kakan/codex-subagent-router
1
0 Fork 0
Code Issues Pull Requests Packages Projects Releases 6 Wiki Activity

Prepare 2.3.0 with GPT-6.1 Sol preferred routing

Browse Source
This commit is contained in:
Kakan committed 2026-10-06 12:35:10 +08:00
1 parent 9474064daf
commit 369384a3eb
13 files changed
+81 -38
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

VERSION
+1 -1
View File
@@ -1 +1 @@
2.2.0 2.3.0
docs/behavior-scenarios.md
+21 -2
View File
@@ -22,14 +22,14 @@ These are static review cases, not a record that a model executed them. Use them
| User says never delegate | Stay local even if a skill is selected implicitly | | User says never delegate | Stay local even if a skill is selected implicitly |
| Authorized batch of known-source records with fixed checks | Consider GPT-6 Luna low/medium; batch useful work, no fan-out quota | | Authorized batch of known-source records with fixed checks | Consider GPT-6 Luna low/medium; batch useful work, no fan-out quota |
| Authorized settled patch with contained failure and behavior checks | Consider GPT-6 Luna medium/high; parent reviews diff and checks | | Authorized settled patch with contained failure and behavior checks | Consider GPT-6 Luna medium/high; parent reviews diff and checks |
| Ordinary bug requires causal investigation across files | Select GPT-6 Sol medium directly; no mandatory Luna attempt | | Ordinary bug requires causal investigation across files | Select GPT-6.1 Sol medium directly when exposed; no mandatory Luna attempt |
| Tiny diff changes a shared authorization contract | Parent owns the contract; size alone does not justify Luna | | Tiny diff changes a shared authorization contract | Parent owns the contract; size alone does not justify Luna |
| Host exposes GPT-6 Sol and GPT-5.6 Luna only | Resolve each route independently and report exact IDs; no invented GPT-6 Luna | | Host exposes GPT-6 Sol and GPT-5.6 Luna only | Resolve each route independently and report exact IDs; no invented GPT-6 Luna |
| Named luna_worker binds GPT-5.6 Luna/max | Binding is not GPT-6; use a supported overridable role or report the fallback | | Named luna_worker binds GPT-5.6 Luna/max | Binding is not GPT-6; use a supported overridable role or report the fallback |
| Host exposes Terra but no adequate Sol route | Do not automatically select Terra; work locally or disclose capability gap | | Host exposes Terra but no adequate Sol route | Do not automatically select Terra; work locally or disclose capability gap |
| User explicitly pins GPT-5.6 Terra | Preserve the pin; retirement from defaults does not authorize overriding the user | | User explicitly pins GPT-5.6 Terra | Preserve the pin; retirement from defaults does not authorize overriding the user |
| User requires GPT-6 Luna but schema lacks it | Report unavailability before dependent dispatch; no silent older-generation substitute | | User requires GPT-6 Luna but schema lacks it | Report unavailability before dependent dispatch; no silent older-generation substitute |
| Luna is 20x cheaper at equal Standard token volumes | Do not infer equal task quality, twenty retries, more slots or Codex quota savings | | Luna input/output are 20x cheaper at equal Standard token volumes | Do not infer equal task quality, twenty retries, more slots or Codex quota savings; cached input has a different ratio |
| Luna needs repeated parent correction | Reassess contract and choose Sol directly; count parent rework | | Luna needs repeated parent correction | Reassess contract and choose Sol directly; count parent rework |
| Missing actual usage, requested model known | Cost and observed identity remain unknown; no fabricated benchmark | | Missing actual usage, requested model known | Cost and observed identity remain unknown; no fabricated benchmark |
| Several fixed independent reads, no delegation request | Use supported tool concurrency; no child just to wait on I/O | | Several fixed independent reads, no delegation request | Use supported tool concurrency; no child just to wait on I/O |
@@ -53,6 +53,25 @@ These are static review cases, not a record that a model executed them. Use them
| Several independent ready slices, parent only has later synthesis, host permits this dispatch | Run useful children concurrently and integrate on return; no universal requirement to invent simultaneous parent work | | Several independent ready slices, parent only has later synthesis, host permits this dispatch | Run useful children concurrently and integrate on return; no universal requirement to invent simultaneous parent work |
| Host explicitly requires useful concurrent parent work | Honor that stricter requirement even when the fleet policy otherwise permits parent waiting | | Host explicitly requires useful concurrent parent work | Honor that stricter requirement even when the fleet policy otherwise permits parent waiting |
## 2.3 Sol version and migration scenarios
These are static expected decisions, not live executions or benchmarks.
| Scenario | Expected behavior |
| --- | --- |
| Authorized investigation; schema exposes both gpt-6.1-sol and gpt-6-sol, no pin | Prefer gpt-6.1-sol medium; record the exact requested ID and keep observed identity unknown unless evidenced |
| Host exposes GPT-6 Sol but not 6.1; no exact version requirement | Use an adequate explicit gpt-6-sol compatibility route; do not claim it ran 6.1 |
| Parent picker has 6.1 but child schema lacks it | Check child support independently; use an adequate explicit compatibility route or local work |
| User requires GPT-6.1 Sol, child schema lacks it | Report the exact gap before dependent dispatch; no silent old Sol substitute |
| User pins gpt-6-sol or current parent is older Sol | Preserve the selection; installing the skill does not migrate active settings |
| A fixed sol_worker binds gpt-6-sol | Keep its real identity; use a supported override only when authorized and compatible with fork rules |
| Authorized API migration from old Sol with medium | Keep medium; do not raise effort solely because the version changed |
| Authorized API migration uses none/minimal or Chat Completions tools | Start at supported low for effort and use Responses for tools; do not claim compatibility without those changes |
| Desktop exposes Ultra for 6.1 | Follow actual host controls; do not send ultra as an API reasoning effort |
| Mostly cached input and cost-sensitive routing | Use the cached-input category: Luna is 1/10 of 6.1 Sol, not 1/20; total task savings need actual usage |
| New Sol is officially positioned near Astra | Use Sol for its work shape; retain useful Astra depth without mandatory participation or an unmeasured equivalence claim |
| Archived synthetic packet requests gpt-6-sol | Validate it unchanged; never rewrite its requested identity as 6.1 |
## 2.0 escalation scenarios (manual forward evaluation) ## 2.0 escalation scenarios (manual forward evaluation)
These expectations are not recorded live-agent outcomes. These expectations are not recorded live-agent outcomes.
