docks-kit 0.20.2 → 0.20.4
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 +3 -2
- package/README.md +1 -0
- package/cli/docs/flags.md +5 -2
- package/cli/docs/omp-models.md +47 -21
- package/cli/src/commands/omp.ts +33 -2
- package/cli/src/engine-native/codexPlugins.ts +2 -3
- package/cli/src/engine-native/exec.ts +17 -0
- package/cli/src/engine-native/ompFastMode.ts +56 -0
- package/cli/src/engine-native/ompMarketplace.ts +5 -10
- package/cli/src/engine-native/ompPlugins.ts +2 -3
- package/cli/src/generated/sotPayload.ts +3 -3
- package/package.json +1 -1
package/AGENTS.md
CHANGED
|
@@ -75,8 +75,8 @@ omp SoT notes:
|
|
|
75
75
|
- `ompSync.ts syncMergedYaml` deep-merges `config.yml` through `ompYaml.ts mergeOmpConfig` and `models.yml` through `mergeOmpModels`. Both wrap one generic mapping merge; only the config wrapper prunes stale `retry.fallbackChains` wildcards.
|
|
76
76
|
- `ompSync.ts` runs `ompRemovals.ts syncOmpRemovals, retired-key inventory` right after the config merge, and that pass force-prunes retired kit-owned keys from `~/.omp/agent/config.yml` on every sync, without `--reconcile`. The pass is required because `mergeOmpConfig` is additive, so removing a key from the SoT alone never removes it from a deployed file. A key retired with a recorded value is pruned only while the deployed value still matches that value, so a user edit survives; a key retired outright, such as `providers.webSearchOrder`, is pruned at any value.
|
|
77
77
|
- `cycleOrder` ends with `astra` as its fifth stop. `modelRoles.astra` is `openai-codex/gpt-6-astra:xhigh`, and `modelTags.astra` is visible. Astra and Fable fall back to each other through concrete selectors. `modelRoles.fable` remains `anthropic/claude-fable-5-1:medium`, with visible `modelTags.fable`. The hidden `switch_fable` role uses the same Fable selector and keeps an empty fallback chain.
|
|
78
|
-
- `modelRoles.task` is `openai-codex/gpt-6.1-sol:high`. `advisor` is `anthropic/claude-opus-5-5:medium` with an empty fallback chain, because a GPT-6 Sol advisor looped on repeated reads under an Opus 5.5 session. Never put any GPT model (`openai-codex/gpt-*`, including GPT-6.1 Sol and GPT-6 Astra) in the advisor role or chain; Astra also costs too much for this role. `smol`, `commit`, and `tiny` use `openai-codex/gpt-6-luna`. The four reviewer entries in `task.agentModelOverrides` inherit `task` through `@task`. Only bundled `reviewer` and `security-reviewer` are discoverable OMP agents; `code-reviewer` and `plan-reviewer` stay dormant. The `SoT/toolchain.json` omp floor is 18.4.4, the oldest release the kit tested with `gpt-6.1-sol`. That release lists and serves the model through the `openai-codex` provider. `cli/docs/omp-models.md` records the checks.
|
|
79
|
-
- The
|
|
78
|
+
- `modelRoles.task` is `anthropic/claude-opus-5-5:high`, and `retry.fallbackChains.task` falls back to `openai-codex/gpt-6.1-sol:high`. `task.maxEffort` is `xhigh`: a caller `effort: hi` outranks the role's `:high` suffix and maps to the top of the model ladder, so the cap keeps `hi` at `xhigh` instead of `max`. `advisor` is `anthropic/claude-opus-5-5:medium` with an empty fallback chain, because a GPT-6 Sol advisor looped on repeated reads under an Opus 5.5 session. Never put any GPT model (`openai-codex/gpt-*`, including GPT-6.1 Sol and GPT-6 Astra) in the advisor role or chain; Astra also costs too much for this role. `smol`, `commit`, and `tiny` use `openai-codex/gpt-6-luna`. The four reviewer entries in `task.agentModelOverrides` inherit `task` through `@task`. Only bundled `reviewer` and `security-reviewer` are discoverable OMP agents; `code-reviewer` and `plan-reviewer` stay dormant. The `SoT/toolchain.json` omp floor is 18.4.4, the oldest release the kit tested with `gpt-6.1-sol`. That release lists and serves the model through the `openai-codex` provider. `cli/docs/omp-models.md` records the checks.
