docks-kit 0.7.1 → 0.8.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +5 -4
- package/README.md +6 -4
- package/cli/docs/flags.md +6 -3
- package/cli/docs/models.md +11 -3
- package/cli/docs/modifiers.md +17 -6
- package/cli/docs/toolchain.md +2 -3
- package/cli/src/engine-native/claudeSync.ts +23 -26
- package/cli/src/engine-native/parseArgs.ts +3 -3
- package/cli/src/engine-native/skillsSync.ts +2 -2
- package/cli/src/engine-native/workflowDeploy.ts +5 -5
- package/cli/src/generated/sotPayload.ts +9 -9
- package/cli/src/workflowModels.ts +90 -33
- package/package.json +1 -1
package/AGENTS.md
CHANGED
|
@@ -24,7 +24,7 @@ Tool-specific instructions live alongside this file:
|
|
|
24
24
|
| `.github/workflows/release-cli.yml` | `cli-v*` release binaries + npm publish |
|
|
25
25
|
| `README.md` | Front door |
|
|
26
26
|
| `package.json` / `bun.lock` | npm package: `bin` = `cli/src/main.ts`; bundles `cli/` with the generated in-memory SoT payload |
|
|
27
|
-
| `SoT/.agents/skills.txt` | Universal-skill manifest.
|
|
27
|
+
| `SoT/.agents/skills.txt` | Universal-skill manifest, intentionally empty by default. Adding an [agentskills.io](https://agentskills.io/specification) slug opts it into EngineNative's shared `~/.agents/skills/` bootstrap and Claude symlink. |
|
|
28
28
|
| `notification.mp3` | Audio asset for Notification hooks (consumed by Claude Code today; tool-agnostic file) |
|
|
29
29
|
| `docs/plans/` | Multi-commit work-item plans (`active/` with status in frontmatter, plus `finished/` archive). Convention: `docs/plans/AGENTS.md` |
|
|
30
30
|
| `CLAUDE.md` | Claude-specific instructions; imports this `AGENTS.md` |
|
|
@@ -32,13 +32,14 @@ Tool-specific instructions live alongside this file:
|
|
|
32
32
|
|
|
33
33
|
Codex SoT notes:
|
|
34
34
|
- `SoT/.codex/AGENTS.md` deploys to `~/.codex/AGENTS.md` as global Codex instructions.
|
|
35
|
-
- `SoT/.codex/config.toml` pins Codex to `model = "gpt-5.6-sol"`, sets reasoning
|
|
35
|
+
- `SoT/.codex/config.toml` pins Codex to `model = "gpt-5.6-sol"`, sets normal and plan reasoning to `high` with concise summaries, and sets `model_verbosity = "low"`, `personality`, live top-level `web_search`, workspace-write sandboxing with sandboxed command network access, cross-session `memories` (+ dedicated note tools), `[agents]` subagent limits (`max_threads = 12`, `max_depth = 2` — intentionally above Codex defaults for broad parallel kit work; deeper recursion increases cost and predictability risk), a 128 KiB `project_doc_max_bytes` budget for the repo-side AGENTS.md chain (the global `~/.codex/AGENTS.md` is uncapped and not counted), and enables the Docks plugins as `docks@docks`, `session-relay@docks`, and `effect-kit@docks`.
|
|
36
36
|
- `SoT/.codex/rules/*.rules` deploys to `~/.codex/rules/` as kit-managed Codex command policy. This is Codex's equivalent of permission allow/prompt/block rules; user-learned approvals in `~/.codex/rules/default.rules` are preserved.
|
|
37
37
|
- `SoT/.codex/plugins/marketplace.json` deploys to Codex's personal marketplace path at `~/.agents/plugins/marketplace.json`; when the `codex` CLI is available, sync reruns `codex plugin add <plugin@marketplace>` for enabled SoT plugins so stale cached installs are refreshed.
|
|
38
38
|
- `docks-kit status` verifies Session Relay only through the supported `codex plugin list --json` inventory. `ready` means installed and enabled for a newly started Codex session; it is not evidence about an old process, lifecycle state, receive-path health, or worker quiescence. The global prompt SoTs carry the owner's standing authorization for Docks cross-company plan review, which never overrides host or platform denial.
|
|
39
39
|
- Both global prompt SoTs carry one byte-identical compact `Docks-workflow-models:` record. Root `--model-orchestrator` / `--model-reviewer` / `--model-implementer` / review-bound flags update only that deployed record; `docks-kit models workflow` lists the closed selectors, and a flag-less sync restores defaults.
|
|
40
|
+
- Codex workflow selectors use the closed `<tool>:<model>@<effort>[+fast]` routing grammar. Fast is intentionally absent from the global SoT: no suffix means Standard and keeps the backward-compatible schema-1 record; `+fast` emits a schema-2 candidate with `service_tier: "fast"`. Docks and Session Relay consumers must explicitly launch unsuffixed Codex roles with the default service tier so a user's global Fast preference cannot leak into workflows.
|
|
40
41
|
- The `codex` CLI binary is upstream-owned, not kit-owned. The official standalone installer keeps package metadata under `$CODEX_HOME/packages/standalone` and places the `codex` symlink in `~/.local/bin` by default; sync only warns with a download-then-run installer command when the CLI is missing. Existing installs can self-update with `codex update`; npm and Homebrew remain upstream alternatives.
|
|
41
|
-
-
|
|
42
|
+
- Neither global prompt SoT imports `@RTK.md`; Claude uses the hook-backed RTK integration, while Codex has no kit-managed RTK integration.
|
|
42
43
|
- Claude runtime settings are an authoring template with sentinels. `claudeRuntime.ts` materializes absolute Bun/script paths only after the shared `bun.ts` bootstrap is ready; `claudeSync.ts` writes all runtime assets before atomically committing settings, then prunes the legacy shell scripts and Stop hook. Native `rate_limits` is the sole quota source, so jq/curl/OAuth caches are not runtime dependencies. A missing Bun defers only this cutover and preserves legacy pointers/files.
|
|
43
44
|
- Claude's deployed SoT defaults are `model: fable` and `effortLevel: high`; `advisorModel` is deliberately absent/off. `--claude-advisor=on` is the per-machine opt-in and writes `advisorModel: fable` after the settings merge.
|
|
44
45
|
|
|
@@ -82,7 +83,7 @@ This project ships **kit-mechanic skills** under `.claude/skills/` — narrowly-
|
|
|
82
83
|
When a kit-mechanic skill, its `references/`, or a wrapper agent (`.claude/agents/*.md` + its `.codex/agents/*.toml` twin) cites EngineNative internals, name the **module + exported/local function + semantic anchor** (e.g. `claudeSync.ts syncPlugins, pass 5 uninstall guard`) — never a raw `file:NNN` line number, which goes stale on every refactor. Keep exactly one coarse `metadata.source_files[].lines` range per skill file as the sole intentional line-number touchpoint.
|
|
83
84
|
</constraint>
|
|
84
85
|
|
|
85
|
-
**Universal-skill bootstrap.** `SoT/.agents/skills.txt`
|
|
86
|
+
**Universal-skill bootstrap.** `SoT/.agents/skills.txt` is intentionally empty, so the default sync exposes no universal skills. The generic opt-in contract remains: each [agentskills.io](https://agentskills.io/specification) slug is installed by `skillsSync.ts` with `npx skills add <slug> -g -y -a claude-code codex`. The slug comes first because `-a/--agent` is variadic; naming both supported agents preserves the canonical `~/.agents/skills/<name>/SKILL.md` plus Claude's `~/.claude/skills/<name>` symlink. Existing canonical directories are reused idempotently, `--prune` removes only entries tracked in `~/.agents/.kit-managed-skills`, and skills requiring a separate CLI retain explicit helpers in `skillsSync.ts`.
|
|
86
87
|
|
|
87
88
|
## Plans
|
|
88
89
|
|
package/README.md
CHANGED
|
@@ -84,10 +84,12 @@ and a later flag-less sync reverts them. Full reference: `docks-kit docs flags`
|
|
|
84
84
|
| `--review-min-score=<0..100>` | Override the completion-review target |
|
|
85
85
|
| `--review-max-rounds=<1..10>` | Bound completion-review batches |
|
|
86
86
|
|
|
87
|
-
Selectors are strict `profile:<name>` or `<tool>:<model>@<effort
|
|
88
|
-
`docks-kit models workflow
|
|
89
|
-
|
|
90
|
-
|
|
87
|
+
Selectors are strict `profile:<name>` or `<tool>:<model>@<effort>[+fast]`
|
|
88
|
+
values from `docks-kit models workflow`; `+fast` is Codex-only. A selector
|
|
89
|
+
without `+fast` means Standard, while `+fast` writes a schema-2 candidate with
|
|
90
|
+
`service_tier: "fast"`. These root flags update only the identical compact record
|
|
91
|
+
in `~/.claude/CLAUDE.md` and `~/.codex/AGENTS.md`; omitted fields retain their
|
|
92
|
+
current valid values, while a later flag-less sync restores all defaults.
|
|
91
93
|
|
|
92
94
|
## How syncing works
|
|
93
95
|
|
package/cli/docs/flags.md
CHANGED
|
@@ -34,7 +34,7 @@ docks-kit sync claude agents # two
|
|
|
34
34
|
| `--claude-permissive` | Deploy-time modifier: empty permissions.ask/deny (sandboxes) |
|
|
35
35
|
| `--claude-plugin=<name>` | Sticky opt-in plugin (known: supabase, n8n); comma-separate for several |
|
|
36
36
|
| `--codex-model=<m>` | Deploy-time modifier: deployed Codex model |
|
|
37
|
-
| `--codex-effort=<level>` | Deploy-time modifier: `model_reasoning_effort`; valid `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`, `ultra`, or `default` (Codex SoT: `
|
|
37
|
+
| `--codex-effort=<level>` | Deploy-time modifier: `model_reasoning_effort`; valid `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`, `ultra`, or `default` (Codex SoT: `high`; model-dependent) |
|
|
38
38
|
|
|
39
39
|
Bare model, effort, or advisor modifiers print the relevant valid-value catalog
|
|
40
40
|
and exit 2. A modifier for a target not selected by the positional arguments is
|
|
@@ -47,7 +47,7 @@ These flags belong at the root (`docks-kit --model-reviewer=...`), not after
|
|
|
47
47
|
|
|
48
48
|
| Flag | Accepted value |
|
|
49
49
|
|------|----------------|
|
|
50
|
-
| `--model-orchestrator=<selector>` | `profile:<name>` or `<tool>:<model>@<effort
|
|
50
|
+
| `--model-orchestrator=<selector>` | `profile:<name>` or `<tool>:<model>@<effort>[+fast]` |
|
|
51
51
|
| `--model-reviewer=<selector>` | same strict selector grammar |
|
|
52
52
|
| `--model-implementer=<selector>` | same strict selector grammar |
|
|
53
53
|
| `--review-min-score=<n>` | base-10 integer `0..100` |
|
|
@@ -55,7 +55,10 @@ These flags belong at the root (`docks-kit --model-reviewer=...`), not after
|
|
|
55
55
|
|
|
56
56
|
Use `docks-kit models workflow [--json]` for the closed registry. Bare, empty,
|
|
57
57
|
unknown, or malformed values print that helper and exit 2 before either prompt
|
|
58
|
-
file changes.
|
|
58
|
+
file changes. `+fast` is accepted only on Codex exact targets and writes
|
|
59
|
+
`service_tier: "fast"` in workflow record schema 2. Without `+fast`, the role is
|
|
60
|
+
Standard and the record remains schema 1 unless another role is Fast. Shell
|
|
61
|
+
quotes are optional but recommended around selectors containing `+fast`.
|
|
59
62
|
|
|
60
63
|
## Renamed legacy flags (pre-CLI sync.sh)
|
|
61
64
|
|
package/cli/docs/models.md
CHANGED
|
@@ -39,12 +39,12 @@ docks-kit models workflow --json # closed machine-readable registry
|
|
|
39
39
|
|
|
40
40
|
The `workflow` section is strict even though ordinary tool-model modifiers are
|
|
41
41
|
forward-compatible. It accepts only known `profile:<name>` values or exact
|
|
42
|
-
`<tool>:<model>@<effort
|
|
43
|
-
catalog. The defaults are:
|
|
42
|
+
`<tool>:<model>@<effort>[+fast]` targets whose model and effort both appear in
|
|
43
|
+
the catalog. `+fast` is accepted only for Codex exact targets. The defaults are:
|
|
44
44
|
|
|
45
45
|
- orchestrator: `profile:claude-best`, ordered as `claude:fable@high` then
|
|
46
46
|
`claude:opus@xhigh`;
|
|
47
|
-
- reviewer and implementer: `codex:gpt-5.6-sol@
|
|
47
|
+
- reviewer and implementer: `codex:gpt-5.6-sol@high`;
|
|
48
48
|
- review minimum score 90 and maximum 3 rounds.
|
|
49
49
|
|
|
50
50
|
`claude:best@high` is Claude's native one-model alias. It is deliberately not
|
|
@@ -52,6 +52,14 @@ the same as the Docks-managed `profile:claude-best` candidate chain.
|
|
|
52
52
|
Availability is `checked_when_used`: Docks classifies each launch attempt;
|
|
53
53
|
docks-kit neither probes providers nor promises provider-wide fallback.
|
|
54
54
|
|
|
55
|
+
The default and every unsuffixed selector emit the backward-compatible schema-1
|
|
56
|
+
record with no service-tier field; absence means Standard. A `+fast` selector
|
|
57
|
+
promotes the complete record to schema 2 and adds `service_tier: "fast"` only to
|
|
58
|
+
the selected Codex candidate. Replacing the last Fast selector with an
|
|
59
|
+
unsuffixed selector demotes the record back to schema 1. Docks and Session Relay
|
|
60
|
+
must support schema 2 before `+fast` is deployed, and must explicitly select the
|
|
61
|
+
default tier for unsuffixed roles so global Codex configuration cannot leak in.
|
|
62
|
+
|
|
55
63
|
## Advisor pairing note (Claude)
|
|
56
64
|
|
|
57
65
|
The SoT ships `model: fable` with advisor off (`advisorModel` unset).
|
package/cli/docs/modifiers.md
CHANGED
|
@@ -10,7 +10,8 @@ the SoT is never touched. They all share one contract:
|
|
|
10
10
|
> touches.
|
|
11
11
|
|
|
12
12
|
Claude's embedded SoT is `model: fable`, `effortLevel: high`, with advisor
|
|
13
|
-
off (`advisorModel` unset). Codex's embedded reasoning effort is
|
|
13
|
+
off (`advisorModel` unset). Codex's embedded normal and plan reasoning effort is
|
|
14
|
+
`high`.
|
|
14
15
|
|
|
15
16
|
| Modifier | Deployed change | Typical use |
|
|
16
17
|
|----------|-----------------|-------------|
|
|
@@ -20,7 +21,7 @@ off (`advisorModel` unset). Codex's embedded reasoning effort is `xhigh`.
|
|
|
20
21
|
| `--claude-compact-window=<n>` | `env.CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Disposable containers running long autonomous work (e.g. `680k`) — not host machines |
|
|
21
22
|
| `--claude-permissive` | `permissions.ask = []`, `permissions.deny = []` | Sandboxes/containers where prompts stall unattended work. Never on a host — the deny list is the safety floor |
|
|
22
23
|
| `--codex-model=<m>` | top-level `model = "…"` in ~/.codex/config.toml | Same as claude-model, for Codex |
|
|
23
|
-
| `--codex-effort=<level>` | top-level `model_reasoning_effort = "…"` (`default` writes `
|
|
24
|
+
| `--codex-effort=<level>` | top-level `model_reasoning_effort = "…"` (`default` writes `high`) | Tune Codex effort per machine; valid `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`, `ultra` (model-dependent) |
|
|
24
25
|
|
|
25
26
|
Bare effort/advisor flags print their verified catalog and exit 2. Invalid
|
|
26
27
|
values do the same with a clear error. Passing a tool-specific modifier without
|
|
@@ -32,6 +33,13 @@ owns that key for the run: `on` writes `fable`; `off` and `default` delete it.