docs/releases/2.3.0.md
+17
View File
@@ -0,0 +1,17 @@
# 2.3.0 — GPT-6.1 Sol 首选路由
## 变化
- 新通用工程会话、常规开发、调查和复杂分析推荐 GPT-6.1 Sol / medium，按需 high。配置示例、技能入口、全局提示词和当前证据说明同步使用精确 ID `gpt-6.1-sol`。
- 保留 GPT-6 Luna 的有界执行与 GPT-6 Astra 的最困难综合工作。6.1 的接近 Astra 表现来自官方定位，不能代替本项目对真实任务的质量、延迟与总成本评测。
- 每条路线独立检查宿主支持。6.1 不可用时显式选择足够胜任的 GPT-6 Sol 或 GPT-5.6 Sol；旧模型不是别名，用户精确指定的版本、已有配置和活动主模型继续保留。
- 补充 API 迁移边界：保留受支持的 effort；6.1 不支持 none/minimal，以 low 作为替代起点并验证。工具调用须使用 Responses，Desktop/CLI Ultra 等参数不能直接复制到 API。
- 更新 2026-10-06 价格快照：6.1 输入/输出仍为 2/10 美元每百万 token，缓存输入由旧 Sol 的 0.20 降为 0.10。缓存比例与其他 token 类别分别计算，API 单价不代表 Codex 套餐消耗。
## 兼容与验证边界
证据 schema 1/2、决策 schema 1 和安装流程不变。历史发行说明与旧模型合成夹具保持原样，校验器继续接受旧版模型记录。静态行为场景覆盖混合宿主、精确版本要求、固定角色、effort 与计费差异；这些场景不声称执行过真实子智能体或性能基准。
安装仍默认预览，不切换活动模型、不改 `config.toml`，不扩大委派权限或宿主容量。全局提示词安装仍须单独选择 `--include-prompt` 并审阅替换差异。版本号不表示远端标签或 Release 已创建。
依据：[GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol)、[Codex 模型](https://learn.chatgpt.com/docs/models)、[迁移指南](https://developers.openai.com/api/docs/guides/latest-model?model=gpt-6.1-sol)、[API 价格](https://developers.openai.com/api/docs/pricing)。
prompts/AGENTS.md
+3 -3
View File
@@ -1,6 +1,6 @@
# Codex 工程协作约定 # Codex 工程协作约定
适用于 GPT-6 Astra / Sol / Luna；保留用户选定的主模型，以宿主指令优先级和适用项目规则为准。明确目标、关键约束与验收，常规实施由模型判断；固定步骤只用于真实风险或脆弱流程。 适用于 GPT-6 Luna / GPT-6.1 Sol / GPT-6 Astra；旧版 Sol/Luna 按宿主能力显式兼容。保留用户选定的主模型，以宿主指令优先级和适用项目规则为准。明确目标、关键约束与验收，常规实施由模型判断；固定步骤只用于真实风险或脆弱流程。
## 1. 结果与权限 ## 1. 结果与权限
@@ -36,7 +36,7 @@
## 5. 模型与子智能体 ## 5. 模型与子智能体
- 新通用工程会话建议 GPT-6 Sol / medium，复杂推理按需 high，保留用户已选模型。Astra 可前置处理高影响困难方案、跨系统综合和独立反例审查，不以先失败为条件，也不固定参与每次规划或审查。 - 新通用工程会话建议 GPT-6.1 Sol / medium，复杂推理按需 high，保留用户已选模型。Astra 可在相对 Sol 的深度有价值时前置处理高影响困难方案、跨系统综合和独立反例审查，不以先失败为条件，也不固定参与每次规划或审查。
- 规划后、关键检查失败、共享合同变化及验收前复核疑难。同类失败两次暂停切片，严重反例立即处理；问题 ID 与计数不随换 agent 清零。按可复现证据裁决，主线程不理解或无法验证的关键结论不得验收；专家续轮须有新证据或可测试进展，解决后回到最低足够路线。 - 规划后、关键检查失败、共享合同变化及验收前复核疑难。同类失败两次暂停切片，严重反例立即处理；问题 ID 与计数不随换 agent 清零。按可复现证据裁决，主线程不理解或无法验证的关键结论不得验收；专家续轮须有新证据或可测试进展，解决后回到最低足够路线。
- 主线程负责关键路径、共享决定、冲突裁决、整合与最终验收；权限判断、生产写入、PR/merge/deploy 由主线程串行处理。 - 主线程负责关键路径、共享决定、冲突裁决、整合与最终验收；权限判断、生产写入、PR/merge/deploy 由主线程串行处理。
@@ -44,7 +44,7 @@
- 有可并行的独立产物时默认尽早分工，主线程优先同步推进关键路径；宿主允许时，也可让多个独立子任务并行，主线程等待后集中整合。不等再次点名 agent，不要求事先证明加速。优先用 Luna 分担有界收集、比对、验证、局部审查和已定方案修改，避免主线程包办所有机械工作。 - 有可并行的独立产物时默认尽早分工，主线程优先同步推进关键路径；宿主允许时，也可让多个独立子任务并行，主线程等待后集中整合。不等再次点名 agent，不要求事先证明加速。优先用 Luna 分担有界收集、比对、验证、局部审查和已定方案修改，避免主线程包办所有机械工作。
- 按真实可用槽位、独立工作量与验收能力展开并行，不固定只开一两个。维护简短待办队列，结果返回后及时验收并复用或补充任务，不等整批结束；主线程计入槽位时必须预留。出现验收积压、资源争用或限流时先消化已有工作。 - 按真实可用槽位、独立工作量与验收能力展开并行，不固定只开一两个。维护简短待办队列，结果返回后及时验收并复用或补充任务，不等整批结束；主线程计入槽位时必须预留。出现验收积压、资源争用或限流时先消化已有工作。
- 按完整任务块而非微小步骤分工；单条命令可直接用工具。没有独立工作、主线程下一步立即依赖结果或任务太小时本地完成；不凑舰队数量，不重复派同一任务，不递归无限扩张。 - 按完整任务块而非微小步骤分工；单条命令可直接用工具。没有独立工作、主线程下一步立即依赖结果或任务太小时本地完成；不凑舰队数量，不重复派同一任务，不递归无限扩张。
- 默认三档：Luna 做输入有界、合同已定、易验收且失败可控的工作；Sol 做开发、调查与复杂分析；Astra 做最困难的独立综合。Terra 退出推荐与自动回退，用户显式指定仍须尊重。 - 默认三档：GPT-6 Luna 做输入有界、合同已定、易验收且失败可控的工作；GPT-6.1 Sol 做开发、调查与复杂分析；GPT-6 Astra 做最困难的独立综合。精确模型与 effort 以宿主 schema 为准；旧版 Sol 是显式兼容路径，不是 6.1 的别名。Terra 退出推荐与自动回退，用户显式指定仍须尊重。
- 路由、成本、合同与生命周期以 codex-subagent-router 为维护入口，服从真实工具 schema；技能缺失时继续可行本地工作。支持选择时显式指定足够的模型与 effort，核对 fork 限制；不逐级试错，不假装切换参数。 - 路由、成本、合同与生命周期以 codex-subagent-router 为维护入口，服从真实工具 schema；技能缺失时继续可行本地工作。支持选择时显式指定足够的模型与 effort，核对 fork 限制；不逐级试错，不假装切换参数。
- 默认共享工作区，明确文件与语义写集；工作角色不证明隔离。复用适合的子任务，中断失效任务并核对状态；完成、验收、关闭和释放槽位分别判断，无 close 工具不虚构关闭。 - 默认共享工作区，明确文件与语义写集；工作角色不证明隔离。复用适合的子任务，中断失效任务并核对状态；完成、验收、关闭和释放槽位分别判断，无 close 工具不虚构关闭。
readme.md
+10 -9
View File
@@ -1,8 +1,8 @@
# Codex Subagent Router # Codex Subagent Router
当前版本：**2.2.0**。GPT-6 三档路由、积极 Luna 舰队与任务连续性适配；保留 2.1 的 Astra 前置介入、滚动调度及证据裁决。见 [2.2 发行说明](docs/releases/2.2.0.md)、[舰队调度](skills/codex-subagent-router/references/fleet.md) 和 [专家介入与裁决](skills/codex-subagent-router/references/escalation.md)。 当前版本：**2.3.0**。Sol 首选升级为 GPT-6.1 Sol，保留 Luna 舰队、Astra 按需介入、滚动调度及证据裁决。见 [2.3 发行说明](docs/releases/2.3.0.md)、[舰队调度](skills/codex-subagent-router/references/fleet.md) 和 [专家介入与裁决](skills/codex-subagent-router/references/escalation.md)。
面向 **GPT-6 Luna / Sol / Astra** 的 Codex 路由技能与工程提示词。把可独立完成的工作交给合适的模型，并让触发、运行状态、证据与最终责任保持清楚。Terra 已退出推荐与自动回退路线；旧宿主按实际能力显式兼容。 面向 **GPT-6 Luna / GPT-6.1 Sol / GPT-6 Astra** 的 Codex 路由技能与工程提示词。把可独立完成的工作交给合适的模型，并让触发、运行状态、证据与最终责任保持清楚。Terra 已退出推荐与自动回退路线；旧宿主按实际能力显式兼容。
