roadmodel 0.2.87__tar.gz → 0.2.89__tar.gz

{roadmodel-0.2.87 → roadmodel-0.2.89}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: roadmodel
-Version: 0.2.87
+Version: 0.2.89
 Summary: BYO-key CLI that recommends the right AI model, platform, and settings for a prompt.
 Project-URL: Homepage, https://roadmodel.ai
 Project-URL: Repository, https://github.com/nathanramoscfa/roadmodel
@@ -525,10 +525,13 @@ multi-file blast radius without over-buying the ceiling.
 
 The **setting fields are platform-conditional**: a block carries only
 the dials the chosen platform actually has. Claude Code exposes an
-effort dial and a thinking toggle, so the example emits `EFFORT` and
-`THINKING` and no `MAX MODE` line at all — Claude Code has no Max Mode
-control, and a dial a surface lacks is omitted rather than reported as
-`Off`. Cursor is the inverse: it emits `MAX MODE` and no `EFFORT` /
+effort dial and, on a model that can turn thinking off such as Opus
+4.7, a thinking toggle, so the example emits `EFFORT` and `THINKING`
+and no `MAX MODE` line at all — Claude Code has no Max Mode control,
+and a dial a surface lacks is omitted rather than reported as `Off`.
+A model that always thinks (Opus 5.5, Sonnet 5.5, Haiku 5.5, the Fable
+models) has no thinking toggle on any surface, so its block carries
+`EFFORT` and no `THINKING`. Cursor is the inverse: it emits `MAX MODE` and no `EFFORT` /
 `THINKING`. `MODEL`, `BACKUP`, `PLATFORM`, `CONVERSATION`, and
 `RATIONALE` are always present.
 
@@ -636,7 +639,8 @@ complexity; `PLATFORM` and the settings that come with it are filled
 by the `<access-selection>` step, which depends on the subscriptions
 and API-key state declared in your `user-context.md`. Because the
 platform decides which dials exist, the field set varies per block:
-an effort/thinking surface emits `EFFORT` + `THINKING`, Cursor emits
+an effort/thinking surface emits `EFFORT` + `THINKING` (`EFFORT` alone
+for a model that always thinks), Cursor emits
 `MAX MODE`, and a dial the surface does not have is left out entirely
 instead of being reported as `Off` or `N/A`.
 

{roadmodel-0.2.87 → roadmodel-0.2.89}/README.md

@@ -274,10 +274,13 @@ multi-file blast radius without over-buying the ceiling.
 
 The **setting fields are platform-conditional**: a block carries only
 the dials the chosen platform actually has. Claude Code exposes an
-effort dial and a thinking toggle, so the example emits `EFFORT` and
-`THINKING` and no `MAX MODE` line at all — Claude Code has no Max Mode
-control, and a dial a surface lacks is omitted rather than reported as
-`Off`. Cursor is the inverse: it emits `MAX MODE` and no `EFFORT` /
+effort dial and, on a model that can turn thinking off such as Opus
+4.7, a thinking toggle, so the example emits `EFFORT` and `THINKING`
+and no `MAX MODE` line at all — Claude Code has no Max Mode control,
+and a dial a surface lacks is omitted rather than reported as `Off`.
+A model that always thinks (Opus 5.5, Sonnet 5.5, Haiku 5.5, the Fable
+models) has no thinking toggle on any surface, so its block carries
+`EFFORT` and no `THINKING`. Cursor is the inverse: it emits `MAX MODE` and no `EFFORT` /
 `THINKING`. `MODEL`, `BACKUP`, `PLATFORM`, `CONVERSATION`, and
 `RATIONALE` are always present.
 
@@ -385,7 +388,8 @@ complexity; `PLATFORM` and the settings that come with it are filled
 by the `<access-selection>` step, which depends on the subscriptions
 and API-key state declared in your `user-context.md`. Because the
 platform decides which dials exist, the field set varies per block:
-an effort/thinking surface emits `EFFORT` + `THINKING`, Cursor emits
+an effort/thinking surface emits `EFFORT` + `THINKING` (`EFFORT` alone
+for a model that always thinks), Cursor emits
 `MAX MODE`, and a dial the surface does not have is left out entirely
 instead of being reported as `Off` or `N/A`.
 