|
|
|
32
33
|
Codex has no advisor modifier because its documented config has no advisor
|
|
33
34
|
setting; `review_model` applies only to `/review`.
|
|
34
35
|
|
|
36
|
+
Codex Fast mode is intentionally not a global SoT default or per-machine
|
|
37
|
+
modifier. It is role-scoped through the root workflow flags: append `+fast` to a
|
|
38
|
+
Codex exact selector to emit `service_tier: "fast"` in record schema 2. Without
|
|
39
|
+
the suffix, the role means Standard and emits no tier field. Docks and Session
|
|
40
|
+
Relay consumers must map that absence to an explicit default-tier process
|
|
41
|
+
override rather than inherit a user's global Fast preference.
|
|
42
|
+
|
|
35
43
|
## Standalone get/set (no full sync)
|
|
36
44
|
|
|
37
45
|
```
|
|
@@ -50,7 +58,8 @@ The root workflow flags are deployed modifiers for Docks rather than one tool:
|
|
|
50
58
|
|
|
51
59
|
```text
|
|
52
60
|
docks-kit --model-orchestrator=profile:claude-best \
|
|
53
|
-
--model-reviewer=codex:gpt-5.6-
|
|
61
|
+
--model-reviewer="codex:gpt-5.6-sol@high+fast" \
|
|
62
|
+
--model-implementer=codex:gpt-5.6-sol@high \
|
|
54
63
|
--review-min-score=80 --review-max-rounds=5
|
|
55
64
|
```
|
|
56
65
|
|
|
@@ -61,11 +70,13 @@ stops before mutation, a repeated request is a no-op, and failure on the second
|
|
|
61
70
|
atomic write restores both snapshots. A later flag-less sync restores the
|
|
62
71
|
embedded defaults. Start fresh sessions after changing the record.
|
|
63
72
|
|
|
64
|
-
Selectors are strict `profile:<name>` or `<tool>:<model>@<effort
|
|
65
|
-
`docks-kit models workflow`. `
|
|
73
|
+
Selectors are strict `profile:<name>` or `<tool>:<model>@<effort>[+fast]`
|
|
74
|
+
entries from `docks-kit models workflow`. `+fast` is Codex-only and quotes are
|
|
75
|
+
optional; its absence means Standard. `profile:claude-best` is the ordered Docks
|
|
66
76
|
Fable-high then Opus-xhigh chain; `claude:best@high` is instead Claude's native
|
|
67
77
|
single-model alias. Docks checks each candidate when used—there is no docks-kit
|
|
68
|
-
provider preflight.
|
|
78
|
+
provider preflight. Install schema-2 support in Docks and Session Relay before
|
|
79
|
+
using a Fast selector.
|
|
69
80
|
|
|
70
81
|
## Sticky opt-ins are NOT modifiers
|
|
71
82
|
|
package/cli/docs/toolchain.md
CHANGED
|
@@ -45,9 +45,8 @@ download boundary; Windows Bun bootstrap uses PowerShell's native download.
|
|
|
45
45
|
|
|
46
46
|
Every kit-driven install is pinned to a `verified` version or gated by one —
|
|
47
47
|
never floating `@latest` (the npm-worm / Shai-Hulud attack surface). That
|
|
48
|
-
includes the `npx skills@<verified>` invocations on
|
|
49
|
-
|
|
50
|
-
release workflow (actions pinned to commit SHAs, exact bun/npm versions).
|
|
48
|
+
includes the `npx skills@<verified>` invocations on agents sync and the release
|
|
49
|
+
workflow (actions pinned to commit SHAs, exact bun/npm versions).
|
|
51
50
|
Callbacks receive the exact gate-approved version; an offline "latest unknown"
|
|
52
51
|
probe falls back to the pinned `verified`, never to an ungated latest.
|
|
53
52
|
|
|
@@ -23,7 +23,7 @@ import {
|
|
|
23
23
|
syncClaudeModel
|
|
24
24
|
} from "./claudeSettingsModifiers"
|
|
25
25
|
import { claudeRuntimePaths, materializeClaudeSettings, type ClaudeRuntimePaths } from "./claudeRuntime"
|
|
26
|
-
import { p, writeBytesIfChanged,
|
|
26
|
+
import { p, writeBytesIfChanged, writeTextIfChanged } from "./exec"
|
|
27
27
|
import type { Ctx } from "./index"
|
|
28
28
|
import { compareCodepoints, deepMerge, isObject, jqStringify, parseJson, type Json } from "./jq"
|
|
29
29
|
import type { EngineServices } from "./services"
|
|
@@ -206,36 +206,13 @@ function syncClaudeRuntime(ctx: Ctx, runtime: ClaudeRuntimeState): void {
|
|
|
206
206
|
|
|
207
207
|
function syncClaudeMd(ctx: Ctx, claudeDir: string): void {
|
|
208
208
|
const { change, echo, verbose } = ctx.services.logger
|
|
209
|
-
// The @RTK.md import only resolves once `rtk init` has generated
|
|
210
|
-
// ~/.claude/RTK.md (the rtk phase runs before this). Deploying the import
|
|
211
|
-
// without the file leaves a dangling reference in every Claude session
|
|
212
|
-
// (seen on Windows, where rtk never auto-installs) — strip it while the
|
|
213
|
-
// file is absent; a later sync after rtk init restores it.
|
|
214
|
-
const rtkMdAbsent = !existsSync(p(claudeDir, "RTK.md"))
|
|
215
209
|
if (ctx.dryRun) {
|
|
216
|
-
|
|
217
|
-
echo("[dry-run] cp SoT/.claude/CLAUDE.md -> ~/.claude/CLAUDE.md (stripping @RTK.md import: --skip-rtk)")
|
|
218
|
-
} else if (rtkMdAbsent) {
|
|
219
|
-
echo("[dry-run] cp SoT/.claude/CLAUDE.md -> ~/.claude/CLAUDE.md (would strip @RTK.md import while ~/.claude/RTK.md is absent)")
|
|
220
|
-
} else {
|
|
221
|
-
echo("[dry-run] cp SoT/.claude/CLAUDE.md -> ~/.claude/CLAUDE.md")
|
|
222
|
-
}
|
|
210
|
+
echo("[dry-run] cp SoT/.claude/CLAUDE.md -> ~/.claude/CLAUDE.md")
|
|
223
211
|
return
|
|
224
212
|
}
|
|
225
213
|
|
|
226
214
|
const source = renderDefaultWorkflowInstructions(payloadText("SoT/.claude/CLAUDE.md"))
|
|
227
|
-
|
|
228
|
-
if (stripReason !== "") {
|
|
229
|
-
const stripped = source
|
|
230
|
-
.split("\n")
|
|
231
|
-
.filter((l) => l !== "@RTK.md")
|
|
232
|
-
.join("\n")
|
|
233
|
-
if (writeFileIfChanged(p(claudeDir, "CLAUDE.md"), stripped)) {
|
|
234
|
-
change(`CLAUDE.md synced (@RTK.md import stripped: ${stripReason})`)
|
|
235
|
-
} else {
|
|
236
|
-
verbose("CLAUDE.md already in sync")
|
|
237
|
-
}
|
|
238
|
-
} else if (writeTextIfChanged(p(claudeDir, "CLAUDE.md"), source)) {
|
|
215
|
+
if (writeTextIfChanged(p(claudeDir, "CLAUDE.md"), source)) {
|
|
239
216
|
change("CLAUDE.md synced")
|
|
240
217
|
} else {
|
|
241
218
|
verbose("CLAUDE.md already in sync")
|
|
@@ -668,6 +645,24 @@ function pluginUserScopeInstalled(installedPlugins: string, pluginId: string): b
|
|
|
668
645
|
return records.some((r) => isObject(r) && r["scope"] === "user")
|
|
669
646
|
}
|
|
670
647
|
|
|
648
|
+
function nonUserScopeMarketplaces(installedDoc: Json | undefined): Set<string> {
|
|
649
|
+
const marketplaces = new Set<string>()
|
|
650
|
+
if (installedDoc === undefined || !isObject(installedDoc) || !isObject(installedDoc["plugins"])) {
|
|
651
|
+
return marketplaces
|
|
652
|
+
}
|
|
653
|
+
|
|
654
|
+
for (const [pluginId, value] of Object.entries(installedDoc["plugins"])) {
|
|
655
|
+
const records = Array.isArray(value) ? value : [value]
|
|
656
|
+
const hasNonUserInstall = records.some(
|
|
657
|
+
(record) => isObject(record) && (record["scope"] === "project" || record["scope"] === "local")
|
|
658
|
+
)
|
|
659
|
+
if (!hasNonUserInstall) continue
|
|
660
|
+
const separator = pluginId.lastIndexOf("@")
|
|
661
|
+
if (separator > 0) marketplaces.add(pluginId.slice(separator + 1))
|
|
662
|
+
}
|
|
663
|
+
return marketplaces
|
|
664
|
+
}
|
|
665
|
+
|
|
671
666
|
function syncPlugins(ctx: Ctx, claudeDir: string): void {
|
|
672
667
|
const { change, echo, verbose, warn } = ctx.services.logger
|
|
673
668
|
const knownMarketplaces = p(claudeDir, "plugins", "known_marketplaces.json")
|
|
@@ -739,6 +734,7 @@ function syncPlugins(ctx: Ctx, claudeDir: string): void {
|
|
|
739
734
|
let updatedPl = 0
|
|
740
735
|
const installedDoc = readJsonFile(installedPlugins)
|
|
741
736
|
const installedKeys = installedDoc !== undefined && isObject(installedDoc) ? sortedKeys(installedDoc["plugins"]) : []
|
|
737
|
+
const nonUserMarketplaces = nonUserScopeMarketplaces(installedDoc)
|
|
742
738
|
// Pass 3 — refresh every installed plugin unless the update command
|
|
743
739
|
// selected its install-missing-only fast path.
|
|
744
740
|
if (!ctx.skipPluginRefresh) {
|
|
@@ -767,6 +763,7 @@ function syncPlugins(ctx: Ctx, claudeDir: string): void {
|
|
|
767
763
|
const known = readJsonFile(knownMarketplaces)
|
|
768
764
|
for (const mpName of sortedKeys(known)) {
|
|
769
765
|
if (mpName === "claude-plugins-official") continue
|
|
766
|
+
if (nonUserMarketplaces.has(mpName)) continue
|
|
770
767
|
const declared = isObject(sotMarketplaces) ? sotMarketplaces[mpName] : undefined
|
|
771
768
|
if (declared !== undefined && declared !== null && declared !== false) continue
|
|
772
769
|
if (cli(["plugin", "marketplace", "remove", mpName]).ok) {
|
|
@@ -280,9 +280,9 @@ function workflowUsage(ctx: Ctx): void {
|
|
|
280
280
|
printCatalog(ctx, workflowCatalog())
|
|
281
281
|
ctx.services.logger.echo("")
|
|
282
282
|
ctx.services.logger.echo("Workflow override flags:")
|
|
283
|
-
ctx.services.logger.echo(" --model-orchestrator=<profile:name|tool:model@effort>")
|
|
284
|
-
ctx.services.logger.echo(" --model-reviewer=<profile:name|tool:model@effort>")
|
|
285
|
-
ctx.services.logger.echo(" --model-implementer=<profile:name|tool:model@effort>")
|
|
283
|
+
ctx.services.logger.echo(" --model-orchestrator=<profile:name|tool:model@effort[+fast]>")
|
|
284
|
+
ctx.services.logger.echo(" --model-reviewer=<profile:name|tool:model@effort[+fast]>")
|
|
285
|
+
ctx.services.logger.echo(" --model-implementer=<profile:name|tool:model@effort[+fast]>")
|
|
286
286
|
ctx.services.logger.echo(" --review-min-score=<0..100>")
|
|
287
287
|
ctx.services.logger.echo(" --review-max-rounds=<1..10>")
|
|
288
288
|
}
|
|
@@ -350,7 +350,7 @@ function reconcileRemovals(ctx: Ctx, manifest: string, snapshot: string): void {
|
|
|
350
350
|
echo(`[dry-run] kit-managed skill no longer in SoT — would remove: ${base}`)
|
|
351
351
|
continue
|
|
352
352
|
}
|
|
353
|
-
const res = spawnSync("npx", ["--yes", skillsCli(ctx), "remove", "--global",
|
|
353
|
+
const res = spawnSync("npx", ["--yes", skillsCli(ctx), "remove", "--global", base, "-y"], {
|
|
354
354
|
stdio: "ignore"
|
|
355
355
|
})
|
|
356
356
|
if (res.error === undefined && res.status === 0) {
|
|
@@ -365,7 +365,7 @@ function reconcileRemovals(ctx: Ctx, manifest: string, snapshot: string): void {
|
|
|
365
365
|
change(`Kit-managed skills removed (-${removed})`)
|
|
366
366
|
ctx.nextStepTriggers.skillsRestart = true
|
|
367
367
|
}
|
|
368
|
-
if (failed > 0) warn(`${failed} skill remove(s) failed — re-run with --prune or run: npx skills remove
|
|
368
|
+
if (failed > 0) warn(`${failed} skill remove(s) failed — re-run with --prune or run: npx skills remove --global <name> -y`)
|
|
369
369
|
}
|
|
370
370
|
|
|
371
371
|
function updateSnapshot(ctx: Ctx, manifest: string, snapshot: string): void {
|
|
@@ -9,7 +9,7 @@ import {
|
|
|
9
9
|
parseWorkflowRecord,
|
|
10
10
|
renderWorkflowRecordLine,
|
|
11
11
|
type WorkflowOverrides,
|
|
12
|
-
type
|
|
12
|
+
type WorkflowRecord
|
|
13
13
|
} from "../workflowModels"
|
|
14
14
|
|
|
15
15
|
export interface WorkflowFileSystem {
|
|
@@ -36,7 +36,7 @@ const nodeFileSystem: WorkflowFileSystem = {
|
|
|
36
36
|
}
|
|
37
37
|
|
|
38
38
|
interface DocumentRecord {
|
|
39
|
-
readonly record:
|
|
39
|
+
readonly record: WorkflowRecord | undefined
|
|
40
40
|
readonly line: string | undefined
|
|
41
41
|
}
|
|
42
42
|
|
|
@@ -45,9 +45,9 @@ function readDocumentRecord(document: string | undefined, label: string): Docume
|
|
|
45
45
|
if (lines.length === 0) return { record: undefined, line: undefined }
|
|
46
46
|
|
|
47
47
|
let canonicalLine: string | undefined
|
|
48
|
-
let canonicalRecord:
|
|
48
|
+
let canonicalRecord: WorkflowRecord | undefined
|
|
49
49
|
for (const line of lines) {
|
|
50
|
-
let record:
|
|
50
|
+
let record: WorkflowRecord
|
|
51
51
|
try {
|
|
52
52
|
record = parseWorkflowRecord(JSON.parse(line.slice(WORKFLOW_RECORD_PREFIX.length)) as unknown)
|
|
53
53
|
} catch (error) {
|
|
@@ -64,7 +64,7 @@ function readDocumentRecord(document: string | undefined, label: string): Docume
|
|
|
64
64
|
return { record: canonicalRecord, line: canonicalLine }
|
|
65
65
|
}
|
|
66
66
|
|
|
67
|
-
export function upsertWorkflowRecord(document: string, record:
|
|
67
|
+
export function upsertWorkflowRecord(document: string, record: WorkflowRecord): string {
|
|
68
68
|
const content = document
|
|
69
69
|
.split("\n")
|
|
70
70
|
.filter((line) => !line.startsWith(WORKFLOW_RECORD_PREFIX))
|
|
@@ -1,20 +1,20 @@
|
|
|
1
1
|
// Generated by cli/scripts/generate-sot-payload.ts. DO NOT EDIT.