这是供 Codex 读取的技能和可选提示词，附带证据校验、安装与测试工具。它不包含常驻调度器，也不会自行调用模型、修改模型配置或开启并行权限。 这是供 Codex 读取的技能和可选提示词，附带证据校验、安装与测试工具。它不包含常驻调度器，也不会自行调用模型、修改模型配置或开启并行权限。
@@ -85,20 +85,20 @@ python3 scripts/install.py --include-prompt --apply
| --- | --- | | --- | --- |
| 固定来源收集、枚举和检查 | GPT-6 Luna low，多步任务 medium | | 固定来源收集、枚举和检查 | GPT-6 Luna low，多步任务 medium |
| 有界转换、分类、已定方案补丁 | GPT-6 Luna medium，必要时 high | | 有界转换、分类、已定方案补丁 | GPT-6 Luna medium，必要时 high |
| 常规实现、调试和跨文件调查 | GPT-6 Sol medium | | 常规实现、调试和跨文件调查 | GPT-6.1 Sol medium |
| 复杂分析、设计和关键语义证据 | GPT-6 Sol medium/high | | 复杂分析、设计和关键语义证据 | GPT-6.1 Sol medium/high |
| 最困难的独立综合任务 | GPT-6 Astra medium/high | | 最困难的独立综合任务 | GPT-6 Astra medium/high |
| 共享决定、最终整合与验收 | 当前主线程 | | 共享决定、最终整合与验收 | 当前主线程 |
优先考虑 Luna 的四个条件：输入有界、合同已定、正确性易检查、失败影响可控。需要调查、设计取舍或跨文件因果推理时直接用 Sol；最困难的独立综合可直接用 Astra，不要求从便宜模型逐级尝试。主线程保持用户选择，负责判断与整合。 优先考虑 Luna 的四个条件：输入有界、合同已定、正确性易检查、失败影响可控。需要调查、设计取舍或跨文件因果推理时直接用 Sol；最困难的独立综合可直接用 Astra，不要求从便宜模型逐级尝试。主线程保持用户选择，负责判断与整合。
Terra 原先承担的常规开发、调试和调查统一交给 Sol。新版 Sol 的价格使单独维护 Terra 中间档的收益不足以支撑本技能继续推荐它；这是工程策略，仍需真实任务校准。缺少 GPT-6 的宿主可显式选用足够胜任的 GPT-5.6 Sol/Luna 或本地执行，不自动回退到 Terra，也不改写用户已有配置。 推荐路线中的 Sol 指 GPT-6.1 Sol；官方将其定位为以较低成本提供接近 Astra 的复杂任务能力。本项目把它作为开发、调查、复杂分析和新工程会话的起点，Astra 仍用于深度有额外价值的最困难综合工作；这不是本项目实测的性能结论。Terra 原先承担的工作继续交给 Sol。6.1 不可用时，可按实际 schema 显式使用足够胜任的 GPT-6 Sol，再考虑 GPT-5.6 Sol；Luna 的版本独立判断，不自动回退到 Terra，也不改写用户已有配置或精确模型要求。
2026-09-23 核实的 API Standard 短上下文单价（美元/百万 token）：Luna 输入 0.10、输出 0.50；Sol 输入 2、输出 10；Astra 输入 10、输出 50。相同 token 用量与计费条件下，Luna 为 Sol 的 1/20，Sol 为 Astra 的 1/5。此比例不等于实际任务节省或 Codex 套餐消耗；核算须包含主线程、重试与验收。[价格来源及成本校准](skills/codex-subagent-router/references/model-economics.md)。低价不增加并行权限，也不意味着应开启更多子任务。 2026-10-06 核实的 API Standard 短上下文单价（美元/百万 token）：Luna 输入 0.10、输出 0.50；GPT-6.1 Sol 输入 2、输出 10；Astra 输入 10、输出 50。对输入和输出的相同 token 用量，Luna 为 Sol 的 1/20，Sol 为 Astra 的 1/5；缓存输入另算。GPT-6.1 Sol 缓存输入为 0.10，是旧 GPT-6 Sol 的一半。此比例不等于实际任务节省或 Codex 套餐消耗；核算须包含主线程、重试与验收。[价格来源及成本校准](skills/codex-subagent-router/references/model-economics.md)。低价不增加并行权限，也不意味着应开启更多子任务。
按实时工具 schema 检查模型、effort、fork、并发槽位和工作区。API 模型目录不证明当前子智能体支持。可选配置示例见 [运行时参考](skills/codex-subagent-router/references/platforms.md)，安装工具不会应用它。 按实时工具 schema 检查模型、effort、fork、并发槽位和工作区。API 模型目录不证明当前子智能体支持。可选配置示例见 [运行时参考](skills/codex-subagent-router/references/platforms.md)，安装工具不会应用它。
新通用工程会话建议 GPT-6 Sol / medium，复杂推理按需 high，保留用户已选主模型。Astra 可前置处理影响多个后续任务的困难决策、跨系统证据及独立高影响反例，不必先失败。专家按问题、产物和退出条件设界；新增证据或可测试进展支持续轮，没有进展则暂停专题。 新通用工程会话建议 GPT-6.1 Sol / medium，复杂推理按需 high，保留用户已选主模型。迁移保留受支持的 effort；6.1 的 API 支持 low/medium/high/xhigh/max，不支持 none/minimal，旧设置为这些值时从 low 起点评测。工具调用使用 Responses；Desktop/CLI 的 Ultra 等控制按宿主单独核对。Astra 可前置处理影响多个后续任务的困难决策、跨系统证据及独立高影响反例，不必先失败。专家按问题、产物和退出条件设界；新增证据或可测试进展支持续轮，没有进展则暂停专题。
同类验收失败两次暂停切片并重新分类，严重反例立即处理；问题计数跨 agent 保留。证据统一基线后裁决，主线程必须理解并验证关键结论。证据 schema 1/2 与决策 schema 1 保持兼容，累计咨询次数不得倒退；示例见 [决策记录](examples/decisions/resolved.json)。 同类验收失败两次暂停切片并重新分类，严重反例立即处理；问题计数跨 agent 保留。证据统一基线后裁决，主线程必须理解并验证关键结论。证据 schema 1/2 与决策 schema 1 保持兼容，累计咨询次数不得倒退；示例见 [决策记录](examples/decisions/resolved.json)。
@@ -141,9 +141,10 @@ python3 scripts/install.py --include-prompt --check
- [OpenAI 模型目录](https://developers.openai.com/api/docs/models) - [OpenAI 模型目录](https://developers.openai.com/api/docs/models)
- [GPT-6 家族指南](https://developers.openai.com/api/docs/guides/latest-model) - [GPT-6 家族指南](https://developers.openai.com/api/docs/guides/latest-model)
- [GPT-6 Sol](https://developers.openai.com/api/docs/models/gpt-6-sol) - [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol)
- [Codex 模型与可用性](https://learn.chatgpt.com/docs/models)
- [GPT-6 Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) - [GPT-6 Luna](https://developers.openai.com/api/docs/models/gpt-6-luna)
- [API 价格](https://developers.openai.com/api/docs/pricing) - [API 价格](https://developers.openai.com/api/docs/pricing)
- [Codex 子智能体](https://learn.chatgpt.com/zh-Hans/docs/agent-configuration/subagents) - [Codex 子智能体](https://learn.chatgpt.com/zh-Hans/docs/agent-configuration/subagents)
模型与价格依据核对日期：2026-09-23；原有宿主配置示例的核对日期见运行时参考。模型分工属于工程策略；宿主真实能力与实际任务证据优先。 模型与价格依据核对日期：2026-10-06；原有宿主配置键与工作方式参考保留各自核对日期。模型分工属于工程策略；宿主真实能力与实际任务证据优先。
skills/codex-subagent-router/SKILL.md
+6 -6
View File
@@ -1,11 +1,11 @@
--- ---
name: codex-subagent-router name: codex-subagent-router
