agent-policy-kit 0.4.0 → 0.5.1

package/docs/reference/model-catalog.md

@@ -1,12 +1,12 @@
 # Model catalog
 
-This document describes `models/catalog.json`, the model catalog of release 0.4.0. It explains the fields, lists the models and effort levels for each AI assistant, and records defaults, lifecycle dates and access requirements. It is for everyone who chooses a model in Custom or wants to know which values a release accepts.
+This document describes `models/catalog.json`, the model catalog of release 0.5.0. It explains the fields, lists the models and effort levels for each AI assistant, and records defaults, lifecycle dates and access requirements. It is for everyone who chooses a model in Custom or wants to know which values a release accepts.
 
 ## What the catalog is
 
 The model catalog is a dated snapshot of the native subagent selectors that each AI assistant accepts. A selector is the value that a native role setting takes: a model ID, an alias or a tier. The catalog ships inside the package. One package version has one catalog, as with presets (see [Presets](presets.md)).
 
-- The snapshot date is `reviewedAt`: 2026-11-01 UTC. The review checked the installed native clients and the current vendor documentation. No vendor released or retired a subagent model between the previous check on 2026-10-30 and this one.
+- The snapshot date is `reviewedAt`: 2026-11-02 UTC. On that date the lifecycle of the Claude 4.5 models was checked again. See [Lifecycle](#lifecycle). The full review of 2026-11-01 checked the installed native clients and the current vendor documentation. No vendor released or retired a subagent model between the previous check on 2026-10-30 and this one.
 - The configurator page and the preferences validation use the same data. For the validation rules, see [Preferences](../guide/preferences.md).
 - APK never fetches a catalog at run time. Normal agent work never reads the catalog.
 - The catalog is not a live inventory and not a list of what one account can use. Account access and custom deployment IDs vary.
@@ -48,7 +48,7 @@ Some entries have optional fields:
 | `delegationModes` | Execution modes such as `ultra`. These are not effort levels. |
 | `nativeSource` | A second source for the native behavior. |
 | `effortResolution` | How an alias or `inherit` resolves effort. |
-| `lifecycle` | Status (`active`, `deprecated` or `retired`), a retirement date or earliest retirement date, the scope and the source. |
+| `lifecycle` | Status (`active`, `deprecated` or `retired`), a retirement date (`retirementDate`) or earliest retirement date (`earliestRetirement`), the scope and the source. Optional: the deprecation date (`deprecationDate`), the recommended replacement ID (`replacement`), a `note`, and `partners`, a list of partner platforms that set their own schedule. Each partner entry has `platform`, `source` and, where announced, the partner's own `status`, `earliestRetirement` or `endOfLife`, or a `note`. |
 | `upstreamModelId`, `thinkingRequired`, `planRequirement` | Kimi: the upstream model, whether thinking must be on, and the plan that the model needs. |
 | `documented` | `false` when the native client accepts a selector that the vendor documentation does not list. |
 
@@ -98,7 +98,7 @@ The inventory has 14 versioned IDs, 4 family aliases and `inherit`. The review c
 | `claude-opus-4-6` | Opus 4.6 | low, medium, high, max | high |
 | `claude-sonnet-4-6` | Sonnet 4.6 | low, medium, high, max | high |
 | `claude-opus-4-5-20251101` | Opus 4.5 | none | not documented |
-| `claude-sonnet-4-5-20250929` | Sonnet 4.5 (deprecated) | none | not documented |
+| `claude-sonnet-4-5-20250929` | Sonnet 4.5 (retires 2026-11-30) | none | not documented |
 | `claude-haiku-4-5-20251001` | Haiku 4.5 | none | not documented |
 | `fable` | Fable (alias) | low, medium, high, xhigh, max | high |
 | `opus` | Opus (alias) | low, medium, high, xhigh, max | not documented |
@@ -148,25 +148,41 @@ The native role field takes a tier, not a model ID. The review checked the Antig
 
 The inventory has 4 model IDs from the documented xAI model list. The review checked Grok Build 1.0.70.
 
-| ID | Label | Native efforts | API efforts |
+The client `efforts` list is `low`, `medium`, `high`, `xhigh` and `max`: the values that Grok Build 1.0.70 accepts in the `effort` field of an agent file. A custom model ID can request these levels. Grok Build drops an agent with any other value.
+
+| ID | Label | Native efforts | Native default |
 |---|---|---|---|
-| `grok-4.7` | Grok 4.7 | none | low, medium, high (default), xhigh |
-| `grok-4.6` | Grok 4.6 | none | not recorded |
-| `grok-4.5` | Grok 4.5 | none | not recorded |
-| `grok-build-0.1` | Grok Build 0.1 | none | not recorded |
+| `grok-4.7` | Grok 4.7 | low, medium, high, xhigh | high |
+| `grok-4.6` | Grok 4.6 | not verified, none offered | not documented |
+| `grok-4.5` | Grok 4.5 | not verified, none offered | not documented |
+| `grok-build-0.1` | Grok Build 0.1 | none | none |
 
-The Grok 4.7 levels are API capabilities. APK writes only a model for each Grok role, so the catalog has no native efforts for Grok. For how Grok Build resolves subagent effort, see [Roles](roles.md#how-effort-applies).
+- The Grok 4.7 levels and default come from the Grok Build model list (`supports_reasoning_effort`, `reasoning_efforts`) of 1.0.70. They are the same as the API levels in `apiEfforts`. `max` is not listed for Grok 4.7, so APK does not write it for that model.
+- Grok Build 0.1 has no effort setting. Grok Build ignores an effort for a model without effort support.
+- The levels of Grok 4.6 and 4.5 were not verified, so the catalog offers no effort for them.
+- For where APK writes the effort and how Grok Build applies it, see [Roles](roles.md#how-effort-applies).
 
 ## Lifecycle
 
 | Model | Status | Date | Scope |
 |---|---|---|---|
 | GPT-5.5 | retired | 2026-10-14 | Codex with ChatGPT sign-in. API-key sign-in keeps access. |
-| Sonnet 4.5 | deprecated | retirement 2026-11-30 | Anthropic-operated platforms. Partner schedules differ. |
-| Opus 4.5 | active | earliest retirement 2026-11-24 | Anthropic model lifecycle |
-| Haiku 4.5 | active | earliest retirement 2026-10-15 | Anthropic model lifecycle |
+| Sonnet 4.5 | deprecated since 2026-09-30 | retirement 2026-11-30 | Claude API, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed) and Microsoft Foundry. Replacement: `claude-sonnet-5-5`. |
+| Opus 4.5 | active (legacy) | earliest retirement 2026-11-24 | Anthropic-operated platforms and Microsoft Foundry. No deprecation notice. |
+| Haiku 4.5 | active (legacy) | earliest retirement 2026-10-15 | Anthropic-operated platforms and Microsoft Foundry. No deprecation notice. |
+
+Partner platforms set their own schedules:
+
+| Model | Amazon Bedrock | Google Cloud (Google managed) |
+|---|---|---|
+| Sonnet 4.5 | Legacy. End of life 2027-04-08. | No retirement date announced. The earliest retirement date, 2026-09-29, passed. |
+| Opus 4.5 | Not on the legacy list | Earliest retirement 2026-11-24 |
+| Haiku 4.5 | Not on the legacy list | Earliest retirement 2026-12-07 |
 
