feat: add adaptive native waits

CONTRIBUTING.md

@@ -59,6 +59,11 @@ personal paths.
 The required thread cap is features.multi_agent_v2.max_concurrent_threads_per_session;
 the optional root agents table may contain only default subagent model and
 reasoning-effort values.
+The V2 table also accepts optional `min_wait_timeout_ms`, `default_wait_timeout_ms`
+and `max_wait_timeout_ms`. Values must be integers from 0 through 3600000; after
+applying native defaults, minimum <= default <= maximum must hold. See
+[configuration](docs/configuration.md#native-child-wait-settings). Explain any
+different choice without claiming unmeasured token savings.
 An optional hook is a contained relative directory with a README.md documenting
 installation, supported runtime and entrypoint; its implementation may use any
 supported language and does not require a guard.py file.

README.md

@@ -11,7 +11,7 @@ third-party orchestration service to use these files.
 [Skills](skills/README.md) · [Plugins](plugins/README.md) ·
 [Validation and compatibility](docs/validation.md)
 
-Version 0.2.1 is a community preview. Historical hook and selected-role tests are
+Version 0.3.0 is a community preview. Historical hook and selected-role tests are
 recorded; the revised allocations and caps are not fully runtime-certified.
 
 ## Choose an arrangement
@@ -26,6 +26,11 @@ The three arrangements provide progressively smaller role catalogs and enable
 Multi-Agent V2. Roles are available choices, not agents started together. Allocate only useful,
 independent work; parallel calls consume additional model tokens.
 
+All three use a one-minute minimum and five-minute default for native child
+waits. [Adaptive waiting](docs/orchestration.md#adaptive-waiting) explains how to
+choose task-appropriate windows and reduce empty polling without changing budgets.
+This is not a measured quota-savings guarantee.
+
 Advanced Delivery targets complex product work and spends more of its model
 allocation on design, advice, critical review and coupled implementation.
 Balanced Delivery reserves Astra for advice and coupled implementation, and Sol

arrangements/advanced-delivery/AGENTS.snippet.md

@@ -2,7 +2,7 @@
 
 ### Role selection
 
-- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
+- Before delegating, coordinating ongoing work, or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
 - Read the relevant live role descriptions and instructions; choose the least resource-intensive role suited to the task and required artifact. Read-only roles never receive implementation work. `list_agents` shows running children, not available roles.
 
 ### Dispatch contract
@@ -13,6 +13,7 @@
 
 ### Ownership and return
 
+- When only delegated work remains, use task-appropriate native waits; avoid repeated status polling.
 - Keep writing assignments disjoint; serialize shared files, state, and interacting contracts.
 - Stop or redirect a child that exceeds scope, conflicts with owned work, or repeats failure. The parent owns integration, inspects each delivery and checks the affected behavior before acceptance; missing required evidence remains a blocker.
 - Use `followup_task` to resume a suitable completed child; `send_message` only queues a message. A recommended role need not already be running.

arrangements/advanced-delivery/AGENTS.with-skill.snippet.md

@@ -2,7 +2,7 @@
 
 ### Role selection
 
-- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
+- Before delegating, coordinating ongoing work, or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
 - Read the relevant live role descriptions and instructions; choose the least resource-intensive role suited to the task and required artifact. Read-only roles never receive implementation work. `list_agents` shows running children, not available roles.
 
 ### Dispatch contract
@@ -13,6 +13,7 @@
 
 ### Ownership and return
 
+- When only delegated work remains, use task-appropriate native waits; avoid repeated status polling.
 - Keep writing assignments disjoint; serialize shared files, state, and interacting contracts.
 - Stop or redirect a child that exceeds scope, conflicts with owned work, or repeats failure. The parent owns integration, inspects each delivery and checks the affected behavior before acceptance; missing required evidence remains a blocker.
 - Use `followup_task` to resume a suitable completed child; `send_message` only queues a message. A recommended role need not already be running.

arrangements/advanced-delivery/README.md

@@ -44,4 +44,10 @@ This is an adapted public roster, not a full personal-profile export. Retained r
 