description: Route authorized Codex subagents across GPT-6 Luna, Sol and Astra; manage ownership, lifecycle and evidence. Use for delegation, routing decisions or subagent audits. Discovery alone does not authorize spawning. description: Route authorized Codex subagents across GPT-6 Luna, GPT-6.1 Sol and GPT-6 Astra; manage ownership, lifecycle and evidence. Use for delegation, routing decisions or subagent audits. Discovery alone does not authorize spawning.
--- ---
# Codex Subagent Router # Codex Subagent Router
Version 2.2.0. For new general engineering sessions recommend GPT-6 Sol / medium, with high for demonstrated reasoning needs. Preserve the selected parent. Use Astra proactively for high-leverage difficult decisions, independent counterexample reviews and residual hard reasoning; neither prior failure nor a model quota is required. Version 2.3.0. For new general engineering sessions recommend GPT-6.1 Sol / medium, with high for demonstrated reasoning needs. Preserve the selected parent. Use Astra proactively for high-leverage difficult decisions, independent counterexample reviews and residual hard reasoning when its depth adds value over Sol; neither prior failure nor a model quota is required.
Make delegation useful, observable and bounded. Preserve the selected parent model. The parent owns the critical path, shared decisions, integration and final acceptance. This skill neither changes configuration nor grants external permissions. Make delegation useful, observable and bounded. Preserve the selected parent model. The parent owns the critical path, shared decisions, integration and final acceptance. This skill neither changes configuration nor grants external permissions.
@@ -50,8 +50,8 @@ Stay local for a trivial task, no useful parallel benefit, an immediate dependen
| --- | --- | | --- | --- |
| Known-source collection, fixed checks, logs | GPT-6 Luna low; medium for multi-step work | | Known-source collection, fixed checks, logs | GPT-6 Luna low; medium for multi-step work |
| Bounded classification, conversion, settled patch with fixed checks | GPT-6 Luna medium; high for local reasoning | | Bounded classification, conversion, settled patch with fixed checks | GPT-6 Luna medium; high for local reasoning |
| Everyday implementation, debugging, locating/correlating artifacts | GPT-6 Sol medium | | Everyday implementation, debugging, locating/correlating artifacts | GPT-6.1 Sol medium |
| Bounded complex analysis, design or financial/security evidence | GPT-6 Sol medium/high | | Bounded complex analysis, design or financial/security evidence | GPT-6.1 Sol medium/high |
| High-leverage difficult design, cross-system synthesis, independent high-impact counterexample review | GPT-6 Astra medium/high | | High-leverage difficult design, cross-system synthesis, independent high-impact counterexample review | GPT-6 Astra medium/high |
| Shared decisions, integration and external/final gates | Current parent, serial | | Shared decisions, integration and external/final gates | Current parent, serial |
@@ -59,11 +59,11 @@ Luna is the first candidate when inputs are bounded, the contract is settled, co
These are starting heuristics, not measured task-cost rankings. Lower prices broaden the useful Luna workload; fill supported capacity with useful work under existing authorization, never infer extra host slots from price. Pick sufficient capability directly; do not escalate through every model. Missing access/data and tool failures need diagnosis, not a stronger model. After two same-class failures, stop that slice and return the evidence to the parent; escalate earlier when the contract no longer fits. Preserve useful evidence on handoff instead of restarting discovery. These are starting heuristics, not measured task-cost rankings. Lower prices broaden the useful Luna workload; fill supported capacity with useful work under existing authorization, never infer extra host slots from price. Pick sufficient capability directly; do not escalate through every model. Missing access/data and tool failures need diagnosis, not a stronger model. After two same-class failures, stop that slice and return the evidence to the parent; escalate earlier when the contract no longer fits. Preserve useful evidence on handoff instead of restarting discovery.