{roadmodel-0.2.87/roadmodel/data → roadmodel-0.2.89/docs}/catalog.json

@@ -1,9 +1,9 @@
 {
   "schema_version": "4",
   "output_contract_version": 2,
-  "generated_at_utc": "2026-10-20T01:36:08Z",
+  "generated_at_utc": "2026-10-21T02:30:06Z",
   "source_doc_sha256": {
-    "model-selector.txt": "2d46e000b8bc75345da7dd53eddfeab05baccbe36a91c2a804f12cbd5fbcb8c5",
+    "model-selector.txt": "e2ef6c5a18f05ff952fad9f576720b8fc4637f563f60ce5c077c5501fc21d1b7",
     "model-tier-cost-scale.md": "286d95759952ae60448114e5803c13b6de6aeb5d63a043b40aa6489175cbdc89"
   },
   "models": [
@@ -30,6 +30,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -55,6 +56,7 @@
       "superseded_by": "claude-fable-5.1",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": true,
       "retires_on": "2026-10-24"
     },
     {
@@ -80,6 +82,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": true,
       "retires_on": null
     },
     {
@@ -105,6 +108,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": "2026-10-20",
+      "always_thinks": true,
       "retires_on": null
     },
     {
@@ -130,6 +134,7 @@
       "superseded_by": "claude-opus-5-5",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -155,6 +160,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": true,
       "retires_on": null
     },
     {
@@ -180,6 +186,7 @@
       "superseded_by": "claude-sonnet-5-5",
       "superseded_on": "2026-10-02",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-11-01"
     },
     {
@@ -205,6 +212,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": true,
       "retires_on": null
     },
     {
@@ -230,6 +238,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -255,6 +264,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -280,6 +290,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -305,6 +316,7 @@
       "superseded_by": "deepseek-flash",
       "superseded_on": "2026-10-02",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-11-01"
     },
     {
@@ -330,6 +342,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -355,6 +368,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -380,6 +394,7 @@
       "superseded_by": "gemini-3.8-flash",
       "superseded_on": "2026-10-02",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-11-01"
     },
     {
@@ -405,6 +420,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": "2026-10-07",
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -430,6 +446,7 @@
       "superseded_by": "gemini-3.8-flash",
       "superseded_on": "2026-10-02",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-11-01"
     },
     {
@@ -455,6 +472,7 @@
       "superseded_by": "gemini-3.8-flash",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -480,6 +498,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": "2026-10-07",
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -505,6 +524,7 @@
       "superseded_by": "gemini-3.8-flash",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -530,6 +550,7 @@
       "superseded_by": "gemini-3.8-flash",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -555,6 +576,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -580,6 +602,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": "2026-10-20",
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -605,6 +628,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -630,6 +654,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -655,6 +680,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -680,6 +706,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -705,6 +732,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -730,6 +758,7 @@
       "superseded_by": "gpt-5.6-luna",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -755,6 +784,7 @@
       "superseded_by": "gpt-5.6-luna",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -780,6 +810,7 @@
       "superseded_by": "gpt-5.6-luna",
       "superseded_on": "2026-10-01",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-31"
     },
     {
@@ -805,6 +836,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -830,6 +862,7 @@
       "superseded_by": "gpt-5.6-luna",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -855,6 +888,7 @@
       "superseded_by": "gpt-5.6-terra",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -880,6 +914,7 @@
       "superseded_by": "gpt-5.6-terra",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -905,6 +940,7 @@
       "superseded_by": "gpt-5.6-terra",
       "superseded_on": "2026-10-01",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-31"
     },
     {
@@ -930,6 +966,7 @@
       "superseded_by": "gpt-5.6-terra",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -955,6 +992,7 @@
       "superseded_by": "gpt-5.6-luna",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -980,6 +1018,7 @@
       "superseded_by": "gpt-5.6-luna",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -1005,6 +1044,7 @@