-The earliest retirement date of Haiku 4.5, 2026-10-15, passed without an announced deprecation. This was the state on the review date, 2026-11-01.
+- This is the state on 2026-11-02. Sonnet 4.5 still works for organizations that already have access, so the catalog records it as deprecated, not retired. The Anthropic Models API describes a deprecated model as closed to new adopters, so a new account can already fail with it.
+- The page offers Sonnet 4.5 with the label "Sonnet 4.5 (retires 2026-11-30)". After that date, a role that names `claude-sonnet-4-5-20250929` fails on the Claude API, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed) and Microsoft Foundry. Choose Sonnet 5.5 instead.
+- Anthropic gives at least 60 days' notice before it retires a model. Opus 4.5 and Haiku 4.5 had no deprecation notice, so their earliest retirement dates are floors, not scheduled dates. The date for Haiku 4.5, 2026-10-15, passed without an announcement.
+- The Claude Code aliases `sonnet`, `haiku` and `default` can resolve to these 4.5 models on some providers. See [AI assistants](assistants.md#claude-model-aliases-on-other-providers).
 
 A release does not keep a retired model available. See [Updates and removal](../guide/updates-and-removal.md).
 
@@ -186,7 +202,7 @@ A catalog entry does not grant access. The account plan and the provider decide
 Each entry has a `source` URL in `models/catalog.json`. The main sources are:
 
 - ChatGPT: [OpenAI models](https://learn.chatgpt.com/docs/models) and the Codex CLI 0.166.0 bundled and server catalogs.
-- Claude: [Claude Code model configuration](https://code.claude.com/docs/en/model-config) and [model lifecycle](https://platform.claude.com/docs/en/about-claude/model-deprecations).
+- Claude: [Claude Code model configuration](https://code.claude.com/docs/en/model-config), [model lifecycle](https://platform.claude.com/docs/en/about-claude/model-deprecations), [Bedrock legacy models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html) and [Google partner model deprecations](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/deprecations/partner-models).
 - Kimi: [Kimi Code models](https://www.kimi.com/code/docs/en/kimi-code/models) and [membership](https://www.kimi.com/code/docs/en/kimi-code/membership.html).
 - Gemini: [Antigravity subagents](https://antigravity.google/docs/subagents?tab=cli) and the CLI 1.4.12 parser.
 - Grok: [xAI models](https://docs.x.ai/developers/models) and [Grok Build subagents](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/16-subagents.md).

package/docs/reference/presets.md

@@ -1,6 +1,6 @@
 # Presets
 
-This document lists the three presets of release 0.4.0: Light, Standard and Top-tier. It gives the model and effort that each preset selects for each role and AI assistant, the top models switch, the parallel limits and the design principles. It is for everyone who chooses a preset or wants to know why a preset has its values.
+This document lists the three presets of release 0.5.0: Light, Standard and Top-tier. It gives the model and effort that each preset selects for each role and AI assistant, the top models switch, the parallel limits and the design principles. It is for everyone who chooses a preset or wants to know why a preset has its values.
 
 A preset is a named set of preferences that the release supplies. The data is in `policies/fast.json` (Light), `policies/balanced.json` (Standard) and `policies/quality.json` (Top-tier). The CLI uses the ids `fast`, `balanced` and `quality`. The page and this document use the labels. For the roles, see [Roles](roles.md). For model IDs, efforts and access requirements, see [Model catalog](model-catalog.md). The detailed evidence is in the [model review of 2026-11-01](../research/2026-11-01-model-review.md).
 
@@ -23,7 +23,7 @@ The presets were reviewed on 2026-11-01. They are starting recommendations, not
 - Vendors' effort labels and subscription usage are not directly comparable. One role can therefore get different effort levels in different assistants.
 - Presets pin at most `high`. The only exception is the Claude top choice at `xhigh`. Higher effort gives quickly diminishing returns. Higher levels stay available in Custom.
 - No preset bans a model. A model that a preset does not select stays available in Custom. Personal avoid lists stay available in preferences and CLI input.
-- Each table cell is `model · effort`. A cell without an effort means that the assistant has no per-role effort setting. Gemini and Grok cells have no effort for this reason. See [Roles](roles.md#how-effort-applies).
+- Each table cell is `model · effort`. A cell without an effort means that the preset writes no effort, so the native default applies. Gemini cells have no effort because Antigravity has no per-role effort setting. Grok cells keep the native default of each model. See [Roles](roles.md#how-effort-applies).
 
 ### Light
 
@@ -48,7 +48,7 @@ Light uses light models for every role, so plan limits last longest. It suits en
 
 | Role | ChatGPT | Claude | Kimi | Gemini | Grok |
 |---|---|---|---|---|---|
-| Coder | Sol · medium | Sonnet 5.5 · medium | K3 256K · high | Pro | Grok 4.7 |
+| Coder | Sol · medium | Sonnet 5.5 · high | K3 256K · high | Pro | Grok 4.7 |
 | Reviewer | Sol · high | Sonnet 5.5 · high | K3 256K · high | Pro | Grok 4.7 |
 | Code explorer | Luna · high | Haiku 5.5 · medium | K2.8 Preview · low | Flash | Grok Build 0.1 |
 | Test writer | Sol · high | Sonnet 5.5 · high | K3 256K · high | Pro | Grok 4.7 |
@@ -58,6 +58,8 @@ Light uses light models for every role, so plan limits last longest. It suits en
 Standard uses stronger models for implementation, review, test creation and documentation. It uses light models for fact gathering and mechanical work.
 
 - ChatGPT runs GPT-6.1 Sol for code, review and tests. Luna runs at high for exploration. GPT-6.1 Terra runs at medium for docs: OpenAI positions Terra for clear writing, at half of Sol's usage.
+- Claude runs Sonnet 5.5 at high for code, review and tests. Anthropic's own per-effort results put Sonnet 5.5 at medium far behind high on agentic coding: 28.8% against 43.0% on Terminal-Bench 4.0. Opus 5.5 at medium scores higher than Sonnet 5.5 at high, but it costs 1.5 to 2.3 times more per task and more per solved task on every measurement. That is a Top-tier trade, not a balance. See [the decision of 2026-11-02](../research/2026-11-01-model-review.md#what-this-means-for-the-standard-claude-coder).
+- The Claude Coder effort is also the effort of Claude subagents that have no named role (capped at high). In Standard these subagents therefore also run at high, and they use more of the plan than at medium. See [Roles](roles.md#default-subagent-per-assistant).
 - Claude's Haiku 5.5 explorer uses medium, its native default.
 - Kimi uses K3 256K for code, review, tests and docs. Its quota footprint is smaller than that of the full-context K3. Larger-context choices stay editable.
 - Gemini uses Flash for exploration and docs.
@@ -116,10 +118,10 @@ These values are product defaults, not benchmark results. A limit does not start
 These are short reasons. The sources and the detailed comparisons are in the [model review of 2026-11-01](../research/2026-11-01-model-review.md).
 
