minimax: move to MiniMax-M3.1-Flash-Preview; drop bare minimax/minimax-m2 slugs

- new context minimax-m31-flash/v1 (model pin; no thinking-budget init, Flash ignores it); four composites switch from minimax-m3-max/v1 (kept for rollback) - models + registry for minimax-m31-flash-{max,medium}; removes the dangling model-registry/minimax.yaml (endpoint "minimax" never existed) - tiers, harness-roles, minimax-* task templates and the *-review-loop@1 workflows use the Flash slugs (MiniMax silently maps unknown names to M3, so the provider-id translation lands in agent-runtimes)
2026-10-13 10:55:03 +13:00
parent c8c9e7f7d0
commit d7decc1dec
21 changed files with 121 additions and 32 deletions
--- a/harnesses/composites/best-practices-minimax-repo/v1/harness.yaml
+++ b/harnesses/composites/best-practices-minimax-repo/v1/harness.yaml
@@ -6,6 +6,6 @@ description: "Best practices review agent on MiniMax M3 (max effort) + repo clon
 layers:
  - context: best-practices/v1
  - context: minimax/v1
-  - context: minimax-m3-max/v1
+  - context: minimax-m31-flash/v1
  - context: gitea-ssh/v1
  - context: agent-repo/v1
--- a/harnesses/composites/integration-direct/v1/harness.yaml
+++ b/harnesses/composites/integration-direct/v1/harness.yaml
@@ -9,7 +9,7 @@ layers:
  # personal-subscription OAuth — integration runs are frequent/mechanical
  # and were draining the interactive 5-hour window (2026-09-02).
  - context: minimax/v1
-  - context: minimax-m3-max/v1
+  - context: minimax-m31-flash/v1
  - context: gitea-ssh/v1
  - context: agent-repo/v1
  - context: direct-push/v1
--- a/harnesses/composites/scaffolding-repo/v1/harness.yaml
+++ b/harnesses/composites/scaffolding-repo/v1/harness.yaml
@@ -8,6 +8,6 @@ layers:
  # MiniMax M3 — scaffolding is mechanical (stub files so tests import);
  # moved off the personal Anthropic subscription 2026-09-02.
  - context: minimax/v1
-  - context: minimax-m3-max/v1
+  - context: minimax-m31-flash/v1
  - context: gitea-ssh/v1
  - context: agent-repo/v1
--- a/harnesses/composites/test-writing-repo/v1/harness.yaml
+++ b/harnesses/composites/test-writing-repo/v1/harness.yaml
@@ -9,6 +9,6 @@ layers:
  # 2026-09-02 (the "credential layer swappable" swap this composite was
  # designed for).
  - context: minimax/v1
-  - context: minimax-m3-max/v1
+  - context: minimax-m31-flash/v1
  - context: gitea-ssh/v1
  - context: agent-repo/v1
--- a/harnesses/contexts/minimax-m31-flash/v1/harness.yaml
+++ b/harnesses/contexts/minimax-m31-flash/v1/harness.yaml
@@ -0,0 +1,17 @@
+kind: context
+name: minimax-m31-flash
+version: 1
+description: "Pin MiniMax-M3.1-Flash-Preview (1M context) — layer AFTER minimax/v1 (auth + base URL come from there). Thinking depth is set per dispatch via --effort (models/*.yaml default_flags.reasoning_effort), not here."
+requires: []
+provides: []
+
+# Replaces minimax-m3-max/v1 (kept for rollback). Differences:
+# - Flash always thinks and ignores MAX_THINKING_TOKENS/budget_tokens (effort is
+#   the only depth control, server default max), so there is no init.sh.
+# - No [1m] suffix: Flash is 1M natively (verified 2026-10-13, modelUsage.contextWindow).
+# - CLAUDE_CODE_AUTO_COMPACT_WINDOW stays: an unknown model id otherwise gets
+#   Claude Code's 200K default and compacts early.
+env:
+  ANTHROPIC_MODEL: "MiniMax-M3.1-Flash-Preview"
+  ANTHROPIC_SMALL_FAST_MODEL: "MiniMax-M3.1-Flash-Preview"
+  CLAUDE_CODE_AUTO_COMPACT_WINDOW: "1000000"
--- a/model-registry/harness-roles.yaml
+++ b/model-registry/harness-roles.yaml
@@ -5,5 +5,6 @@ roles:
    claude-sonnet-5: code-sonnet-tdd-repo
    claude-opus-5: code-opus-tdd-repo
    claude-haiku-4-5: code-haiku-tdd-repo
-    minimax: code-minimax-tdd-repo
+    minimax-m31-flash-max: code-minimax-tdd-repo
+    minimax-m31-flash-medium: code-minimax-tdd-repo
    claude-fable-5: code-fable-tdd-repo
--- a/model-registry/minimax-m31-flash-max.yaml
+++ b/model-registry/minimax-m31-flash-max.yaml
@@ -0,0 +1,21 @@
+# agent-runtime-framework — model-registry/ (CRS tag: model-registry)
+# Max-effort Flash; replaces minimax-m3-max in planning/draft-heavy and explicit-model nodes.