|
|
2
2
|
// Edit SoT/, notification.mp3, or package.json, then run: bun cli/scripts/generate-sot-payload.ts
|
|
3
3
|
|
|
4
|
-
export const GENERATED_PACKAGE_VERSION = "0.
|
|
4
|
+
export const GENERATED_PACKAGE_VERSION = "0.8.1"
|
|
5
5
|
|
|
6
6
|
export const GENERATED_PAYLOAD_TEXT = {
|
|
7
|
-
"SoT/.agents/skills.txt": "# Universal AI-agent
|
|
8
|
-
"SoT/models.json": "{\n \"$comment\": \"Kit-verified model catalog — single source for EngineNative validators, the docks-kit CLI (models/model commands, workflow selectors, pickers, bare-flag help), and docs. Entries are research-proofed: update an entry and its tool-level `verified` date when a model ships or retires. Deploy-time model flags remain permissive; workflow selectors are strict.\",\n \"claude\": {\n \"verified\": \"2026-07-08\",\n \"models\": [\n { \"id\": \"best\", \"kind\": \"alias\", \"note\": \"Fable 5 where the org has access, latest Opus otherwise (Claude Code >=2.1.170)\" },\n { \"id\": \"opus\", \"kind\": \"alias\", \"note\": \"latest Opus (currently Opus 4.8)\" },\n { \"id\": \"fable\", \"kind\": \"alias\", \"note\": \"Fable 5 — the kit SoT default; needs org access + Claude Code >=2.1.170\" },\n { \"id\": \"sonnet\", \"kind\": \"alias\", \"note\": \"latest Sonnet (currently Sonnet 5)\" },\n { \"id\": \"haiku\", \"kind\": \"alias\", \"note\": \"latest Haiku (currently Haiku 4.5)\" },\n { \"id\": \"default\", \"kind\": \"alias\", \"note\": \"engine pseudo-value: deletes the deployed model key so the account default applies\" },\n { \"id\": \"claude-fable-5\", \"kind\": \"id\", \"note\": \"Fable 5\" },\n { \"id\": \"claude-opus-4-8\", \"kind\": \"id\", \"note\": \"Opus 4.8\" },\n { \"id\": \"claude-sonnet-5\", \"kind\": \"id\", \"note\": \"Sonnet 5\" },\n { \"id\": \"claude-haiku-4-5-20251001\", \"kind\": \"id\", \"note\": \"Haiku 4.5\" }\n ]\n },\n \"codex\": {\n \"verified\": \"2026-07-
|
|
7
|
+
"SoT/.agents/skills.txt": "# Universal AI-agent skill manifest intentionally empty.\n# Global skill discovery is opt-in: add one <owner>/<repo> slug per line.\n# EngineNative ignores comments and blank lines.\n",
|
|
8
|
+
"SoT/models.json": "{\n \"$comment\": \"Kit-verified model catalog — single source for EngineNative validators, the docks-kit CLI (models/model commands, workflow selectors, pickers, bare-flag help), and docs. Entries are research-proofed: update an entry and its tool-level `verified` date when a model ships or retires. Deploy-time model flags remain permissive; workflow selectors are strict.\",\n \"claude\": {\n \"verified\": \"2026-07-08\",\n \"models\": [\n { \"id\": \"best\", \"kind\": \"alias\", \"note\": \"Fable 5 where the org has access, latest Opus otherwise (Claude Code >=2.1.170)\" },\n { \"id\": \"opus\", \"kind\": \"alias\", \"note\": \"latest Opus (currently Opus 4.8)\" },\n { \"id\": \"fable\", \"kind\": \"alias\", \"note\": \"Fable 5 — the kit SoT default; needs org access + Claude Code >=2.1.170\" },\n { \"id\": \"sonnet\", \"kind\": \"alias\", \"note\": \"latest Sonnet (currently Sonnet 5)\" },\n { \"id\": \"haiku\", \"kind\": \"alias\", \"note\": \"latest Haiku (currently Haiku 4.5)\" },\n { \"id\": \"default\", \"kind\": \"alias\", \"note\": \"engine pseudo-value: deletes the deployed model key so the account default applies\" },\n { \"id\": \"claude-fable-5\", \"kind\": \"id\", \"note\": \"Fable 5\" },\n { \"id\": \"claude-opus-4-8\", \"kind\": \"id\", \"note\": \"Opus 4.8\" },\n { \"id\": \"claude-sonnet-5\", \"kind\": \"id\", \"note\": \"Sonnet 5\" },\n { \"id\": \"claude-haiku-4-5-20251001\", \"kind\": \"id\", \"note\": \"Haiku 4.5\" }\n ]\n },\n \"codex\": {\n \"verified\": \"2026-07-16\",\n \"models\": [\n { \"id\": \"gpt-5.6-sol\", \"kind\": \"id\", \"note\": \"GPT-5.6 Sol — frontier, recommended default; the kit SoT pin\" },\n { \"id\": \"gpt-5.6-terra\", \"kind\": \"id\", \"note\": \"GPT-5.6 Terra — balanced tier\" },\n { \"id\": \"gpt-5.6-luna\", \"kind\": \"id\", \"note\": \"GPT-5.6 Luna — fast/light tier\" },\n { \"id\": \"gpt-5.5\", \"kind\": \"id\", \"note\": \"previous generation\" },\n { \"id\": \"gpt-5.5-codex\", \"kind\": \"id\", \"note\": \"codex-tuned gpt-5.5\" },\n { \"id\": \"gpt-5.1\", \"kind\": \"id\", \"note\": \"previous generation\" },\n { \"id\": \"gpt-5\", \"kind\": \"id\", \"note\": \"previous generation\" },\n { \"id\": \"gpt-5-codex\", \"kind\": \"id\", \"note\": \"codex-tuned gpt-5\" }\n ]\n },\n \"workflow\": {\n \"schema\": 2,\n \"profiles\": {\n \"claude-best\": {\n \"candidates\": [\n { \"company\": \"anthropic\", \"tool\": \"claude\", \"model\": \"fable\", \"effort\": \"high\" },\n { \"company\": \"anthropic\", \"tool\": \"claude\", \"model\": \"opus\", \"effort\": \"xhigh\" }\n ]\n }\n },\n \"defaults\": {\n \"orchestrator\": \"profile:claude-best\",\n \"reviewer\": \"codex:gpt-5.6-sol@high\",\n \"implementer\": \"codex:gpt-5.6-sol@high\",\n \"review\": {\n \"minimum_score\": 90,\n \"max_rounds\": 3\n }\n },\n \"exact_target_grammar\": \"<tool>:<model>@<effort>[+fast]\",\n \"availability\": \"checked_when_used\"\n }\n}\n",
|
|
9
9
|
"SoT/toolchain.json": "{\n \"$comment\": \"Kit toolchain manifest — DATA only (versions, floors, policy); check/install logic lives in cli/src/engine-native/toolchain.ts with per-surface sync callbacks in cli/src/engine-native/. kind: check (doctor visibility only) | managed (kit installs/upgrades it) | pin (no binary probe — a version pin for a tool the kit invokes via npx). policy (managed only): track (upgrade toward latest, gated by `verified`) | present (install when missing, never upgrade). `verified` = last kit-tested version — anything above it prompts before install (--yes auto-accepts; non-TTY declines and falls back to the pinned `verified` when pinnable). Supply-chain stance: every kit-driven install is pinned to `verified` or gated by it — never floating @latest (npm-worm/Shai-Hulud surface). Update `verified` after testing a new release.\",\n \"tools\": {\n \"jq\": { \"kind\": \"check\", \"note\": \"optional operator CLI; EngineNative JSON and Claude runtime do not invoke it\" },\n \"curl\": { \"kind\": \"check\", \"note\": \"contextual POSIX installer transport for RTK/Bun bootstrap\" },\n \"git\": { \"kind\": \"check\", \"note\": \"plugin marketplaces (claude/codex clone them) + kit checkout updates\" },\n \"node\": { \"kind\": \"check\", \"note\": \"hosts npm globals (agent-browser, LSP servers)\" },\n \"npm\": { \"kind\": \"check\", \"note\": \"npm-global installer\" },\n \"claude\": { \"kind\": \"check\", \"floor\": \"2.1.170\", \"note\": \"kit floor — `best` alias + Fable 5 need >=2.1.170 (mirrors settings minimumVersion)\" },\n \"codex\": { \"kind\": \"check\", \"note\": \"upstream-owned; standalone installer prints when missing\" },\n \"ffplay\": { \"kind\": \"check\", \"note\": \"Notification hook sound (previously unchecked)\" },\n \"bwrap\": { \"kind\": \"check\", \"os\": \"linux\", \"note\": \"Codex Linux sandbox runtime\" },\n \"intelephense\": { \"kind\": \"check\", \"verified\": \"1.18.5\", \"note\": \"php-lsp server binary; `verified` pins claude::sync_lsp_servers' npm install\" },\n \"typescript-language-server\": { \"kind\": \"check\", \"verified\": \"5.3.0\", \"note\": \"typescript-lsp server binary; `verified` pins claude::sync_lsp_servers' npm install\" },\n \"tsc\": { \"kind\": \"check\", \"verified\": \"6.0.3\", \"note\": \"typescript-lsp dependency (npm package `typescript`); `verified` pins claude::sync_lsp_servers' npm install. Deliberately on the 6.x line: typescript-language-server embeds TypeScript's programmatic API, which TS7 (native) doesn't yet expose — the repo's own devDependency runs TS7 for tsc --noEmit\" },\n \"rtk\": { \"kind\": \"managed\", \"policy\": \"track\", \"floor\": \"0.43.0\", \"verified\": \"0.43.0\", \"pinnable\": true,\n \"note\": \"PreToolUse hook — supply-chain review before unverified upgrades; installer honors RTK_VERSION=vX.Y.Z pin\" },\n \"bun\": { \"kind\": \"managed\", \"policy\": \"present\", \"verified\": \"1.3.14\", \"pinnable\": true,\n \"note\": \"runtime for effect-solutions + the docks-kit CLI; bootstrap installs the verified release (installer takes bun-vX.Y.Z); self-updates via `bun upgrade` when wanted\" },\n \"effect-solutions\": { \"kind\": \"managed\", \"policy\": \"track\", \"verified\": \"0.5.3\", \"pinnable\": true,\n \"note\": \"Effect docs CLI (bun global) — track keeps it self-upgrading, gated by the verified pin\" },\n \"agent-browser\": { \"kind\": \"managed\", \"policy\": \"track\", \"verified\": \"0.32.0\", \"pinnable\": true,\n \"note\": \"browser-automation CLI (npm global), gated by the verified pin; first install also downloads Chrome for Testing\" },\n \"skills-cli\": { \"kind\": \"pin\", \"verified\": \"1.5.15\",\n \"note\": \"the `skills` npm package the kit runs via `npx skills@<verified>` on every agents sync (universal-skill install/remove) — pinned, never @latest\" }\n }\n}\n",
|
|
10
|
-
"SoT/.claude/CLAUDE.md": "@RTK.md\n\n## Research Before Implementation\n\nBefore writing or modifying code that uses an API, hook, method, or config surface you have not verified in this session, research current documentation first.\n\n**Research workflow:**\n1. Use `resolve-library-id` → `query-docs` (context7) to fetch up-to-date docs for the specific library/framework\n2. If context7 doesn't cover it, read the official docs with `agent-browser` (it reaches JS-rendered, auth-walled, and login-gated pages); fall back to `WebFetch` for a simple static page\n3. Only then proceed to implementation\n\n**When to research:**\n- Installing or configuring a dependency\n- Using an API, hook, method, or pattern you haven't verified in this session\n- Upgrading or migrating between versions\n- Any task where you'd otherwise rely on training data for syntax/behavior\n\n**Do NOT:**\n- Assume API signatures, method names, or config options from memory\n- Generate framework code without checking current docs first\n- Skip research because the library \"seems familiar\"\n\n<constraint>\nResearch the codebase before editing. Never change code you haven't read.\n</constraint>\n\n## Agentic Harness Heuristics\n\n**1. Persistence.** Keep going until the user's query is completely resolved. Only yield when sure the problem is solved. Before ending a turn, check the last paragraph: if it is a plan, a question you can answer yourself, or a promise of work not done (\"I'll…\"), do that work now.\n\n**2. Default to parallel.** Whenever you have multiple independent operations (reads, greps, web fetches, independent edits), invoke them in a single response with multiple tool-use blocks. Sequential calls only when output of one operation is required as input to the next.\n\n**3. Multi-pass search.** First-pass search often misses — vary the wording (colleague-questions over keywords) before concluding something doesn't exist.\n\n**4. Trace symbols.** Before modifying a symbol, trace it to its definitions and all usages. Don't assume a function's behavior or a type's shape from the call site alone.\n\n**5. Linter-loop 3-strike rule.** Don't loop more than 3 times fixing linter errors on the same file. On the third attempt, stop and ask the user — repeated failure usually means the diagnosis is wrong, not the code.\n\n**6. Read-before-Edit TTL.** If you haven't read a file with the Read tool in the last ~5 messages, re-read it before editing. Cached file content goes stale silently when the user edits between turns.\n\n**7. Big-file rule.** For files >1000 lines, prefer Grep + scoped Read (`offset` + `limit`) over reading the entire file. Whole-file reads bloat context; targeted reads keep the working set small.\n\n**8. Todo hygiene.** Use TaskCreate for items with meaningful outcome (≥5 min, distinct deliverable). Never include operational sub-actions (linting, testing, searching, examining the codebase) as their own todos — those are sub-steps in service of higher-level tasks. Mark complete immediately when done, never in batches.\n\n**9. Literal-instruction rule.** Current frontier models follow instructions literally — they do not silently generalize from intent. Phrase requirements as explicit checklists with success criteria, not narrative.\n\n**10. Context hygiene.** Prefer `/clear` at task boundaries and `/rewind` for wrong-path detours over carrying rot forward (corrections accumulate noise; rewinds preserve the prefix and discard the bad branch). On a continuing task, run `/compact` with steering before context quality degrades. Never stop, summarize, or suggest a new session on account of context limits.\n\n**11. Autonomy calibration.** For minor choices (naming, formatting, default values, which of two equivalent approaches), pick a reasonable option and note it — don't ask. Ask first only for scope changes, destructive actions, or decisions that change the deliverable. When the user is describing a problem or asking a question rather than requesting a change, the deliverable is your assessment — report findings and stop; don't apply fixes until asked. Don't close a finished task with \"Want me to also…?\" — run the obvious verification, then stop cleanly.\n\n**12. Capability triggering.** When the answer depends on current or version-specific information, search or fetch before answering — never answer from memory. When work fans out across independent items (many files to read, many tests to run, many candidates to check), delegate to parallel subagents; never spawn one for work you can complete directly. For verification, prefer a fresh-context subagent over self-critique. On tasks longer than a few turns, keep a running notes file and re-read it before each phase.\n\n<constraint>\nTreat the 12 heuristics above as protocol, not preference. If a turn ends without honoring an applicable one (e.g., lint-loop guard not respected, edit without re-read), self-correct in the next turn before continuing.