|
|
79
|
+
- The six Anthropic roles (`default`, `slow`, `plan`, `designer`, `vision`, `task`) and the `smol`, `tiny`, and `commit` retry chains use `anthropic/claude-opus-5-5` at the levels the role map records. `cli/docs/omp-models.md` carries the Artificial Analysis capture behind the role map, read 2026-09-29 at Intelligence Index v4.3.2 and Coding Agent Index v1.5 from the AA comparison-page metric tables. Opus 5.5 max has the highest index in that topic, at 58. AA has measured speed and latency for Opus 5.5 max and every GPT-6.1 Sol level; GPT-6 Luna medium is the only unmeasured speed and latency row.
|
|
80
80
|
- `modelRoles.web` is `web/firecrawl` and `retry.fallbackChains.web` carries the explicit 20-entry provider order. The kit declares both keys because the legacy `providers.webSearchOrder` key is retired: omp expands it in memory into these two keys and then drops it, and never writes that expansion back to disk. An explicit chain replaces omp's built-in web order wholesale, so every entry left out is a provider omp never tries. The owner removed the seven entries that named older models (Gemini 2.5 Flash, Claude Haiku 4.5, GPT-5.6, GPT-5.5, and Grok 4.5); keep every other provider.
|
|
81
81
|
- `SoT/.omp/models.yml` declares Astra's full `low, medium, high, xhigh, max` ladder with `defaultLevel: xhigh` as the worked provider ladder-override example. The temporary `anthropic.modelOverrides.claude-opus-5-5` block is gone, because the shared catalog now publishes the same limits, ladder, and prices. The removal switches omp from the block's `thinking.mode: effort` (a `budget_tokens` value per level from `ANTHROPIC_THINKING`, no effort value) to the catalog's `anthropic-adaptive` (adaptive thinking with the role's effort level); every kit Opus selector names its level, so the block's bare-selector `defaultLevel: high` is not needed. `ompRemovals.ts syncOmpModelRemovals, retired-block inventory` prunes it from `~/.omp/agent/models.yml` after the models merge, but only while the deployed block still equals the shipped one. `ompYaml.ts mergeOmpModels` preserves deployed-only keys in `~/.omp/agent/models.yml`, because a user file may carry provider credentials. Whole-file replacement is wrong.
|
|
82
82
|
- `SoT/.omp/AGENTS.md` carries the rule `Please remove all mannered prose.` Anthropic's Fable 5.1 prompting guide documents mannered prose as a Fable 5.1 behavior and gives that sentence as its short-version fix: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1
|
|
@@ -87,6 +87,7 @@ omp SoT notes:
|
|
|
87
87
|
- The omp CLI is upstream-owned and self-updating through `omp update`. Sync never installs or upgrades the CLI.
|
|
88
88
|
- `docks-kit omp [--model <selector>|--pick] [args...]` starts one interactive omp session with every model role set to one free model and every retry chain empty. Higher-precedence model selection can replace those overlay values. It renders the overlay to `~/.cache/docks-kit/omp-free-<model>-<digest>.yml` (mode 0600) and passes it through omp's repeatable `--config` flag. `ompOverlay.ts overlayFileName` gives each model its own file, because omp can re-read the overlay during a live session and a second launcher on another model must not rewrite it. Deployed `~/.omp/agent/` files stay untouched, so the next plain `omp` run uses the paid configuration again. Remaining arguments forward verbatim to omp.
|
|
89
89
|
- The session model persists per machine in `~/.docks-kit/kit.db` (table `omp_session`), next to the harness selection. The default is `opencode-zen/muse-spark-1.3-contributor-free` at `xhigh`. `ompOverlay.ts ladderCeiling, advisorLevelFor` derive both levels from the ladder of the chosen model for the `--model` path, and `ompOverlay.ts planEffortChoice` drives the `--pick` wizard, which asks whether every role shares one level and otherwise takes one level for the main roles and one for the advisor from that model's own ladder. Levels never come from a fixed list: free ladders are not uniform, three free models publish no `medium`, and two publish no ladder, which the overlay renders as bare selectors. The picker lists only zero-cost catalog models.
|
|
90
|
+
- `docks-kit omp --fast` toggles `tier.openai` in the deployed `~/.omp/agent/config.yml` between `priority` (omp's `/fast on` tier for OpenAI and OpenAI-Codex models) and `none`, prints the change, and exits. `ompFastMode.ts toggleOpenAiFast` edits only that key. `SoT/.omp/config.yml` does not declare `tier.openai`, so the additive merge keeps the toggled value across sync. There is no Ultrafast flag: omp ignores `ultrafast` for a Codex model whose catalog `serviceTiers` omits it, and the current GPT models omit it.