 - **OpenAI (ChatGPT):** OpenAI positions Astra for demanding work, Sol for a balance of capability and usage, Terra for fast, clear writing and Luna for focused, efficient work. In Codex credits per token, Astra costs 5 times Sol, Terra costs half of Sol and Luna costs a tenth of Terra. OpenAI's subagent guide suggests Sol for demanding agents, Luna for lighter subagent work, high for Luna, and names reviewer or security-focused agents as examples for high. The reviewer example of the same guide uses Sol at medium.
-- **Anthropic (Claude):** Anthropic suggests Sonnet for most coding, Opus for complex architectural work and Haiku for simple subagent tasks. Anthropic suggests Fable only when Opus 5.5 at a higher effort still falls short. Anthropic describes high as the level for work where verification matters and xhigh as deeper reasoning at higher token spend. Anthropic reports that Sonnet 5.5 scored lower at max than at xhigh, because it started review subagents more often.
+- **Anthropic (Claude):** Anthropic suggests Sonnet for most coding, Opus for complex architectural work and Haiku for simple subagent tasks. Anthropic suggests Fable only when Opus 5.5 at a higher effort still falls short. Anthropic describes high as the level for work where verification matters, such as fixing a bug in an existing codebase, and xhigh as deeper reasoning at higher token spend. For Sonnet 5.5 in agentic coding, Anthropic suggests medium for well-specified tasks and high for harder or longer ones. The Standard Coder uses high because Anthropic's per-effort benchmark data puts Sonnet 5.5 at medium 8.6 to 14.2 points below high on Terminal-Bench 4.0, FrontierCode and CursorBench. Anthropic reports that Sonnet 5.5 scored lower at max than at xhigh, because it started review subagents more often.
 - **Moonshot (Kimi):** Kimi describes K2.8 Preview as efficient thinking and K3 256K as a smaller quota footprint than K3. Moonshot recommends K3 256K for routine feature work and K3 for large-codebase analysis and multi-file refactoring. K3.1 Pro Highspeed has the same capabilities as K3.1 Pro at a quota premium, so no preset uses it.
 - **Google (Gemini):** The presets use only the native role tiers of Antigravity. The tiers do not fix the underlying model, and there is no per-role effort.
-- **xAI (Grok):** Grok Build 0.1 is xAI's fast coding model and serves light work. Grok 4.7 is the flagship and serves code, review, tests and docs. Grok 4.6 and 4.5 stay available in Custom.
+- **xAI (Grok):** Grok Build 0.1 is xAI's fast coding model and serves light work. Grok 4.7 is the flagship and serves code, review, tests and docs. Grok 4.6 and 4.5 stay available in Custom. Release 0.5.0 added a per-role effort for Grok and reviewed the Grok presets again. Every Grok preset keeps the native default effort: `high` for Grok 4.7, and no effort setting for Grok Build 0.1. A pinned `high` would give the same level, and presets pin at most `high`. No task comparison supports another level, so Grok has no top choice in this release. The other Grok 4.7 levels stay available in Custom.
 
 Account access to each model varies by plan. A preset does not grant access. For plan requirements, see [Model catalog](model-catalog.md#access-requirements).
 

package/docs/reference/roles.md

@@ -73,10 +73,12 @@ The Reviewer and the Code explorer are read-only roles. Their prompts tell them
 | Claude | `tools: Read, Grep, Glob` |
 | Kimi | `tools: [Read, Grep, Glob]` |
 | Gemini | None. The prompt is the only restriction. |
-| Grok | `permission_mode: plan` |
+| Grok | `capabilityMode: read-only`. When Grok Build starts the subagent, it removes the tools that edit, write, delete or move files and the shell tool. Tools from MCP servers stay. See [AI assistants](assistants.md#grok-read-only-roles). |
 
 The other four roles get no tool restriction. They use the permissions of the native client.
 
+Grok installs made by 0.4.0 or 0.5.0 have `permission_mode: plan` in these two role files. Grok Build ignores this field, so the prompt is their only restriction. A setup with 0.5.1 or later and `--release`, `--preset`, `--config` or explicit tool arguments replaces the files. See [Updates and removal](../guide/updates-and-removal.md#what-happens-during-an-update).
+
 ## Role file contents
 
 For the file paths, see [AI assistants](assistants.md#files-written). Each file has these fields:
@@ -87,7 +89,7 @@ For the file paths, see [AI assistants](assistants.md#files-written). Each file
 | Claude | Markdown with frontmatter | `name`, `description`, `model`, `effort` (only when pinned), `tools` (read-only roles); the body is the prompt |
 | Kimi | Markdown with frontmatter | `name`, `description`, `tools` (read-only roles); the body is the prompt and a routing note |
 | Gemini | Markdown with frontmatter | `name`, `description`, `model` (the tier), `subagent: true`; the body is the prompt |
-| Grok | Markdown with frontmatter | `name`, `description`, `permission_mode: plan` (read-only roles); the body is the prompt |
+| Grok | Markdown with frontmatter | `name`, `description`, `effort` (only when pinned), `capabilityMode: read-only` (read-only roles); the body is the prompt |
 
 - Kimi frontmatter does not select a model. The routing note in the body names the pool alias and the requested effort. The parent selects the alias when it spawns the subagent.
 - Grok takes the model of each role from `[subagents.models]` in `config.toml`, not from the role file.
@@ -103,7 +105,7 @@ APK adds one block to the global instruction file of each assistant. The block s
    - ChatGPT and Claude: use the named role definitions for model and effort, which settings can override them, and that an omitted role effort uses the native default.
    - Kimi: the pool alias and effort for each role, that roles that share an alias share its effort, and that the concurrency limit is guidance.
    - Gemini: the tier for each role, and that per-role effort and a hard concurrency cap are not supported.
-   - Grok: use the named role definitions for model selection, and that subagents use the main session effort.
+   - Grok: use the named role definitions for model and effort, that a role effort applies only when its model supports effort, that a role without an effort uses the native default of its model, and which settings can override them.
 5. If the avoid list is not empty: "Avoid these models when delegating: …. This is routing guidance."
 
