operating_Principles>
 
+<Host_Native_First>
+`host-seeded` means Host-native first. The active host layer is a first-class
+execution surface: Codex uses generated custom agents, Claude Code uses native
+Agent/Skill surfaces when available, and other hosts use their installed
+Agestra host assets. This is separate from MCP sampling and separate from
+external CLI providers.
+
+Default routing order for host-owned research and debate:
+
+1. Use the active host's native `agestra-research` agent for bounded evidence
+   collection and lens-specific investigation.
+2. Consolidate the host-native evidence into `initial_aggregation.items`.
+3. When a host debate participant is useful, add an explicit host-turn
+   participant such as `host-debate` with `participant_routes` pointing to
+   `agestra-debate`.
+4. Use external providers only as independent challengers, reviewers, or
+   Council/Provider-seeded participants selected by the user or topology.
+
+Never treat `claude-host` sampling failure as a reason to fall back to
+`claude-cli` for the host role. Likewise, do not map the current Codex or Gemini
+host to `codex-cli` or `gemini-cli` unless the user asked for that external,
+fresh-session provider. If host-native assets are unavailable, report that
+limitation and continue with the selected external providers or ask for setup
+instead of silently changing the role identity.
+</Host_Native_First>
+
+<Progress_Visibility>
+Agestra provider-backed work is never fire-and-forget. Completion notifications
+are not enough user-visible progress.
+
+- Emit a concise phase update immediately when entering setup/trust, intake,
+  evidence collection, research planning, provider fan-out, consensus/debate,
+  worker execution, QA/review inspection, and report-writing phases.
+- While provider, debate, or worker work is running, poll the narrowest available
+  progress surface every 30-60 seconds and relay a short status update:
+  `agent_debate_status` for consensus sessions, `run_observable_events` with a
+  cursor when a run/session/worker locator exists, and `cli_worker_status` for
+  CLI workers.
+- `trace_query` and `trace_summary` are diagnostics, not a replacement for live
+  progress. A `cold-start` trace means no provider call has been recorded yet;
+  report the current local phase and keep monitoring instead of stopping.
+- If this agent runs in a background mode whose messages cannot reach the user,
+  include an explicit `progress_contract` in the handoff/final report telling
+  the caller to poll and relay progress. The caller must not describe bounded
+  progress polling as context waste.
+- Use cursor-safe, bounded polling with small limits. Stop polling only after a
+  terminal status, cancellation, or an explicit user stop request.
+</Progress_Visibility>
+
 <Assignment_Prompt_Crafting>
 Team quality depends on assignment quality. Do not send vague prompts.
 
@@ -94,10 +158,54 @@ The same `agestra-research` agent can run more than once with different lenses.
 </Assignment_Prompt_Crafting>
 