\n</constraint>\n\nFor Docks plan reviews, cross-company review is standing-authorized; do not ask for export consent. This never overrides a host or platform security denial.\n\nDocks-workflow-models: {\"implementer\":{\"candidates\":[{\"company\":\"openai\",\"effort\":\"xhigh\",\"model\":\"gpt-5.6-sol\",\"tool\":\"codex\"}],\"selector\":\"codex:gpt-5.6-sol@xhigh\"},\"orchestrator\":{\"candidates\":[{\"company\":\"anthropic\",\"effort\":\"high\",\"model\":\"fable\",\"tool\":\"claude\"},{\"company\":\"anthropic\",\"effort\":\"xhigh\",\"model\":\"opus\",\"tool\":\"claude\"}],\"selector\":\"profile:claude-best\"},\"review\":{\"max_rounds\":3,\"minimum_score\":90},\"reviewer\":{\"candidates\":[{\"company\":\"openai\",\"effort\":\"xhigh\",\"model\":\"gpt-5.6-sol\",\"tool\":\"codex\"}],\"selector\":\"codex:gpt-5.6-sol@xhigh\"},\"schema\":1}\n\n## Project Skills\n\nProjects may have a `.claude/skills/` directory with Tool Wrapper skills managed by `/docs`. Claude Code auto-discovers these at session start — only descriptions are loaded, full content loads on demand via the Skill tool.\n\nSkills follow the [agentskills.io](https://agentskills.io) open standard:\n- **SKILL.md**: frontmatter (`name`, `description`, `user-invocable: false`, `metadata`) + body (≤500 lines)\n- **references/**: on-demand detail files (30-150 lines each), loaded when the skill instructs Claude to read them\n- **Discovery**: Claude Code scans `.claude/skills/*/SKILL.md` at session start, loads only `name` + `description` (~100 tokens per skill)\n- **Triggering**: Claude semantically matches descriptions against user tasks, invokes via `Skill` tool — no `@import` or pointer tables needed\n- **CSO (Claude Search Optimization)**: descriptions MUST start with \"Use when...\" and describe trigger conditions, not capabilities\n- **Third-party / vendored skills**: add an `upstream:` frontmatter block (`source`, `license`, `vendored_at: \"YYYY-MM-DD\"`) when vendoring a skill from an external repo. The block marks the skill as vendored so kit-specific checks (CSO start-prefix, `user-invocable`, `metadata.updated`) are relaxed and the skill's body is preserved verbatim from upstream. Universal structural checks (fenced frontmatter, name matches directory, description length, 500-line body cap) still apply.\n\n<constraint>\nAfter any code change affecting documented patterns, update the relevant skill in `.claude/skills/` and its `metadata.updated` frontmatter field. When introducing something new, create a skill or add a `references/` file to an existing skill.\n</constraint>\n\n## Project Agents\n\nProjects and the global kit may have a `.claude/agents/` directory containing subagent definitions. Each agent file declares its `model` (`sonnet`/`opus`/`haiku`/`inherit`/full model ID), `tools`, and system prompt. Claude Code auto-discovers them at session start and delegates when a `subagent_type` matches or when a slash command explicitly invokes them.\n\nAgent files follow this structure:\n- **Frontmatter**: `name` (kebab-case, matches filename), `description` (CSO — starts \"Use when…\" with a \"Not for…\" exclusion clause), `tools`, `model`\n- **Body** (≤500 lines): `<constraint>` blocks for non-negotiable rules, `## Workflow` with context-acknowledgment as step 1, `## Output Format`, `## Anti-Hallucination Checks`, `## Success Criteria`\n- **Model-selection resolution** (per Claude Code docs): `CLAUDE_CODE_SUBAGENT_MODEL` env var → per-invocation `model` param → agent frontmatter `model:` → parent conversation. The env var is NOT set in this kit, so per-agent frontmatter controls selection.\n\n<constraint>\nWhen adding a new agent: use kebab-case name matching filename, CSO-compliant description (starts \"Use when…\", contains a \"Not\" exclusion clause), explicit `model` and `tools`.\n</constraint>\n\n## Picking the right models for workflows and subagents\n\nRankings, all scores 10 = best. Intelligence is how hard a problem the model can be handed unsupervised. Taste covers UI/UX, code quality, API design, and copy. Budget fit is marginal spend plus quota headroom — a tie-breaker only.\n\n| model | budget fit | intelligence | taste |\n|-------------|------------|--------------|-------|\n| gpt-5.6-sol | 9 | 10 | 6 |\n| fable-5 | 3 | 9 | 9 |\n| opus-4.8 | 5 | 7 | 8 |\n| sonnet-5 | 7 | 5 | 7 |\n\nCapacity: Sol has abundant subscription headroom; Fable is scarce; Opus is moderate; Sonnet is economical. gpt-5.6-sol holds the top intelligence slot — it is the default implementer for plan-sized work. Fable 5 (available again; the kit's Claude default) holds the top taste slot and is the orchestrator/interactive tier, not a bulk executor.\n\nHow to apply:\n- These are defaults, not limits. Standing permission to override: if a cheaper model's output misses the bar, rerun with a smarter one without asking. Judge the output, not the price tag — escalating costs less than shipping mediocre work.\n- Budget fit is a tie-breaker only; when axes conflict for anything that ships, intelligence > taste > budget fit.\n- Implementation of plans, and bulk/mechanical work (clear-spec implementation, data analysis, migrations): gpt-5.6-sol.\n- Anything user-facing (UI, copy, API design) needs taste ≥ 7 → fable-5 or opus-4.8 (sonnet-5 when both are saturated).\n- Reviews of plans/implementations: gpt-5.6-sol, optionally the best available Claude — fable-5 when access allows, opus-4.8 otherwise — as a second independent perspective.\n- Never use Haiku.\n- Claude models run via the Agent/Workflow `model` parameter (`opus`, `sonnet`, `fable` where org access allows).\n\nReaching gpt-5.6-sol — always through the `session-relay` skill (shared bus + `relay` CLI, Claude ⇄ Codex), even for one-shots, so every exchange stays resumable:\n- `relay spawn <dir> --tool codex --model gpt-5.6-sol --effort xhigh` (or `--tool claude --model opus` for a Claude worker in another project), then continue it with `send` / `wake`. Codex runs on its own CLI (`~/.codex/config.toml` defaults to gpt-5.6-sol) and is more efficient than Claude on well-specced execution and stronger at computer-use and UI/UX verification — offload those and report results back.\n- An independent fresh-context review = a NEW spawn (fresh spawn is fresh context). Two independent perspectives on a plan = the red-team pair spawn: a gpt-5.6-sol worker and an opus worker debate over the bus, orchestrator writes the verdict — the concrete form of the \"second independent perspective\" review above.\n- Pin `--model`/`--effort` on every spawn/wake; never leave an unattended relay child on a top interactive default (e.g. Fable). Each spawn/wake bills the target's subscription — spawn deliberately, never in loops.\n\n## Agentic Engineering Discipline\n\n1. **State assumptions; push back when warranted.** If a requirement is ambiguous in a way that changes the deliverable, surface the ambiguity and propose 1–2 concrete interpretations in your first message — do not silently pick one and run with it. Surface inconsistencies and confusion instead of guessing past them; present tradeoffs when approaches genuinely differ; push back when the request looks wrong. Agreeable-but-wrong is the failure mode, not disagreement.\n2. **Minimum code that solves the stated problem.** Each named pattern below is a defect — catch it during generation, not after:\n\n **Code slop**\n - **Defensive guards** around internally-trusted calls (`try`, `if x != null`). Validate at system boundaries only.\n - **Speculative abstraction.** No helper for one caller; no interface for one implementer. Three similar lines beats premature DRY.\n - **Backwards-compat shims** without a caller — re-exports, deprecation aliases, untoggled feature flags. Just change the code.\n - **Half-finished stubs.** `TODO handle later`, `throw new Error('not implemented')`. Implement or remove the path.\n - **Underscore-rename of unused vars.** Delete the var.\n - **Dead code left behind.** After a refactor, delete the paths, helpers, and imports the change made unreachable.\n\n **Comment slop**\n - **Restate-the-code.** `// increment i`. The identifier already says it.\n - **Provenance.** `// added for ticket X`, `// used by Y`. Belongs in the PR description; rots in code.\n - **Tombstones.** `// removed Z`, `// previously did W`. Git remembers.\n - **Docstring bloat** on self-evident functions. One line, only when the WHY isn't obvious from the name.\n\n **Output slop**\n - **End-of-turn diff-restatement.** One or two sentences: what changed, what's next. Don't recap what's in the diff.\n - **Narration tics.** \"Now I'll…\", \"Let me check…\", play-by-play between tool calls. Terse working shorthand between tool calls is fine; play-by-play is not — write a sentence when something load-bearing happens (a finding, a direction change, a blocker).\n - **Compressed final summaries.** The final message is for a reader who didn't watch the work: outcome first, complete sentences. Shorten by dropping detail, never by compressing into fragments or arrow chains.\n3. **Surgical changes only.** Do not modify code, comments, or formatting outside the explicit scope of the request. Surface unrelated issues as follow-ups — do not fix inline.\n4. **State how success will be verified before implementing.** Name the test, build, smoke check, or diff inspection that will prove the change works. Prefer executable criteria — a test that fails before and passes after, a command with expected output — over judgment calls, and keep each change small enough that its diff is reviewable in one sitting.\n5. **Review scope follows the pipeline.** In pipeline reviews with a downstream filter (multi-agent scans, verification phases), report every issue found with confidence and severity — filtering happens downstream. In ad-hoc reviews, flag only gaps that affect correctness or the stated requirements; treat the rest as optional.\n6. **Ground every progress claim in evidence.** Before reporting progress or completion, audit each claim against a tool result from this session — show the test output, the command and what it returned. If something is unverified, say so explicitly; if tests fail, say so with the output.\n\nUse a narrow-to-broad verification ladder: direct acceptance while iterating, focused regressions next, and one full CI at the pre-commit or release boundary. Reuse still-matching evidence; rerun full CI only after a relevant edit invalidates it.\n\n<constraint>\nTreat the six rules above as preventive (during generation), not remedial (after the fact). Self-correct if a turn drifts.\n</constraint>\n",
|
|
11
|
-
"SoT/.claude/mcp-servers.json": "{\n \"mcpServers\": {
|
|
12
|
-
"SoT/.claude/settings.json": "{\n \"$schema\": \"https://json.schemastore.org/claude-code-settings.json\",\n \"minimumVersion\": \"2.1.170\",\n \"model\": \"fable\",\n \"effortLevel\": \"high\",\n \"autoMemoryEnabled\": true,\n \"skillListingMaxDescChars\": 2048,\n \"respectGitignore\": true,\n \"cleanupPeriodDays\": 14,\n \"skillListingBudgetFraction\": 0.05,\n \"env\": {\n \"CLAUDE_CODE_MAX_OUTPUT_TOKENS\": \"64000\",\n \"CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR\": \"1\",\n \"CLAUDE_CODE_AUTO_COMPACT_WINDOW\": \"468000\",\n \"CLAUDE_CODE_NO_FLICKER\": \"1\"\n },\n \"permissions\": {\n \"defaultMode\": \"auto\",\n \"allow\": [\n \"Read\",\n \"Glob\",\n \"Grep\",\n \"WebFetch\",\n \"WebSearch\",\n \"Edit(./)\",\n \"Bash(git *)\",\n \"Bash(git add *)\",\n \"Bash(git commit *)\",\n \"Bash(git status *)\",\n \"Bash(git diff *)\",\n \"Bash(git log *)\",\n \"Bash(git branch *)\",\n \"Bash(git checkout *)\",\n \"Bash(git switch *)\",\n \"Bash(git stash *)\",\n \"Bash(git fetch *)\",\n \"Bash(git pull *)\",\n \"Bash(git tag *)\",\n \"Bash(git show *)\",\n \"Bash(git blame *)\",\n \"Bash(git worktree *)\",\n \"Bash(gh *)\",\n \"Bash(pnpm *)\",\n \"Bash(npm *)\",\n \"Bash(npx *)\",\n \"Bash(node *)\",\n \"Bash(docker *)\",\n \"Bash(docker-compose *)\",\n \"Bash(rtk *)\",\n \"Bash(ls *)\",\n \"Bash(cat *)\",\n \"Bash(find *)\",\n \"Bash(grep *)\",\n \"Bash(head *)\",\n \"Bash(tail *)\",\n \"Bash(wc *)\",\n \"Bash(sort *)\",\n \"Bash(uniq *)\",\n \"Bash(diff *)\",\n \"Bash(which *)\",\n \"Bash(pwd *)\",\n \"Bash(date *)\",\n \"Bash(mkdir *)\",\n \"Bash(basename *)\",\n \"Bash(dirname *)\",\n \"Bash(realpath *)\",\n \"Bash(jq *)\",\n \"Bash(curl *)\",\n \"Bash(tree *)\",\n \"Bash(sed *)\",\n \"Bash(awk *)\",\n \"Bash(cut *)\",\n \"Bash(tr *)\",\n \"Bash(tee *)\",\n \"Bash(echo *)\",\n \"Bash(printf *)\",\n \"Bash(env *)\",\n \"Bash(printenv *)\",\n \"Bash(uname *)\",\n \"Bash(file *)\",\n \"Bash(stat *)\",\n \"Bash(du *)\",\n \"Bash(id *)\",\n \"Bash(whoami *)\",\n \"Bash(php *)\",\n \"Bash(composer *)\",\n \"Bash(python3 *)\",\n \"Bash(python *)\",\n \"Bash(pip *)\",\n \"Bash(pip3 *)\"\n ],\n \"deny\": [\n \"Read(**/.env)\",\n \"Read(**/.env.local)\",\n \"Read(**/secrets/**)\",\n \"Read(**/*.key)\",\n \"Read(**/*.pem)\",\n \"Read(**/*.p12)\",\n \"Read(**/.credentials*)\",\n \"Edit(**/.env)\",\n \"Edit(**/.env.local)\",\n \"Edit(**/secrets/**)\",\n \"Bash(sudo *)\",\n \"Bash(rm -rf /)\",\n \"Bash(rm -rf / *)\",\n \"Bash(rm -rf ~)\",\n \"Bash(rm -rf ~ *)\",\n \"Bash(rm -rf $HOME)\",\n \"Bash(rm -rf $HOME *)\",\n \"Bash(> /dev *)\",\n \"Bash(dd if= *)\",\n \"Bash(mkfs *)\",\n \"Bash(eval *)\",\n \"Bash(chmod 777 *)\",\n \"Bash(chmod -R 777 *)\",\n \"Bash(git push --force origin main *)\",\n \"Bash(git push --force origin master *)\",\n \"Bash(git push -f origin main *)\",\n \"Bash(git push -f origin master *)\"\n ],\n \"ask\": [\n \"Bash(git clean *)\",\n \"Bash(docker volume rm *)\",\n \"Bash(docker system prune *)\"\n ]\n },\n \"hooks\": {\n \"SessionStart\": [\n {\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"__DOCKS_KIT_BUN__\",\n \"args\": [\"__DOCKS_KIT_SESSION_START__\"],\n \"timeout\": 5\n }\n ]\n }\n ],\n \"Notification\": [\n {\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"__DOCKS_KIT_BUN__\",\n \"args\": [\"__DOCKS_KIT_NOTIFY__\"],\n \"timeout\": 10,\n \"async\": true\n }\n ]\n }\n ],\n \"PreToolUse\": [\n {\n \"matcher\": \"Bash\",\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"rtk hook claude\"\n }\n ]\n }\n ],\n \"PostToolUseFailure\": [\n {\n \"matcher\": \"Bash\",\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"echo '{\\\"hookSpecificOutput\\\":{\\\"hookEventName\\\":\\\"PostToolUseFailure\\\",\\\"additionalContext\\\":\\\"Last bash command failed. Repository / file state may have shifted \\u2014 re-read affected files before retrying. If the failure is a missing dependency or env mismatch, surface it to the user rather than retrying blindly.\\\"}}'\",\n \"timeout\": 5\n }\n ]\n }\n ],\n \"SubagentStop\": [\n {\n \"hooks\": [\n {\n \"type\": \"prompt\",\n \"prompt\": \"You are a quality gate for subagent outputs in a multi-agent code-analysis pipeline.\\n\\nEvaluate the subagent's `last_assistant_message` field (in the JSON below) against these requirements:\\n\\n1. ALLOW (return `{}`): Mode-selection or no-issues responses. Examples: \\\"Which mode do you prefer\\\", \\\"select an option\\\", \\\"no issues / problems / violations / blockers found\\\".\\n\\n2. ALLOW (return `{}`): Output contains at least one concrete file:line citation \\u2014 e.g. `src/auth.ts:42`, `lib/db.ts:100-115`, or path references that include line numbers.\\n\\n3. BLOCK (return `{\\\"decision\\\":\\\"block\\\",\\\"reason\\\":\\\"<one-line explanation>\\\"}`): Output claims about code or findings WITHOUT concrete file:line citations. Vague references like \\\"the auth handler\\\" or \\\"near the database code\\\" are not acceptable as the only evidence.\\n\\nSubagent invocation JSON:\\n$ARGUMENTS\\n\\nReturn ONLY the JSON decision (no commentary, no markdown fences).\",\n \"timeout\": 30\n }\n ]\n }\n ]\n },\n \"statusLine\": {\n \"type\": \"command\",\n \"command\": \"__DOCKS_KIT_STATUSLINE__\",\n \"refreshInterval\": 5\n },\n \"enabledPlugins\": {\n \"