 ## Default subagent per assistant
@@ -116,7 +118,7 @@ A subagent can start without a named role. Most assistants then use a native def
 | Claude | `CLAUDE_CODE_SUBAGENT_MODEL` | `CLAUDE_CODE_SUBAGENT_EFFORT`, when pinned, capped at `high` |
 | Kimi | `secondary_model.default_model` (the alias) | The per-alias effort of that alias, when pinned |
 | Gemini | Not set | Not set |
-| Grok | `subagents.models.general-purpose` | Not set. Subagents use the main session effort. |
+| Grok | `subagents.models.general-purpose` | Not set. The pinned model runs at its default effort. |
 
 - **Claude cap:** a role effort of `xhigh` or `max` becomes `high` for the default subagent. The Claude top choice at `xhigh` therefore does not raise subagents without a named role. Claude Code 2.1.316 or later reads `CLAUDE_CODE_SUBAGENT_EFFORT`. Earlier versions ignore it, and those subagents keep the main session effort.
 - **Gemini:** APK writes no configuration file for Antigravity, so subagents without a role follow native Antigravity behavior.
@@ -132,7 +134,7 @@ Effort is the reasoning level that a model uses. An unpinned effort (`null`, or
 | Claude | `effort` in the role file | `CLAUDE_CODE_EFFORT_LEVEL` overrides the `effort` field of subagents. Aliases and the resolved provider model can clamp or ignore a level. |
 | Kimi | `models.<alias>.overrides.default_effort` | One effort for each alias. See below. |
 | Gemini | None | `--effort` and `/effort` apply to the whole session. |
-| Grok | None | Grok Build resolves subagent effort from a spawn override, a role default, a persona default and then the parent session. APK writes only a model, so subagents use the main session effort. |
+| Grok | `effort` in the role file | Grok Build applies it only when the model supports effort. Without it, a role runs at the default effort of its pinned model (Grok 4.7: `high`), not at the main session effort. A spawn override from the harness or a Grok role with the same name as the agent wins over the field. See [AI assistants](assistants.md#grok-role-effort). |
 
 A known model accepts only the levels in the [model catalog](model-catalog.md). The page offers only those levels.
 

package/docs/research/2026-11-01-model-review.md

@@ -1,6 +1,6 @@
 # Model review of 2026-11-01
 
-This document records the evidence behind the presets and the model catalog of APK 0.4.0. It is for maintainers who prepare the next review and for users who want to know why a preset has its values. It lists the sources per vendor, compares Opus 5.5 with Sonnet 5.5 at different effort levels, compares Fable 5.1 with Opus 5.5, and summarizes what the evidence says about effort and small models. It also lists the decisions of 0.4.0 and the questions that need local verification. The current preset values are in [presets](../reference/presets.md). The catalog fields are in [model catalog](../reference/model-catalog.md). The procedure for the next review is in the [model review procedure](../maintainers/model-review.md).
+This document records the evidence behind the presets and the model catalog of APK 0.4.0. It is for maintainers who prepare the next review and for users who want to know why a preset has its values. It lists the sources per vendor, compares Opus 5.5 with Sonnet 5.5 at different effort levels, compares Fable 5.1 with Opus 5.5, and summarizes what the evidence says about effort and small models. It also lists the decisions of 0.4.0 and the questions that need local verification. An update of 2026-11-02 checked the equal-effort numbers for Opus 5.5 and Sonnet 5.5 against primary sources and recorded the decision for the Standard Claude Coder ([#29](https://github.com/automatis-tools/agent-policy-kit/issues/29)). It also checked the lifecycle of the Claude 4.5 models again ([#28](https://github.com/automatis-tools/agent-policy-kit/issues/28)). The current preset values are in [presets](../reference/presets.md). The catalog fields are in [model catalog](../reference/model-catalog.md). The procedure for the next review is in the [model review procedure](../maintainers/model-review.md).
 
 ## Scope and method
 
@@ -77,6 +77,9 @@ No Anthropic model was released after 2026-10-30. The current models are Fable 5
 | Frontmatter `effort` overrides the session effort but not `CLAUDE_CODE_EFFORT_LEVEL`. | [Model configuration](https://code.claude.com/docs/en/model-config) (primary) |
 | Claude Code 2.1.316 adds `CLAUDE_CODE_SUBAGENT_EFFORT`. It sets the effort of subagents that name no effort, instead of the session effort. The documentation pages do not describe it yet. | Claude Code 2.1.316 release notes, installed with the client (primary) |
 | Sonnet 4.5 (`claude-sonnet-4-5-20250929`) is deprecated and retires on 2026-11-30. Opus 4.5 retires not sooner than 2026-11-24. Haiku 4.5 retires not sooner than 2026-10-15; that date passed without a deprecation notice. | [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) (primary) |
+| Check of 2026-11-02 (#28): Sonnet 4.5 was deprecated on 2026-09-30 with the replacement Sonnet 5.5. Its retirement on 2026-11-30 applies to the Claude API, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed) and Microsoft Foundry. Opus 4.5 and Haiku 4.5 are "Active (legacy)" with no deprecation notice. Anthropic gives at least 60 days' notice before a retirement, so the Opus 4.5 date is a floor, not a scheduled date. | [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations), [Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview), [Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) (primary) |
+| Partner schedules for Sonnet 4.5: Amazon Bedrock lists it as Legacy from 2026-10-08 with end of life on 2027-04-08. Google Cloud (Google managed) announces no retirement date; its earliest retirement date, 2026-09-29, passed. Google's earliest retirement dates are 2026-11-24 for Opus 4.5 and 2026-12-07 for Haiku 4.5. | [Bedrock legacy models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html), [Google: Sonnet 4.5](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/sonnet-4-5), [Google partner model deprecations](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/deprecations/partner-models) (primary) |
+| The Claude Code aliases resolve to 4.5 models outside the Anthropic API: `sonnet` to Sonnet 4.5 on Bedrock, Google Cloud's Agent Platform and Microsoft Foundry; `haiku` to Haiku 4.5 on every provider except the Anthropic API; `default` to Sonnet 4.5 on Microsoft Foundry. Foundry follows the Claude API lifecycle. | [Model configuration](https://code.claude.com/docs/en/model-config), [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) (primary) |
 | Plans: Pro, Max ($100, 5 times Pro) and Ultra ($200, no 5-hour limit). On Pro, Fable uses usage credits. On Max and Ultra, Fable has a separate weekly limit. | [Claude pricing](https://claude.com/pricing), [Use Claude Code with your Pro or Max plan](https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan) (primary) |
 | In non-interactive `-p` mode, Fable usage is billed without a consent prompt. | [Model configuration](https://code.claude.com/docs/en/model-config) (primary) |
 
@@ -175,44 +178,58 @@ Per token, Opus 5.5 costs twice as much as Sonnet 5.5. Subscription plans meter
 | Anthropic: FrontierCode (Sonnet at max) | 54.4% | 46.2% | [Sonnet 5.5](https://www.anthropic.com/claude-sonnet-5-5) (primary) |
 | Anthropic: FrontierCode, Sonnet 5.5 at xhigh | — | 52.1% | [Haiku 5.5](https://www.anthropic.com/claude-haiku-5-5) (primary) |
 
-Caveat for the Terminal-Bench lead of Sonnet 5.5 in Anthropic's numbers: apidog reports, with the system card as its source, that a fallback was used in 1.5% of Sonnet 5.5 trials and in 10% of Opus 5.5 trials. Source: [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/) (secondary). This review did not check the caveat in the system card.
+Caveat for the Terminal-Bench lead of Sonnet 5.5 in Anthropic's numbers: a fallback served 1.2% of the Sonnet 5.5 requests (1.5% of trials) and 2.5% of the Opus 5.5 requests (10% of trials). These rates apply only to the headline runs, Sonnet 5.5 at max and Opus 5.5 at xhigh. No source publishes fallback rates per effort level. Sources: Sonnet 5.5 system card, §8.5, p.113, and Opus 5.5 system card, §8.5, p.178 (primary). The 0.4.0 review had this caveat only from [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/) (secondary). Artificial Analysis saw the same asymmetry independently: in the Terminal-Bench part of its Coding Agent Index, the fallback served 6 of 198 Sonnet 5.5 attempts and 24 of 198 Opus 5.5 attempts. Source: [Artificial Analysis: coding agents](https://artificialanalysis.ai/agents/coding) (primary).
 