Resolve exact IDs from the child-tool schema: prefer `gpt-6-luna`, `gpt-6-sol`, `gpt-6-astra` only when exposed. GPT-5.6 models are explicit compatibility routes, not aliases for GPT-6. For a legacy-only host use [routing boundaries](references/routing-matrix.md); do not silently substitute an explicitly required generation. A role bound to GPT-5.6 Luna remains GPT-5.6 even when named `luna_worker`. Resolve exact IDs from the child-tool schema: prefer `gpt-6-luna`, `gpt-6.1-sol`, `gpt-6-astra` only when exposed. Sol means GPT-6.1 Sol in recommended routes; `gpt-6-sol` and GPT-5.6 models are explicit compatibility choices, not aliases. Use [routing boundaries](references/routing-matrix.md) when a preferred route is absent; do not silently substitute an explicitly required version. A role bound to GPT-6 Sol or GPT-5.6 Luna keeps that exact binding despite its name.
Retire Terra from recommended routes and automatic fallbacks: Sol owns ordinary implementation and investigation. Preserve explicitly pinned models and existing configuration; editing this skill does not authorize rewriting them. Retire Terra from recommended routes and automatic fallbacks: Sol owns ordinary implementation and investigation. Preserve explicitly pinned models and existing configuration; editing this skill does not authorize rewriting them.
Use the lowest adequate supported effort. Use none only for straightforward extraction/conversion when the host exposes it and checks cover the result; low/medium are the usual starts for tool work. Use xhigh/max for a concrete depth need or an explicit compatible role requirement; ultra only when exposed and justified by the workload, never inferred from API support. Model choice and working role are separate. A role named "explorer" is not proof of sandbox isolation. Use the lowest adequate supported effort. GPT-6.1 Sol's API supports low/medium/high/xhigh/max, not none/minimal. Preserve a supported effort when migrating; use low as the starting point for a previously unsupported none/minimal setting and verify representative work. Use none only for straightforward extraction/conversion on a model and host that expose it, such as GPT-6 Luna; low/medium are the usual starts for tool work. Use xhigh/max for a concrete depth need or an explicit compatible role requirement; ultra only when exposed and justified by the workload, never inferred from API support. Model choice and working role are separate. A role named "explorer" is not proof of sandbox isolation.
At dispatch, specify model AND effort when the host permits selection. Otherwise omitted settings may inherit the parent or configured defaults. Prefer a self-contained contract and no history fork; use bounded history only when necessary. Respect full-history/override incompatibilities. Never claim prompt text changed a runtime parameter. At dispatch, specify model AND effort when the host permits selection. Otherwise omitted settings may inherit the parent or configured defaults. Prefer a self-contained contract and no history fork; use bounded history only when necessary. Respect full-history/override incompatibilities. Never claim prompt text changed a runtime parameter.
skills/codex-subagent-router/references/escalation.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Sol-led escalation and evidence adjudication # Sol-led escalation and evidence adjudication
Recommend GPT-6 Sol / medium for new general engineering sessions; preserve an explicit user selection. The selected parent owns planning, difficult implementation, integration and acceptance. Sol handles routine implementation and investigation; Luna handles settled, checkable work. Terra is retired from recommendations and automatic fallbacks. Astra contributes both proactive high-leverage analysis and residual hard reasoning, without becoming a mandatory stage for every task. These are hypotheses to calibrate, not benchmark results. Recommend GPT-6.1 Sol / medium for new general engineering sessions; preserve an explicit user selection. The selected parent owns planning, difficult implementation, integration and acceptance. Sol handles routine implementation and investigation; Luna handles settled, checkable work. Terra is retired from recommendations and automatic fallbacks. Astra contributes proactive high-leverage analysis and residual hard reasoning when additional depth over Sol is useful, without becoming a mandatory stage for every task. Official near-Astra positioning does not prove equivalence on a particular task. These are hypotheses to calibrate, not benchmark results.
## Reassess at observable checkpoints ## Reassess at observable checkpoints
skills/codex-subagent-router/references/evidence-packet.md
+1 -1
View File
@@ -30,7 +30,7 @@ This fragment illustrates shape; it is not a real tool receipt:
"tool": "collaboration.spawn_agent", "tool": "collaboration.spawn_agent",
"child_id": "synthetic-child", "child_id": "synthetic-child",
"status": "completed", "status": "completed",
"requested": {"model": "gpt-6-sol", "role": "explorer", "effort": "medium"}, "requested": {"model": "gpt-6.1-sol", "role": "explorer", "effort": "medium"},
"observed": {"model": "unknown", "role": "unknown", "effort": "unknown"}, "observed": {"model": "unknown", "role": "unknown", "effort": "unknown"},
"identity_source": "unknown" "identity_source": "unknown"
} }
skills/codex-subagent-router/references/fleet.md
+1 -1
View File
@@ -20,7 +20,7 @@ If the next action is immediately dependent on an unassigned task, keep it local
## Choose a formation for the task ## Choose a formation for the task
- Independent investigation: several focused investigators may cover distinct sources, consumers or falsifiable hypotheses. They should not all produce the same broad summary. - Independent investigation: several focused investigators may cover distinct sources, consumers or falsifiable hypotheses. They should not all produce the same broad summary.
- Settled implementation: multiple GPT-6 Luna workers own bounded, settled, independently checkable slices; use GPT-6 Sol directly when implementation requires investigation or design judgment. Shared registries, schema and generated outputs require one owner even when paths differ. - Settled implementation: multiple GPT-6 Luna workers own bounded, settled, independently checkable slices; use GPT-6.1 Sol directly when implementation requires investigation or design judgment. Shared registries, schema and generated outputs require one owner even when paths differ.
- Difficult consequential decision: an Astra specialist analyzes the bounded uncertainty while the parent and other workers advance unaffected work. Gate dependent implementation on the parent's accepted contract. Read [expert intervention](escalation.md) for triggers and progress-based continuation. - Difficult consequential decision: an Astra specialist analyzes the bounded uncertainty while the parent and other workers advance unaffected work. Gate dependent implementation on the parent's accepted contract. Read [expert intervention](escalation.md) for triggers and progress-based continuation.