+# PLACEHOLDER scores/costs: scores are copied from the M3 entry this replaces and
+# costs are set just below it so cheapest-wins (tiers.yaml) selects Flash over
+# the retained M3 entries. Revisit with observed scores and published pricing.
+name: minimax-m31-flash-max
+endpoint: minimax-m31-flash-max
+provider: minimax
+family: minimax
+scores:
+  complexity: 10
+  test_pass_rate: 9
+  creativity: 10
+  spec_adherence: 9
+  cost_efficiency: 5
+  context_utilisation: 10
+cost_per_1k_tokens:
+  input: 0.0025
+  output: 0.0125
+source: benchmark
+harness_version: null
--- a/model-registry/minimax-m31-flash-medium.yaml
+++ b/model-registry/minimax-m31-flash-medium.yaml
@@ -0,0 +1,21 @@
+# agent-runtime-framework — model-registry/ (CRS tag: model-registry)
+# Medium-effort Flash; replaces minimax-m3 in the build/integrate/spec-test/coding tiers.
+# PLACEHOLDER scores/costs: scores are copied from the M3 entry this replaces and
+# costs are set just below it so cheapest-wins (tiers.yaml) selects Flash over
+# the retained M3 entries. Revisit with observed scores and published pricing.
+name: minimax-m31-flash-medium
+endpoint: minimax-m31-flash-medium
+provider: minimax
+family: minimax
+scores:
+  complexity: 8
+  test_pass_rate: 9
+  creativity: 8
+  spec_adherence: 9
+  cost_efficiency: 6
+  context_utilisation: 9
+cost_per_1k_tokens:
+  input: 0.00125
+  output: 0.00625
+source: benchmark
+harness_version: null
--- a/model-registry/minimax.yaml
+++ b/model-registry/minimax.yaml
@@ -1,15 +0,0 @@
-name: minimax
-endpoint: minimax
-provider: minimax
-scores:
-  complexity: 10
-  test_pass_rate: 9
-  creativity: 10
-  spec_adherence: 9
-  cost_efficiency: 3
-  context_utilisation: 10
-cost_per_1k_tokens:
-  input: 0.0
-  output: 0.0
-source: benchmark
-harness_version: null
--- a/model-registry/tiers.yaml
+++ b/model-registry/tiers.yaml
@@ -22,7 +22,7 @@ tiers:
      context_utilisation: 9
    qualifies_today:
      - deepseek-v4flash       # benchmark-inflated 9s; hold to allowed_models ceiling
-      - minimax
+      - minimax-m31-flash-max
      - claude-opus-5
    note: >
      WF-SCH-14 allowed_models ceiling remains authoritative until M7 observed-score
@@ -37,7 +37,8 @@ tiers:
      spec_adherence: 9
      test_pass_rate: 9
    qualifies_today:
-      - minimax
+      - minimax-m31-flash-max
+      - minimax-m31-flash-medium
      - claude-sonnet-5
      - claude-opus-5

@@ -51,7 +52,8 @@ tiers:
    qualifies_today:
      - airouter-qwen3
      - airouter-deepseekv4flash
-      - minimax
+      - minimax-m31-flash-max
+      - minimax-m31-flash-medium
      - claude-sonnet-5
      - claude-opus-5
      - claude-fable-5
--- a/models/minimax-m31-flash-max.yaml
+++ b/models/minimax-m31-flash-max.yaml
@@ -0,0 +1,21 @@
+# agent-runtime-framework — models/ (CRS tag: models)
+# MiniMax-M3.1-Flash-Preview at reasoning_effort max. Always thinks (thinking
+# cannot be disabled; effort is the only depth control). The claude runner maps
+# default_flags.reasoning_effort to `--effort` (agent-runtimes ME-6a). Verified
+# 2026-10-13: the container MiniMax key reaches this model on both
+# api.minimax.io and api.minimaxi.chat; 1M context window.
+# Endpoint name MUST equal the registry name (MR-12).
+name: minimax-m31-flash-max
+provider: minimax
+family: minimax
+endpoint:
+  type: cloud_api
+  base_url: "https://api.minimax.io/anthropic"
+  api_key_env: MINIMAX_API_KEY
+runner: claude
+default_flags:
+  model: "MiniMax-M3.1-Flash-Preview"
+  reasoning_effort: max
+provider_context_ref: "minimax/v1"
+provider_secret_ref: "MINIMAX_API_KEY"
+session_capable: false
--- a/models/minimax-m31-flash-medium.yaml
+++ b/models/minimax-m31-flash-medium.yaml
@@ -0,0 +1,21 @@
+# agent-runtime-framework — models/ (CRS tag: models)
+# MiniMax-M3.1-Flash-Preview at reasoning_effort medium. Always thinks (thinking
+# cannot be disabled; effort is the only depth control). The claude runner maps
+# default_flags.reasoning_effort to `--effort` (agent-runtimes ME-6a). Verified
+# 2026-10-13: the container MiniMax key reaches this model on both
+# api.minimax.io and api.minimaxi.chat; 1M context window.
+# Endpoint name MUST equal the registry name (MR-12).