 The two independent measurements put Opus 5.5 ahead by 2.4 index points and by about 1 percentage point. At these effort levels the models are almost equal.
 
-### Results at equal high effort
+### Results at equal effort
 
-Only one source compares the two models at the same effort level. It is secondary: apidog cites the Sonnet 5.5 system card. This review did not check these numbers against the system card. The cost is the API cost of one attempt at one task.
+Anthropic publishes per-effort results for both models on three coding benchmarks. They are the data behind the "Accuracy vs. cost" charts on the model pages: the pages embed the chart data in their HTML. The system cards confirm the CursorBench values and the Opus 5.5 FrontierCode result at medium in text. The cost is the list-price API cost of one attempt at one task.
 
-| Benchmark | Sonnet 5.5 high | Opus 5.5 high | Source |
-|---|---|---|---|
-| Terminal-Bench 4.0 | 43.0% ($1.94) | 64.2% ($3.88) | [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/) (secondary) |
-| FrontierCode | 49.4% ($0.42) | 54.0% ($1.09) | [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/) (secondary) |
-| CursorBench | 47.8% ($1.67) | 56.0% ($3.97) | [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/) (secondary) |
+The 0.4.0 review took the high-effort numbers and the Terminal-Bench numbers for Opus 5.5 at medium and Sonnet 5.5 at xhigh from a secondary source, [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/). The check of 2026-11-02 confirmed every one of these numbers in the primary data. apidog names the Sonnet 5.5 system card as its source, but most of the numbers are only in the model-page charts.
+
+| Benchmark | Sonnet 5.5 medium | Sonnet 5.5 high | Opus 5.5 medium | Opus 5.5 high | Source |
+|---|---|---|---|---|---|
+| Terminal-Bench 4.0 | 28.8% ($0.83) | 43.0% ($1.94) | 57.6% ($2.94) | 64.2% ($3.88) | Chart data on [Sonnet 5.5](https://www.anthropic.com/claude-sonnet-5-5) and [Opus 5.5](https://www.anthropic.com/claude-opus-5-5) (primary) |
+| FrontierCode v1.1 Main | 36.5% ($0.24) | 49.4% ($0.42) | 54.6% ($0.80) | 54.0% ($1.09) | Chart data on [Sonnet 5.5](https://www.anthropic.com/claude-sonnet-5-5) and [Opus 5.5](https://www.anthropic.com/claude-opus-5-5). Opus 5.5 at medium also in the Opus 5.5 system card, §8.4, p.176 (primary) |
+| CursorBench 4.0 | 39.2% ($0.70) | 47.8% ($1.67) | 52.5% ($2.91) | 56.0% ($3.97) | Chart data on [Sonnet 5.5](https://www.anthropic.com/claude-sonnet-5-5). Scores also in the Sonnet 5.5 system card, §8.8, p.115, and the Opus 5.5 system card, §8.8, p.179 (primary) |
+
+- Terminal-Bench 4.0 ran in Claude Code (`--bare`) with safeguards on and 5 trials per task. The standard error is about ±2.5 points. Sonnet 5.5 at xhigh scores 61.5% ($5.30). Source: [Sonnet 5.5](https://www.anthropic.com/claude-sonnet-5-5) chart data (primary).
+- Cursor reported the CursorBench scores. Anthropic estimated the costs from Cursor's token counts.
+- The model page does not say how the Sonnet 5.5 FrontierCode costs were measured.
+- The Opus 5.5 system card says that its highest FrontierCode scores are at medium effort and that performance declines above medium.
 
-The same source gives two more Terminal-Bench 4.0 results: Opus 5.5 at medium 57.6% ($2.94) and Sonnet 5.5 at xhigh 61.5% ($5.30). Source: [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/) (secondary). The source has no result for Sonnet 5.5 at medium, which is the Standard Coder setting.
+On FrontierCode, Opus 5.5 at medium (54.6%) is above Sonnet 5.5 at xhigh (52.1%) and at max (46.2%) in Anthropic's own numbers.
+
+Artificial Analysis measures both models per effort in its own harness, not in Claude Code. Its results are close to Anthropic's. Sources: [Artificial Analysis: Sonnet 5.5 medium](https://artificialanalysis.ai/models/claude-sonnet-5-5-medium), the `-high` page and the same pages for `claude-opus-5-5` (primary).
+
+| Measurement (Artificial Analysis) | Sonnet 5.5 medium | Sonnet 5.5 high | Opus 5.5 medium | Opus 5.5 high |
+|---|---|---|---|---|
+| Terminal-Bench 4.0 | 29.8% ($1.58) | 43.9% ($2.19) | 52.5% ($4.04) | 56.6% ($5.12) |
+| FrontierCode v1.1 | 29.3% | 44.3% | 57.1% | 54.0% |
+| FrontierCode 2.0 | 11.0% ($0.32) | 25.7% ($0.76) | 33.1% ($1.71) | 35.9% ($2.49) |
+| Intelligence Index | 30.3 | 41.1 | 48.1 | 51.7 |
 
-Anthropic gives two primary results for Opus 5.5 at medium: FrontierCode 54.6% and CursorBench 52.5%. Source: [Opus 5.5](https://www.anthropic.com/claude-opus-5-5) (primary). On FrontierCode, Opus 5.5 at medium (54.6%) is above Sonnet 5.5 at xhigh (52.1%) and at max (46.2%) in Anthropic's own numbers. The two Anthropic pages do not say that they used the same harness.
+Vals AI publishes per-effort results only for Opus 5.5 and has no medium value. Source: [Vals AI: Terminal-Bench 4.0](https://www.vals.ai/benchmarks/terminal-bench-4) (primary). No source publishes SWE-bench results per effort.
 
 ### Cost per solved task
 
-The cost per solved task is derived in this document. It is the cost of one attempt divided by the success rate, from the apidog numbers above. No source publishes these values.
+The cost per solved task is derived in this document. It is the cost of one attempt divided by the success rate, from the primary numbers above. The values use the unrounded chart costs, so they can differ by one cent from a division of the rounded values. FrontierCode is a composite score, so for it the value is the cost per score point. No source publishes these values.
 