       "superseded_by": "gpt-5.6-sol",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -1030,6 +1070,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1055,6 +1096,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1080,6 +1122,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1105,6 +1148,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1130,6 +1174,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1155,6 +1200,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1180,6 +1226,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": "2026-10-01",
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1205,6 +1252,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1230,6 +1278,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1255,6 +1304,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1280,6 +1330,7 @@
       "superseded_by": "grok-4.7",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -1305,6 +1356,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1330,6 +1382,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1355,6 +1408,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1380,6 +1434,7 @@
       "superseded_by": "mistral-small-4",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -1405,6 +1460,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1430,6 +1486,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1455,6 +1512,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": null,
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1480,6 +1538,7 @@
       "superseded_by": null,
       "superseded_on": null,
       "added_on": "2026-10-20",
+      "always_thinks": false,
       "retires_on": null
     },
     {
@@ -1505,6 +1564,7 @@
       "superseded_by": "claude-opus-5-5",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -1530,6 +1590,7 @@
       "superseded_by": "claude-opus-5-5",
       "superseded_on": "2026-09-24",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-10-24"
     },
     {
@@ -1555,6 +1616,7 @@
       "superseded_by": "claude-sonnet-5-5",
       "superseded_on": "2026-10-07",
       "added_on": null,
+      "always_thinks": false,
       "retires_on": "2026-11-06"
     }
   ],
@@ -1652,7 +1714,7 @@
       "exposes_max_mode": "no",
       "exposes_thinking": "yes",
       "exposes_orchestration": "yes",
-      "best_for": "Default for Claude coding or terminal tasks when a claude.ai Max subscription is active \u2014 $0 marginal cost until the Max budget is exhausted, full tool-use surface, runs as a CLI, IDE extension inside Cursor, native VS Code extension, and as of 2.1.170+ also ships Claude Fable 5 (Mythos-class) plus a first-class Claude in Chrome browser-control integration (GA in 2.1.198), with Claude Sonnet 5 now the default model (2.1.197+) at native 1M-token context; as of 2.1.219 Claude Opus 5 ships as the new default Opus (1M context, fast mode at $10/$50 per Mtok) and Opus 4.7 is removed from fast mode so `/fast` now applies to Opus 5 and Opus 4.8; 2.1.280 ships Claude Opus 5.5 as the new default Opus (1M context, $4/$20 per Mtok with $0.20/Mtok cache reads) and changes the Pro and Team Standard default model from Sonnet to Opus (matching Max / Team Premium / Enterprise); 2.1.220\u20132.1.280 are bug-fix / reliability / self-hosted-runner / UI-polish / plugin-safety / VS Code / Claude apps / AGENTS.md / auto-mode-server-classifier releases with no effort/thinking surface changes beyond the 2.1.267 `maxEffortLevel` cap and the 2.1.269 `CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS` (1\u2013256) knob for the Workflow tool's per-run concurrent-agent limit noted below (2.1.224 adds `claude self-hosted-runner` for turning your own machines into places where Claude Code web/mobile/desktop sessions can run, cross-session `SendMessage`, and archive-plugin sources; 2.1.225 adds gateway spend-limit reporting to the usage warning; 2.1.227 polishes the slash-command menu and fixes feature-flag evaluation for expired login tokens; 2.1.257 ships Claude Fable 5.1 as the new default Fable at 1M context and $10/$50 per Mtok; 2.1.259 adds `managedMcpServers` policy and `--permission-prompts none` for unattended headless hosts; 2.1.260 adds an inline `/diff` panel and a headless text form of `/advisor`; 2.1.261 adds `/skill-doctor` and `bashOutputMaxChars` / `taskOutputMaxChars` settings; 2.1.263 is a reliability release; 2.1.265 adds a `--plugin-dir` folder-of-plugins mode and tightens plugin path containment; 2.1.266 restores gateway/proxy behavior when `CLAUDE_CODE_USE_GATEWAY` is set alongside an API key or `apiKeyHelper`; 2.1.267 adds a `maxEffortLevel` setting \u2014 top-level or per model under `modelSettings` \u2014 that CAPS the effort level on every provider including Bedrock, Vertex, and Foundry while still letting users pick any lower level, plus `--system-prompt-snapshot off` for iterating on prompt text and a fix for `effort:` frontmatter on custom commands, skills, and subagents being ignored on models whose default effort is still pinned; 2.1.269 adds `claude plugin eval` for scored plugin eval suites, `/output-style [name]` to list and switch output styles (including over Remote Control and in headless sessions), a Bash-tool file-edit diff (setting `bashEditDiffEnabled`), `OTEL_METRICS_INCLUDE_REPOSITORY` for tagging OpenTelemetry metrics and events with `vcs.