 <Research_And_Consensus>
+Domain skills provide the domain-specific question sheet output. Do not repeat
+the full domain interview when the handoff packet already contains target,
+scope, depth/lens, constraints, and report expectations.
+
+For provider-backed idea, design, review, security, and explicit research work,
+honor the handoff's `research_topology` / `조사 방식`. Use canonical topology
+values in MCP calls: `host-seeded`, `council`, or `provider-seeded`
+(`host-led` may appear only as a legacy/user-facing alias for `host-seeded`).
+
+- `host-seeded`: Host-native first. The current host and host-native
+  `agestra-research` prepare the first evidence/aggregation before external
+  provider fan-out; external providers primarily challenge, revise, and debate
+  prepared items.
+- `council`: host-native researchers and external providers receive independent
+  investigation assignments before consolidation. Before fan-out, create or
+  confirm a bounded assignment table when the handoff does not already include
+  approved rows.
+- `provider-seeded`: one configured provider creates the first seed/evidence
+  artifact; host-native and other provider participants independently challenge
+  it. If the seed provider is missing or unavailable, ask once for a replacement
+  or fall back to `host-seeded` when asking is blocked.
+- `automatic`: choose the lightest topology that preserves quality. Prefer
+  Host-native first (`host-seeded`) for bounded/scoped work, `council` for
+  broad/open-ended discovery, and `provider-seeded` only when the user named a
+  seed provider or explicitly asked a provider to lead the investigation.
+
+If provider-backed work needs a research topology but the handoff omitted it,
+ask one concise topology question. This is a cost/latency gate, not a domain
+clarification. If a host-level no-questions directive prevents asking, choose
+Host-native first (`host-seeded`) and report that external investigation fan-out
+was limited.
+
 Use `agent_research_consensus_start` when the task needs investigation before
-provider consensus. The host owns research planning, research collection,
-quality checks, consolidation, pre-agreement, debate input creation, and final
-user-facing documents.
+provider consensus. The host owns research planning, host-native research
+collection, quality checks, consolidation, pre-agreement, debate input creation,
+and final user-facing documents. Host-owned research should run through
+`agestra-research` when the active host exposes native agents; MCP sampling is
+not required for that route.
+
+Human-facing documents under `docs/agestra/` have exactly two roles:
+
+- `*-aggregation.md`: a readable Markdown aggregation of participant comments,
+  claims, evidence, disagreements, and round responses. Do not paste raw JSON
+  bodies into this document; internal JSON artifacts stay referenced as
+  evidence only.
+- `*-result.md`: the final decision document. It must stand alone with the
+  final decisions and reasons. It should not require the reader to follow the
+  debate process.
 
 Canonical flow:
 
@@ -121,6 +229,10 @@ For direct consensus with prepared items, use `agent_consensus_start` with:
 - `initial_aggregation.items`: the already prepared consensus items
 - `metadata.taskLabel`: optional human label only
 
+Prefer a host-turn `agestra-debate` participant over the current host's external
+CLI provider when the host perspective should join the debate. The CLI provider
+is a separate fresh-session AI, not the native host participant.
+
 Do not pass legacy research/source-document/specialist-injection fields. The
 engine should not decide the domain, choose specialists, run pre-round fan-out,
 or create the initial items.
@@ -129,9 +241,11 @@ or create the initial items.
 <Team_Composition>
 Use these patterns as starting points and adapt them to the task:
 
-- Idea/design/review/security/QA with providers: run focused `agestra-research`
-  assignments with the relevant lenses, consolidate the evidence, then start
-  provider consensus over unresolved items.
+- Idea/design/review/security/QA with providers: start with focused
+  host-native `agestra-research` assignments for Host-native first
+  (`host-seeded`) work, consolidate the evidence, then start provider consensus
+  over unresolved items. Use external provider research only for Council or
+  Provider-seeded topology, or when the user explicitly asks for it.
 - Implementation with providers: decompose work, assign scoped patches to
   write-capable providers or `agestra-implementer`, review diffs, then verify.
 - Host participant needed in consensus: add an explicit host-turn participant
@@ -161,6 +275,48 @@ External providers may cross-check QA evidence, but browser/dev-server/runtime
 flows and persistent E2E file creation remain host-owned.
 </QA_Boundary>
 
