okstra 0.65.0 → 0.66.0

package/docs/kr/cli.md

@@ -296,7 +296,7 @@ scripts/okstra.sh --task-type implementation-planning --workers claude,codex --p
 ```
 
 > 모든 `--*-model` 플래그는 `scripts/okstra_ctl/models.py` 의 provider 별 mapping 에 등록된 alias 만 허용합니다. 등록되지 않은 값은 `UnknownModelError` 로 즉시 거부됩니다 (manifest 의 `modelExecutionValue` 와 실제 실행값 불일치로 인한 contract-violation 을 사전에 차단). 허용값:
-> - Claude (`--lead-model` / `--claude-model` / `--report-writer-model`): `opus`, `opus-4-7`, `claude-opus-4-7`, `opus-4-6`, `claude-opus-4-6`, `sonnet`, `sonnet-4-6`, `claude-sonnet-4-6`, `haiku`, `haiku-4-5`, `claude-haiku-4-5`, `claude-haiku-4-5-20251001`
+> - Claude (`--lead-model` / `--claude-model` / `--report-writer-model`): `fable`, `fable-5`, `claude-fable-5`, `opus`, `opus-4-8`, `claude-opus-4-8`, `opus-4-7`, `claude-opus-4-7`, `opus-4-6`, `claude-opus-4-6`, `sonnet`, `sonnet-4-6`, `claude-sonnet-4-6`, `haiku`, `haiku-4-5`, `claude-haiku-4-5`, `claude-haiku-4-5-20251001`
 > - Codex (`--codex-model`): `gpt-5.5`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.3-codex`, `gpt-5.2`, `codex-auto-review`
 > - Gemini (`--gemini-model`): `auto`, `pro`, `gemini-3-flash-preview`, `gemini-3-pro-preview` (그리고 `gemini auto` / `gemini pro` 별칭)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "okstra",
-  "version": "0.65.0",
+  "version": "0.66.0",
   "description": "Multi-agent cross-verification orchestrator runtime + Claude Code skills.",
   "license": "MIT",
   "author": "devonshin",

package/runtime/BUILD.json

@@ -1,5 +1,5 @@
 {
-  "package": "0.65.0",
-  "builtAt": "2026-06-10T08:26:08.228Z",
+  "package": "0.66.0",
+  "builtAt": "2026-06-10T09:21:55.603Z",
   "repoRoot": "/home/runner/work/okstra/okstra"
 }

package/runtime/agents/SKILL.md

@@ -225,7 +225,7 @@ Spawn **analysis workers only** in the same turn (Phase 4 in Teams mode; Phase 5
 
 **Agent `name` on dispatch (BLOCKING — token-usage attribution depends on it).** Every analysis-worker `Agent(...)` call MUST set `name: "<workerId>-worker"` — `name: "claude-worker"` / `name: "codex-worker"` / `name: "gemini-worker"` — exactly as the report-writer dispatch sets `name: "report-writer"` ([okstra-report-writer](./skills/okstra-report-writer/SKILL.md)). The Agent harness records this `name` as `agentName` in the subagent session jsonl, and the Phase 7 token collector matches each worker's session by that `agentName` (`okstra_token_usage/collect.py`). A worker dispatched **without** `name` produces a session with no `agentName`; the collector cannot attribute it and records the worker as `source: "unavailable"` even though the session exists and is team-tagged (observed in `dev-9692` error-analysis: `claude`/`codex` workers dispatched without `name` → both `unavailable`, while the named `report-writer` collected normally). Convergence reverify dispatches keep the prefix (`<workerId>-worker-reverify-r<N>`); implementation executor/verifier variants keep `<workerId>-worker` / `<workerId>-executor`.
 
-**Agent `model:` on dispatch (BLOCKING — assignment is otherwise ignored).** The `Claude worker` `Agent(...)` call MUST set `model: "<family token of that role's modelExecutionValue>"` (`opus` / `sonnet` / `haiku`), per [okstra-team-contract](./skills/okstra-team-contract/SKILL.md) "Model Assignment Rules" #3–#4. The claude-worker definition is `model: inherit`, so omitting this parameter makes the worker silently run on the lead's model instead of its manifest assignment — the assigned-vs-actual deviation. `Codex worker` / `Gemini worker` are exempt: their CLI model is applied via the wrapper's own `--model` argument, so leave their Agent `model:` at `inherit` (rule #5).
+**Agent `model:` on dispatch (BLOCKING — assignment is otherwise ignored).** The `Claude worker` `Agent(...)` call MUST set `model: "<family token of that role's modelExecutionValue>"` (`fable` / `opus` / `sonnet` / `haiku`), per [okstra-team-contract](./skills/okstra-team-contract/SKILL.md) "Model Assignment Rules" #3–#4. The claude-worker definition is `model: inherit`, so omitting this parameter makes the worker silently run on the lead's model instead of its manifest assignment — the assigned-vs-actual deviation. `Codex worker` / `Gemini worker` are exempt: their CLI model is applied via the wrapper's own `--model` argument, so leave their Agent `model:` at `inherit` (rule #5).