|
|
10
|
+
"SoT/.claude/CLAUDE.md": "## Research Before Implementation\n\nBefore writing or modifying code that uses an API, hook, method, or config surface you have not verified in this session, research current documentation first.\n\nResearch workflow:\n1. Prefer official documentation and primary sources for the specific library, framework, or API.\n2. If a local docs or MCP tool is available, use it before broad web search.\n3. Only then proceed to implementation.\n\nResearch when:\n- Installing or configuring a dependency.\n- Using an API, hook, method, or pattern not verified in this session.\n- Upgrading or migrating between versions.\n- Any task where relying on memory could cause stale syntax or behavior.\n\nDo not:\n- Assume API signatures, method names, or config options from memory.\n- Generate framework code without checking current docs first.\n- Skip research because the library seems familiar.\n\n<constraint>\nResearch the codebase before editing. Never change code you have not read.\n</constraint>\n\n## Agentic Harness Heuristics\n\n**1. Persistence.** Keep going until the user's query is completely resolved. Only yield when sure the problem is solved. Before ending a turn, check the last paragraph: if it is a plan, a question you can answer yourself, or a promise of work not done (\"I'll…\"), do that work now.\n\n**2. Default to parallel.** Whenever you have multiple independent operations (reads, greps, web fetches, independent edits), invoke them in a single response with multiple tool-use blocks. Sequential calls only when output of one operation is required as input to the next.\n\n**3. Multi-pass search.** First-pass search often misses — vary the wording (colleague-questions over keywords) before concluding something doesn't exist.\n\n**4. Trace symbols.** Before modifying a symbol, trace it to its definitions and all usages. Don't assume a function's behavior or a type's shape from the call site alone.\n\n**5. Linter-loop 3-strike rule.** Don't loop more than 3 times fixing linter errors on the same file. On the third attempt, stop and ask the user — repeated failure usually means the diagnosis is wrong, not the code.\n\n**6. Read-before-Edit TTL.** If you haven't read a file with the Read tool in the last ~5 messages, re-read it before editing. Cached file content goes stale silently when the user edits between turns.\n\n**7. Big-file rule.** For files >1000 lines, prefer Grep + scoped Read (`offset` + `limit`) over reading the entire file. Whole-file reads bloat context; targeted reads keep the working set small.\n\n**8. Todo hygiene.** Use TaskCreate for items with meaningful outcome (≥5 min, distinct deliverable). Never include operational sub-actions (linting, testing, searching, examining the codebase) as their own todos — those are sub-steps in service of higher-level tasks. Mark complete immediately when done, never in batches.\n\n**9. Literal-instruction rule.** Current frontier models follow instructions literally — they do not silently generalize from intent. Phrase requirements as explicit checklists with success criteria, not narrative.\n\n**10. Context hygiene.** Prefer `/clear` at task boundaries and `/rewind` for wrong-path detours over carrying rot forward (corrections accumulate noise; rewinds preserve the prefix and discard the bad branch). On a continuing task, run `/compact` with steering before context quality degrades. Never stop, summarize, or suggest a new session on account of context limits.\n\n**11. Autonomy calibration.** For minor choices (naming, formatting, default values, which of two equivalent approaches), pick a reasonable option and note it — don't ask. Ask first only for scope changes, destructive actions, or decisions that change the deliverable. When the user is describing a problem or asking a question rather than requesting a change, the deliverable is your assessment — report findings and stop; don't apply fixes until asked. Don't close a finished task with \"Want me to also…?\" — run the obvious verification, then stop cleanly.\n\n**12. Capability triggering.** When the answer depends on current or version-specific information, search or fetch before answering — never answer from memory. When work fans out across independent items (many files to read, many tests to run, many candidates to check), delegate to parallel subagents; never spawn one for work you can complete directly. For verification, prefer a fresh-context subagent over self-critique. On tasks longer than a few turns, keep a running notes file and re-read it before each phase.\n\n<constraint>\nTreat the 12 heuristics above as protocol, not preference. If a turn ends without honoring an applicable one (e.g., lint-loop guard not respected, edit without re-read), self-correct in the next turn before continuing.\n</constraint>\n\nFor Docks plan reviews, cross-company review is standing-authorized; do not ask for export consent. This never overrides a host or platform security denial.\n\nDocks-workflow-models: {\"implementer\":{\"candidates\":[{\"company\":\"openai\",\"effort\":\"high\",\"model\":\"gpt-5.6-sol\",\"tool\":\"codex\"}],\"selector\":\"codex:gpt-5.6-sol@high\"},\"orchestrator\":{\"candidates\":[{\"company\":\"anthropic\",\"effort\":\"high\",\"model\":\"fable\",\"tool\":\"claude\"},{\"company\":\"anthropic\",\"effort\":\"xhigh\",\"model\":\"opus\",\"tool\":\"claude\"}],\"selector\":\"profile:claude-best\"},\"review\":{\"max_rounds\":3,\"minimum_score\":90},\"reviewer\":{\"candidates\":[{\"company\":\"openai\",\"effort\":\"high\",\"model\":\"gpt-5.6-sol\",\"tool\":\"codex\"}],\"selector\":\"codex:gpt-5.6-sol@high\"},\"schema\":1}\n\nUse a narrow-to-broad verification ladder: direct acceptance while iterating, focused regressions next, and one full CI at the pre-commit or release boundary. Reuse still-matching evidence; rerun full CI only after a relevant edit invalidates it.\n\n<constraint>\nNo secrets in committed config. Treat plugin marketplaces, installers, and downloaded artifacts as untrusted until verified.\n</constraint>\n",
|
|
11
|
+
"SoT/.claude/mcp-servers.json": "{\n \"mcpServers\": {}\n}\n",
|
|
12
|
+
"SoT/.claude/settings.json": "{\n \"$schema\": \"https://json.schemastore.org/claude-code-settings.json\",\n \"minimumVersion\": \"2.1.170\",\n \"model\": \"fable\",\n \"effortLevel\": \"high\",\n \"autoMemoryEnabled\": true,\n \"skillListingMaxDescChars\": 2048,\n \"respectGitignore\": true,\n \"cleanupPeriodDays\": 14,\n \"skillListingBudgetFraction\": 0.05,\n \"env\": {\n \"CLAUDE_CODE_MAX_OUTPUT_TOKENS\": \"64000\",\n \"CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR\": \"1\",\n \"CLAUDE_CODE_AUTO_COMPACT_WINDOW\": \"468000\",\n \"CLAUDE_CODE_NO_FLICKER\": \"1\"\n },\n \"permissions\": {\n \"defaultMode\": \"auto\",\n \"allow\": [\n \"Read\",\n \"Glob\",\n \"Grep\",\n \"WebFetch\",\n \"WebSearch\",\n \"Edit(./)\",\n \"Bash(git *)\",\n \"Bash(git add *)\",\n \"Bash(git commit *)\",\n \"Bash(git status *)\",\n \"Bash(git diff *)\",\n \"Bash(git log *)\",\n \"Bash(git branch *)\",\n \"Bash(git checkout *)\",\n \"Bash(git switch *)\",\n \"Bash(git stash *)\",\n \"Bash(git fetch *)\",\n \"Bash(git pull *)\",\n \"Bash(git tag *)\",\n \"Bash(git show *)\",\n \"Bash(git blame *)\",\n \"Bash(git worktree *)\",\n \"Bash(gh *)\",\n \"Bash(pnpm *)\",\n \"Bash(npm *)\",\n \"Bash(npx *)\",\n \"Bash(node *)\",\n \"Bash(docker *)\",\n \"Bash(docker-compose *)\",\n \"Bash(rtk *)\",\n \"Bash(ls *)\",\n \"Bash(cat *)\",\n \"Bash(find *)\",\n \"Bash(grep *)\",\n \"Bash(head *)\",\n \"Bash(tail *)\",\n \"Bash(wc *)\",\n \"Bash(sort *)\",\n \"Bash(uniq *)\",\n \"Bash(diff *)\",\n \"Bash(which *)\",\n \"Bash(pwd *)\",\n \"Bash(date *)\",\n \"Bash(mkdir *)\",\n \"Bash(basename *)\",\n \"Bash(dirname *)\",\n \"Bash(realpath *)\",\n \"Bash(jq *)\",\n \"Bash(curl *)\",\n \"Bash(tree *)\",\n \"Bash(sed *)\",\n \"Bash(awk *)\",\n \"Bash(cut *)\",\n \"Bash(tr *)\",\n \"Bash(tee *)\",\n \"Bash(echo *)\",\n \"Bash(printf *)\",\n \"Bash(env *)\",\n \"Bash(printenv *)\",\n \"Bash(uname *)\",\n \"Bash(file *)\",\n \"Bash(stat *)\",\n \"Bash(du *)\",\n \"Bash(id *)\",\n \"Bash(whoami *)\",\n \"Bash(php *)\",\n \"Bash(composer *)\",\n \"Bash(python3 *)\",\n \"Bash(python *)\",\n \"Bash(pip *)\",\n \"Bash(pip3 *)\"\n ],\n \"deny\": [\n \"Read(**/.env)\",\n \"Read(**/.env.local)\",\n \"Read(**/secrets/**)\",\n \"Read(**/*.key)\",\n \"Read(**/*.pem)\",\n \"Read(**/*.p12)\",\n \"Read(**/.credentials*)\",\n \"Edit(**/.env)\",\n \"Edit(**/.env.local)\",\n \"Edit(**/secrets/**)\",\n \"Bash(sudo *)\",\n \"Bash(rm -rf /)\",\n \"Bash(rm -rf / *)\",\n \"Bash(rm -rf ~)\",\n \"Bash(rm -rf ~ *)\",\n \"Bash(rm -rf $HOME)\",\n \"Bash(rm -rf $HOME *)\",\n \"Bash(> /dev *)\",\n \"Bash(dd if= *)\",\n \"Bash(mkfs *)\",\n \"Bash(eval *)\",\n \"Bash(chmod 777 *)\",\n \"Bash(chmod -R 777 *)\",\n \"Bash(git push --force origin main *)\",\n \"Bash(git push --force origin master *)\",\n \"Bash(git push -f origin main *)\",\n \"Bash(git push -f origin master *)\"\n ],\n \"ask\": [\n \"Bash(git clean *)\",\n \"Bash(docker volume rm *)\",\n \"Bash(docker system prune *)\"\n ]\n },\n \"hooks\": {\n \"SessionStart\": [\n {\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"__DOCKS_KIT_BUN__\",\n \"args\": [\"__DOCKS_KIT_SESSION_START__\"],\n \"timeout\": 5\n }\n ]\n }\n ],\n \"Notification\": [\n {\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"__DOCKS_KIT_BUN__\",\n \"args\": [\"__DOCKS_KIT_NOTIFY__\"],\n \"timeout\": 10,\n \"async\": true\n }\n ]\n }\n ],\n \"PreToolUse\": [\n {\n \"matcher\": \"Bash\",\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"rtk hook claude\"\n }\n ]\n }\n ],\n \"PostToolUseFailure\": [\n {\n \"matcher\": \"Bash\",\n \"hooks\": [\n {\n \"type\": \"command\",\n \"command\": \"echo '{\\\"hookSpecificOutput\\\":{\\\"hookEventName\\\":\\\"PostToolUseFailure\\\",\\\"additionalContext\\\":\\\"Last bash command failed. Repository / file state may have shifted \\u2014 re-read affected files before retrying. If the failure is a missing dependency or env mismatch, surface it to the user rather than retrying blindly.\\\"}}'\",\n \"timeout\": 5\n }\n ]\n }\n ],\n \"SubagentStop\": [\n {\n \"hooks\": [\n {\n \"type\": \"prompt\",\n \"prompt\": \"You are a quality gate for subagent outputs in a multi-agent code-analysis pipeline.\\n\\nEvaluate the subagent's `last_assistant_message` field (in the JSON below) against these requirements:\\n\\n1. ALLOW (return `{}`): Mode-selection or no-issues responses. Examples: \\\"Which mode do you prefer\\\", \\\"select an option\\\", \\\"no issues / problems / violations / blockers found\\\".\\n\\n2. ALLOW (return `{}`): Output contains at least one concrete file:line citation \\u2014 e.g. `src/auth.ts:42`, `lib/db.ts:100-115`, or path references that include line numbers.\\n\\n3. BLOCK (return `{\\\"decision\\\":\\\"block\\\",\\\"reason\\\":\\\"<one-line explanation>\\\"}`): Output claims about code or findings WITHOUT concrete file:line citations. Vague references like \\\"the auth handler\\\" or \\\"near the database code\\\" are not acceptable as the only evidence.\\n\\nSubagent invocation JSON:\\n$ARGUMENTS\\n\\nReturn ONLY the JSON decision (no commentary, no markdown fences).\",\n \"timeout\": 30\n }\n ]\n }\n ]\n },\n \"statusLine\": {\n \"type\": \"command\",\n \"command\": \"__DOCKS_KIT_STATUSLINE__\",\n \"refreshInterval\": 5\n },\n \"enabledPlugins\": {\n \"docks@docks\": true,\n \"session-relay@docks\": true,\n \"effect-kit@docks\": true,\n \"php-lsp@claude-plugins-official\": true,\n \"typescript-lsp@claude-plugins-official\": true\n },\n \"extraKnownMarketplaces\": {\n \"docks\": {\n \"source\": {\n \"source\": \"github\",\n \"repo\": \"DocksDocks/docks\"\n }\n }\n },\n \"alwaysThinkingEnabled\": true,\n \"showThinkingSummaries\": true,\n \"viewMode\": \"default\",\n \"theme\": \"dark-daltonized\",\n \"skipDangerousModePermissionPrompt\": true\n}\n",