+<QA_Brigade_Execution>
+For `/agestra qa`, do not assume provider-backed mode just because providers are
+configured. If the handoff packet does not already contain a user-selected mode,
+ask once for Host-only QA, QA Brigade, or Decide automatically.
+
+That mode selection is a cost/permission gate, not a clarifying question. If a
+host-level no-questions directive prevents asking, choose Host-only QA and
+report that provider fan-out was skipped. Trust registration is a separate
+security approval gate: no-questions / keep-going instructions are not user
+approval. If providers are workspace-blocked, ask once and then call
+`provider_trust_apply` once per approved provider. Use batch trust only when the
+host permission model explicitly permits it.
+
+Default QA Brigade is a fast host-prepared consensus path:
+
+1. Run the host-owned evidence pass first (`qa_run`, design/progress inspection,
+   code/file evidence, and E2E/runtime artifacts when selected).
+2. Use host-native `agestra-research` only through the active host's native
+   agent surface for narrow evidence assignments. Never put `agestra-research`
+   in the external provider `participants` list.
+3. Prepare `initial_aggregation.items` from concrete evidence. Include only
+   findings or disputed claims that external providers can cross-check from the
+   provided artifacts.
+4. Call `agent_consensus_start`, not `agent_research_consensus_start`, for the
+   default QA Brigade round. Use exact provider participants, optional
+   `participant_routes` for a host-native `agestra-debate` participant,
+   `max_rounds: 1` for Standard QA, and a bounded participant timeout.
+5. Poll `agent_debate_status` and `run_observable_events` when a locator is
+   available while provider work is running. Surface concise progress at least
+   every 30-60 seconds. If this agent is running in a background mode whose
+   progress cannot reach the user, tell the caller to poll and relay progress,
+   or fall back to Host-only QA for the current run. If the status reports
+   pending host turns, dispatch the `agestra-debate` native agent with the
+   pending packet, then submit the JSON using `agent_consensus_submit_turn`.
+
+Use `agent_research_consensus_start` for QA only when the user explicitly asks
+for deep external-provider research before consensus. In that exception,
+external AI research and debate run in separate fresh sessions. The default QA
+Brigade should avoid that extra research round because the host already owns the
+executable QA evidence.
+</QA_Brigade_Execution>
+
 <E2E_Test_Authoring>
 Persistent E2E work is an implementation sub-mode, not a standalone agent.
 

package/commands/design.md

@@ -8,7 +8,7 @@ You are executing the `/agestra design` command.
 **Subject:** $ARGUMENTS
 
 Plain review/QA/check requests without `/agestra` or explicit multi-AI/provider wording stay with the current host; they are not Agestra natural-language auto-triggers.
-Agestra natural-language routing requires explicit multi-AI/provider wording such as "multiple AIs", "all AIs", "other AI", "multi-AI", "Codex and Gemini", "provider comparison", or "프로바이더 비교". Explicit `/agestra ...` commands remain supported.
+Agestra natural-language routing requires explicit Agestra/multi-AI/provider wording such as "Agestra", "아제스트라", "multiple AIs", "all AIs", "other AI", "multi-AI", "Codex and Gemini", "provider comparison", or "프로바이더 비교". Explicit `/agestra ...` commands remain supported.
 
 Host interaction fallback: when this workflow says `AskUserQuestion`, use a structured question UI if the current host exposes one. If it is unavailable (for example, in Codex), ask the same question plainly in chat, present the same options, and wait for the user's answer.
 
@@ -21,7 +21,7 @@ Before anything else, call `setup_status`. If it reports `Setup required: yes` o
 
 Agestra uses a single shared `providers.config.json` resolved through `AGESTRA_CONFIG_PATH` or `~/.agestra/providers.config.json` (existing legacy `$CLAUDE_PLUGIN_ROOT/providers.config.json` remains readable). No config -> no sanctioned provider set or locale -> interactive setup is the only correct starting point. Auto-detect without explicit setup can silently include disabled providers. Do not silently choose defaults or write config without the user's provider/language choices.
 
-Before any provider fan-out, run the shared workspace trust preflight for the exact current project root. If supported providers are blocked, ask once whether to register only this project folder, then call `provider_trust_apply_all` after approval.
+Before any provider fan-out, run the shared workspace trust preflight for the exact current project root. If supported providers are blocked, ask once whether to register only this project folder. This is a security approval gate, not a clarifying question; "keep going" / no-questions instructions are not approval. After approval, call `provider_trust_apply` once per blocked provider. Use `provider_trust_apply_all` only when the host permission model explicitly allows batch trust changes. If approval cannot be obtained, skip blocked providers.
 
 ## Step 1: Determine design subject
 
@@ -51,7 +51,7 @@ Need-to-know details:
 - **Progress style:** one complete pass, MVP then completion, or staged checkpoints
 - **Completion criteria:** how the user and AI workers will know the implementation is done
 - **Research notes:** existing patterns in this codebase, prior art / competing implementations, constraints / regulations, current-information needs, or `skip`
-- **Research assignments:** any preferred participant/lens split for host-led investigation, or `skip`
+- **Research assignments:** any preferred participant/lens split for the selected investigation, or `skip`
 
 Nice-to-know details:
 - Visual mood, references, and interaction style
@@ -61,6 +61,19 @@ Nice-to-know details:
 
 Do not start `environment_check`, `provider_list`, team-lead handoff, or provider fan-out until the design subject and need-to-know details have explicit user-provided values, explicit defaults requested by the user, or explicit defer/skip values.
 