*` attributes, `CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS` to extend the LLM gateway `/v1/models` discovery timeout, and `CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS` (1\u2013256) to raise the Workflow tool's per-run concurrent-agent limit for inference-bound fan-outs \u2014 none of which change the `/effort` vocabulary; 2.1.270 fixes read-only git commands in Bash unexpectedly asking for permission after a session had been running for a while, a 2.1.269 regression, with no surface changes; 2.1.271 adds fast mode in Claude Code Remote (cloud and self-hosted runner) sessions where organization policy allows it, mouse support in the `/config` panel, per-command Bash / PowerShell / Monitor `allowed_domains` in auto mode with sandboxing, agent-frontmatter and `--agents` JSON `omitClaudeMd` to let custom / plugin subagents run without CLAUDE.md files (managed policy still loads), and `--accept-command <sha256>` for `claude plugin install` / `update`; 2.1.272 is a bug-fix / reliability release; 2.1.273 adds `x-claude-code-*` LLM-gateway request-hint headers behind `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1`, forking a `--remote-control` / `/remote-control` session from the Claude app as a local background session, and MCP-server-disconnected notifications, plus fixes for permission handling, credential/auth error messages, prompt-cache retention across `/login` / `/upgrade` / `/extra-usage`, and gateway 401 messaging \u2014 no effort/thinking surface changes; 2.1.274 adds a critical-memory-usage warning with recovery steps, `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` to bound how long the first non-interactive turn waits for connecting MCP servers, an `effort` attribute on the `claude_code.llm_request` OpenTelemetry trace span, plus assorted VS Code, Claude Code on the web, Claude Tag, and Code Review fixes and improvements \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.275 adds signed-in account confirmation for Claude apps gateway sign-in, a send-now key (ctrl+enter, or ctrl+x ctrl+s) that flushes queued messages mid-turn, syncing of claude.ai-account skills and plugins into terminal sessions (opt out with `syncClaudeAiSkills: false` / `syncClaudeAiPlugins: false`), `/plugin install <plugin> --marketplace <source>`, and a startup warning when `otelHeadersHelper` fails, plus a broad set of reliability and rendering fixes \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.276 is a hotfix for a 2.1.275 regression where every request behind a proxy or gateway failed with `400 \u2026 Input tag 'advisor_20260301'`, with no surface changes; 2.1.277 adds AGENTS.md fallback support (in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead \u2014 configurable under \"Project instructions\" in `/config`; extended by 2.1.281 to Bedrock, Vertex, Foundry, LLM gateways and telemetry-disabled sessions), `CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1` for Claude apps gateways whose only egress is a forward proxy, an optional `headers:` map on Claude apps gateway upstreams, plus assorted reliability, plugin, background-task, and VS Code / Claude Code on the web / Claude Tag fixes \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.278 changes auto mode for Claude API and Enterprise users, and on Bedrock, Vertex, Foundry and gateways, to default to the server-side classifier that does not charge for classifier overhead (opt out on Bedrock, Vertex, Foundry and gateways with `CLAUDE_CODE_AUTO_MODE_SERVER=0`; warns on billed fallback) and adds an `Auto mode server` row to `/status` showing whether this session's auto mode classifier runs on the server \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.280 ships Claude Opus 5.5 as the new default Opus model at 1M context and $4/$20 per Mtok, changes the Pro and Team Standard default model from Sonnet to Opus (matching Max / Team Premium / Enterprise), and stops Opus 4.7, Opus 4.8 and Fable 5 from holding their launch-default effort over an explicit `/effort`, `effortLevel`, project or managed setting \u2014 the `/effort` vocabulary itself is unchanged; 2.1.281\u20132.1.285 are reliability / plugin / gateway / VS Code / Claude Tag / Artifact releases, with 2.1.284 adding Claude Sonnet 5.5 as the default Sonnet on the Anthropic API (1M context, $2/$10 per Mtok) and making Ultracode its own `/effort` toggle, and 2.1.285 adding `claude --desktop` to open the Claude desktop app on the current directory and an `allowedProviders` managed setting). Exposes the full `/effort` dial (low/medium/high/xhigh/max \u2014 Opus 4.6 and Sonnet 4.6 top out at max with no xhigh step; Opus 5, Opus 5.5, Opus 4.7, Opus 4.8, Sonnet 5, Sonnet 5.5, Fable 5, and Fable 5.1 expose the full range; effort levels a model does not support fall back to the highest supported level at or below the requested