 ## Validation status
 
+Revision 0.3.0 adds a one-minute minimum and five-minute default for native child
+waits, without changing this roster or cap. Choose explicit waits according to
+the task; see [adaptive waiting](../../docs/orchestration.md#adaptive-waiting)
+and [upgrade instructions](../../docs/installation.md#upgrading-from-02x).
+Configuration checks are not measurements of quota savings or waiting behavior.
+
 Revision 0.2.0 changes allocations and caps. Historical native tests from 0.1.0 do not certify this revision. Full live role coverage, concurrency saturation, and slot release remain unverified; see [the validation record](../../docs/validation.md). Installation still requires account/model availability and compatible runtime checks.

arrangements/advanced-delivery/arrangement.toml

@@ -1,6 +1,6 @@
 schema_version = 1
 id = "advanced-delivery"
-version = "0.2.1"
+version = "0.3.0"
 author = "Rafael Bittencourt"
 description = "Advanced Delivery: Complex product delivery with dedicated reasoning for decisions, diagnosis, ordinary review, critical review, and coupled implementation."
 license = "MIT"

arrangements/advanced-delivery/config.toml

@@ -7,4 +7,6 @@ multi_agent = true
 [features.multi_agent_v2]
 enabled = true
 tool_namespace = "agents"
+min_wait_timeout_ms = 60000
+default_wait_timeout_ms = 300000
 max_concurrent_threads_per_session = 5

arrangements/balanced-delivery/AGENTS.snippet.md

@@ -2,7 +2,7 @@
 
 ### Role selection
 
-- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
+- Before delegating, coordinating ongoing work, or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
 - Read the relevant live role descriptions and instructions; choose the least resource-intensive role suited to the task and required artifact. Read-only roles never receive implementation work. `list_agents` shows running children, not available roles.
 
 ### Dispatch contract
@@ -13,6 +13,7 @@
 
 ### Ownership and return
 
+- When only delegated work remains, use task-appropriate native waits; avoid repeated status polling.
 - Keep writing assignments disjoint; serialize shared files, state, and interacting contracts.
 - Stop or redirect a child that exceeds scope, conflicts with owned work, or repeats failure. The parent owns integration, inspects each delivery and checks the affected behavior before acceptance; missing required evidence remains a blocker.
 - Use `followup_task` to resume a suitable completed child; `send_message` only queues a message. A recommended role need not already be running.

arrangements/balanced-delivery/AGENTS.with-skill.snippet.md

@@ -2,7 +2,7 @@
 
 ### Role selection
 
-- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
+- Before delegating, coordinating ongoing work, or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
 - Read the relevant live role descriptions and instructions; choose the least resource-intensive role suited to the task and required artifact. Read-only roles never receive implementation work. `list_agents` shows running children, not available roles.
 
 ### Dispatch contract
@@ -13,6 +13,7 @@
 
 ### Ownership and return
 
+- When only delegated work remains, use task-appropriate native waits; avoid repeated status polling.
 - Keep writing assignments disjoint; serialize shared files, state, and interacting contracts.
 - Stop or redirect a child that exceeds scope, conflicts with owned work, or repeats failure. The parent owns integration, inspects each delivery and checks the affected behavior before acceptance; missing required evidence remains a blocker.
 - Use `followup_task` to resume a suitable completed child; `send_message` only queues a message. A recommended role need not already be running.

arrangements/balanced-delivery/README.md

@@ -41,4 +41,10 @@ This is an adapted public roster, not a full personal-profile export. Retained r
 
 ## Validation status
 
+Revision 0.3.0 adds a one-minute minimum and five-minute default for native child
+waits, without changing this roster or cap. Choose explicit waits according to
+the task; see [adaptive waiting](../../docs/orchestration.md#adaptive-waiting)
+and [upgrade instructions](../../docs/installation.md#upgrading-from-02x).
+Configuration checks are not measurements of quota savings or waiting behavior.
+
 Revision 0.2.0 changes allocations and caps. Historical native tests from 0.1.0 do not certify this revision. Full live role coverage, concurrency saturation, and slot release remain unverified; see [the validation record](../../docs/validation.md). Installation still requires account/model availability and compatible runtime checks.

arrangements/balanced-delivery/arrangement.toml

@@ -1,6 +1,6 @@
 schema_version = 1
 id = "balanced-delivery"
-version = "0.2.1"
+version = "0.3.0"
 author = "Rafael Bittencourt"
 description = "Balanced Delivery: Everyday product delivery with Luna implementing established patterns, Sol handling backend work and integration review, and Astra handling decisions and coupled implementation."
 license = "MIT"

arrangements/balanced-delivery/config.toml

@@ -7,4 +7,6 @@ multi_agent = true
 [features.multi_agent_v2]
 enabled = true
 tool_namespace = "agents"
+min_wait_timeout_ms = 60000
+default_wait_timeout_ms = 300000
 max_concurrent_threads_per_session = 4

arrangements/lean-delivery/AGENTS.snippet.md

@@ -2,7 +2,7 @@
 
 ### Role selection
 
-- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
+- Before delegating, coordinating ongoing work, or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
 - Read the relevant live role descriptions and instructions; choose the least resource-intensive role suited to the task and required artifact. Read-only roles never receive implementation work. `list_agents` shows running children, not available roles.
 