 
 The no-`team_name` fallback (Phase 5) is only legal when team-state's `teamCreate.status` is `"error"` for this run. If `teamCreate` is missing or `attempted: false`, the correct action when an Agent dispatch is rejected for a missing team is to GO BACK to Phase 3 and call `TeamCreate` — never to strip `team_name` and continue.
 

package/runtime/python/okstra_ctl/models.py

@@ -8,7 +8,12 @@ from __future__ import annotations
 from dataclasses import dataclass
 
 CLAUDE_MAPPING = {
+    "fable": ("fable", "fable"),
+    "fable-5": ("fable-5", "claude-fable-5"),
+    "claude-fable-5": ("fable-5", "claude-fable-5"),
     "opus": ("opus", "opus"),
+    "opus-4-8": ("opus-4-8", "claude-opus-4-8"),
+    "claude-opus-4-8": ("opus-4-8", "claude-opus-4-8"),
     "opus-4-7": ("opus-4-7", "claude-opus-4-7"),
     "claude-opus-4-7": ("opus-4-7", "claude-opus-4-7"),
     "opus-4-6": ("opus-4-6", "claude-opus-4-6"),

package/runtime/python/okstra_ctl/render_final_report.py

@@ -358,7 +358,8 @@ def _enforce_schema(data: dict) -> None:
 # 구체버전 계열로 돌았는지" 가독성만 준다. CLI 가 실제 고른 버전과 다를 수
 # 있으나 표시이므로 실행에는 무해하다. 새 버전이 나오면 여기만 갱신한다.
 _DISPLAY_CONCRETE_CLAUDE = {
-    "opus": "claude-opus-4-7",
+    "fable": "claude-fable-5",
+    "opus": "claude-opus-4-8",
     "sonnet": "claude-sonnet-4-6",
     "haiku": "claude-haiku-4-5",
 }

package/runtime/python/okstra_ctl/wizard.py

@@ -90,7 +90,7 @@ _STAGE_SCOPED_TASK_TYPES = ("implementation", "final-verification")
 CANONICAL_BASE_REFS = ["main", "dev", "staging", "preprod", "prod"]
 BASE_REF_FREE_INPUT_TOKEN = "__free_input__"
 
-CLAUDE_MODEL_OPTIONS = ["default", "opus", "sonnet", "haiku"]
+CLAUDE_MODEL_OPTIONS = ["default", "fable", "opus", "sonnet", "haiku"]
 CODEX_MODEL_OPTIONS = ["default", "gpt-5.5", "gpt-5.4", "gpt-5.4-mini"]
 GEMINI_MODEL_OPTIONS = ["default", "gemini-3-pro-preview", "gemini-3-flash-preview", "auto"]
 

package/runtime/python/okstra_token_usage/pricing.py

@@ -4,9 +4,9 @@ Pricing is matched by substring against the model id recorded in the session
 transcript, so keys must reflect the *actual* model id form emitted by each
 provider:
 
-  * Anthropic — `claude-opus-4-*`, `claude-sonnet-4-*`, `claude-haiku-4-5-*`,
-    `claude-3-5-sonnet-*`, `claude-3-5-haiku-*`, `claude-3-opus-*`,
-    `claude-3-haiku-*`.
+  * Anthropic — `claude-fable-5*`, `claude-opus-4-*`, `claude-sonnet-4-*`,
+    `claude-haiku-4-5-*`, `claude-3-5-sonnet-*`, `claude-3-5-haiku-*`,
+    `claude-3-opus-*`, `claude-3-haiku-*`.
   * OpenAI / Codex — `gpt-5*`, `gpt-4o*`, `gpt-4*`.
   * Google / Gemini — `gemini-2.5-pro*`, `gemini-2.5-flash*`, `gemini-2.0-flash*`.
 
@@ -45,7 +45,11 @@ CLAUDE_PRICING = {
     "3-sonnet":   (3.0, 3.75, 0.30, 15.0),     # legacy 3 Sonnet
     "3-haiku":    (0.25, 0.30, 0.03, 1.25),    # Haiku 3
 
+    # Claude Fable 5 (tier above Opus).
+    "fable-5":    (10.0, 12.5, 1.0, 50.0),     # Fable 5 (cache prices derived from ratios)
+
     # Claude 4 point releases (explicit so future divergence is easy to see).
+    "opus-4-8":   (5.0, 6.25, 0.50, 25.0),     # Opus 4.8 (cache prices derived from ratios)
     "opus-4-7":   (5.0, 6.25, 0.50, 25.0),     # Opus 4.7 (cache prices derived from ratios)
     "opus-4-6":   (5.0, 6.25, 0.50, 25.0),     # Opus 4.6 (legacy; pricing matches 4.7 per Anthropic)
     "sonnet-4-6": (3.0, 3.75, 0.30, 15.0),     # Sonnet 4.6 (cache prices derived from ratios)

package/runtime/skills/okstra-schedule/SKILL.md

@@ -56,15 +56,15 @@ Subsequent `okstra <subcmd>` calls self-bootstrap their Python path, so this ski
 
 This skill performs cross-task synthesis (multi-task classification, dependency reasoning, phase placement, Gantt/timeline assembly) which benefits substantially from Opus-class reasoning. The frontmatter `model: opus` field above instructs supporting Claude Code harness versions to switch automatically; if the harness ignores it, this gate catches the case explicitly.