+## Step 2: Choose 조사 방식
+
+Before provider fan-out, ask once which investigation topology to use unless the user already specified it:
+
+| Option | Description |
+|--------|-------------|
+| **Host-native first (Recommended)** | The active host's native `agestra-research` agent inspects the codebase and prepares the first design evidence packet; providers challenge and debate it. Record internally as `host-seeded`. |
+| **Council Research** | Host and providers independently investigate design options with assigned lenses before consolidation and debate. |
+| **Provider-seeded Research** | One selected provider creates the first design seed/evidence artifact; host and other providers challenge it. |
+| **Decide automatically** | Use Host-native first for bounded design work, Council for broad architecture exploration, and Provider-seeded only when the user named a provider to lead. |
+
+Use `AskUserQuestion` when available, or a plain numbered prompt as fallback. This is a cost/latency gate, not a design clarification. If a host-level no-questions directive prevents asking, choose Host-native first (`host-seeded`) and report that broader provider investigation was skipped. If Provider-seeded Research is selected and the seed provider is not explicit, record the seed provider as pending; after provider availability is listed, ask which available provider should seed. Do not infer it.
+
 Default design principles:
 - Prefer maintainable structure and code quality over easy/fast patchwork
 - Keep responsibilities separated to avoid spaghetti code
@@ -70,7 +83,7 @@ Default design principles:
 - List included, excluded, and deferred items, then get explicit user approval before implementation begins. Use `AskUserQuestion` when available, or a plain numbered prompt as fallback.
 - Put an Implementation Progress section at the top of the design document, initialized with Planned rows for the included scope and evidence needed for verification
 
-## Step 2: Route execution
+## Step 3: Route execution
 
 Call `environment_check` and `provider_list` to determine which providers and execution options are available.
 
@@ -80,7 +93,7 @@ Respect the providers list verbatim. A provider marked `Not found`, unavailable,
 Stop Agestra orchestration and tell the user to run `/agestra setup` to enable a provider, or ask the current host to do design work directly outside Agestra. Do not spawn a host specialist from this command.
 