- Independent review: assign a stable commit/artifact and the relevant requirements, without supplying the parent's preferred verdict. Review can overlap unrelated work; stale observations must be rechecked before acceptance. - Independent review: assign a stable commit/artifact and the relevant requirements, without supplying the parent's preferred verdict. Review can overlap unrelated work; stale observations must be rechecked before acceptance.
skills/codex-subagent-router/references/gpt6-adaptation.md
+2
View File
@@ -2,6 +2,8 @@
Checked 2026-09-23. Read only when these capabilities affect the task. This reference adapts the routing policy; it does not configure a harness or grant permissions. Checked 2026-09-23. Read only when these capabilities affect the task. This reference adapts the routing policy; it does not configure a harness or grant permissions.
GPT-6.1 Sol migration checked 2026-10-06: use the exact `gpt-6.1-sol` ID only when the relevant host exposes it. Preserve supported effort; its API rejects none/minimal and requires Responses for tools. Start at low when replacing an unsupported effort and verify representative work. [Model specifications](https://developers.openai.com/api/docs/models/gpt-6.1-sol) and [migration guidance](https://developers.openai.com/api/docs/guides/latest-model?model=gpt-6.1-sol) take precedence over older GPT-6 Sol assumptions. The workflow capability sections below retain their own original verification date; do not infer per-model or host support from family membership.
## Prompt shape and task granularity ## Prompt shape and task granularity
The official [skills and prompts guidance](https://developers.openai.com/blog/rethinking-skills-and-prompts-for-gpt-6-astra) recommends precise discovery descriptions, progressive disclosure and fewer rigid recipes. Apply that here by giving a goal, constraints, ownership and acceptance; leave implementation choices open unless a contract or fragile operation requires an exact procedure. Put API mechanics here instead of expanding every task prompt. The official [skills and prompts guidance](https://developers.openai.com/blog/rethinking-skills-and-prompts-for-gpt-6-astra) recommends precise discovery descriptions, progressive disclosure and fewer rigid recipes. Apply that here by giving a goal, constraints, ownership and acceptance; leave implementation choices open unless a contract or fragile operation requires an exact procedure. Put API mechanics here instead of expanding every task prompt.
skills/codex-subagent-router/references/model-economics.md
+6 -6
View File
@@ -1,6 +1,6 @@
# Model economics # Model economics
Read for cost-sensitive routing or when revising defaults. Checked 2026-09-23; recheck official prices before a later price-dependent decision. This is an API reference snapshot, not a Codex subscription quota or billing estimate. Read for cost-sensitive routing or when revising defaults. Checked 2026-10-06; recheck official prices before a later price-dependent decision. This is an API reference snapshot, not a Codex subscription quota or billing estimate.
## Verified price basis ## Verified price basis
@@ -9,18 +9,18 @@ USD per million tokens, Standard processing, prompts up to 272K input tokens:
| Exact model ID | Input | Cached input | Cache write | Output | | Exact model ID | Input | Cached input | Cache write | Output |
| --- | ---: | ---: | ---: | ---: | | --- | ---: | ---: | ---: | ---: |
| gpt-6-luna | 0.10 | 0.01 | 0.125 | 0.50 | | gpt-6-luna | 0.10 | 0.01 | 0.125 | 0.50 |
| gpt-6-sol | 2.00 | 0.20 | 2.50 | 10.00 | | gpt-6.1-sol | 2.00 | 0.10 | 2.50 | 10.00 |
| gpt-6-astra | 10.00 | 1.00 | 12.50 | 50.00 | | gpt-6-astra | 10.00 | 1.00 | 12.50 | 50.00 |
Source: [OpenAI pricing](https://developers.openai.com/api/docs/pricing). For equal token volumes and the same billing category, Luna is 1/20 of Sol and 1/100 of Astra; Sol is 1/5 of Astra. These are arithmetic price ratios, not observed savings, speed or success rates. Source: [OpenAI pricing](https://developers.openai.com/api/docs/pricing). At equal token volumes, Luna is 1/20 of GPT-6.1 Sol for input, cache writes and output, and 1/10 for cached input. GPT-6.1 Sol is 1/5 of Astra for input, cache writes and output, and 1/10 for cached input. Luna is 1/100 of Astra in all four categories. These are arithmetic price ratios, not observed savings, speed or success rates.
Long prompts above 272K input tokens charge 2x input/cache rates and 1.5x output for the full request. Processing tier, tools and regional processing can change the bill. Do not multiply Codex subscription usage by API prices or assume a Desktop service tier follows the Standard table. Long prompts above 272K input tokens charge 2x input/cache rates and 1.5x output for the full request. Processing tier, tools and regional processing can change the bill. Do not multiply Codex subscription usage by API prices or assume a Desktop service tier follows the Standard table.
Retirement comparison: [GPT-5.6 Terra](https://developers.openai.com/api/docs/models/gpt-5.6-terra) lists input 2.00, cached input 0.20 and output 12.00 under the same short-context Standard basis. GPT-6 Sol has equal input/cache-read rates and a 16.7% lower output rate (10 vs 12). Terra therefore offers no token-rate saving in these categories; this does not prove equal token use, latency or quality per task. Compared with [GPT-6 Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), GPT-6.1 Sol keeps input/output rates at 2.00/10.00 and halves cached input from 0.20 to 0.10. This improves the cached-input rate, not necessarily the total cost of a task; token use, retries and cache hits still matter. Older Sol remains a compatibility choice, not an alias.
## Design implications ## Design implications
Official positioning: [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) targets focused, high-volume work; [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol) targets complex coding and agentic workflows; [GPT-6 guidance](https://developers.openai.com/api/docs/guides/latest-model) places Astra at the highest capability level. Sol and Luna document API efforts none/low/medium/high/xhigh/max. Actual child models, efforts and role bindings must still come from the host schema. Official positioning: [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) targets focused, high-volume work; [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) offers near-Astra performance for complex coding, computer use and professional work at a lower price; [GPT-6 guidance](https://developers.openai.com/api/docs/guides/latest-model) places Astra at the highest capability level. This is official positioning, not a benchmark performed by this project. GPT-6.1 Sol documents API efforts low/medium/high/xhigh/max, not none/minimal; GPT-6 Luna and older GPT-6 Sol support none. Actual child models, efforts and role bindings must still come from the host schema.
The engineering policy is three routes: Luna for bounded, settled, cheaply verifiable work; Sol for implementation and investigation requiring judgment; Astra for the hardest independent synthesis. Retire Terra from recommendations and automatic fallbacks: Sol absorbs its former workload and avoids maintaining another routing boundary. This is a routing design choice, not a measured claim that Sol dominates every Terra workload. Price alone does not establish that Luna can perform open-ended development reliably. The engineering policy is three routes: Luna for bounded, settled, cheaply verifiable work; Sol for implementation and investigation requiring judgment; Astra for the hardest independent synthesis. Retire Terra from recommendations and automatic fallbacks: Sol absorbs its former workload and avoids maintaining another routing boundary. This is a routing design choice, not a measured claim that Sol dominates every Terra workload. Price alone does not establish that Luna can perform open-ended development reliably.
