From de21ea0b80f01780579015193497f2e60fdce3c5 Mon Sep 17 00:00:00 2001 From: John Osumi <931193+sumitake@users.noreply.github.com> Date: Mon, 17 Aug 2026 21:27:40 -0700 Subject: [PATCH] intent-check: request standard effort/profile instead of frontier/maximum The Step-0 intent check is a bounded two-document interpretation comparison, not architecture-grade deliberation, yet it hardcoded quality_profile:frontier + effort_class:maximum in its coordinator request -- making it the single most expensive high-frequency managed call in the system with no quality justification. For the context.documents.intent route the quality_profile knob is functionally inert (identical candidate lists across economical/standard/ frontier), so this is a pure cost reduction with no routing change. Matches the existing teamwork/orchestrate standard/standard default pattern. Edited at source (skill-specs/intent-check.md + skill-build-config.json's intent_check_defaults_block) and regenerated SKILL.md via build_skills.py. No version bump -- the in-flight v6.0.6 release owns versioning (operator direction); this fragment compiles into that release. Companion: sumitake/agent-collab-workspace#2770 downgrades the route-level effort_class floor. Workspace merges FIRST -- a request below the floor is rejected effort_ineligible, so merging this first would break intent-check. --- changelog.d/2026-08-18-intent-check-effort-standard.md | 4 ++++ plugins/agent-collab/skills/intent-check/SKILL.md | 6 +++--- scripts/skill-build-config.json | 2 +- skill-specs/intent-check.md | 2 +- tests/test_unified_skill_runtime_contract.py | 4 ++-- 5 files changed, 11 insertions(+), 7 deletions(-) create mode 100644 changelog.d/2026-08-18-intent-check-effort-standard.md diff --git a/changelog.d/2026-08-18-intent-check-effort-standard.md b/changelog.d/2026-08-18-intent-check-effort-standard.md new file mode 100644 index 0000000..7e86e5e --- /dev/null +++ b/changelog.d/2026-08-18-intent-check-effort-standard.md @@ -0,0 +1,4 @@ +### agent-collab — 2026-08-18 + +#### Changed +- `intent-check` skill now requests `quality_profile: standard` / `effort_class: standard` (was `frontier` / `maximum`). The Step-0 intent check is a bounded two-document interpretation comparison, not architecture-grade deliberation; the top-tier pin made it the most expensive high-frequency managed call in the system with no quality justification. For the `context.documents.intent` route the `quality_profile` knob is functionally inert (identical candidate lists across all profiles), so this is a pure cost reduction with no routing change. Matches the existing `teamwork` / `orchestrate` standard/standard default pattern. Companion workspace PR downgrades the route-level `effort_class` floor so the new request is admitted (workspace merges first — a request below the floor is rejected `effort_ineligible`). diff --git a/plugins/agent-collab/skills/intent-check/SKILL.md b/plugins/agent-collab/skills/intent-check/SKILL.md index e0d39b1..498f7fa 100644 --- a/plugins/agent-collab/skills/intent-check/SKILL.md +++ b/plugins/agent-collab/skills/intent-check/SKILL.md @@ -2,8 +2,8 @@ name: intent-check version: 6.0.5 defaults: - quality_profile: frontier - effort_class: maximum + quality_profile: standard + effort_class: standard description: Verify that the active primary's interpretation matches the operator's request before consequential planning or execution. Use when the user says "intent check," "confirm what I asked," "check for scope drift," or "/agent-collab:intent-check." Also offer this proactively when a major request has multiple constraints whose omission would materially change the result. --- @@ -24,7 +24,7 @@ request. The runtime selects an eligible independent route; the caller does not construct an agent/action pair. ```json coordinator-request -{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"frontier","effort_class":"maximum","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":""},{"label":"primary_interpretation","content":""}]} +{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"standard","effort_class":"standard","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":""},{"label":"primary_interpretation","content":""}]} ``` ## Workflow diff --git a/scripts/skill-build-config.json b/scripts/skill-build-config.json index 96ee3b0..71ae65b 100644 --- a/scripts/skill-build-config.json +++ b/scripts/skill-build-config.json @@ -55,7 +55,7 @@ "visual_review_defaults_block": "defaults:\n quality_profile: frontier\n effort_class: maximum\n", "visual_review_call_params": "with no managed image route in this release", "orchestrate_defaults_block": "defaults:\n quality_profile: standard\n effort_class: standard\n", - "intent_check_defaults_block": "defaults:\n quality_profile: frontier\n effort_class: maximum\n", + "intent_check_defaults_block": "defaults:\n quality_profile: standard\n effort_class: standard\n", "teamwork_defaults_block": "defaults:\n quality_profile: standard\n effort_class: standard\n", "consultant_agent": "an eligible managed consultant" } diff --git a/skill-specs/intent-check.md b/skill-specs/intent-check.md index 82de111..6dbe4fd 100644 --- a/skill-specs/intent-check.md +++ b/skill-specs/intent-check.md @@ -17,7 +17,7 @@ request. The runtime selects an eligible independent route; the caller does not construct an agent/action pair. ```json coordinator-request -{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"frontier","effort_class":"maximum","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":""},{"label":"primary_interpretation","content":""}]} +{"request_id":"intent-check-1","logical_action":"context.documents.intent","quality_profile":"standard","effort_class":"standard","target_agent":null,"timeout_ms":120000,"prompt":"Compare the operator request with the primary interpretation. Identify only material omissions, added scope, or ambiguity; do not design or execute the work.","documents":[{"label":"operator_request","content":""},{"label":"primary_interpretation","content":""}]} ``` ## Workflow diff --git a/tests/test_unified_skill_runtime_contract.py b/tests/test_unified_skill_runtime_contract.py index f2ed37d..c97c754 100644 --- a/tests/test_unified_skill_runtime_contract.py +++ b/tests/test_unified_skill_runtime_contract.py @@ -119,8 +119,8 @@ def test_intent_check_uses_the_descriptor_owned_untargeted_action(self) -> None: request = json.loads(matches[0]) self.assertEqual(request["logical_action"], "context.documents.intent") self.assertIsNone(request["target_agent"]) - self.assertEqual(request["quality_profile"], "frontier") - self.assertEqual(request["effort_class"], "maximum") + self.assertEqual(request["quality_profile"], "standard") + self.assertEqual(request["effort_class"], "standard") self.assertEqual( set(request), {