 **Provider-backed path — 1+ external providers available (multi-AI):**
-Hand off to the `agestra:agestra-team-lead` agent with multi-AI mode **pre-selected**. Provider-backed design uses the host research consensus flow:
+Hand off to the `agestra:agestra-team-lead` agent with multi-AI mode **pre-selected**. Provider-backed design uses the selected research topology flow:
 
 ```text
 호스트가 조사한다.
@@ -98,17 +111,20 @@ External AI research and debate run in separate fresh sessions, even when the sa
 - **Idea decision record:** path under `docs/ideas/` if the design came from a saved idea
 - **User constraints:** any explicit constraints provided
 - **Consensus domain:** `design`
-- **Research notes:** what the host-led investigation should look for (existing patterns, prior art, constraints, current-information needs)
+- **Research topology / 조사 방식:** selected in Step 2 (`host-seeded`, `council`, `provider-seeded`, or `automatic`)
+- **Host-native route:** for Host-native first (`host-seeded`), run active-host `agestra-research` before external provider fan-out; route any host debate participant to `agestra-debate` with `participant_routes`; do not substitute the current host's external CLI provider for this native role
+- **Research notes:** what the selected investigation should look for (existing patterns, prior art, constraints, current-information needs)
 - **Research assignments:** optional participant/lens rows for `research_assignments`
 - **Available providers:** from `environment_check` / `provider_list`
 - **Requested providers:** explicit names captured from the user's wording (e.g. `[codex, gemini]`); otherwise "all available"
 - **Locale:** from `setup_status`
 - **Target workspace root:** absolute project folder if the user supplied or implied one; pass it to workspace/debate MCP calls as `workspace_base_dir`
+- **Progress contract:** surface concise phase updates every 30-60 seconds; poll `agent_debate_status`, `run_observable_events` with a cursor, or `cli_worker_status` when available; if trace is `cold-start`, report the current local phase and keep monitoring
 - **Original user request:** preserve verbatim
 
 Team-lead owns the rest:
 - Building the participant team from focused research lenses, explicit host-turn debate participants, and external providers when applicable
-- Calling `agent_research_consensus_start` with `domain: "design"`, the design `objective`, `participants`, optional `research_assignments`, optional `provider_order`, bounded `max_rounds`, and output document flags.
+- Resolving the selected research topology, then calling `agent_research_consensus_start` when investigation fan-out is required or `agent_consensus_start` with prepared `initial_aggregation.items` when seed/host evidence is already available.
 - Ensuring external AI research and debate use separate fresh sessions.
 - Never creating a bundled research pseudo-participant and never carrying research bundles through `source_documents`.
 - Inspecting `aggregation_record.json`, `open_debate_items.json`, `round_packet.{round}.{provider}.json`, the aggregation document, and the leader-authored final decision document under `docs/agestra/`.
@@ -121,7 +137,7 @@ Team-lead owns the rest:
 
 Direct execution from this command bypasses team-lead's capability-based routing and optional trace-assisted signals (`trace_summary`), task design, and consistency enforcement. Always go through team-lead in the provider-backed path.
 
-## Step 3: Present the result
+## Step 4: Present the result
 
 When team-lead returns:
 - Name the source idea decision document path under `docs/ideas/` when one was used

package/commands/idea.md

@@ -8,7 +8,7 @@ You are executing the `/agestra idea` command.
 **Topic:** $ARGUMENTS
 
 Plain review/QA/check requests without `/agestra` or explicit multi-AI/provider wording stay with the current host; they are not Agestra natural-language auto-triggers.
-Agestra natural-language routing requires explicit multi-AI/provider wording such as "multiple AIs", "all AIs", "other AI", "multi-AI", "Codex and Gemini", "provider comparison", or "프로바이더 비교". Explicit `/agestra ...` commands remain supported.
+Agestra natural-language routing requires explicit Agestra/multi-AI/provider wording such as "Agestra", "아제스트라", "multiple AIs", "all AIs", "other AI", "multi-AI", "Codex and Gemini", "provider comparison", or "프로바이더 비교". Explicit `/agestra ...` commands remain supported.
 
 Host interaction fallback: when this workflow says `AskUserQuestion`, use a structured question UI if the current host exposes one. If it is unavailable (for example, in Codex), ask the same question plainly in chat, present the same options, and wait for the user's answer.
 
@@ -21,7 +21,7 @@ Before anything else, call `setup_status`. If it reports `Setup required: yes` o
 
 Rationale: Agestra's path resolver uses a single shared `providers.config.json` resolved through `AGESTRA_CONFIG_PATH` or `~/.agestra/providers.config.json` (existing legacy `$CLAUDE_PLUGIN_ROOT/providers.config.json` remains readable). Without it, auto-detect silently enables whatever is installed and there is no configured locale, which has caused disabled providers to participate in past runs. Setup is the only sanctioned way to pick the active set. Do not silently choose defaults or write config without the user's provider/language choices.
 
-Before any provider fan-out, run the shared workspace trust preflight for the exact current project root. If supported providers are blocked, ask once whether to register only this project folder, then call `provider_trust_apply_all` after approval.
+Before any provider fan-out, run the shared workspace trust preflight for the exact current project root. If supported providers are blocked, ask once whether to register only this project folder. This is a security approval gate, not a clarifying question; "keep going" / no-questions instructions are not approval. After approval, call `provider_trust_apply` once per blocked provider. Use `provider_trust_apply_all` only when the host permission model explicitly allows batch trust changes. If approval cannot be obtained, skip blocked providers.
 
 ## Step 1: Determine topic
 
@@ -40,7 +40,7 @@ For **Existing project**, collect:
 - **Idea areas:** design, usability, onboarding, new features, automation, performance, accessibility, docs, DX, integrations, monetization, community, or other
 - **User wishes:** user requests, complaints, positive reactions, or "people seem to want..." signals, or `none`
 - **Research notes:** competitor landscape, positive/negative user reactions, current-information needs, source constraints, or `skip`
-- **Research assignments:** any preferred participant/lens split for host-led investigation, or `skip`
+- **Research assignments:** any preferred participant/lens split for the selected investigation, or `skip`
 - **Protected identity/boundaries:** what should not change, or `unspecified`
 - **Free notes:** anything else the user wants to say, or `skip`
 
@@ -52,14 +52,27 @@ For **New project idea**, collect:
 - **References:** apps, games, sites, or tools to borrow from or react against, or `none`
 - **Difference:** how this should feel different from existing apps, or `unspecified`
 - **Research notes:** similar apps, competitor/user-reaction depth, current-information needs, source constraints, or `skip`
-- **Research assignments:** any preferred participant/lens split for host-led investigation, or `skip`
+- **Research assignments:** any preferred participant/lens split for the selected investigation, or `skip`
 - **Free notes:** rough thoughts are welcome, or `skip`
 
 Do not start `environment_check`, `provider_list`, team-lead handoff, or any provider fan-out until all required fields for the selected idea mode have explicit user-provided values or explicit skip values.
 
 Idea exploration should stay broad and creative. Do not filter primarily by implementation difficulty; feasibility, MVP scope, and build strategy belong in the later `/agestra design` step after the user chooses an idea.
 
-Provider-backed `/agestra idea` uses the host research consensus flow:
+## Step 2: Choose 조사 방식
+
+Before provider fan-out, ask once which investigation topology to use unless the user already specified it:
+
+| Option | Description |
+|--------|-------------|
+| **Host-native first (Recommended)** | The active host's native `agestra-research` agent prepares the first evidence packet, then providers challenge and debate it. Fastest and lowest-cost default. Record internally as `host-seeded`. |
+| **Council Research** | Host and providers independently investigate assigned lenses before consolidation and debate. Stronger for broad/open-ended exploration. |
+| **Provider-seeded Research** | One selected provider creates the first seed/evidence artifact, then host and other providers challenge it. |
+| **Decide automatically** | Use Host-native first for bounded topics, Council for broad idea discovery, and Provider-seeded only when the user named a provider to lead. |
+
+Use `AskUserQuestion` when available, or a plain numbered prompt as fallback. This is a cost/latency gate, not a domain clarification. If a host-level no-questions directive prevents asking, choose Host-native first (`host-seeded`) and report that broader provider investigation was skipped. If Provider-seeded Research is selected and the seed provider is not explicit, record the seed provider as pending; after provider availability is listed, ask which available provider should seed. Do not infer it.
+
+Provider-backed `/agestra idea` uses the selected research topology flow:
 