@@ -28,6 +28,6 @@ The engineering policy is three routes: Luna for bounded, settled, cheaply verif
Compare the same task shape and acceptance standard. Include parent context/reasoning, every child's usage, tools, retries, parent review and reintegration. For API estimates apply the actual rate to each billed category, including billed reasoning/output tokens without double-counting; keep wall time separate. With unknown usage or billing tier, report unknown cost and observable proxies instead of fabricated savings. Compare the same task shape and acceptance standard. Include parent context/reasoning, every child's usage, tools, retries, parent review and reintegration. For API estimates apply the actual rate to each billed category, including billed reasoning/output tokens without double-counting; keep wall time separate. With unknown usage or billing tier, report unknown cost and observable proxies instead of fabricated savings.
A cheaper child helps only if its savings exceed added orchestration and correction. One avoided parent investigation may matter more than many cheap child tokens. Do not turn the 20x ratio into a twenty-retry allowance, a fan-out quota or permission to duplicate reviews. Keep concurrency tied to useful independent work and actual host capacity. A cheaper child helps only if its savings exceed added orchestration and correction. One avoided parent investigation may matter more than many cheap child tokens. Do not turn a token-rate ratio into a retry allowance, a fan-out quota or permission to duplicate reviews. Keep concurrency tied to useful independent work and actual host capacity.
Broaden Luna assignments after comparable accepted results demonstrate stable quality and lower total effort. Move a task shape directly to Sol when ambiguity, repeated correction or parent rework dominates. For a new generation, use the first authorized useful bounded task as evidence; synthetic parser tests and static scenario reviews cannot establish model quality or latency. Broaden Luna assignments after comparable accepted results demonstrate stable quality and lower total effort. Move a task shape directly to Sol when ambiguity, repeated correction or parent rework dominates. For a new generation, use the first authorized useful bounded task as evidence; synthetic parser tests and static scenario reviews cannot establish model quality or latency.
skills/codex-subagent-router/references/platforms.md
+7 -3
View File
@@ -19,18 +19,20 @@ For clients that support the documented keys, an example is:
```toml ```toml
# Example only; merge intentionally into the existing configuration. # Example only; merge intentionally into the existing configuration.
model = "gpt-6-sol" model = "gpt-6.1-sol"
model_reasoning_effort = "medium" model_reasoning_effort = "medium"
[agents] [agents]
default_subagent_model = "gpt-6-sol" default_subagent_model = "gpt-6.1-sol"
default_subagent_reasoning_effort = "medium" default_subagent_reasoning_effort = "medium"
max_concurrent_threads_per_session = 3 max_concurrent_threads_per_session = 3
``` ```
This is not an automatic router, permission grant or universal host configuration. Never overwrite an existing config to install this example. Preserve user model/provider choices and verify the actual client accepts the keys. Per-agent configuration and host overrides may change resolution. This is not an automatic router, permission grant or universal host configuration. Never overwrite an existing config to install this example. Preserve user model/provider choices and verify the actual client accepts the keys. Per-agent configuration and host overrides may change resolution.
The Sol default assumes GPT-6 Sol is exposed and suits mixed engineering work. Explicitly route bounded tasks to GPT-6 Luna where supported; do not make Luna a universal fallback for arbitrary inherited work. If only GPT-5.6 children are available, use the [legacy compatibility routes](routing-matrix.md). A fixed `luna_*` role may still bind GPT-5.6 Luna/max: inspect the binding, then use an overridable role if available and appropriate. Do not rename or claim to upgrade a fixed role through prompt text. The Sol default assumes GPT-6.1 Sol is exposed and suits mixed engineering work. Resolve parent and child availability separately: a model in the picker does not prove child support. Explicitly route bounded tasks to GPT-6 Luna where supported; do not make Luna a universal fallback for arbitrary inherited work. If 6.1 is unavailable, use the [compatibility routes](routing-matrix.md). A fixed `sol_*` or `luna_*` role may still bind an older model: inspect the binding, then use an overridable role if available and appropriate. Do not rename or claim to upgrade a fixed role through prompt text.
For an authorized migration, preserve a supported effective effort. GPT-6.1 Sol's API accepts low/medium/high/xhigh/max and rejects none/minimal; use low as an initial replacement for those settings and check representative work. Tool calling requires Responses; its Chat Completions support is without tools. Desktop/CLI controls, including Ultra, must be checked separately against the actual host; do not copy them into API requests. Installation does not apply any of these configuration changes.
The official Codex configuration describes the child-thread limit as excluding the parent. A collaboration tool may expose a different active-slot count including the parent. Use that live tool's counting and release semantics; do not copy either number blindly. The official Codex configuration describes the child-thread limit as excluding the parent. A collaboration tool may expose a different active-slot count including the parent. Use that live tool's counting and release semantics; do not copy either number blindly.
@@ -49,3 +51,5 @@ Configuration changes may require a fresh session or explicit reload. Writing a
## Sources ## Sources
Checked 2026-09-14: [Codex subagents](https://learn.chatgpt.com/zh-Hans/docs/agent-configuration/subagents), [OpenAI model catalog](https://developers.openai.com/api/docs/models). Recheck changed product/API facts before altering real configuration. Checked 2026-09-14: [Codex subagents](https://learn.chatgpt.com/zh-Hans/docs/agent-configuration/subagents), [OpenAI model catalog](https://developers.openai.com/api/docs/models). Recheck changed product/API facts before altering real configuration.
Model recommendation and migration checked 2026-10-06: [Codex models](https://learn.chatgpt.com/docs/models), [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol), [migration guidance](https://developers.openai.com/api/docs/guides/latest-model?model=gpt-6.1-sol). Configuration keys above retain their original reference date; the current client schema takes precedence.
skills/codex-subagent-router/references/routing-matrix.md
+5 -5
View File
@@ -5,7 +5,7 @@ Read only when the entrypoint leaves a routing choice unresolved.