-| Benchmark | Setting | Success rate | Cost per attempt | Cost per solved task (derived) |
+| Measurement | Sonnet 5.5 medium | Sonnet 5.5 high | Opus 5.5 medium | Opus 5.5 high |
 |---|---|---|---|---|
-| Terminal-Bench 4.0 | Sonnet 5.5 high | 43.0% | $1.94 | $4.51 |
-| Terminal-Bench 4.0 | Opus 5.5 medium | 57.6% | $2.94 | $5.10 |
-| Terminal-Bench 4.0 | Opus 5.5 high | 64.2% | $3.88 | $6.04 |
-| Terminal-Bench 4.0 | Sonnet 5.5 xhigh | 61.5% | $5.30 | $8.62 |
-| FrontierCode | Sonnet 5.5 high | 49.4% | $0.42 | $0.85 |
-| FrontierCode | Opus 5.5 high | 54.0% | $1.09 | $2.02 |
-| CursorBench | Sonnet 5.5 high | 47.8% | $1.67 | $3.49 |
-| CursorBench | Opus 5.5 high | 56.0% | $3.97 | $7.09 |
+| Anthropic: Terminal-Bench 4.0 | $2.90 | $4.51 | $5.10 | $6.05 |
+| Anthropic: FrontierCode v1.1 | $0.65 | $0.85 | $1.47 | $2.02 |
+| Anthropic: CursorBench 4.0 | $1.79 | $3.49 | $5.54 | $7.09 |
+| Artificial Analysis: Terminal-Bench 4.0 | $5.30 | $4.97 | $7.70 | $9.05 |
+| Artificial Analysis: FrontierCode 2.0 | $2.95 | $2.95 | $5.17 | $6.92 |
 
 What the derived values show:
 
-- At high, Sonnet 5.5 has the lowest cost per solved task on all three benchmarks, but it solves fewer tasks.
-- On Terminal-Bench 4.0, Opus 5.5 at medium solves 14.6 percentage points more tasks than Sonnet 5.5 at high. Its cost per solved task is about 13% higher.
-- Sonnet 5.5 at xhigh costs more per solved task than Opus 5.5 at high, and it solves fewer tasks (61.5% vs 64.2%).
+- Sonnet 5.5 at medium solves the fewest tasks. Sonnet 5.5 at high scores 8.6 to 14.8 points more on every measurement, at 1.4 to 2.4 times the cost per task. On the Artificial Analysis Terminal-Bench run, its cost per solved task is even lower than at medium ($4.97 against $5.30).
+- Opus 5.5 at medium scores 4.7 to 14.6 points more than Sonnet 5.5 at high. It costs 1.5 to 2.3 times more per task, and its cost per solved task is 13% to 75% higher on all five measurements.
+- The largest Opus gain is on Terminal-Bench 4.0. On FrontierCode and CursorBench, which are closer to repository work, Opus 5.5 at medium leads Sonnet 5.5 at high by about 5 points.
+- Sonnet 5.5 at xhigh costs more per solved task on Terminal-Bench 4.0 ($8.62) than Opus 5.5 at high, and it solves fewer tasks (61.5% against 64.2%).
 
 ### The Sonnet 5.5 regression at max
 
@@ -227,16 +244,22 @@ Anthropic reports that Sonnet 5.5 scored lower on FrontierCode at max than at xh
 | The example read-only code reviewer uses Sonnet at high. | [Subagents](https://code.claude.com/docs/en/sub-agents) (primary) |
 | Sonnet 5.5 is "a faster, lower-cost complement to Claude Opus 5.5" for "well-scoped everyday tasks, bug fixes". | [Sonnet 5.5](https://www.anthropic.com/claude-sonnet-5-5) (primary) |
 | A customer (Factory) calls Opus 5.5 "the first model we'd default to at medium effort". This is a customer quote, not Anthropic guidance. | [Opus 5.5](https://www.anthropic.com/claude-opus-5-5) (primary) |
+| For Sonnet 5.5: "For agentic coding and multistep tool use, start with `medium` for well-specified tasks and move to `high` for harder or longer ones." | [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) (primary) |
+| High is for "Work where verification matters or edge cases are likely, such as fixing a bug in an existing codebase". | [Model configuration](https://code.claude.com/docs/en/model-config) (primary) |
+| Opus "uses meaningfully more of your quota, so consider switching to Sonnet for routine work". No official per-model multiplier for plan limits exists. | [Models, usage, and limits in Claude Code](https://support.claude.com/en/articles/14552983), [Claude pricing](https://claude.com/pricing) (primary) |
 
 ### What this means for the Standard Claude Coder
 
-The Standard Claude Coder stays Sonnet 5.5 at medium in 0.4.0. The reasons:
+In 0.4.0 the Standard Claude Coder stayed Sonnet 5.5 at medium. That review said that the equal-effort data came only from a secondary source and that no source measured Sonnet 5.5 at medium. Both statements were wrong. Anthropic publishes the equal-effort data and Sonnet 5.5 at medium on three coding benchmarks, and Artificial Analysis measures both independently. See [Results at equal effort](#results-at-equal-effort).
 
-- The equal-effort data that favors Opus 5.5 at medium comes only from a secondary source.
-- No source measures Sonnet 5.5 at medium, so the current cell has no measured position.
-- Anthropic's guidance puts Sonnet first for most coding.
+Decision of 2026-11-02 ([#29](https://github.com/automatis-tools/agent-policy-kit/issues/29), release 0.5.0): the Standard Claude Coder changes from Sonnet 5.5 · medium to Sonnet 5.5 · high. Confidence: medium.
 
-The candidates for a local A/B comparison are Sonnet 5.5 at high and Opus 5.5 at medium. On Terminal-Bench 4.0 their derived costs per solved task are close ($4.51 and $5.10), and Opus 5.5 at medium solves more tasks. A test must use representative repository tasks and count the plan usage, not only the API price. The Coder effort also becomes the effort of unnamed subagents in Claude Code 2.1.316 and later (capped at high), so a change to the Coder also changes those subagents. [Roles](../reference/roles.md) describes this default subagent.
+- **Sonnet 5.5 at medium is the weak point.** On Terminal-Bench 4.0 it scores 28.8% in Anthropic's run and 29.8% in the Artificial Analysis run. On FrontierCode 2.0 it scores 11.0%. High adds 8.6 to 14.8 points on every measurement.
+- **Opus 5.5 at medium is stronger, but it is a quality-first choice.** Its cost per solved task is higher than that of Sonnet 5.5 at high on all five measurements, and Anthropic says that Opus uses "meaningfully more of your quota". That fits Top-tier, not a balance preset. Its largest gain is on Terminal-Bench 4.0, which Anthropic describes as science-adjacent and frontier-engineering tasks.
+- **Sonnet 5.5 at high matches Anthropic's guidance for the role.** The Coder implements tasks and fixes bugs in existing code. The Sonnet 5.5 effort guidance and the Claude Code definition of high both point to high. Anthropic still suggests Sonnet for most coding.
+- **Why the confidence is medium:** benchmark tasks are harder than many well-scoped subagent tasks, and Anthropic says that medium fits clear-scope work. No source gives fallback rates per effort. No official plan-usage multiplier exists, so the API cost ratios are only a proxy. A local A/B comparison on representative repository tasks is still the definitive check (open question 2).
+
+Side effect: setup writes `CLAUDE_CODE_SUBAGENT_EFFORT` from the Coder effort, capped at high (Claude Code 2.1.316 and later). In Standard, Claude subagents without a named role therefore also move from medium to high, and they use more of the plan. [Roles](../reference/roles.md#default-subagent-per-assistant) describes this default subagent. With the Coder at high, the Standard Claude Reviewer and Test writer equal the `code` choice, so `policies/balanced.json` no longer carries separate entries for them. Their values do not change.
 