 ### Dispatch contract
@@ -13,6 +13,7 @@
 
 ### Ownership and return
 
+- When only delegated work remains, use task-appropriate native waits; avoid repeated status polling.
 - Keep writing assignments disjoint; serialize shared files, state, and interacting contracts.
 - Stop or redirect a child that exceeds scope, conflicts with owned work, or repeats failure. The parent owns integration, inspects each delivery and checks the affected behavior before acceptance; missing required evidence remains a blocker.
 - Use `followup_task` to resume a suitable completed child; `send_message` only queues a message. A recommended role need not already be running.

arrangements/lean-delivery/AGENTS.with-skill.snippet.md

@@ -2,7 +2,7 @@
 
 ### Role selection
 
-- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
+- Before delegating, coordinating ongoing work, or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
 - Read the relevant live role descriptions and instructions; choose the least resource-intensive role suited to the task and required artifact. Read-only roles never receive implementation work. `list_agents` shows running children, not available roles.
 
 ### Dispatch contract
@@ -13,6 +13,7 @@
 
 ### Ownership and return
 
+- When only delegated work remains, use task-appropriate native waits; avoid repeated status polling.
 - Keep writing assignments disjoint; serialize shared files, state, and interacting contracts.
 - Stop or redirect a child that exceeds scope, conflicts with owned work, or repeats failure. The parent owns integration, inspects each delivery and checks the affected behavior before acceptance; missing required evidence remains a blocker.
 - Use `followup_task` to resume a suitable completed child; `send_message` only queues a message. A recommended role need not already be running.

arrangements/lean-delivery/README.md

@@ -37,4 +37,10 @@ This is an adapted public roster, not a full personal-profile export. Retained r
 
 ## Validation status
 
+Revision 0.3.0 adds a one-minute minimum and five-minute default for native child
+waits, without changing this roster or cap. Choose explicit waits according to
+the task; see [adaptive waiting](../../docs/orchestration.md#adaptive-waiting)
+and [upgrade instructions](../../docs/installation.md#upgrading-from-02x).
+Configuration checks are not measurements of quota savings or waiting behavior.
+
 Revision 0.2.0 changes allocations and caps. Historical native tests from 0.1.0 do not certify this revision. Full live role coverage, concurrency saturation, and slot release remain unverified; see [the validation record](../../docs/validation.md). Installation still requires account/model availability and compatible runtime checks.

arrangements/lean-delivery/arrangement.toml

@@ -1,6 +1,6 @@
 schema_version = 1
 id = "lean-delivery"
-version = "0.2.1"
+version = "0.3.0"
 author = "Rafael Bittencourt"
 description = "Lean Delivery: Cost-conscious, well-bounded delivery with Luna implementing and reviewing, Sol reconciling deliveries, and one Astra advisor for decisions."
 license = "MIT"

arrangements/lean-delivery/config.toml

@@ -7,4 +7,6 @@ multi_agent = true
 [features.multi_agent_v2]
 enabled = true
 tool_namespace = "agents"
+min_wait_timeout_ms = 60000
+default_wait_timeout_ms = 300000
 max_concurrent_threads_per_session = 3

docs/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.3.0 — 2026-09-13
+
+- Set native child waits to a one-minute minimum and five-minute default in all
+  three arrangements, preserving budgets, goals, models, caps and hooks.
+- Extend the existing optional orchestration skill with task-appropriate waits,
+  meaningful progress signals and a separate point for investigating a stall.
+  Keep the installable rules concise.
+- Explain context flow, automatic goal continuation, timing tradeoffs, upgrade
+  and rollback; distinguish configuration evidence from unmeasured quota savings.
+- Validate optional wait fields, including types, bounds and effective ordering.
+
 ## 0.2.1 — 2026-09-13
 
 - Keep insertable delegation rules concise: remove roster counts, concurrency