|
|
90
91
|
|
|
91
92
|
For per-tool SoT layouts (`SoT/.claude/`, `SoT/.codex/`, `SoT/.omp/`), see the matching SoT directory.
|
|
92
93
|
|
package/README.md
CHANGED
|
@@ -49,6 +49,7 @@ docks-kit update [--no-sync] self-update the kit (autodetects
|
|
|
49
49
|
docks-kit model <claude|codex> [value] get/set the DEPLOYED model (TTY picker)
|
|
50
50
|
docks-kit models [claude|codex|omp] [--refresh] live catalogs for enabled harnesses (`--json`)
|
|
51
51
|
docks-kit omp [--model <m>|--pick] [args...] one omp session on a free model, nothing deployed changes
|
|
52
|
+
docks-kit omp --fast toggle omp fast mode for OpenAI/Codex models, then exit
|
|
52
53
|
docks-kit toolchain [check|ensure <tool>|outdated|upgrade] verified-version floors for external tools
|
|
53
54
|
docks-kit status [--json] deployed-vs-SoT drift + toolchain + counts
|
|
54
55
|
docks-kit plugins list [--json] enabledPlugins tri-state vs installed
|
package/cli/docs/flags.md
CHANGED
|
@@ -58,16 +58,19 @@ ignored with a warning; Claude modifiers never touch Codex config and vice versa
|
|
|
58
58
|
|------|--------|
|
|
59
59
|
| `--model <selector>` | Session model for this run and later runs; rejected unless the live catalog reports zero input and output cost; recorded in `~/.docks-kit/kit.db` (table `omp_session`) |
|
|
60
60
|
| `--pick` | Interactive picker over free catalog models; records the choice the same way |
|
|
61
|
+
| `--fast` | Toggle `tier.openai` between `priority` and `none` in the deployed `~/.omp/agent/config.yml`, print the change, and exit; the same tier omp's `/fast on` selects for OpenAI and Codex models |
|
|
61
62
|
|
|
62
63
|
Remaining arguments forward verbatim to omp after the launcher flags.
|
|
63
64
|
`docks-kit omp -p "..."` runs one prompt. `docks-kit omp --continue` resumes
|
|
64
65
|
the previous session. A bare `docks-kit omp` opens an interactive session.
|
|
65
|
-
The launcher changes no deployed file and never invokes `sync
|
|
66
|
+
The launcher changes no deployed file and never invokes `sync`, except for
|
|
67
|
+
`--fast`, which changes only `tier.openai` and launches nothing. `--fast` over
|
|
68
|
+
`ultrafast` selects `priority`.
|
|
66
69
|
The boundary opens at the first token that is neither a declared launcher
|
|
67
70
|
flag nor a declared global flag. Declared flags stay with docks-kit and
|
|
68
71
|
never reach omp:
|
|
69
72
|
|
|
70
|
-
- `--model`, `--pick`
|
|
73
|
+
- `--model`, `--pick`, `--fast`
|
|
71
74
|
- `--help`, `--version`, `--log-level`, `--wizard`, `--completions`
|
|
72
75
|
|
|
73
76
|
The same names on omp stay reachable behind an explicit delimiter. Use
|
package/cli/docs/omp-models.md
CHANGED
|
@@ -11,7 +11,7 @@ against.
|
|
|
11
11
|
| `default` | `anthropic/claude-opus-5-5` | high | 54 | $1.82 | 52.85 s |
|
|
12
12
|
| `slow` | `anthropic/claude-opus-5-5` | xhigh | 56 | $3.46 | 136.30 s |
|
|
13
13
|
| `plan` | `anthropic/claude-opus-5-5` | xhigh | 56 | $3.46 | 136.30 s |
|
|
14
|
-
| `task` | `
|
|
14
|
+
| `task` | `anthropic/claude-opus-5-5` | high | 54 | $1.82 | 52.85 s |
|
|
15
15
|
| `advisor` | `anthropic/claude-opus-5-5` | medium | 51 | $1.34 | 21.87 s |
|
|
16
16
|
| `designer` | `anthropic/claude-opus-5-5` | high | 54 | $1.82 | 52.85 s |
|
|
17
17
|
| `vision` | `anthropic/claude-opus-5-5` | medium | 51 | $1.34 | 21.87 s |
|
|
@@ -83,7 +83,7 @@ and `security-reviewer` exist as OMP agents (omp's task tool lists `scout`,
|
|
|
83
83
|
`reviewer`, `security-reviewer`, `task`, and `sonic`), so those two inherit
|
|
84
84
|
whatever `task` resolves to. The `code-reviewer` and `plan-reviewer` entries
|
|
85
85
|
are dormant until an OMP agent with that name exists.