 ## Fable 5.1 and Opus 5.5
 
@@ -255,7 +278,7 @@ The strongest argument for Fable 5.1: Anthropic says that the gap is "narrower i
 
 Fable 5.1 also has different billing. On Pro it uses usage credits, and on Max and Ultra it has a separate weekly limit. In `-p` mode it bills without a consent prompt. Sources: [Model configuration](https://code.claude.com/docs/en/model-config), [Use Claude Code with your Pro or Max plan](https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan) (primary).
 
-The gain of xhigh over high on Opus 5.5 is small: 66.4% (xhigh, primary, [Opus 5.5](https://www.anthropic.com/claude-opus-5-5)) against 64.2% (high, secondary, [apidog](https://apidog.com/blog/claude-sonnet-5-5-benchmarks/)) on Terminal-Bench 4.0. The switch therefore buys more reasoning on the same model, not a different model with separate billing.
+The gain of xhigh over high on Opus 5.5 is small: 66.4% (xhigh, primary, [Opus 5.5](https://www.anthropic.com/claude-opus-5-5)) against 64.2% (high, primary, chart data on [Opus 5.5](https://www.anthropic.com/claude-opus-5-5)) on Terminal-Bench 4.0. The switch therefore buys more reasoning on the same model, not a different model with separate billing.
 
 ## Effort returns
 
@@ -309,11 +332,19 @@ The release also changed setup for Claude. Setup writes `CLAUDE_CODE_SUBAGENT_EF
 
 The catalog snapshot of 0.4.0 records these facts from this review: GPT-5.5 retired for ChatGPT sign-in, the GPT-6 Astra server default, the excluded `gpt-reserve`, the client versions, the Opus 4.5 and Haiku 4.5 retirement dates, the Kimi plan requirements, the undocumented Flash Lite tier and the Grok 4.7 reasoning levels. [Model catalog](../reference/model-catalog.md) describes the fields.
 
+### Changes after the review
+
+| Preset | Assistant | Cells | 0.4.0 | 0.5.0 | Main evidence | Confidence |
+|---|---|---|---|---|---|---|
+| Standard | Claude | Coder (and Claude subagents without a named role) | Sonnet 5.5 · medium | Sonnet 5.5 · high | Anthropic's per-effort data: Sonnet 5.5 at medium scores 8.6 to 14.2 points below high. Opus 5.5 at medium costs more per solved task on every measurement. See [What this means for the Standard Claude Coder](#what-this-means-for-the-standard-claude-coder). | Medium |
+
+The catalog of 0.5.0 also records the Claude 4.5 lifecycle check of 2026-11-02 (#28): the deprecation date and replacement of Sonnet 4.5, the platforms that its retirement on 2026-11-30 applies to, the partner schedules, and the legacy status of Opus 4.5 and Haiku 4.5.
+
 ### Cells left unchanged on purpose
 
 | Cell | Why it did not change |
 |---|---|
-| Standard, Claude, Coder: Sonnet 5.5 · medium | The equal-effort evidence is secondary. Anthropic suggests Sonnet for most coding. Candidates for a local A/B test: Sonnet 5.5 · high and Opus 5.5 · medium. See [What this means for the Standard Claude Coder](#what-this-means-for-the-standard-claude-coder). |
+| Standard, Claude, Coder: Sonnet 5.5 · medium | In 0.4.0: the equal-effort evidence was secondary, and Anthropic suggests Sonnet for most coding. Changed in 0.5.0 to Sonnet 5.5 · high after a check of the primary data. See [Changes after the review](#changes-after-the-review). |
 | Light, ChatGPT, Code explorer and Docs writer: Luna · low | OpenAI's "start with high" also applies, but Light saves usage on purpose. No data shows that low harms discovery or writing. |
 | Top-tier, Kimi, Code explorer and Docs writer: K3 · high | They share the `kimi-code/k3` alias with the Coder, so their effort cannot go down alone. Moonshot suggests `k3` for large-codebase analysis. |
 | Top-tier, Kimi, Task runner: K2.8 Preview · high | K2.8 Preview has no medium level. The alias effort is shared. |
@@ -328,14 +359,14 @@ The catalog snapshot of 0.4.0 records these facts from this review: GPT-5.5 reti
 | # | Question | Why it matters | How to check |
 |---|---|---|---|
 | 1 | How does `CLAUDE_CODE_SUBAGENT_EFFORT` rank against frontmatter `effort`, the Agent tool parameter and `CLAUDE_CODE_EFFORT_LEVEL`? | The 0.4.0 setup writes this setting. | Test on Claude Code 2.1.316 or later. Read the documentation when Anthropic adds it. |
-| 2 | Is Sonnet 5.5 · high or Opus 5.5 · medium a better Standard Claude Coder than Sonnet 5.5 · medium? | Only secondary data compares them. | Run an A/B comparison on representative repository tasks. Count solved tasks and plan usage. |
+| 2 | Is Sonnet 5.5 · high or Opus 5.5 · medium the better Standard Claude Coder on real repository work? | Primary benchmark data led 0.5.0 to Sonnet 5.5 · high (#29). Benchmark tasks are harder than many subagent tasks, and plan usage is not measured. | Run an A/B comparison of Sonnet 5.5 · high and Opus 5.5 · medium on representative repository tasks. Count solved tasks and plan usage. |
 | 3 | Does Grok Build 1.0.70 accept `reasoning_effort` for `[subagents.roles.<name>]`? How does a persona bind to an `apk-*` agent? | Per-role Grok effort and a Grok 4.7 · xhigh switch depend on it. | Use an isolated Grok home directory with a role and a persona. Read the effort of the subagent in the logs. |
 | 4 | Does `grok-build-0.1` appear in the Grok Build model picker for signed-in accounts on each plan? | Light and Standard use it for Grok. | Check the model list of signed-in clients on different plans. Record only whether the model is offered, not account details. |
 | 5 | Which models do the Antigravity tiers `pro`, `flash` and `flash_lite` use on the Pro and Ultra plans? | `pro` may not mean Gemini 4 Argon on every plan. | Start one subagent per tier and read the resolved model name in the CLI log. |
 | 6 | Does `flash_lite` use less Antigravity quota than `flash`? | It decides whether Flash Lite is useful in Light. | No official data exists. Compare usage statistics. |
 | 7 | Is Terra available for Codex subagents on all paid plans and in the IDE extension? What do Free and Go plans get? | The Standard ChatGPT Docs writer uses Terra. | Compare the Codex model catalog on different plans. Start a subagent with `gpt-6.1-terra`. |
 | 8 | What do the catalog field `multi_agent_reasoning_effort: "xhigh"` and the hidden `gpt-reserve` model mean? | The field may set subagent effort in Codex Ultra mode. | Wait for OpenAI documentation. Compare server catalogs over time. |
-| 9 | Is the Opus 4.5 ID `claude-opus-4-5-20251101` (catalog) or `claude-opus-4-5-20251001` (deprecations page as read in this review)? | The catalog ID may be wrong. | Compare with [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations). |
+| 9 | Is the Opus 4.5 ID `claude-opus-4-5-20251101` (catalog) or `claude-opus-4-5-20251001` (deprecations page as read in this review)? | Resolved on 2026-11-02: the catalog ID `claude-opus-4-5-20251101` is correct. | Every Anthropic source uses `20251101`: the [model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) table and the [Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview) page (Bedrock `anthropic.claude-opus-4-5-20251101-v1:0`, Google `claude-opus-4-5@20251101`). No page has `claude-opus-4-5-20251001`. It probably mixes Opus 4.5 with the Haiku 4.5 snapshot date (`claude-haiku-4-5-20251001`). |
 | 10 | What is the untitled Anthropic item dated 2026-11-01? | It may be a new model after this review. | Read [Anthropic news](https://www.anthropic.com/news) again. |
 | 11 | What is the exact Fable limit on Ultra ("50% of weekly limits*")? | The review read it only through a summary tool. | Read [Claude pricing](https://claude.com/pricing) directly. |
 | 12 | Will a stable Kimi Code release limit subagents to the configured model pool? Does per-spawn model selection also take an effort? | The APK model pool must then contain every role model. | Watch [Kimi Code releases](https://github.com/MoonshotAI/kimi-code/releases). |