one; deployments may set `maxEffortLevel` to cap the maximum reachable level on every provider), the Option+T/Alt+T, `alwaysThinkingEnabled`, and `MAX_THINKING_TOKENS=0` on/off controls, plus Ultracode (session-wide Dynamic Workflows tied to xhigh; since 2.1.284 its own `/effort` toggle \u2014 Tab or `/effort ultracode [on|off]` \u2014 that keeps the current effort level, with only `claude --effort ultracode` also setting xhigh; set via `/effort ultracode` or `\"ultracode\": true`; 2.1.202+ adds a `/config` \"Dynamic workflow size\" advisory guideline, 2.1.219 defaults it to medium (aim for fewer than 15 agents) with the `workflowSizeGuideline` settings key to set it from any settings file, and 2.1.269 adds `CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS` (1\u2013256) to raise the per-run concurrent-agent cap for the Workflow tool) and the per-turn `ultrathink` keyword (`think`/`think hard`/`think more` are not recognized).",
+      "best_for": "Default for Claude coding or terminal tasks when a claude.ai Max subscription is active \u2014 $0 marginal cost until the Max budget is exhausted, full tool-use surface, runs as a CLI, IDE extension inside Cursor, native VS Code extension, and as of 2.1.170+ also ships Claude Fable 5 (Mythos-class) plus a first-class Claude in Chrome browser-control integration (GA in 2.1.198), with Claude Sonnet 5 now the default model (2.1.197+) at native 1M-token context; as of 2.1.219 Claude Opus 5 ships as the new default Opus (1M context, fast mode at $10/$50 per Mtok) and Opus 4.7 is removed from fast mode so `/fast` now applies to Opus 5 and Opus 4.8; 2.1.280 ships Claude Opus 5.5 as the new default Opus (1M context, $4/$20 per Mtok with $0.20/Mtok cache reads) and changes the Pro and Team Standard default model from Sonnet to Opus (matching Max / Team Premium / Enterprise); 2.1.220\u20132.1.280 are bug-fix / reliability / self-hosted-runner / UI-polish / plugin-safety / VS Code / Claude apps / AGENTS.md / auto-mode-server-classifier releases with no effort/thinking surface changes beyond the 2.1.267 `maxEffortLevel` cap and the 2.1.269 `CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS` (1\u2013256) knob for the Workflow tool's per-run concurrent-agent limit noted below (2.1.224 adds `claude self-hosted-runner` for turning your own machines into places where Claude Code web/mobile/desktop sessions can run, cross-session `SendMessage`, and archive-plugin sources; 2.1.225 adds gateway spend-limit reporting to the usage warning; 2.1.227 polishes the slash-command menu and fixes feature-flag evaluation for expired login tokens; 2.1.257 ships Claude Fable 5.1 as the new default Fable at 1M context and $10/$50 per Mtok; 2.1.259 adds `managedMcpServers` policy and `--permission-prompts none` for unattended headless hosts; 2.1.260 adds an inline `/diff` panel and a headless text form of `/advisor`; 2.1.261 adds `/skill-doctor` and `bashOutputMaxChars` / `taskOutputMaxChars` settings; 2.1.263 is a reliability release; 2.1.265 adds a `--plugin-dir` folder-of-plugins mode and tightens plugin path containment; 2.1.266 restores gateway/proxy behavior when `CLAUDE_CODE_USE_GATEWAY` is set alongside an API key or `apiKeyHelper`; 2.1.267 adds a `maxEffortLevel` setting \u2014 top-level or per model under `modelSettings` \u2014 that CAPS the effort level on every provider including Bedrock, Vertex, and Foundry while still letting users pick any lower level, plus `--system-prompt-snapshot off` for iterating on prompt text and a fix for `effort:` frontmatter on custom commands, skills, and subagents being ignored on models whose default effort is still pinned; 2.1.269 adds `claude plugin eval` for scored plugin eval suites, `/output-style [name]` to list and switch output styles (including over Remote Control and in headless sessions), a Bash-tool file-edit diff (setting `bashEditDiffEnabled`), `OTEL_METRICS_INCLUDE_REPOSITORY` for tagging OpenTelemetry metrics and events with `vcs.*` attributes, `CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS` to extend the LLM gateway `/v1/models` discovery timeout, and `CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS` (1\u2013256) to raise the Workflow tool's per-run concurrent-agent limit for inference-bound fan-outs \u2014 none of which change the `/effort` vocabulary; 2.1.270 fixes read-only git commands in Bash unexpectedly asking for permission after a session had been running for a while, a 2.1.269 regression, with no surface changes; 2.1.271 adds fast mode in Claude Code Remote (cloud and self-hosted runner) sessions where organization policy allows it, mouse support in the `/config` panel, per-command Bash / PowerShell / Monitor `allowed_domains` in auto mode with sandboxing, agent-frontmatter and `--agents` JSON `omitClaudeMd` to let custom / plugin subagents run without CLAUDE.md files (managed policy still loads), and `--accept-command <sha256>` for `claude plugin install` / `update`; 2.1.272 is a bug-fix / reliability release; 2.1.273 adds `x-claude-code-*` LLM-gateway request-hint headers behind `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1`, forking a `--remote-control` / `/remote-control` session from the Claude app as a local background session, and MCP-server-disconnected notifications, plus fixes for permission handling, credential/auth error messages, prompt-cache retention across `/login` / `/upgrade` / `/extra-usage`, and gateway 401 messaging \u2014 no effort/thinking surface changes; 2.1.274 adds a critical-memory-usage warning with recovery steps, `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` to bound how long the first non-interactive turn waits for connecting MCP servers, an `effort` attribute on the `claude_code.llm_request` OpenTelemetry trace span, plus assorted VS Code, Claude Code on the web, Claude Tag, and Code Review fixes and improvements \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.275 adds signed-in account confirmation for Claude apps gateway sign-in, a send-now key (ctrl+enter, or ctrl+x ctrl+s) that flushes queued messages mid-turn, syncing of claude.ai-account skills and plugins into terminal sessions (opt out with `syncClaudeAiSkills: false` / `syncClaudeAiPlugins: false`), `/plugin install <plugin> --marketplace <source>`, and a startup warning when `otelHeadersHelper` fails, plus a broad set of reliability and rendering fixes \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.276 is a hotfix for a 2.1.275 regression where every request behind a proxy or gateway failed with `400 \u2026 Input tag 'advisor_20260301'`, with no surface changes; 2.1.277 adds AGENTS.md fallback support (in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead \u2014 configurable under \"Project instructions\" in `/config`; extended by 2.1.281 to Bedrock, Vertex, Foundry, LLM gateways and telemetry-disabled sessions), `CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1` for Claude apps gateways whose only egress is a forward proxy, an optional `headers:` map on Claude apps gateway upstreams, plus assorted reliability, plugin, background-task, and VS Code / Claude Code on the web / Claude Tag fixes \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.278 changes auto mode for Claude API and Enterprise users, and on Bedrock, Vertex, Foundry and gateways, to default to the server-side classifier that does not charge for classifier overhead (opt out on Bedrock, Vertex, Foundry and gateways with `CLAUDE_CODE_AUTO_MODE_SERVER=0`; warns on billed fallback) and adds an `Auto mode server` row to `/status` showing whether this session's auto mode classifier runs on the server \u2014 no changes to the `/effort` vocabulary or extended-thinking controls; 2.1.280 ships Claude Opus 5.5 as the new default Opus model at 1M context and $4/$20 per Mtok, changes the Pro and Team Standard default model from Sonnet to Opus (matching Max / Team Premium / Enterprise), and stops Opus 4.7, Opus 4.8 and Fable 5 from holding their launch-default effort over an explicit `/effort`, `effortLevel`, project or managed setting \u2014 the `/effort` vocabulary itself is unchanged; 2.1.281\u20132.1.285 are reliability / plugin / gateway / VS Code / Claude Tag / Artifact releases, with 2.1.284 adding Claude Sonnet 5.5 as the default Sonnet on the Anthropic API (1M context, $2/$10 per Mtok) and making Ultracode its own `/effort` toggle, and 2.1.285 adding `claude --desktop` to open the Claude desktop app on the current directory and an `allowedProviders` managed setting). Exposes the full `/effort` dial (low/medium/high/xhigh/max \u2014 Opus 4.6 and Sonnet 4.6 top out at max with no xhigh step; Opus 5, Opus 5.5, Opus 4.7, Opus 4.8, Sonnet 5, Sonnet 5.5, Haiku 5.5, Fable 5, and Fable 5.1 expose the full range; effort levels a model does not support fall back to the highest supported level at or below the requested one; deployments may set `maxEffortLevel` to cap the maximum reachable level on every provider), the Option+T/Alt+T, `alwaysThinkingEnabled`, and `MAX_THINKING_TOKENS=0` on/off controls on models that can turn thinking off (2.1.281 and 2.1.300 drop the Thinking switch for the always-thinking Opus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5 and Fable 5.1), plus Ultracode (session-wide Dynamic Workflows tied to xhigh; since 2.1.284 its own `/effort` toggle \u2014 Tab or `/effort ultracode [on|off]` \u2014 that keeps the current effort level, with only `claude --effort ultracode` also setting xhigh; set via `/effort ultracode` or `\"ultracode\": true`; 2.1.202+ adds a `/config` \"Dynamic workflow size\" advisory guideline, 2.1.219 defaults it to medium (aim for fewer than 15 agents) with the `workflowSizeGuideline` settings key to set it from any settings file, and 2.1.269 adds `CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS` (1\u2013256) to raise the per-run concurrent-agent cap for the Workflow tool) and the per-turn `ultrathink` keyword (`think`/`think hard`/`think more` are not recognized).",
       "effort_levels": [
         "low",
         "medium",