|
|
86
|
-
`retry.fallbackChains.task`
|
|
86
|
+
`retry.fallbackChains.task` holds `openai-codex/gpt-6.1-sol:high` as a
|
|
87
87
|
cross-vendor fallback.
|
|
88
88
|
|
|
89
89
|
`retry.fallbackChains.astra` holds `anthropic/claude-fable-5-1:medium`.
|
|
@@ -317,14 +317,16 @@ baseline for the GPT-6 Luna switch.
|
|
|
317
317
|
|
|
318
318
|
Price: $0.20 in, $1.20 out, $0.02 cache hit per 1M. Context 1M.
|
|
319
319
|
|
|
320
|
-
## Why `task` runs
|
|
320
|
+
## Why `task` runs Opus 5.5 high
|
|
321
321
|
|
|
322
|
-
`task` runs `
|
|
323
|
-
|
|
324
|
-
|
|
325
|
-
Astra
|
|
322
|
+
`task` runs `anthropic/claude-opus-5-5:high`, the same model and level as
|
|
323
|
+
`default`. The owner moved it from `openai-codex/gpt-6.1-sol:high` on
|
|
324
|
+
2026-10-09. GPT-6.1 Sol high is now the `task` retry fallback. The owner uses
|
|
325
|
+
Astra only for main orchestration, so Astra has a dedicated `astra` cycle stop
|
|
326
|
+
at `xhigh`. This comparison keeps the retired Astra-low, GPT-5.6 Sol, and
|
|
327
|
+
GPT-6.1 Sol choices beside the current Opus level.
|
|
326
328
|
|
|
327
|
-
| Metric | Astra low, retired | GPT-5.6 Sol high,
|
|
329
|
+
| Metric | Astra low, retired | GPT-5.6 Sol high, retired | GPT-6.1 Sol high, fallback | GPT-6.1 Sol max | Opus 5.5 high, current |
|
|
328
330
|
|---|---:|---:|---:|---:|---:|
|
|
329
331
|
| Intelligence Index | 46 | 42 | 50 | 52 | 54 |
|
|
330
332
|
| Cost per Index task | $0.82 | $0.81 | $0.32 | $0.72 | $1.82 |
|
|
@@ -349,9 +351,11 @@ $0.32 per index task. Astra low has the shorter TTFT, 2.81 s against
|
|
|
349
351
|
|
|
350
352
|
GPT-6.1 Sol max scores two index points above high, at 52 against 50. It
|
|
351
353
|
costs $0.72 against $0.32 per index task, with TTFT of 267.64 s against
|
|
352
|
-
57.26 s.
|
|
353
|
-
|
|
354
|
-
|
|
354
|
+
57.26 s.
|
|
355
|
+
|
|
356
|
+
Opus 5.5 high scores 54 against GPT-6.1 Sol high at 50, 57% against 52% on
|
|
357
|
+
Terminal-Bench 4.0, and 1705 against 1471 on AA-Briefcase. It costs $1.82
|
|
358
|
+
against $0.32 per index task. Its answer TTFT is 52.85 s against 57.26 s.
|
|
355
359
|
|
|
356
360
|
The `astra` cycle stop runs xhigh: index 52, $2.31 per index task, and
|
|
357
361
|
126.90 s TTFT. AA publishes a Coding Agent Index entry for Astra only at
|
|
@@ -373,19 +377,28 @@ quick answer.
|
|
|
373
377
|
|
|
374
378
|
- The bundled `scout` and `sonic` agents carry `model: "@smol"` and
|
|
375
379
|
`thinking-level: medium` in their embedded frontmatter, so they run Luna,
|
|
376
|
-
not
|
|
380
|
+
not Opus 5.5 or Astra. To move them, change `modelRoles.smol` or add a
|
|
377
381
|
`task.agentModelOverrides` entry for the agent name.
|
|
378
382
|
- The bundled `task` agent carries `model: "@task"` and
|
|
379
|
-
`thinking-level: auto`. It resolves
|
|
380
|
-
|
|
383
|
+
`thinking-level: auto`. It resolves Opus 5.5 high. The `:high` suffix on
|
|
384
|
+
`modelRoles.task` is an explicit level, so it outranks the agent's `auto`,
|
|
385
|
+
and the auto classifier does not run for a `task` spawn.