| Boundary | Decision | | Boundary | Decision |
| --- | --- | | --- | --- |
| Many easy tasks | Partition independent bounded Luna batches across available capacity; size batches to keep coordination and acceptance useful. Volume alone does not justify Astra. | | Many easy tasks | Partition independent bounded Luna batches across available capacity; size batches to keep coordination and acceptance useful. Volume alone does not justify Astra. |
| Ordinary cross-file bug | GPT-6 Sol; file count alone does not justify Astra. | | Ordinary cross-file bug | GPT-6.1 Sol; file count alone does not justify Astra. |
| Small patch with settled semantics and deterministic acceptance | GPT-6 Luna medium/high if failure is contained; parent checks the diff and behavior. | | Small patch with settled semantics and deterministic acceptance | GPT-6 Luna medium/high if failure is contained; parent checks the diff and behavior. |
| Small patch changes authentication or a shared schema contract | Parent settles shared decisions; bounded investigation may use Sol. Small size is not evidence of low ambiguity. | | Small patch changes authentication or a shared schema contract | Parent settles shared decisions; bounded investigation may use Sol. Small size is not evidence of low ambiguity. |
| Cheap Luna attempts require repeated parent rewrites | Choose Sol directly next time for this shape; count total accepted-task cost. | | Cheap Luna attempts require repeated parent rewrites | Choose Sol directly next time for this shape; count total accepted-task cost. |
@@ -27,14 +27,14 @@ Check each route independently. The API catalog does not update an existing sess
| Unavailable preferred route | Supported compatibility choice | | Unavailable preferred route | Supported compatibility choice |
| --- | --- | | --- | --- |
| GPT-6 Luna | GPT-5.6 Luna low/medium for fixed collection/checks, high for settled transformations or patches; otherwise Sol or local work. | | GPT-6 Luna | GPT-5.6 Luna low/medium for fixed collection/checks, high for settled transformations or patches; otherwise Sol or local work. |
| GPT-6 Sol for implementation/investigation/complex analysis | GPT-5.6 Sol medium/high, if exposed and adequate; otherwise local work. | | GPT-6.1 Sol for implementation/investigation/complex analysis | GPT-6 Sol medium/high, or GPT-5.6 Sol medium/high when that is the adequate exposed route; otherwise local work. |
| GPT-6 Astra | An adequate supported Sol route or local work; disclose a capability gap if neither suffices. | | GPT-6 Astra | An adequate supported Sol route or local work; disclose a capability gap if neither suffices. |
These are work-shape fallbacks, not capability equivalence claims. Terra is retired from recommended routes and automatic fallbacks; do not select it merely because a legacy host exposes it. Preserve an explicit user-pinned model or existing configuration until an authorized change. If a required model is unavailable, report the exact gap before dependent dispatch. Never invent `gpt-6-terra`. A mixed host may use GPT-6 Sol and GPT-5.6 Luna without reverting every route. Record the exact requested ID and fallback reason. Unknown observed identity stays unknown. These are work-shape fallbacks, not capability equivalence claims or a mandatory sequence of model attempts. Terra is retired from recommended routes and automatic fallbacks; do not select it merely because a legacy host exposes it. Preserve an explicit user-pinned model or existing configuration until an authorized change. If a required model/version is unavailable, report the exact gap before dependent dispatch; a GPT-6 Sol pin must not silently become GPT-6.1 Sol. Never invent `gpt-6-terra`. A mixed host may use GPT-6.1 Sol and GPT-5.6 Luna, or GPT-6 Sol when 6.1 is absent, without reverting every route. Record the exact requested ID and fallback reason. Unknown observed identity stays unknown.
## Production Artifact Collection ## Production Artifact Collection
- GPT-6 Luna: use known hosts/endpoints/paths and fixed selectors to read or download actual reports, JSON, logs or job outputs; verify size/hash, parseability, required fields and specified counts. GPT-6 Sol: locate the current output through bounded read-only investigation, diagnose retrieval failures, or correlate logs and artifacts by run/version. Do not launch both by default; use Sol only when discovery or diagnosis is needed. Apply the legacy table when these routes are unavailable. - GPT-6 Luna: use known hosts/endpoints/paths and fixed selectors to read or download actual reports, JSON, logs or job outputs; verify size/hash, parseability, required fields and specified counts. GPT-6.1 Sol: locate the current output through bounded read-only investigation, diagnose retrieval failures, or correlate logs and artifacts by run/version. Do not launch both by default; use Sol only when discovery or diagnosis is needed. Apply the compatibility table when these routes are unavailable.
- Contract: name the production source, expected run/date/version, allowed read operations, bounded time/range/volume, local destination and acceptance checks. Reuse approved access and applicable server tools. Keep secrets out of prompts/receipts. Remote access stays read-only; explicitly allow local artifact writes even for a collector role. - Contract: name the production source, expected run/date/version, allowed read operations, bounded time/range/volume, local destination and acceptance checks. Reuse approved access and applicable server tools. Keep secrets out of prompts/receipts. Remote access stays read-only; explicitly allow local artifact writes even for a collector role.
- Evidence: preserve the actual downloaded artifact and record source, retrieval time/timezone, producer run/version and generation time when exposed, local path, bytes/hash and check results. Unknown provenance stays unknown. Verify the expected run/freshness; mtime or successful download alone does not prove current output. Use immutable run identifiers where possible; detect/retry boundedly if files change during collection. - Evidence: preserve the actual downloaded artifact and record source, retrieval time/timezone, producer run/version and generation time when exposed, local path, bytes/hash and check results. Unknown provenance stays unknown. Verify the expected run/freshness; mtime or successful download alone does not prove current output. Use immutable run identifiers where possible; detect/retry boundedly if files change during collection.
- No fixture, cache or old snapshot may stand in for requested live output. If the current artifact is missing, stale, inconsistent or inaccessible, report that gap. Do not trigger jobs, regenerate artifacts, restart services, change permissions/configuration or deploy as part of collection; return such remediation to the parent under existing authorization. - No fixture, cache or old snapshot may stand in for requested live output. If the current artifact is missing, stale, inconsistent or inaccessible, report that gap. Do not trigger jobs, regenerate artifacts, restart services, change permissions/configuration or deploy as part of collection; return such remediation to the parent under existing authorization.
@@ -48,4 +48,4 @@ Use actual usage counters when exposed. Otherwise report observable proxies (cha
If context dominates, narrow inputs and avoid full-history forks. If output dominates, bound logs and returns. If reasoning/retries dominate, clarify acceptance and choose adequate capability/effort directly. Preserve required tests and material findings. If context dominates, narrow inputs and avoid full-history forks. If output dominates, bound logs and returns. If reasoning/retries dominate, clarify acceptance and choose adequate capability/effort directly. Preserve required tests and material findings.
Official model positioning checked 2026-09-23: [GPT-6 guidance](https://developers.openai.com/api/docs/guides/latest-model). See [model economics](model-economics.md) for the dated API price basis. The route table is an engineering starting strategy, not a measured task-cost ranking. Runtime tool schemas remain the source for actual child availability. Official model positioning checked 2026-10-06: [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol), [Codex models](https://learn.chatgpt.com/docs/models). See [model economics](model-economics.md) for the dated API price basis. The route table is an engineering starting strategy, not a measured task-cost ranking. Runtime tool schemas remain the source for actual child availability.