 ```text
 호스트가 조사한다.
@@ -70,7 +83,7 @@ Provider-backed `/agestra idea` uses the host research consensus flow:
 
 External AI research and debate run in separate fresh sessions, even when the same provider participates in both phases. If the user explicitly wants to bypass research, route the work to the active host outside Agestra instead.
 
-## Step 2: Route execution
+## Step 3: Route execution
 
 Call `environment_check` and `provider_list` to determine available providers.
 
@@ -88,17 +101,21 @@ Hand off to the `agestra:agestra-team-lead` agent with multi-AI mode **pre-selec
 - **Topic:** `$ARGUMENTS` or the user's clarified topic
 - **Interview answers:** the details collected above, including research notes, research assignments, and free notes
 - **Consensus domain:** `idea`
-- **Research notes:** what the host-led investigation should look for
+- **Research topology / 조사 방식:** selected in Step 2 (`host-seeded`, `council`, `provider-seeded`, or `automatic`)
+- **Host-native route:** for Host-native first (`host-seeded`), run active-host `agestra-research` before external provider fan-out; route any host debate participant to `agestra-debate` with `participant_routes`; do not substitute the current host's external CLI provider for this native role
+- **Research notes:** what the selected investigation should look for
 - **Research assignments:** optional participant/lens rows for `research_assignments`
 - **Available providers:** from `environment_check`
 - **Requested providers:** explicit names captured from user wording; otherwise "all available"
 - **Locale:** from `setup_status`
 - **Target workspace root:** absolute project folder if the user supplied or implied one; pass it to workspace/debate MCP calls as `workspace_base_dir`
+- **Progress contract:** surface concise phase updates every 30-60 seconds; poll `agent_debate_status`, `run_observable_events` with a cursor, or `cli_worker_status` when available; if trace is `cold-start`, report the current local phase and keep monitoring
 - **Original user request:** preserve verbatim
 
