mobygate 0.8.2 → 0.8.3

package/CHANGELOG.md

@@ -4,6 +4,81 @@ All notable changes to mobygate are documented here. Format loosely follows
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); version numbers are
 [Semantic Versioning](https://semver.org/).
 
+## [0.8.3] — 2026-04-28
+
+OpenClaw .26 compatibility, sonnet 1M context, and observability for
+silent model swaps. Found by upgrading mobygate to v0.8.1 on Windows
+during heavy multi-agent testing.
+
+### Fixed
+
+- **OpenClaw connector wrote deprecated `models.main` / `models.default`
+  keys**, which OpenClaw `2026.4.26+` outright rejects with `Unrecognized
+  keys: "main", "default"`. The gateway refused to start until
+  `openclaw doctor --fix` cleaned them up.
+
+  v0.8.3 connector now writes the modern path:
+  - `agents.defaults.model.primary` (the active default)
+  - `agents.defaults.models` (registered model id map)
+
+  Plus on every `plan()` it removes the deprecated top-level keys if a
+  previous mobygate version (v0.8.0–v0.8.2) wrote them. Re-running
+  `mobygate connect openclaw` after upgrading will repair any broken
+  config in place.
+
+  Why this didn't bite Mac users: hand-rolled configs that never went
+  through `mobygate connect`'s apply path were never written by the
+  bad code. It surfaced on Windows when `mobygate init` auto-wired
+  detected clients during a fresh upgrade.
+
+- **Sonnet 4.6 silently capped at 200k context.** v0.8.2 routed
+  `claude-sonnet-4-6` through directly but didn't append the `[1m]`
+  suffix the way opus 4.7 does, so the SDK ran sonnet at the default
+  200k window. Confirmed via `modelUsage.contextWindow=200000` in the
+  diagnostic logging.
+
+  Fix: `claude-sonnet-4-6` now maps to `claude-sonnet-4-6[1m]`. Verified
+  next-turn `modelUsage` shows `contextWindow: 1000000`. Matches the
+  capability we already advertise in `/v1/models`.
+
+  Side note: `claude-sonnet-4-6-200k` added as an explicit alias for
+  callers that want the cheaper 200k variant.
+
+### Added
+
+- **`[model-billed]` diagnostic log line.** Every successful (non-tool-
+  use-aborted) request now logs the SDK's `modelUsage` map showing
+  what model Anthropic actually billed against. Output looks like:
+
+  ```
+  [model-billed] requested=claude-sonnet-4-6[1m]
+  modelUsage={"claude-sonnet-4-6[1m]":{"inputTokens":3,"costUSD":0.029,
+              "contextWindow":1000000,...}}
+  ```
+
+  This was originally added as a temporary diagnostic to chase whether
+  Anthropic was silently swapping sonnet → opus. The data confirmed
+  no swap is happening — but the line is too useful to remove. Surfaces
+  cost-per-turn, actual context window, and any future silent model
+  changes the SDK might introduce. Low log volume (one line per
+  result message, ~50% of requests since tool_use turns abort
+  before result).
+
+  Bonus finding from this log: the SDK transparently uses **two models
+  per opus turn** — a haiku for fast intermediate work and opus for
+  the final response. Adds ~$0.024 per opus turn beyond what the
+  capture summary shows. Worth knowing for cost analysis.
+
+### Notes
+
+The "claude.ai/settings/usage Sonnet only stuck at 0%" mystery turned
+out to be a Claude Max plan accounting design: the "Sonnet only" bar
+is overflow that only ticks once "All models" is exhausted. On Max
+plans, sonnet usage rolls into the "All models" bar (which was
+climbing as expected). Not a mobygate bug — investigation surfaced
+the v0.8.2 [1m] context omission, which IS a mobygate bug, so net
+positive on the chase.
+
 ## [0.8.2] — 2026-04-28
 
 Multi-agent fixes. Found the day after v0.8.1 shipped, while testing

package/lib/anthropic.js

@@ -36,17 +36,23 @@ import { v4 as uuidv4 } from 'uuid';
  * against shape variations (the Claude Agent SDK sometimes nests these
  * under `.usage`, sometimes places them flat on the message). Returns
  * a complete usage shape with cache_read / cache_creation fields zeroed
- * out if absent. Used by the 4 mobygate handlers to populate response
- * captures and dashboard cache-hit metrics.
+ * out if absent, plus `modelUsage` (the SDK's per-model usage breakdown,
+ * keyed by the actual model name Anthropic billed against — useful for
+ * spotting silent model fallbacks where the requested model differs
+ * from what Anthropic actually ran).
+ *
+ * Used by the 4 mobygate handlers to populate response captures and
+ * dashboard cache-hit metrics.
  */
 export function extractSdkUsage(message) {
-  if (!message) return { input_tokens: 0, output_tokens: 0, cache_read_input_tokens: 0, cache_creation_input_tokens: 0 };
+  if (!message) return { input_tokens: 0, output_tokens: 0, cache_read_input_tokens: 0, cache_creation_input_tokens: 0, modelUsage: null };
   const u = message.usage || message;
   return {
     input_tokens: u.input_tokens || 0,
     output_tokens: u.output_tokens || 0,
     cache_read_input_tokens: u.cache_read_input_tokens || 0,
     cache_creation_input_tokens: u.cache_creation_input_tokens || 0,
+    modelUsage: message.modelUsage || null,
   };
 }
 