 
-1. Inspect the active session model. The model is shown in the status line, accessible via `/model`, and embedded in the runtime context as the model name (e.g. `claude-opus-4-7`, `claude-sonnet-4-6`, `claude-haiku-4-5-*`).
-2. If the active model is **Opus-class** (`claude-opus-*`): proceed to Step 1.
+1. Inspect the active session model. The model is shown in the status line, accessible via `/model`, and embedded in the runtime context as the model name (e.g. `claude-fable-5`, `claude-opus-4-7`, `claude-sonnet-4-6`, `claude-haiku-4-5-*`).
+2. If the active model is **Opus-class or above** (`claude-opus-*`, `claude-fable-*`): proceed to Step 1.
 3. If the active model is **Sonnet or Haiku-class**: STOP and output the following message verbatim, then wait for user response:
    ```
    okstra-schedule는 Opus-class 모델에서 실행하는 것을 권장합니다 (현재: <active-model>).
    /model opus 로 전환 후 다시 호출하시거나, 'sonnet으로 진행' 이라고 명시하시면 그대로 실행합니다.
    ```
 4. If the user explicitly insists on the lower model ("sonnet으로 진행", "그대로 진행", "force", or similar): proceed to Step 1, but prepend a single-line warning at the top of the generated schedule file: `> ⚠️ Generated with <model> (not Opus). Cross-task synthesis quality may be reduced.`
-5. Skip this gate ONLY when the harness has clearly enforced `model: opus` from the frontmatter — verifiable by the active model already being Opus-class without manual switching.
+5. Skip this gate ONLY when the harness has clearly enforced `model: opus` from the frontmatter — verifiable by the active model already being Opus-class or above without manual switching.
 
 ### Step 1: Resolve task-group and collect tasks
 

package/runtime/skills/okstra-team-contract/SKILL.md

@@ -38,7 +38,7 @@ okstra tasks are always operated using the `Claude lead` + required worker team
 1. `resultContract.requiredWorkerRoles` in `task-manifest.json` (and the lead model metadata) is the canonical source. There is no role-level fallback — a missing assignment is a manifest defect, not a license to invent one.
 2. If `modelExecutionValue` differs from `model`, use `modelExecutionValue` during execution.
 3. **Spawn-time enforcement for in-process Claude subagents (BLOCKING).** `Claude worker` and `Report writer worker` are in-process Claude subagents whose agent definitions declare `model: inherit` (`agents/workers/claude-worker.md`, `agents/workers/report-writer-worker.md`). `inherit` follows the **lead's** runtime model, NOT the role's assignment — so an opus assignment silently runs on a sonnet lead. To make the assignment binding (not merely declared), lead MUST pass an explicit `model:` parameter on every `Agent(...)` dispatch for these two roles, derived from that role's `modelExecutionValue`. The dispatch `model:` parameter overrides the `inherit` frontmatter; the frontmatter remains only as the fallback when no parameter is supplied. Omitting `model:` on a Claude-side dispatch is a contract violation that reproduces the assigned-vs-actual model deviation.
-4. **`modelExecutionValue` → Agent `model:` family token.** The Agent tool's `model` parameter accepts family tokens only — `opus` / `sonnet` / `haiku` (an exact version such as `claude-opus-4-7` is NOT a valid value). Map by prefix: a `modelExecutionValue` of `opus*` / `claude-opus*` → `"opus"`, `sonnet*` / `claude-sonnet*` → `"sonnet"`, `haiku*` / `claude-haiku*` → `"haiku"`. This enforces the assignment at **family granularity** (opus vs sonnet vs haiku); the exact version within a family is still inherited from the lead session and cannot be pinned via this parameter.
+4. **`modelExecutionValue` → Agent `model:` family token.** The Agent tool's `model` parameter accepts family tokens only — `fable` / `opus` / `sonnet` / `haiku` (an exact version such as `claude-opus-4-7` is NOT a valid value). Map by prefix: a `modelExecutionValue` of `fable*` / `claude-fable*` → `"fable"`, `opus*` / `claude-opus*` → `"opus"`, `sonnet*` / `claude-sonnet*` → `"sonnet"`, `haiku*` / `claude-haiku*` → `"haiku"`. This enforces the assignment at **family granularity** (fable vs opus vs sonnet vs haiku); the exact version within a family is still inherited from the lead session and cannot be pinned via this parameter.
 5. **Codex / Gemini wrappers are out of scope for the Agent `model:` rule.** `Codex worker` / `Gemini worker` subagents are Claude wrappers that shell out to an external CLI; the role's `modelExecutionValue` is already applied via the CLI's own `--model <modelExecutionValue>` argument (see `agents/workers/_cli-wrapper-template.md`). The Agent `model:` parameter for these wrappers would only set the wrapper's own orchestration model, not the external CLI's model — leave it at `inherit` and do NOT map it from `modelExecutionValue`.
 
 ### Dynamic Worker Role Determination