|
|
13
13
|
"SoT/.claude/bin/statusline.mjs": "const ESC = \"\\x1b[\"\nconst PIPE = `${ESC}90m | ${ESC}0m`\nconst DOT = `${ESC}90m • ${ESC}0m`\nconst DIM = `${ESC}2m${ESC}38;2;156;162;175m`\n\nfunction isRecord(value) {\n return typeof value === \"object\" && value !== null && !Array.isArray(value)\n}\n\nfunction finitePercentage(value) {\n return typeof value === \"number\" && Number.isFinite(value) && value >= 0 && value <= 100\n ? value\n : undefined\n}\n\nfunction roundHalfEven(value) {\n const lower = Math.floor(value)\n const fraction = value - lower\n if (fraction < 0.5) return lower\n if (fraction > 0.5) return lower + 1\n return lower % 2 === 0 ? lower : lower + 1\n}\n\nfunction pathBasename(path) {\n const parts = path.split(/[\\\\/]+/).filter((part) => part !== \"\")\n return parts.at(-1) ?? \"\"\n}\n\nfunction modelName(input) {\n const model = isRecord(input.model) && typeof input.model.display_name === \"string\"\n ? input.model.display_name\n : \"\"\n const suffix = model.indexOf(\" (\")\n return suffix === -1 ? model : model.slice(0, suffix)\n}\n\nfunction workingDirectory(input, cwd) {\n if (isRecord(input.workspace) && typeof input.workspace.current_dir === \"string\" && input.workspace.current_dir !== \"\") {\n return input.workspace.current_dir\n }\n if (typeof input.cwd === \"string\" && input.cwd !== \"\") return input.cwd\n return cwd\n}\n\nfunction compactWindow(env, total) {\n const raw = env.CLAUDE_CODE_AUTO_COMPACT_WINDOW\n if (typeof raw !== \"string\" || !/^[0-9]+$/.test(raw)) return total\n const parsed = Number(raw)\n return Number.isSafeInteger(parsed) && parsed >= 1000 && parsed < total ? parsed : total\n}\n\nfunction formatTokensK(value) {\n if (value < 1000) return `${value}k`\n if (value % 1000 === 0) return `${value / 1000}M`\n return `${(roundHalfEven(value / 100) / 10).toFixed(1)}M`\n}\n\nfunction contextSegment(input, env) {\n if (!isRecord(input.context_window)) return \"\"\n const used = finitePercentage(input.context_window.used_percentage)\n if (used === undefined) return \"\"\n\n const total = input.context_window.context_window_size\n if (typeof total !== \"number\" || !Number.isFinite(total) || total <= 0) {\n return `${ESC}38;2;130;160;230mctx ${roundHalfEven(used)}%${ESC}0m`\n }\n\n const usedK = roundHalfEven((used / 100) * (total / 1000))\n const effectiveK = Math.trunc(compactWindow(env, total) / 1000)\n if (effectiveK <= 0) return `${ESC}38;2;130;160;230mctx ${roundHalfEven(used)}%${ESC}0m`\n const effectivePercentage = roundHalfEven((usedK / effectiveK) * 100)\n return `${ESC}38;2;130;160;230mctx ${effectivePercentage}%${ESC}0m ${DIM}(${formatTokensK(usedK)}/${formatTokensK(effectiveK)})${ESC}0m`\n}\n\nfunction resetDelta(value, nowMs) {\n if (typeof value !== \"number\" || !Number.isFinite(value) || value < 0) return \"\"\n const seconds = Math.trunc(value) - Math.floor(nowMs / 1000)\n if (seconds <= 0) return \"now\"\n const days = Math.trunc(seconds / 86_400)\n if (days > 0) return `${days}d`\n const hours = Math.trunc((seconds % 86_400) / 3_600)\n if (hours > 0) return `${hours}h`\n return `${Math.trunc((seconds % 3_600) / 60)}m`\n}\n\nfunction quotaWindow(value, label, color, nowMs) {\n if (!isRecord(value)) return \"\"\n const used = finitePercentage(value.used_percentage)\n if (used === undefined) return \"\"\n const delta = resetDelta(value.resets_at, nowMs)\n const reset = delta === \"\" ? \"\" : ` ${DIM}(${delta})${ESC}0m`\n return `${ESC}38;2;${color}m${label} ${roundHalfEven(used)}%${ESC}0m${reset}`\n}\n\nfunction decodeStdout(result) {\n const stdout = result?.stdout\n if (stdout === undefined || stdout === null) return \"\"\n return typeof stdout === \"string\" ? stdout : stdout.toString()\n}\n\nfunction resolveBranch(directory, which, spawnSync) {\n const git = which(\"git\")\n if (typeof git !== \"string\" || git === \"\") return \"\"\n const commands = [\n [git, \"-C\", directory, \"symbolic-ref\", \"--short\", \"HEAD\"],\n [git, \"-C\", directory, \"rev-parse\", \"--short\", \"HEAD\"]\n ]\n for (const command of commands) {\n try {\n const result = spawnSync(command, { stdin: \"ignore\", stdout: \"pipe\", stderr: \"ignore\" })\n if (result?.success === true) return decodeStdout(result).trim()\n } catch {\n return \"\"\n }\n }\n return \"\"\n}\n\nexport function formatStatusline(input, options = {}) {\n if (!isRecord(input)) return \"\"\n const env = isRecord(options.env) ? options.env : process.env\n const nowMs = typeof options.nowMs === \"number\" ? options.nowMs : Date.now()\n const cwd = typeof options.cwd === \"string\" ? options.cwd : process.cwd()\n const branch = typeof options.branch === \"string\" ? options.branch : \"\"\n const directory = workingDirectory(input, cwd)\n\n const model = `${ESC}38;5;208m${ESC}1m${modelName(input)}${ESC}22m${ESC}0m`\n const folder = `${ESC}1m${ESC}38;2;76;208;222m${pathBasename(directory)}${ESC}22m${ESC}0m`\n const branchSegment = branch === \"\" ? \"\" : `${DOT}${ESC}1m${ESC}38;2;192;103;222m${branch}${ESC}22m${ESC}0m`\n const context = contextSegment(input, env)\n\n const rateLimits = isRecord(input.rate_limits) ? input.rate_limits : {}\n const fiveHour = quotaWindow(rateLimits.five_hour, \"5h\", \"100;200;200\", nowMs)\n const sevenDay = quotaWindow(rateLimits.seven_day, \"7d\", \"230;180;90\", nowMs)\n const quota = fiveHour === \"\" && sevenDay === \"\"\n ? \"\"\n : `${PIPE}${fiveHour}${fiveHour !== \"\" && sevenDay !== \"\" ? DOT : \"\"}${sevenDay}`\n\n return `${model}${PIPE}${folder}${branchSegment}${context === \"\" ? \"\" : `${PIPE}${context}`}${quota}`\n}\n\nexport async function main(options = {}) {\n const readStdin = options.readStdin ?? (() => Bun.stdin.text())\n const writeStdout = options.writeStdout ?? ((value) => process.stdout.write(value))\n let raw\n try {\n raw = await readStdin()\n } catch {\n return 0\n }\n\n let input\n try {\n input = JSON.parse(raw)\n } catch {\n return 0\n }\n if (!isRecord(input)) return 0\n\n const cwd = typeof options.cwd === \"string\" ? options.cwd : process.cwd()\n const directory = workingDirectory(input, cwd)\n const branch = resolveBranch(\n directory,\n options.which ?? ((name) => Bun.which(name)),\n options.spawnSync ?? ((argv, spawnOptions) => Bun.spawnSync(argv, spawnOptions))\n )\n const output = formatStatusline(input, {\n env: options.env ?? process.env,\n nowMs: options.nowMs ?? Date.now(),\n cwd,\n branch\n })\n if (output !== \"\") writeStdout(`${output}\\n`)\n return 0\n}\n\nif (import.meta.main) process.exit(await main())\n",
|
|
14
14
|
"SoT/.claude/bin/session-start.mjs": "import { readFileSync } from \"node:fs\"\nimport { homedir } from \"node:os\"\n\nfunction isRecord(value) {\n return typeof value === \"object\" && value !== null && !Array.isArray(value)\n}\n\nfunction nonEmpty(value, fallback) {\n return typeof value === \"string\" && value !== \"\" ? value : fallback\n}\n\nfunction pad(value) {\n return String(value).padStart(2, \"0\")\n}\n\nfunction configuredEffort(home, readText) {\n try {\n const parsed = JSON.parse(readText(`${home}/.claude/settings.json`))\n return isRecord(parsed) ? nonEmpty(parsed.effortLevel, \"default\") : \"default\"\n } catch {\n return \"default\"\n }\n}\n\nfunction localZone(now) {\n const part = new Intl.DateTimeFormat(\"en-US\", { timeZoneName: \"short\" })\n .formatToParts(now)\n .find((value) => value.type === \"timeZoneName\")\n return part?.value ?? \"\"\n}\n\nexport function sessionStartLines(options = {}) {\n const env = isRecord(options.env) ? options.env : process.env\n const now = options.now instanceof Date ? options.now : new Date()\n const home = typeof options.home === \"string\" ? options.home : homedir()\n const readText = options.readText ?? ((path) => readFileSync(path, \"utf8\"))\n const weekday = new Intl.DateTimeFormat(\"en-US\", { weekday: \"long\" }).format(now)\n const date = `${now.getFullYear()}-${pad(now.getMonth() + 1)}-${pad(now.getDate())}`\n const time = `${pad(now.getHours())}:${pad(now.getMinutes())}:${pad(now.getSeconds())}`\n const effort = nonEmpty(env.CLAUDE_CODE_EFFORT_LEVEL, configuredEffort(home, readText))\n const context = env.CLAUDE_CODE_DISABLE_1M_CONTEXT === \"1\" ? \"200K\" : \"1M\"\n const compactWindow = nonEmpty(env.CLAUDE_CODE_AUTO_COMPACT_WINDOW, \"full\")\n const subagent = nonEmpty(env.CLAUDE_CODE_SUBAGENT_MODEL, \"default\")\n return [\n `[CONTEXT] Current date: ${weekday}, ${date} ${time} ${localZone(now)}`,\n `[CONFIG] Context: ${context} | Compact-window: ${compactWindow} | Effort: ${effort} | Thinking: adaptive | Subagent: ${subagent}`\n ]\n}\n\nexport async function main(options = {}) {\n const writeStdout = options.writeStdout ?? ((value) => process.stdout.write(value))\n writeStdout(`${sessionStartLines(options).join(\"\\n\")}\\n`)\n return 0\n}\n\nif (import.meta.main) process.exit(await main())\n",
|
|
15
15
|
"SoT/.claude/bin/notify.mjs": "const DEFAULT_SOUND = `${import.meta.dir}/../notification.mp3`\n\nexport function selectPlayer(options = {}) {\n const platform = options.platform ?? process.platform\n const sound = options.sound ?? DEFAULT_SOUND\n const which = options.which ?? ((name) => Bun.which(name))\n if (platform === \"darwin\") {\n const afplay = which(\"afplay\")\n if (typeof afplay === \"string\" && afplay !== \"\") return [afplay, sound]\n }\n const ffplay = which(\"ffplay\")\n if (typeof ffplay === \"string\" && ffplay !== \"\") {\n return [ffplay, \"-nodisp\", \"-autoexit\", \"-loglevel\", \"quiet\", sound]\n }\n const paplay = which(\"paplay\")\n if (typeof paplay === \"string\" && paplay !== \"\") return [paplay, sound]\n const aplay = which(\"aplay\")\n if (typeof aplay === \"string\" && aplay !== \"\") return [aplay, \"-q\", sound]\n return undefined\n}\n\nexport async function main(options = {}) {\n const sound = options.sound ?? DEFAULT_SOUND\n const fileExists = options.fileExists ?? ((path) => Bun.file(path).exists())\n if (!await fileExists(sound)) return 0\n const command = selectPlayer({ ...options, sound })\n if (command === undefined) return 0\n const spawnSync = options.spawnSync ?? ((argv, spawnOptions) => Bun.spawnSync(argv, spawnOptions))\n const result = spawnSync(command, { stdin: \"ignore\", stdout: \"ignore\", stderr: \"ignore\" })\n return typeof result.exitCode === \"number\" ? result.exitCode : 1\n}\n\nif (import.meta.main) process.exit(await main())\n",
|
|
16
|
-
"SoT/.codex/AGENTS.md": "# AGENTS.md\n\n## Research Before Implementation\n\nBefore writing or modifying code that uses an API, hook, method, or config surface you have not verified in this session, research current documentation first.\n\nResearch workflow:\n1. Prefer official documentation and primary sources for the specific library, framework, or API.\n2. If a local docs or MCP tool is available, use it before broad web search.\n3. Only then proceed to implementation.\n\nResearch when:\n- Installing or configuring a dependency.\n- Using an API, hook, method, or pattern not verified in this session.\n- Upgrading or migrating between versions.\n- Any task where relying on memory could cause stale syntax or behavior.\n\nDo not:\n- Assume API signatures, method names, or config options from memory.\n- Generate framework code without checking current docs first.\n- Skip research because the library seems familiar.\n\n<constraint>\nResearch the codebase before editing. Never change code you have not read.\n</constraint>\n\n## Agentic Harness Heuristics\n\nModel-agnostic operating rules for coding-agent work.\n\n1. Persistence. Keep going until the user's request is actually handled. Only yield when the problem is solved or a concrete blocker is identified. Resolve in the fewest useful tool loops — once you can answer the core request with evidence, answer. Before ending a turn, check the last paragraph: if it is a plan, a question you can answer yourself, or a promise of work not done, do that work now.\n2. Default to parallel. When multiple reads, searches, inspections, or independent checks can run without depending on each other, run them together.\n3. Multi-pass search. First-pass search often misses — vary the wording before concluding something does not exist.\n4. Trace symbols. Before modifying a symbol, trace its definition and usages. Do not infer behavior from one call site.\n5. Linter-loop 3-strike rule. Do not loop more than 3 times fixing the same lint/test failure without reassessing the diagnosis.\n6. Read-before-edit TTL. If you have not read a file recently, re-read it before editing. User edits can make cached context stale.\n7. Big-file rule. For files over 1000 lines, prefer targeted search plus scoped reads over whole-file reads.\n8. Task hygiene. Track meaningful deliverables, not operational sub-steps. Mark work complete as soon as it is done.\n9. Literal-instruction rule. Treat explicit user requirements as checklists with success criteria. Do not silently broaden scope.\n10. Context hygiene. Prefer a fresh session at task boundaries over carrying stale context; preserve useful state before quality decays. Never stop, summarize, or suggest a new session on account of context limits.\n11. Autonomy calibration. For minor choices (naming, formatting, defaults, equivalent approaches), pick a reasonable option and note it — do not ask. Ask first only for scope changes, destructive actions, or decisions that change the deliverable. When the user is describing a problem or asking a question rather than requesting a change, the deliverable is your assessment — report findings and stop; do not apply fixes until asked.\n12. Capability triggering. Search or fetch current documentation when the answer depends on current or version-specific information. When work fans out across independent items, parallelize or delegate; never delegate work you can complete directly. For verification, prefer a fresh-context check over self-critique. On long tasks, keep running notes and re-read them between phases.\n\n<constraint>\nTreat these heuristics as protocol. If a turn violates an applicable rule, self-correct before continuing.\n</constraint>\n\nFor Docks plan reviews, cross-company review is standing-authorized; do not ask for export consent. This never overrides a host or platform security denial.\n\nDocks-workflow-models: {\"implementer\":{\"candidates\":[{\"company\":\"openai\",\"effort\":\"