package/lib/connectors/openclaw.js

@@ -169,8 +169,12 @@ export const openclawConnector = {
       configPath: det.configPath,
       mobyProviderExists: !!providers[PROVIDER_NAME_OPENAI],
       mobyNativeProviderExists: !!providers[PROVIDER_NAME_ANTHROPIC],
-      currentMain: det.parsed?.models?.main || null,
-      currentDefault: det.parsed?.models?.default || null,
+      currentPrimary: det.parsed?.agents?.defaults?.model?.primary || null,
+      // Old keys: still surfaced so the user/dashboard can spot if a
+      // pre-v0.8.3 connector run left these around (they're invalid in
+      // OpenClaw .26+). A non-null value here is a "needs reconnect" hint.
+      deprecatedMain: det.parsed?.models?.main || null,
+      deprecatedDefault: det.parsed?.models?.default || null,
       shadowProviders, // pre-v0.8.0 entries pointing at our base URL
     };
   },
@@ -212,14 +216,52 @@ export const openclawConnector = {
           : null;
       if (preferredProvider) {
         const target = `${preferredProvider}/claude-opus-4-7`;
-        after.models.main = target;
-        after.models.default = target;
+
+        // Modern OpenClaw schema (>=2026.4.x): defaults live under
+        // `agents.defaults.model.primary` and `agents.defaults.models`.
+        // The old `models.main` / `models.default` top-level keys were
+        // valid in earlier OpenClaw versions but `.26+` rejects them
+        // ("Unrecognized keys: main, default"). v0.8.0/0.8.1 connector
+        // wrote the old shape and broke OpenClaw `.26` startup. Fixed
+        // in v0.8.3 by switching to the modern path + cleaning up any
+        // old keys it previously wrote.
+        if (!after.agents)                  after.agents = {};
+        if (!after.agents.defaults)         after.agents.defaults = {};
+        if (!after.agents.defaults.model)   after.agents.defaults.model = {};
+        if (!after.agents.defaults.models)  after.agents.defaults.models = {};
+
+        after.agents.defaults.model.primary = target;
+        // Register every model we surface in the provider so OpenClaw
+        // sees them in agents-list. Keep existing entries to preserve
+        // user-registered models (ollama, anthropic-direct, etc).
+        for (const m of MODELS_NATIVE_SURFACE) {
+          const id = `${preferredProvider}/${m.id}`;
+          if (!after.agents.defaults.models[id]) {
+            after.agents.defaults.models[id] = {};
+          }
+        }
+
+        // Cleanup: remove the deprecated top-level keys if a previous
+        // connector run (v0.8.0/0.8.1) wrote them. OpenClaw `.26`
+        // rejects the config outright if these are present.
+        if (after.models?.main !== undefined)    delete after.models.main;
+        if (after.models?.default !== undefined) delete after.models.default;
       }
     }
 
     const summary = diffSummary(
-      { providers: before.models?.providers, main: before.models?.main, default: before.models?.default },
-      { providers: after.models.providers,  main: after.models.main,  default: after.models.default },
+      {
+        providers: before.models?.providers,
+        primary: before.agents?.defaults?.model?.primary,
+        deprecatedMain: before.models?.main,
+        deprecatedDefault: before.models?.default,
+      },
+      {
+        providers: after.models.providers,
+        primary: after.agents?.defaults?.model?.primary,
+        deprecatedMain: after.models?.main,        // should be undefined post-fix
+        deprecatedDefault: after.models?.default,  // should be undefined post-fix
+      },
     );
 