+name: minimax-m31-flash-medium
+provider: minimax
+family: minimax
+endpoint:
+  type: cloud_api
+  base_url: "https://api.minimax.io/anthropic"
+  api_key_env: MINIMAX_API_KEY
+runner: claude
+default_flags:
+  model: "MiniMax-M3.1-Flash-Preview"
+  reasoning_effort: medium
+provider_context_ref: "minimax/v1"
+provider_secret_ref: "MINIMAX_API_KEY"
+session_capable: false
--- a/task-templates/minimax-code-repo.yaml
+++ b/task-templates/minimax-code-repo.yaml
@@ -1,6 +1,6 @@
 name: minimax-code-repo
 description: "MiniMax code agent — repo clone, agent-repo branch persistence"
-model: minimax
+model: minimax-m31-flash-max
 harness: code-minimax-repo/v1
 requires_tags: [claude-code, coding-agent, git-access, project-repo]
 required_params: [repo_url, agent_repo_url]
--- a/task-templates/minimax-code-tdd.yaml
+++ b/task-templates/minimax-code-tdd.yaml
@@ -1,6 +1,6 @@
 name: minimax-code-tdd
 description: "MiniMax code agent with TDD enforcement — tests are read-only and must pass before the task finishes"
-model: minimax
+model: minimax-m31-flash-max
 harness: code-minimax-tdd-repo/v1
 requires_tags: [coding-agent, git-access, project-repo, tdd-gate]
 required_params: [repo_url, agent_repo_url]
--- a/task-templates/minimax-planning.yaml
+++ b/task-templates/minimax-planning.yaml
@@ -1,6 +1,6 @@
 name: minimax-planning
 description: "MiniMax planning agent — specs, reviews, architecture docs"
-model: minimax
+model: minimax-m31-flash-max
 harness: planning-minimax-repo/v1
 requires_tags: [claude-code, planning-agent, git-access, project-repo]
 required_params: [repo_url, agent_repo_url]
--- a/task-templates/minimax-security-review.yaml
+++ b/task-templates/minimax-security-review.yaml
@@ -1,6 +1,6 @@
 name: minimax-security-review
 description: "MiniMax security review agent — security audit via Anthropic-compatible proxy"
-model: minimax
+model: minimax-m31-flash-max
 harness: security-review-minimax-repo/v1
 requires_tags: [claude-code, security-reviewer, best-practices, git-access, project-repo]
 required_params: [repo_url, agent_repo_url]
--- a/task-templates/minimax-tdd-impl.yaml
+++ b/task-templates/minimax-tdd-impl.yaml
@@ -1,6 +1,6 @@
 name: minimax-tdd-impl
 description: "MiniMax TDD implementation agent — tests locked read-only, cannot be modified by agent"
-model: minimax
+model: minimax-m31-flash-max
 harness: minimax-tdd-impl/v1
 requires_tags: [claude-code, coding-agent, git-access, project-repo]
 required_params: [repo_url, agent_repo_url]
--- a/task-templates/minimax-test-writer.yaml
+++ b/task-templates/minimax-test-writer.yaml
@@ -1,6 +1,6 @@
 name: minimax-test-writer
 description: "MiniMax test writing agent — comprehensive tests with edge cases"
-model: minimax
+model: minimax-m31-flash-max
 harness: test-writing-minimax-repo/v1
 requires_tags: [claude-code, test-writer, best-practices, git-access, project-repo]
 required_params: [repo_url, agent_repo_url]
--- a/task-templates/workflow/plan-review-loop@1.yaml
+++ b/task-templates/workflow/plan-review-loop@1.yaml
@@ -46,7 +46,7 @@ nodes:
  - id: review-minimax
    kind: agent
    role: plan-review
-    model: minimax-m2
+    model: minimax-m31-flash-max
    runtime_env:
      AGENT_REPO_URL: "git@gitea.oreillyit.nz-ai-enablement:skynet/agent-runtimes-agents.git"
      AGENT_BRANCH: "task/${item.uuid}"
--- a/task-templates/workflow/spec-review-loop@1.yaml
+++ b/task-templates/workflow/spec-review-loop@1.yaml
@@ -54,7 +54,7 @@ nodes:
  - id: review-minimax
    kind: agent
    role: spec-review
-    model: minimax-m2
+    model: minimax-m31-flash-max
    runtime_env:
      AGENT_REPO_URL: "git@gitea.oreillyit.nz-ai-enablement:skynet/agent-runtimes-agents.git"
      AGENT_BRANCH: "spec/${item.uuid}"
--- a/task-templates/workflow/test-write-review-loop@1.yaml
+++ b/task-templates/workflow/test-write-review-loop@1.yaml
@@ -21,7 +21,7 @@ nodes:
    role: test-write-review  # M36 v0.6 (bug 69370eda fix): role + model replaces
                             # the ungrounded `template: minimax-test-writer`
                             # (a composite that never existed in the catalog).
-    model: minimax-m2
+    model: minimax-m31-flash-max
    runtime_env:
      # WF-COMP-15: stage agents share one per-item work branch so their work
      # accumulates across iterations.