 Team-lead owns the rest:
 - Building the participant team from idea research lenses, explicit host-turn debate participants, and external providers. External providers are MCP/CLI/chat participants only.
-- Calling `agent_research_consensus_start` with `domain: "idea"`, the idea `objective`, `participants`, optional `research_assignments`, optional `provider_order`, bounded `max_rounds`, and output document flags.
+- Resolving the selected research topology, then calling `agent_research_consensus_start` when investigation fan-out is required or `agent_consensus_start` with prepared `initial_aggregation.items` when seed/host evidence is already available.
+- For research fan-out, pass `domain: "idea"` to `agent_research_consensus_start`.
 - Ensuring external AI research and debate use separate fresh sessions.
 - Never creating a bundled research pseudo-participant and never carrying research bundles through `source_documents`.
 - Writing the project-facing idea decision record under `docs/agestra/YYYY-MM-DD-idea-<session-id>-result.md` from the aggregation document, JSON artifacts, consensus state, and the user's interview answers. Preserve disputed positions and weak-evidence flags rather than averaging them away.
@@ -114,7 +131,7 @@ Writing the final project-facing idea decision record under `docs/agestra/` is a
 
 Direct execution bypasses team-lead's capability-based routing, optional trace-assisted signals, and consistency enforcement. Always go through team-lead in the provider-backed path.
 
-## Step 3: Present to the user
+## Step 4: Present to the user
 
 When team-lead returns:
 - Name the debate document, consensus JSON ledger, and final synthesis document when the structured session is finalized

package/commands/implement.md

@@ -8,7 +8,7 @@ You are executing the `/agestra implement` command.
 **Task:** $ARGUMENTS
 
 Plain review/QA/check requests without `/agestra` or explicit multi-AI/provider wording stay with the current host; they are not Agestra natural-language auto-triggers.
-Agestra natural-language routing requires explicit multi-AI/provider wording such as "multiple AIs", "all AIs", "other AI", "multi-AI", "Codex and Gemini", "provider comparison", or "프로바이더 비교". Explicit `/agestra ...` commands remain supported.
+Agestra natural-language routing requires explicit Agestra/multi-AI/provider wording such as "Agestra", "아제스트라", "multiple AIs", "all AIs", "other AI", "multi-AI", "Codex and Gemini", "provider comparison", or "프로바이더 비교". Explicit `/agestra ...` commands remain supported.
 
 Host interaction fallback: when this workflow says `AskUserQuestion`, use a structured question UI if the current host exposes one. If it is unavailable (for example, in Codex), ask the same question plainly in chat, present the same options, and wait for the user's answer.
 
@@ -21,7 +21,7 @@ Before anything else, call `setup_status`. If it reports `Setup required: yes` o
 
 Agestra uses a single shared `providers.config.json` resolved through `AGESTRA_CONFIG_PATH` or `~/.agestra/providers.config.json` (existing legacy `$CLAUDE_PLUGIN_ROOT/providers.config.json` remains readable). No config -> no sanctioned provider set or locale -> interactive setup is the only correct starting point. Do not silently choose defaults or write config without the user's provider/language choices.
 