     return {
@@ -263,14 +305,32 @@ export const openclawConnector = {
         if (providers[name]) { delete providers[name]; changed = true; }
       }
     }
-    // If main/default was pointing at us, blank them — let the user
-    // re-pick rather than guess at a replacement.
-    if (isMobyDefaultPointer(after.models?.main)) {
-      after.models.main = null;
+    // Modern path: if the agents.defaults.model.primary points at us,
+    // blank it out — let OpenClaw fall back to whatever default the
+    // user has configured otherwise.
+    const primary = after.agents?.defaults?.model?.primary;
+    if (isMobyDefaultPointer(primary)) {
+      after.agents.defaults.model.primary = null;
+      changed = true;
+    }
+    // Remove our model registrations from agents.defaults.models.
+    if (after.agents?.defaults?.models) {
+      for (const key of Object.keys(after.agents.defaults.models)) {
+        if (isMobyDefaultPointer(key)) {
+          delete after.agents.defaults.models[key];
+          changed = true;
+        }
+      }
+    }
+    // Legacy cleanup: remove deprecated top-level main/default if present
+    // (left over from v0.8.0/0.8.1 connector). OpenClaw .26 rejects them
+    // outright, so removing on disconnect is the right move.
+    if (after.models?.main !== undefined) {
+      delete after.models.main;
       changed = true;
     }
-    if (isMobyDefaultPointer(after.models?.default)) {
-      after.models.default = null;
+    if (after.models?.default !== undefined) {
+      delete after.models.default;
       changed = true;
     }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mobygate",
-  "version": "0.8.2",
+  "version": "0.8.3",
   "description": "OpenAI-compatible local proxy for Claude Max. The Möbius-strip gateway: OpenAI shape in, Claude Max out.",
   "type": "module",
   "main": "server.js",

package/server.js

@@ -186,13 +186,14 @@ const MODEL_MAP = {
   'claude-opus-4-7[1m]': 'claude-opus-4-7[1m]',
   'claude-opus-4-7-1m': 'claude-opus-4-7[1m]',
   'claude-opus-4-7-200k': 'claude-opus-4-7',
-  'claude-sonnet-4': 'claude-sonnet-4-6',         // current latest sonnet
-  'claude-sonnet-4-5': 'claude-sonnet-4-5-20250929', // explicit request for older 4-5
-  'claude-sonnet-4-6': 'claude-sonnet-4-6',       // SDK now supports natively; was retired-mapped before v0.8.2
+  'claude-sonnet-4': 'claude-sonnet-4-6[1m]',         // current latest sonnet, 1M context
+  'claude-sonnet-4-5': 'claude-sonnet-4-5-20250929',  // explicit request for older 4-5
+  'claude-sonnet-4-6': 'claude-sonnet-4-6[1m]',       // SDK supports natively; [1m] unlocks 1M context (same pattern as opus 4.7)
+  'claude-sonnet-4-6-200k': 'claude-sonnet-4-6',      // explicit 200k variant
   'claude-haiku-4': 'claude-haiku-4-5-20251001',
   'claude-haiku-4-5': 'claude-haiku-4-5-20251001',
   'opus': 'claude-opus-4-7[1m]',
-  'sonnet': 'claude-sonnet-4-6',                  // current latest sonnet
+  'sonnet': 'claude-sonnet-4-6[1m]',                  // current latest sonnet, 1M context
   'haiku': 'claude-haiku-4-5-20251001',
 };
 
@@ -590,6 +591,7 @@ async function handleStreaming(req, res, body, requestId, sessionKey) {
         outputTokens = usage.output_tokens;
         cacheReadTokens = usage.cache_read_input_tokens;
         cacheCreateTokens = usage.cache_creation_input_tokens;
+        console.log(`  [model-billed] requested=${resolvedModel} modelUsage=${JSON.stringify(usage.modelUsage || '(none)')}`);
         break;
       }
     }
@@ -795,6 +797,7 @@ async function handleNonStreaming(res, body, requestId, sessionKey) {
         outputTokens = usage.output_tokens;
         cacheReadTokens = usage.cache_read_input_tokens;
         cacheCreateTokens = usage.cache_creation_input_tokens;
+        console.log(`  [model-billed] requested=${resolvedModel} modelUsage=${JSON.stringify(usage.modelUsage || '(none)')}`);
         if (message.subtype) stopReason = message.subtype;
         break;
       }
@@ -1009,6 +1012,7 @@ async function handleAnthropicNonStreaming(res, body, requestId, sessionKey) {
         outputTokens = usage.output_tokens;
         cacheReadTokens = usage.cache_read_input_tokens;
         cacheCreateTokens = usage.cache_creation_input_tokens;
+        console.log(`  [model-billed] requested=${resolvedModel} modelUsage=${JSON.stringify(usage.modelUsage || '(none)')}`);
         stopReason = mapStopReason(message);
         break;
       }
@@ -1254,6 +1258,7 @@ async function handleAnthropicStreaming(req, res, body, requestId, sessionKey) {
         outputTokens = usage.output_tokens;
         cacheReadTokens = usage.cache_read_input_tokens;
         cacheCreateTokens = usage.cache_creation_input_tokens;
+        console.log(`  [model-billed] requested=${resolvedModel} modelUsage=${JSON.stringify(usage.modelUsage || '(none)')}`);
         if (!toolUseEmitted) stopReason = mapStopReason(message);
         break;
       }