package/models/catalog.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "reviewedAt": "2026-11-01",
+  "reviewedAt": "2026-11-02",
   "scope": "Documented/native coding-tool selectors at this release; account access and custom deployment IDs vary.",
   "clients": {
     "chatgpt": {
@@ -515,20 +515,44 @@
           "lifecycle": {
             "status": "active",
             "earliestRetirement": "2026-11-24",
+            "scope": "Claude API, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed) and Microsoft Foundry",
+            "note": "Legacy model with no deprecation notice. The date is a floor, not a scheduled retirement; Anthropic gives at least 60 days' notice.",
+            "partners": [
+              {
+                "platform": "Google Cloud (Google managed)",
+                "earliestRetirement": "2026-11-24",
+                "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/deprecations/partner-models"
+              }
+            ],
             "source": "https://platform.claude.com/docs/en/about-claude/model-deprecations"
           }
         },
         {
           "id": "claude-sonnet-4-5-20250929",
-          "label": "Sonnet 4.5 (deprecated)",
+          "label": "Sonnet 4.5 (retires 2026-11-30)",
           "efforts": [],
           "defaultEffort": null,
           "source": "https://code.claude.com/docs/en/model-config",
           "kind": "model",
           "lifecycle": {
             "status": "deprecated",
+            "deprecationDate": "2026-09-30",
             "retirementDate": "2026-11-30",
-            "scope": "Anthropic-operated platforms; partner lifecycles differ",
+            "replacement": "claude-sonnet-5-5",
+            "scope": "Claude API, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed) and Microsoft Foundry",
+            "partners": [
+              {
+                "platform": "Amazon Bedrock",
+                "status": "legacy",
+                "endOfLife": "2027-04-08",
+                "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html"
+              },
+              {
+                "platform": "Google Cloud (Google managed)",
+                "note": "No retirement date announced. The earliest retirement date, 2026-09-29, passed.",
+                "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/sonnet-4-5"
+              }
+            ],
             "source": "https://platform.claude.com/docs/en/about-claude/model-deprecations"
           }
         },
@@ -542,6 +566,15 @@
           "lifecycle": {
             "status": "active",
             "earliestRetirement": "2026-10-15",
+            "scope": "Claude API, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed) and Microsoft Foundry",
+            "note": "Legacy model with no deprecation notice. The earliest retirement date passed without an announcement.",
+            "partners": [
+              {
+                "platform": "Google Cloud (Google managed)",
+                "earliestRetirement": "2026-12-07",
+                "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/deprecations/partner-models"
+              }
+            ],
             "source": "https://platform.claude.com/docs/en/about-claude/model-deprecations"
           }
         },
@@ -721,14 +754,25 @@
     },
     "grok": {
       "label": "Grok",
-      "efforts": [],
+      "efforts": [
+        "low",
+        "medium",
+        "high",
+        "xhigh",
+        "max"
+      ],
       "observedClientVersion": "1.0.70",
       "models": [
         {
           "id": "grok-4.7",
           "label": "Grok 4.7",
-          "efforts": [],
-          "defaultEffort": null,
+          "efforts": [
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ],
+          "defaultEffort": "high",
           "source": "https://docs.x.ai/developers/models",
           "nativeSource": "https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/16-subagents.md",
           "kind": "model",
@@ -768,7 +812,7 @@
           "kind": "model"
         }
       ],
-      "note": "Per-subagent models are set in config.toml [subagents.models]; model IDs follow the documented xAI model list and account access varies. Grok 4.7 supports low/medium/high/xhigh reasoning effort and Grok Build resolves subagent effort from a spawn override, role default, persona default and then the parent session. The [subagents.models] entries that APK writes carry only a model, so APK leaves effort to the main session. [subagents] max_concurrent is a native cap."
+      "note": "Per-subagent models are set in config.toml [subagents.models]; model IDs follow the documented xAI model list and account access varies. APK writes a role effort as effort in the agent frontmatter (agents/apk-<role>.md); Grok Build 1.0.70 accepts low/medium/high/xhigh/max there and drops the whole agent for any other value. The effort applies only when the model supports effort: Grok 4.7 lists low/medium/high/xhigh with default high, Grok Build 0.1 has no configurable effort, and the effort levels of Grok 4.6 and 4.5 are not verified. A role without an effort runs at the default effort of its pinned model, not at the main session effort; a role named like the agent ([subagents.roles.<agent>] reasoning_effort) or a harness spawn override wins over the frontmatter. [subagents] max_concurrent is a native cap."
     }
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-policy-kit",
-  "version": "0.4.0",
+  "version": "0.5.1",
   "description": "Configure native subagent settings across AI assistants, then exit",
   "type": "module",
   "license": "MIT",
@@ -65,5 +65,5 @@
   "bugs": {
     "url": "https://github.com/automatis-tools/agent-policy-kit/issues"
   },
-  "homepage": "https://agent-policy-kit.trymenow.io/v/0.4.0/"
+  "homepage": "https://agent-policy-kit.trymenow.io/v/0.5.1/"
 }

package/policies/balanced.json

@@ -34,25 +34,17 @@
     "claude": {
       "code": {
         "model": "claude-sonnet-5-5",
-        "effort": "medium"
+        "effort": "high"
       },
       "light": {
         "model": "claude-haiku-5-5",
         "effort": "low"
       },
       "roles": {
-        "reviewer": {
-          "model": "claude-sonnet-5-5",
-          "effort": "high"
-        },
         "explorer": {
           "model": "claude-haiku-5-5",
           "effort": "medium"
         },
-        "tester": {
-          "model": "claude-sonnet-5-5",
-          "effort": "high"
-        },
         "writer": {
           "model": "claude-sonnet-5-5",
           "effort": "medium"

package/schema/policy.schema.json

@@ -395,7 +395,14 @@
           "$ref": "#/$defs/identifier"
         },
         "effort": {
-          "type": "null"
+          "enum": [
+            null,
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
         }
       }
     },