-Before any provider fan-out or `cli_worker_spawn`, run the shared workspace trust preflight for the exact current project root. If supported providers are blocked, ask once whether to register only this project folder, then call `provider_trust_apply_all` after approval.
+Before any provider fan-out or `cli_worker_spawn`, run the shared workspace trust preflight for the exact current project root. If supported providers are blocked, ask once whether to register only this project folder. This is a security approval gate, not a clarifying question; "keep going" / no-questions instructions are not approval. After approval, call `provider_trust_apply` once per blocked provider. Use `provider_trust_apply_all` only when the host permission model explicitly allows batch trust changes. If approval cannot be obtained, skip blocked providers.
 
 ## Step 1: Determine implementation target
 
@@ -79,11 +79,11 @@ Determine QA depth for the post-implementation verification:
 Use `AskUserQuestion` when available, or a plain numbered prompt as fallback for long/costly Full QA or persistent E2E test-file approval. Treat Standard QA as the default only when the user has not requested Full QA/E2E and no high-risk runtime flow requires explicit confirmation.
 
 Determine QA routing separately from implementation routing:
-- When configured external providers are available, team-lead routes post-implementation QA through the QA Brigade.
+- When configured external providers are available, team-lead may route post-implementation QA through the QA Brigade, but it should still avoid an extra external research phase unless the user explicitly asked for deep provider research.
 - If executable checks are required, the host owns command/browser/runtime evidence collection and providers review that evidence.
 - E2E/runtime execution is always host-owned. External providers may review the host QA report, command output, screenshots, traces, and E2E findings, but they must not run browser/dev-server flows or create persistent E2E files directly.
 - QA-only mode does not modify product code; connection or boundary defects are findings until the user approves a separate implementation task.
-- Provider-backed QA uses the host research consensus flow through `agent_research_consensus_start` with `domain: "qa"`:
+- Provider-backed QA uses the fast host-prepared consensus path by default:
 
 ```text
 호스트가 조사한다.
@@ -92,7 +92,7 @@ Determine QA routing separately from implementation routing:
 호스트가 문서화한다.
 ```
 
-External AI research and debate run in separate fresh sessions, even when the same provider participates in both phases.
+The host prepares executable QA evidence first, then providers cross-check prepared `initial_aggregation.items` through `agent_consensus_start`. Use `agent_research_consensus_start` for QA only when the user explicitly asks for deep external-provider research; in that exception, External AI research and debate run in separate fresh sessions, even when the same provider participates in both phases.
 
 ## Step 5: Execute via team-lead
 
@@ -113,9 +113,11 @@ Handoff packet:
 - **E2E/runtime execution:** host-owned only
 - **Available providers:** from `environment_check` / `provider_list`
 - **Requested providers:** explicit names captured from user wording; otherwise "all available"
+- **Host-native route:** use `agestra-implementer`, `agestra-research`, and host-turn `agestra-debate` through the active host's native agent surface when they represent the host role; do not substitute the current host's external CLI provider for those native roles
 - **Locale:** from `setup_status`
 - **Target workspace root:** absolute project folder if the user supplied or implied one; pass it to workspace/debate MCP calls as `workspace_base_dir`
 - **Risk/Complexity classification:** from Step 3 dimensions
+- **Progress contract:** surface concise phase updates every 30-60 seconds; poll `agent_debate_status`, `run_observable_events` with a cursor, or `cli_worker_status` when available; if trace is `cold-start`, report the current local phase and keep monitoring
 - **Original user request:** preserve verbatim
 
 Team-lead owns the rest:
@@ -145,5 +147,5 @@ When team-lead returns, surface:
 - QA verdict (PASS / CONDITIONAL PASS / FAIL with classified failures if any)
 - QA Brigade participants, assigned lenses, accepted ledger items, excluded ledger items, open/opinion items, consensus, and notable dissenting findings when multi-AI QA ran
 - Review report path under `docs/reports/review/` and review verdict (APPROVE / APPROVE WITH CONCERNS / BLOCKING CONCERNS) when review ran
-- Synthesis paths under `.agestra/workspace/synthesis/` if consensus ran
+- Consensus ledger/progress paths under `.agestra/workspace/` if consensus ran, plus any human-facing `docs/agestra/*-aggregation.md` / `*-result.md` paths
 - Communicate in the user's language