okstra 0.201.0 → 0.201.1

package/docs/cli.md

@@ -799,7 +799,16 @@ Each GLM child process uses `https://api.z.ai/api/anthropic` and its own model/a
 
 The runtime rejects a missing `ZAI_API_KEY` before starting the worker. Catalog visibility does not verify the account's model entitlement or remaining quota. The installed Claude Code version and Z.ai account must support the selected model. See [Z.ai's Claude Code setup](https://docs.z.ai/devpack/tool/claude) and [Coding Plan usage policy](https://docs.z.ai/devpack/usage-policy) for provider requirements.
 
-GLM response model identities are recorded as `zai/<model>`; a startup model label alone is not treated as proof of the served model. The final Claude Code usage event supplies input, output, cache-creation, and cache-read counters. Repeated dispatches are summed by their status files. Missing usage stays unavailable, and billing-cost estimates are omitted rather than using Anthropic prices or treating subscription usage as metered API spend.
+GLM response model identities are recorded as `zai/<model>`; a startup model label alone is not treated as proof of the served model. The final Claude Code usage event supplies input, output, cache-creation, and cache-read counters. Repeated dispatches are summed by their status files. Costs use Z.ai's public API token prices regardless of whether the account uses a subscription or metered API billing. Missing usage or an unknown model price stays unavailable.
+
+The [official API prices](https://docs.z.ai/guides/overview/pricing), checked on 2026-09-14, are USD per million tokens:
+
+| Model | Input | Cached input | Output |
+|---|---:|---:|---:|
+| `glm-5.3` | $1.40 | $0.26 | $4.40 |
+| `glm-5.3-flash` | $0.15 | $0.03 | $0.50 |
+
+Cache-creation tokens use the input rate; cache-read tokens use the cached-input rate. Z.ai currently lists cached-input storage as free for a limited time. The reported cost is the API-equivalent token cost, not the subscription invoice. Regression coverage is in `tests/adapters/accounting/test_cli_provider_transcripts.py` and `tests/adapters/providers/test_provider_registry.py`.
 
 ## `okstra` Node CLI — introspection subcommands
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "okstra",
-  "version": "0.201.0",
+  "version": "0.201.1",
   "description": "Host-aware multi-provider cross-verification orchestrator runtime and agent skills.",
   "license": "MIT",
   "author": "devonshin",

package/runtime/BUILD.json

@@ -1,5 +1,5 @@
 {
-  "package": "0.201.0",
-  "builtAt": "2026-09-13T22:07:32.212Z",
+  "package": "0.201.1",
+  "builtAt": "2026-09-13T23:39:01.225Z",
   "repoRoot": "/home/runner/work/okstra/okstra"
 }

package/runtime/python/okstra_ctl/adapters/providers/zai/adapter.py

@@ -15,10 +15,12 @@ from okstra_ctl.domain.worker_presentation import JsonEvents
 from okstra_ctl.domain.worker_stream import content_block_events
 
 ZAI_MODELS = {
-    name: ModelSpec(name, label, name)
-    for name, label in (
-        ("glm-5.3", "GLM-5.3"),
-        ("glm-5.3-flash", "GLM-5.3 Flash"),
+    # 입력·캐시 입력·출력 USD/100만 토큰, 2026-09-14 공식 단가 확인.
+    # https://docs.z.ai/guides/overview/pricing
+    name: ModelSpec(name, label, name, pricing=pricing)
+    for name, label, pricing in (
+        ("glm-5.3", "GLM-5.3", (1.40, 0.26, 4.40)),
+        ("glm-5.3-flash", "GLM-5.3 Flash", (0.15, 0.03, 0.50)),
     )
 }
 

package/runtime/python/okstra_token_usage/collect.py

@@ -702,10 +702,16 @@ def _cli_usage_block(provider: str, totals: dict, session_paths: list[Path]) ->
     if totals.get("model"):
         block["model"] = totals["model"]
         block["cliModel"] = totals["model"]
-    if provider in _THREE_RATE_PROVIDERS:
+    if provider in _THREE_RATE_PROVIDERS or provider == "zai":
+        input_tokens = totals.get("inputTokens", 0) or 0
+        if provider == "zai":
+            # GLM 상태는 캐시 토큰을 입력과 별도로 보고한다. 공통 단가는
+            # 캐시 포함 입력을 받으며, 캐시 생성은 일반 입력 단가로 계산한다.
+            cached_input = totals.get("cacheReadTokens", 0) or 0
+            input_tokens += (totals.get("cacheCreationTokens", 0) or 0) + cached_input
         rates = (
             totals.get("model"),
-            totals.get("inputTokens", 0) or 0,
+            input_tokens,
             cached_input,
             totals.get("outputTokens", 0) or 0,
         )

package/runtime/python/okstra_token_usage/pricing.py

@@ -243,6 +243,7 @@ _THREE_RATE_TABLES = {
     "codex": CODEX_PRICING,
     "grok": GROK_PRICING,
     "kimi": KIMI_PRICING,
+    "zai": catalog_pricing("zai"),
 }