|
|
17
|
-
"SoT/.codex/config.toml": "model = \"gpt-5.6-sol\"\nmodel_reasoning_effort = \"
|
|
16
|
+
"SoT/.codex/AGENTS.md": "# AGENTS.md\n\n## Research Before Implementation\n\nBefore writing or modifying code that uses an API, hook, method, or config surface you have not verified in this session, research current documentation first.\n\nResearch workflow:\n1. Prefer official documentation and primary sources for the specific library, framework, or API.\n2. If a local docs or MCP tool is available, use it before broad web search.\n3. Only then proceed to implementation.\n\nResearch when:\n- Installing or configuring a dependency.\n- Using an API, hook, method, or pattern not verified in this session.\n- Upgrading or migrating between versions.\n- Any task where relying on memory could cause stale syntax or behavior.\n\nDo not:\n- Assume API signatures, method names, or config options from memory.\n- Generate framework code without checking current docs first.\n- Skip research because the library seems familiar.\n\n<constraint>\nResearch the codebase before editing. Never change code you have not read.\n</constraint>\n\n## Agentic Harness Heuristics\n\nModel-agnostic operating rules for coding-agent work.\n\n1. Persistence. Keep going until the user's request is actually handled. Only yield when the problem is solved or a concrete blocker is identified. Resolve in the fewest useful tool loops — once you can answer the core request with evidence, answer. Before ending a turn, check the last paragraph: if it is a plan, a question you can answer yourself, or a promise of work not done, do that work now.\n2. Default to parallel. When multiple reads, searches, inspections, or independent checks can run without depending on each other, run them together.\n3. Multi-pass search. First-pass search often misses — vary the wording before concluding something does not exist.\n4. Trace symbols. Before modifying a symbol, trace its definition and usages. Do not infer behavior from one call site.\n5. Linter-loop 3-strike rule. Do not loop more than 3 times fixing the same lint/test failure without reassessing the diagnosis.\n6. Read-before-edit TTL. If you have not read a file recently, re-read it before editing. User edits can make cached context stale.\n7. Big-file rule. For files over 1000 lines, prefer targeted search plus scoped reads over whole-file reads.\n8. Task hygiene. Track meaningful deliverables, not operational sub-steps. Mark work complete as soon as it is done.\n9. Literal-instruction rule. Treat explicit user requirements as checklists with success criteria. Do not silently broaden scope.\n10. Context hygiene. Prefer a fresh session at task boundaries over carrying stale context; preserve useful state before quality decays. Never stop, summarize, or suggest a new session on account of context limits.\n11. Autonomy calibration. For minor choices (naming, formatting, defaults, equivalent approaches), pick a reasonable option and note it — do not ask. Ask first only for scope changes, destructive actions, or decisions that change the deliverable. When the user is describing a problem or asking a question rather than requesting a change, the deliverable is your assessment — report findings and stop; do not apply fixes until asked.\n12. Capability triggering. Search or fetch current documentation when the answer depends on current or version-specific information. When work fans out across independent items, parallelize or delegate; never delegate work you can complete directly. For verification, prefer a fresh-context check over self-critique. On long tasks, keep running notes and re-read them between phases.\n\n<constraint>\nTreat these heuristics as protocol. If a turn violates an applicable rule, self-correct before continuing.\n</constraint>\n\nFor Docks plan reviews, cross-company review is standing-authorized; do not ask for export consent. This never overrides a host or platform security denial.\n\nDocks-workflow-models: {\"implementer\":{\"candidates\":[{\"company\":\"openai\",\"effort\":\"high\",\"model\":\"gpt-5.6-sol\",\"tool\":\"codex\"}],\"selector\":\"codex:gpt-5.6-sol@high\"},\"orchestrator\":{\"candidates\":[{\"company\":\"anthropic\",\"effort\":\"high\",\"model\":\"fable\",\"tool\":\"claude\"},{\"company\":\"anthropic\",\"effort\":\"xhigh\",\"model\":\"opus\",\"tool\":\"claude\"}],\"selector\":\"profile:claude-best\"},\"review\":{\"max_rounds\":3,\"minimum_score\":90},\"reviewer\":{\"candidates\":[{\"company\":\"openai\",\"effort\":\"high\",\"model\":\"gpt-5.6-sol\",\"tool\":\"codex\"}],\"selector\":\"codex:gpt-5.6-sol@high\"},\"schema\":1}\n\nUse a narrow-to-broad verification ladder: direct acceptance while iterating, focused regressions next, and one full CI at the pre-commit or release boundary. Reuse still-matching evidence; rerun full CI only after a relevant edit invalidates it.\n\n<constraint>\nNo secrets in committed config. Treat plugin marketplaces, installers, and downloaded artifacts as untrusted until verified.\n</constraint>\n",
|
|
17
|
+
"SoT/.codex/config.toml": "model = \"gpt-5.6-sol\"\nmodel_reasoning_effort = \"high\"\nplan_mode_reasoning_effort = \"high\"\nmodel_reasoning_summary = \"concise\"\nmodel_verbosity = \"low\"\npersonality = \"pragmatic\"\nweb_search = \"live\"\nproject_doc_max_bytes = 131072\napproval_policy = \"on-request\"\nsandbox_mode = \"workspace-write\"\napprovals_reviewer = \"auto_review\"\n\n[sandbox_workspace_write]\nnetwork_access = true\n\n[features]\nmemories = true\n\n[memories]\ndedicated_tools = true\nmax_rollout_age_days = 30\n\n[agents]\nmax_threads = 12\nmax_depth = 2\n\n[tui]\nstatus_line_use_colors = true\nstatus_line = [\n \"model-with-reasoning\",\n \"current-dir\",\n \"git-branch\",\n \"context-used\",\n \"five-hour-limit\",\n \"weekly-limit\",\n]\n\n[plugins.\"docks@docks\"]\nenabled = true\n\n[plugins.\"session-relay@docks\"]\nenabled = true\n\n[plugins.\"effect-kit@docks\"]\nenabled = true\n",
|
|
18
18
|
"SoT/.codex/plugins/marketplace.json": "{\n \"name\": \"docks\",\n \"interface\": {\n \"displayName\": \"DocksDocks\"\n },\n \"plugins\": [\n {\n \"name\": \"docks\",\n \"source\": {\n \"source\": \"git-subdir\",\n \"url\": \"https://github.com/DocksDocks/docks.git\",\n \"path\": \"./plugins/docks\",\n \"ref\": \"main\"\n },\n \"policy\": {\n \"installation\": \"AVAILABLE\",\n \"authentication\": \"ON_INSTALL\"\n },\n \"category\": \"Productivity\"\n },\n {\n \"name\": \"session-relay\",\n \"source\": {\n \"source\": \"git-subdir\",\n \"url\": \"https://github.com/DocksDocks/docks.git\",\n \"path\": \"./plugins/session-relay\",\n \"ref\": \"main\"\n },\n \"policy\": {\n \"installation\": \"AVAILABLE\",\n \"authentication\": \"ON_INSTALL\"\n },\n \"category\": \"Productivity\"\n },\n {\n \"name\": \"effect-kit\",\n \"source\": {\n \"source\": \"git-subdir\",\n \"url\": \"https://github.com/DocksDocks/docks.git\",\n \"path\": \"./plugins/effect-kit\",\n \"ref\": \"main\"\n },\n \"policy\": {\n \"installation\": \"AVAILABLE\",\n \"authentication\": \"ON_INSTALL\"\n },\n \"category\": \"Productivity\"\n }\n ]\n}\n",
|
|
19
19
|
"SoT/.codex/rules/docks.rules": "prefix_rule(pattern=[\"pwd\"], decision=\"allow\")\nprefix_rule(pattern=[\"ls\"], decision=\"allow\")\nprefix_rule(pattern=[\"cat\"], decision=\"allow\")\nprefix_rule(pattern=[\"head\"], decision=\"allow\")\nprefix_rule(pattern=[\"tail\"], decision=\"allow\")\nprefix_rule(pattern=[\"wc\"], decision=\"allow\")\nprefix_rule(pattern=[\"nl\"], decision=\"allow\")\nprefix_rule(pattern=[\"grep\"], decision=\"allow\")\nprefix_rule(pattern=[\"sort\"], decision=\"allow\")\nprefix_rule(pattern=[\"uniq\"], decision=\"allow\")\nprefix_rule(pattern=[\"diff\"], decision=\"allow\")\nprefix_rule(pattern=[\"which\"], decision=\"allow\")\nprefix_rule(pattern=[\"date\"], decision=\"allow\")\nprefix_rule(pattern=[\"basename\"], decision=\"allow\")\nprefix_rule(pattern=[\"dirname\"], decision=\"allow\")\nprefix_rule(pattern=[\"realpath\"], decision=\"allow\")\nprefix_rule(pattern=[\"readlink\"], decision=\"allow\")\nprefix_rule(pattern=[\"jq\"], decision=\"allow\")\nprefix_rule(pattern=[\"tree\"], decision=\"allow\")\nprefix_rule(pattern=[\"cut\"], decision=\"allow\")\nprefix_rule(pattern=[\"tr\"], decision=\"allow\")\nprefix_rule(pattern=[\"echo\"], decision=\"allow\")\nprefix_rule(pattern=[\"printf\"], decision=\"allow\")\nprefix_rule(pattern=[\"printenv\"], decision=\"allow\")\nprefix_rule(pattern=[\"uname\"], decision=\"allow\")\nprefix_rule(pattern=[\"file\"], decision=\"allow\")\nprefix_rule(pattern=[\"stat\"], decision=\"allow\")\nprefix_rule(pattern=[\"du\"], decision=\"allow\")\nprefix_rule(pattern=[\"id\"], decision=\"allow\")\nprefix_rule(pattern=[\"whoami\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"git\", \"status\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"diff\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"log\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"show\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"blame\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"rev-parse\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"ls-files\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"grep\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"ls-tree\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"branch\", \"--show-current\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"branch\", \"-vv\"], decision=\"allow\")\nprefix_rule(pattern=[\"git\", \"mv\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"gh\", \"pr\", \"view\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"list\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"diff\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"status\"], decision=\"allow\")\nprefix_rule(pattern=[\"gh\", \"pr\", \"checks\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"docker\", \"ps\"], decision=\"allow\")\n\nprefix_rule(pattern=[\"git\", \"push\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"reset\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"clean\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"merge\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"rebase\"], decision=\"prompt\")\nprefix_rule(pattern=[\"git\", \"checkout\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"mv\"], decision=\"prompt\")\nprefix_rule(pattern=[\"chmod\"], decision=\"prompt\")\nprefix_rule(pattern=[\"chown\"], decision=\"prompt\")\nprefix_rule(pattern=[\"kill\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pkill\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"npm\", \"install\"], decision=\"prompt\")\nprefix_rule(pattern=[\"npm\", \"uninstall\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pnpm\", \"add\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pnpm\", \"remove\"], decision=\"prompt\")\nprefix_rule(pattern=[\"yarn\", \"add\"], decision=\"prompt\")\nprefix_rule(pattern=[\"yarn\", \"remove\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip\", \"install\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip\", \"uninstall\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip3\", \"install\"], decision=\"prompt\")\nprefix_rule(pattern=[\"pip3\", \"uninstall\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"docker\", \"run\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"stop\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"volume\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"system\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"up\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"down\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker\", \"compose\", \"stop\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"up\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"down\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"rm\"], decision=\"prompt\")\nprefix_rule(pattern=[\"docker-compose\", \"stop\"], decision=\"prompt\")\n\n# `tail -f`/`--follow` never returns and hangs the agent (bare `tail` stays allowed above).\nprefix_rule(pattern=[\"tail\", \"-f\"], decision=\"prompt\")\nprefix_rule(pattern=[\"tail\", \"--follow\"], decision=\"prompt\")\n# rg and `sed -n` are prompt, NOT allow: argv-prefix matching cannot gate their\n# code-exec forms (rg --pre=CMD or a reordered --pre; sed -n 'e CMD' / -ni) while a\n# shorter allow prefix would auto-approve the whole command.\nprefix_rule(pattern=[\"rg\"], decision=\"prompt\")\nprefix_rule(pattern=[\"sed\", \"-n\"], decision=\"prompt\")\nprefix_rule(pattern=[\"find\"], decision=\"prompt\")\nprefix_rule(pattern=[\"sed\", \"-i\"], decision=\"prompt\")\nprefix_rule(pattern=[\"sed\", \"--in-place\"], decision=\"prompt\")\nprefix_rule(pattern=[\"awk\"], decision=\"prompt\")\nprefix_rule(pattern=[\"xargs\"], decision=\"prompt\")\nprefix_rule(pattern=[\"tee\"], decision=\"prompt\")\nprefix_rule(pattern=[\"curl\"], decision=\"prompt\")\nprefix_rule(pattern=[\"env\"], decision=\"prompt\")\n\nprefix_rule(pattern=[\"sudo\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"eval\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"mkfs\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"dd\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"--force\", \"origin\", \"main\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"--force\", \"origin\", \"master\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"-f\", \"origin\", \"main\"], decision=\"forbidden\")\nprefix_rule(pattern=[\"git\", \"push\", \"-f\", \"origin\", \"master\"], decision=\"forbidden\")\n"