{roadmodel-0.2.87 → roadmodel-0.2.89}/docs/claude-commands/roadmap-refresh.md

@@ -220,7 +220,8 @@ For every phase whose roadmap does not exist yet — no
 selector for that session, quality first: it runs the Quality column,
 the strongest `planning` model the operator's access methods reach, at
 the deepest reasoning rung it exposes on its platform (`Max` in Claude
-Code), thinking on, never `Ultracode`, with a backup on its own platform
+Code), thinking on where the model has a Thinking toggle, never
+`Ultracode`, with a backup on its own platform
 and dial — unless `planning/user-context.md` states a rule for
 roadmap-writing sessions, which wins. Where `roadmodel` is installed,
 the table is the ladder `roadmodel ladder --category planning

{roadmodel-0.2.87/roadmodel/data → roadmodel-0.2.89/docs/claude-commands}/roadmap-step.md

@@ -98,7 +98,7 @@ posture changes, so read the table as **intent**, not as a string to
 match exactly — and record what actually ran.
 
 Print one line: `Step {{STEP}} requires: Model <M> · Platform <P> ·
-<the dials the table carries, e.g. Effort <E> · Thinking <T>, or
+<the dials the table carries, e.g. Effort <E>[ · Thinking <T>], or
 Intelligence <I>>. This session: <your own model> on <this surface>.`
 
 - **Ladder tables** (Cost / Balanced / Quality columns, roadmodel 0.2.86