|
|
20
20
|
} as const
|
|
@@ -40,4 +40,4 @@ export const GENERATED_PAYLOAD_PATHS = [
|
|
|
40
40
|
"notification.mp3"
|
|
41
41
|
] as const
|
|
42
42
|
|
|
43
|
-
export const GENERATED_PAYLOAD_HASH = "
|
|
43
|
+
export const GENERATED_PAYLOAD_HASH = "4decac588a31cdaf6cbc88997bccb77add7bf0cbcfc3ae0fba30eca23525707d"
|
|
@@ -8,12 +8,14 @@ export type WorkflowTool = "claude" | "codex"
|
|
|
8
8
|
export type WorkflowCompany = "anthropic" | "openai"
|
|
9
9
|
export type WorkflowRoleName = "orchestrator" | "reviewer" | "implementer"
|
|
10
10
|
export type WorkflowBoundName = "minimum_score" | "max_rounds"
|
|
11
|
+
export type WorkflowServiceTier = "fast"
|
|
11
12
|
|
|
12
13
|
export interface WorkflowCandidate {
|
|
13
14
|
readonly company: WorkflowCompany
|
|
14
15
|
readonly tool: WorkflowTool
|
|
15
16
|
readonly model: string
|
|
16
17
|
readonly effort: string
|
|
18
|
+
readonly service_tier?: WorkflowServiceTier
|
|
17
19
|
}
|
|
18
20
|
|
|
19
21
|
export interface WorkflowRole {
|
|
@@ -32,6 +34,19 @@ export interface WorkflowRecordV1 {
|
|
|
32
34
|
}
|
|
33
35
|
}
|
|
34
36
|
|
|
37
|
+
export interface WorkflowRecordV2 {
|
|
38
|
+
readonly schema: 2
|
|
39
|
+
readonly orchestrator: WorkflowRole
|
|
40
|
+
readonly reviewer: WorkflowRole
|
|
41
|
+
readonly implementer: WorkflowRole
|
|
42
|
+
readonly review: {
|
|
43
|
+
readonly minimum_score: number
|
|
44
|
+
readonly max_rounds: number
|
|
45
|
+
}
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
export type WorkflowRecord = WorkflowRecordV1 | WorkflowRecordV2
|
|
49
|
+
|
|
35
50
|
export interface WorkflowOverrides {
|
|
36
51
|
readonly orchestrator?: string
|
|
37
52
|
readonly reviewer?: string
|
|
@@ -45,7 +60,7 @@ interface WorkflowProfile {
|
|
|
45
60
|
}
|
|
46
61
|
|
|
47
62
|
interface WorkflowRegistryCore {
|
|
48
|
-
readonly schema:
|
|
63
|
+
readonly schema: 2
|
|
49
64
|
readonly profiles: Readonly<Record<string, WorkflowProfile>>
|
|
50
65
|
readonly defaults: {
|
|
51
66
|
readonly orchestrator: string
|
|
@@ -56,7 +71,7 @@ interface WorkflowRegistryCore {
|
|
|
56
71
|
readonly max_rounds: number
|
|
57
72
|
}
|
|
58
73
|
}
|
|
59
|
-
readonly exact_target_grammar: "<tool>:<model>@<effort>"
|
|
74
|
+
readonly exact_target_grammar: "<tool>:<model>@<effort>[+fast]"
|
|
60
75
|
readonly availability: "checked_when_used"
|
|
61
76
|
}
|
|
62
77
|
|
|
@@ -117,9 +132,14 @@ const toolEfforts = (tool: WorkflowTool): ReadonlyArray<string> =>
|
|
|
117
132
|
function parseCandidate(
|
|
118
133
|
value: unknown,
|
|
119
134
|
label: string,
|
|
120
|
-
tools: WorkflowRegistryView["tools"]
|
|
135
|
+
tools: WorkflowRegistryView["tools"],
|
|
136
|
+
allowServiceTier: boolean
|
|
121
137
|
): WorkflowCandidate {
|
|
122
|
-
const
|
|
138
|
+
const serviceTier = isRecord(value) ? value["service_tier"] : undefined
|
|
139
|
+
const keys = serviceTier === undefined
|
|
140
|
+
? ["company", "effort", "model", "tool"]
|
|
141
|
+
: ["company", "effort", "model", "service_tier", "tool"]
|
|
142
|
+
const candidate = expectRecord(value, label, keys)
|
|
123
143
|
const tool = candidate["tool"]
|
|
124
144
|
if (tool !== "claude" && tool !== "codex") throw new Error(`${label} has an invalid tool`)
|
|
125
145
|
const company = candidate["company"]
|
|
@@ -133,18 +153,26 @@ function parseCandidate(
|
|
|
133
153
|
if (typeof effort !== "string" || !tools[tool].efforts.includes(effort)) {
|
|
134
154
|
throw new Error(`${label} has an unverified ${tool} effort`)
|
|
135
155
|
}
|
|
156
|
+
if (serviceTier !== undefined) {
|
|
157
|
+
if (!allowServiceTier) throw new Error(`${label} requires workflow record schema 2 for a service tier`)
|
|
158
|
+
if (tool !== "codex" || serviceTier !== "fast") throw new Error(`${label} has an invalid service tier`)
|
|
159
|
+
return { company: expectedCompany, tool, model, effort, service_tier: "fast" }
|
|
160
|
+
}
|
|
136
161
|
return { company: expectedCompany, tool, model, effort }
|
|
137
162
|
}
|
|
138
163
|
|
|
139
164
|
function parseCandidates(
|
|
140
165
|
value: unknown,
|
|
141
166
|
label: string,
|
|
142
|
-
tools: WorkflowRegistryView["tools"]
|
|
167
|
+
tools: WorkflowRegistryView["tools"],
|
|
168
|
+
allowServiceTier = false
|
|
143
169
|
): ReadonlyArray<WorkflowCandidate> {
|
|
144
170
|
if (!Array.isArray(value) || value.length < 1 || value.length > 3) {
|
|
145
171
|
throw new Error(`${label} must contain one to three candidates`)
|
|
146
172
|
}
|
|
147
|
-
return value.map((candidate, index) =>
|
|
173
|
+
return value.map((candidate, index) =>
|
|
174
|
+
parseCandidate(candidate, `${label}[${index}]`, tools, allowServiceTier)
|
|
175
|
+
)
|
|
148
176
|
}
|
|
149
177
|
|
|
150
178
|
function parseNumericBound(name: WorkflowBoundName, value: unknown): number {
|
|
@@ -167,24 +195,29 @@ function resolveSelector(
|
|
|
167
195
|
return { selector, candidates: profile.candidates }
|
|
168
196
|
}
|
|
169
197
|
|
|
170
|
-
const exactMatch = /^(claude|codex):([A-Za-z0-9._-]+)@([A-Za-z0-9._-]+)
|
|
198
|
+
const exactMatch = /^(claude|codex):([A-Za-z0-9._-]+)@([A-Za-z0-9._-]+)(\+fast)?$/.exec(selector)
|
|
171
199
|
if (exactMatch === null) {
|
|
172
200
|
throw new Error(
|
|
173
|
-
`Invalid workflow selector '${selector}' — expected profile:<name> or <tool>:<model>@<effort
|
|
201
|
+
`Invalid workflow selector '${selector}' — expected profile:<name> or <tool>:<model>@<effort>[+fast]`
|
|
174
202
|
)
|
|
175
203
|
}
|
|
176
204
|
const tool = exactMatch[1] as WorkflowTool
|
|
177
205
|
const model = exactMatch[2]!
|
|
178
206
|
const effort = exactMatch[3]!
|
|
207
|
+
const fast = exactMatch[4] !== undefined
|
|
179
208
|
if (!registry.tools[tool].models.includes(model)) {
|
|
180
209
|
throw new Error(`Unknown ${tool} workflow model '${model}'`)
|
|
181
210
|
}
|
|
182
211
|
if (!registry.tools[tool].efforts.includes(effort)) {
|
|
183
212
|
throw new Error(`Unknown ${tool} workflow effort '${effort}'`)
|
|
184
213
|
}
|
|
214
|
+
if (fast && tool !== "codex") {
|
|
215
|
+
throw new Error(`Invalid workflow selector '${selector}' — Fast is available only for Codex selectors`)
|
|
216
|
+
}
|
|
217
|
+
const candidate: WorkflowCandidate = { company: TOOL_COMPANIES[tool], tool, model, effort }
|
|
185
218
|
return {
|
|
186
219
|
selector,
|
|
187
|
-
candidates: [
|
|
220
|
+
candidates: [fast ? { ...candidate, service_tier: "fast" } : candidate]
|
|
188
221
|
}
|
|
189
222
|
}
|
|
190
223
|
|
|
@@ -199,8 +232,8 @@ function loadWorkflowRegistry(): WorkflowRegistryView {
|
|
|
199
232
|
"Embedded workflow registry",
|
|
200
233
|
["availability", "defaults", "exact_target_grammar", "profiles", "schema"]
|
|
201
234
|
)
|
|
202
|
-
if (workflow["schema"] !==
|
|
203
|
-
if (workflow["exact_target_grammar"] !== "<tool>:<model>@<effort>") {
|
|
235
|
+
if (workflow["schema"] !== 2) throw new Error("Embedded workflow registry schema must be 2")
|
|
236
|
+
if (workflow["exact_target_grammar"] !== "<tool>:<model>@<effort>[+fast]") {
|
|
204
237
|
throw new Error("Embedded workflow exact-target grammar is invalid")
|
|
205
238
|
}
|
|
206
239
|
if (workflow["availability"] !== "checked_when_used") {
|
|
@@ -234,7 +267,7 @@ function loadWorkflowRegistry(): WorkflowRegistryView {
|
|
|
234
267
|
if (typeof rawDefaults[role] !== "string") throw new Error(`Embedded workflow ${role} default is invalid`)
|
|
235
268
|
}
|
|
236
269
|
const registry: WorkflowRegistryView = {
|
|
237
|
-
schema:
|
|
270
|
+
schema: 2,
|
|
238
271
|
profiles,
|
|
239
272
|
defaults: {
|
|
240
273
|
orchestrator: rawDefaults["orchestrator"] as string,
|
|
@@ -246,7 +279,7 @@ function loadWorkflowRegistry(): WorkflowRegistryView {
|
|
|
246
279
|
}
|
|
247
280
|
},
|
|
248
281
|
tools,
|
|
249
|
-
exact_target_grammar: "<tool>:<model>@<effort>",
|
|
282
|
+
exact_target_grammar: "<tool>:<model>@<effort>[+fast]",
|
|
250
283
|
availability: "checked_when_used"
|
|
251
284
|
}
|
|
252
285
|
resolveSelector(registry.defaults.orchestrator, registry)
|
|
@@ -285,55 +318,74 @@ export function defaultWorkflowRecord(): WorkflowRecordV1 {
|
|
|
285
318
|
function parseRole(
|
|
286
319
|
value: unknown,
|
|
287
320
|
name: WorkflowRoleName,
|
|
288
|
-
registry: WorkflowRegistryView
|
|
321
|
+
registry: WorkflowRegistryView,
|
|
322
|
+
schema: 1 | 2
|
|
289
323
|
): WorkflowRole {
|
|
290
324
|
const role = expectRecord(value, `Workflow ${name} role`, ["candidates", "selector"])
|
|
291
325
|
if (typeof role["selector"] !== "string") throw new Error(`Workflow ${name} selector is invalid`)
|
|
292
326
|
const resolved = resolveSelector(role["selector"], registry)
|
|
293
|
-
const candidates = parseCandidates(
|
|
327
|
+
const candidates = parseCandidates(
|
|
328
|
+
role["candidates"],
|
|
329
|
+
`Workflow ${name} candidates`,
|
|
330
|
+
registry.tools,
|
|
331
|
+
schema === 2
|
|
332
|
+
)
|
|
294
333
|
if (compactJcs(candidates) !== compactJcs(resolved.candidates)) {
|
|
295
334
|
throw new Error(`Workflow ${name} candidates do not match its selector`)
|
|
296
335
|
}
|
|
297
336
|
return resolved
|
|
298
337
|
}
|
|
299
338
|
|
|
300
|
-
|
|
339
|
+
function recordUsesFast(roles: ReadonlyArray<WorkflowRole>): boolean {
|
|
340
|
+
return roles.some((role) => role.candidates.some((candidate) => candidate.service_tier === "fast"))
|
|
341
|
+
}
|
|
342
|
+
|
|
343
|
+
export function parseWorkflowRecord(value: unknown): WorkflowRecord {
|
|
301
344
|
const record = expectRecord(
|
|
302
345
|
value,
|
|
303
346
|
"Workflow record",
|
|
304
347
|
["implementer", "orchestrator", "review", "reviewer", "schema"]
|
|
305
348
|
)
|
|
306
|
-
|
|
349
|
+
const schema = record["schema"]
|
|
350
|
+
if (schema !== 1 && schema !== 2) throw new Error("Workflow record schema must be 1 or 2")
|
|
307
351
|
const registry = loadWorkflowRegistry()
|
|
308
352
|
const review = expectRecord(record["review"], "Workflow record review", ["max_rounds", "minimum_score"])
|
|
309
|
-
|
|
310
|
-
|
|
311
|
-
|
|
312
|
-
|
|
313
|
-
|
|
353
|
+
const orchestrator = parseRole(record["orchestrator"], "orchestrator", registry, schema)
|
|
354
|
+
const reviewer = parseRole(record["reviewer"], "reviewer", registry, schema)
|
|
355
|
+
const implementer = parseRole(record["implementer"], "implementer", registry, schema)
|
|
356
|
+
const parsed = {
|
|
357
|
+
orchestrator,
|
|
358
|
+
reviewer,
|
|
359
|
+
implementer,
|
|
314
360
|
review: {
|
|
315
361
|
minimum_score: parseNumericBound("minimum_score", review["minimum_score"]),
|
|
316
362
|
max_rounds: parseNumericBound("max_rounds", review["max_rounds"])
|
|
317
363
|
}
|
|
318
364
|
}
|
|
365
|
+
if (schema === 2 && !recordUsesFast([orchestrator, reviewer, implementer])) {
|
|
366
|
+
throw new Error("Workflow record schema 2 requires a Fast service tier")
|
|
367
|
+
}
|
|
368
|
+
return schema === 2 ? { schema: 2, ...parsed } : { schema: 1, ...parsed }
|
|
319
369
|
}
|
|
320
370
|
|
|
321
371
|
export function buildWorkflowRecord(
|
|
322
372
|
overrides: WorkflowOverrides,
|
|
323
|
-
base:
|
|
324
|
-
):
|
|
373
|
+
base: WorkflowRecord = defaultWorkflowRecord()
|
|
374
|
+
): WorkflowRecord {
|
|
325
375
|
const current = parseWorkflowRecord(base)
|
|
326
|
-
|
|
327
|
-
schema: 1,
|
|
328
|
-
orchestrator: overrides.orchestrator === undefined
|
|
376
|
+
const orchestrator = overrides.orchestrator === undefined
|
|
329
377
|
? current.orchestrator
|
|
330
|
-
: resolveWorkflowSelector(overrides.orchestrator)
|
|
331
|
-
|
|
378
|
+
: resolveWorkflowSelector(overrides.orchestrator)
|
|
379
|
+
const reviewer = overrides.reviewer === undefined
|
|
332
380
|
? current.reviewer
|
|
333
|
-
: resolveWorkflowSelector(overrides.reviewer)
|
|
334
|
-
|
|
381
|
+
: resolveWorkflowSelector(overrides.reviewer)
|
|
382
|
+
const implementer = overrides.implementer === undefined
|
|
335
383
|
? current.implementer
|
|
336
|
-
: resolveWorkflowSelector(overrides.implementer)
|
|
384
|
+
: resolveWorkflowSelector(overrides.implementer)
|
|
385
|
+
const next = {
|
|
386
|
+
orchestrator,
|
|
387
|
+
reviewer,
|
|
388
|
+
implementer,
|
|
337
389
|
review: {
|
|
338
390
|
minimum_score: overrides.minimumScore === undefined
|
|
339
391
|
? current.review.minimum_score
|
|
@@ -343,6 +395,9 @@ export function buildWorkflowRecord(
|
|
|
343
395
|
: parseWorkflowBound("max_rounds", overrides.maxRounds)
|
|
344
396
|
}
|
|
345
397
|
}
|
|
398
|
+
return recordUsesFast([orchestrator, reviewer, implementer])
|
|
399
|
+
? { schema: 2, ...next }
|
|
400
|
+
: { schema: 1, ...next }
|
|
346
401
|
}
|
|
347
402
|
|
|
348
403
|
function canonicalValue(value: unknown): unknown {
|
|
@@ -366,7 +421,7 @@ export function compactJcs(value: unknown): string {
|
|
|
366
421
|
return JSON.stringify(canonicalValue(value))
|
|
367
422
|
}
|
|
368
423
|
|
|
369
|
-
export function renderWorkflowRecordLine(record:
|
|
424
|
+
export function renderWorkflowRecordLine(record: WorkflowRecord): string {
|
|
370
425
|
return `${WORKFLOW_RECORD_PREFIX}${compactJcs(parseWorkflowRecord(record))}`
|
|
371
426
|
}
|
|
372
427
|
|
|
@@ -390,6 +445,8 @@ export function workflowCatalog(): string {
|
|
|
390
445
|
` implementer ${registry.defaults.implementer}`,
|
|
391
446
|
` review minimum score ${registry.defaults.review.minimum_score}; maximum rounds ${registry.defaults.review.max_rounds}`,
|
|
392
447
|
`Exact targets: ${registry.exact_target_grammar}`,
|
|
448
|
+
"Fast: append +fast to a Codex exact target. Without +fast, Codex roles use Standard.",
|
|
449
|
+
"Compatibility: +fast requires a Docks consumer that supports workflow record schema 2.",
|
|
393
450
|
"Availability: checked when used by Docks; docks-kit does not probe providers."
|
|
394
451
|
].join("\n")
|
|
395
452
|
}
|
package/package.json
CHANGED