|
|
381
386
|
- `task.enableEffort` is `true`, so a caller can pass `effort: lo`, `med`, or
|
|
382
|
-
`hi
|
|
383
|
-
|
|
384
|
-
|
|
387
|
+
`hi`. Caller effort outranks the role suffix. omp maps it onto the model's
|
|
388
|
+
own ladder, not onto level names: `lo` selects the lowest level, `med` the
|
|
389
|
+
lower middle, and `hi` the highest (`resolveTaskEffortLevel` in omp's
|
|
390
|
+
`packages/tui/src/thinking.ts`, omp 18.8.5). Then omp caps the result at
|
|
391
|
+
`task.maxEffort`.
|
|
392
|
+
- `task.maxEffort` is `xhigh`. On the `low, medium, high, xhigh, max` ladder
|
|
393
|
+
that Opus 5.5, GPT-6.1 Sol, and GPT-6 Luna publish, `lo` gives `low`, `med`
|
|
394
|
+
gives `high`, and `hi` gives `xhigh`. With the former `max` ceiling, `hi`
|
|
395
|
+
gave `max`: on 2026-10-09, `task` spawns with `effort: hi` ran GPT-6.1 Sol
|
|
396
|
+
at `max` despite the `:high` role suffix. `scout` and `sonic` run GPT-6 Luna
|
|
397
|
+
`medium` by default and GPT-6 Luna `xhigh` with `effort: hi`.
|
|
385
398
|
- The bundled `reviewer` and `security-reviewer` inherit `@task`, now
|
|
386
|
-
|
|
399
|
+
Opus 5.5 high.
|
|
387
400
|
- The `code-reviewer` and `plan-reviewer` override entries remain dormant.
|
|
388
|
-
Both point to `@task`, now
|
|
401
|
+
Both point to `@task`, now Opus 5.5 high. omp's task tool rejects both
|
|
389
402
|
names as unknown agents, so neither can spawn.
|
|
390
403
|
|
|
391
404
|
The runtime per-agent measurement from fresh `omp -p` runs on 2026-09-09
|
|
@@ -412,8 +425,9 @@ through omp's repeatable `--config` flag. Each model gets its own file,
|
|
|
412
425
|
because omp can re-read the overlay during a live session, and a second
|
|
413
426
|
launcher on another model must not rewrite that file. The name sanitizes the
|
|
414
427
|
selector for the file system and appends a digest of the exact selector, so
|
|
415
|
-
two selectors that differ only in separator characters stay apart.
|
|
416
|
-
|
|
428
|
+
two selectors that differ only in separator characters stay apart. A session
|
|
429
|
+
launch never reads or writes `~/.omp/agent/config.yml` or `models.yml`; only
|
|
430
|
+
`--fast`, below, edits `config.yml`. It
|
|
417
431
|
never touches the SoT. The next plain `omp` run uses the paid configuration
|
|
418
432
|
again.
|
|
419
433
|
|
|
@@ -501,6 +515,18 @@ are derived from the catalog row of the chosen model, and under `--pick` the
|
|
|
501
515
|
user chooses them from the ladder that same row publishes. Refresh the
|
|
502
516
|
recorded default and the ladder counts in these docs in the same commit.
|
|
503
517
|
|
|
518
|
+
## OpenAI fast mode (`docks-kit omp --fast`)
|
|
519
|
+
|
|
520
|
+
`docks-kit omp --fast` toggles `tier.openai` in the deployed
|
|
521
|
+
`~/.omp/agent/config.yml` between `priority` and `none`, prints the old and new
|
|
522
|
+
values, and exits without starting a session. `priority` is the tier omp's
|
|
523
|
+
`/fast on` selects for OpenAI and OpenAI-Codex models. `--fast` over
|
|
524
|
+
`ultrafast` selects `priority`. The kit ships no Ultrafast toggle: omp honors
|
|
525
|
+
`ultrafast` for a Codex model only when its catalog `serviceTiers` lists it,
|
|
526
|
+
and the omp 18.4.9 catalog lists none for GPT-6.1 Sol, Astra, or Luna. The SoT
|
|
527
|
+
does not declare `tier.openai`, so the additive sync merge keeps the toggled
|
|
528
|
+
value. New sessions read it; a running session changes through `/fast`.
|
|
529
|
+
|
|
504
530
|
## Maintenance
|
|
505
531
|
|
|
506
532
|
- Refresh each per-level row from the metric table of
|
package/cli/src/commands/omp.ts
CHANGED
|
@@ -21,6 +21,8 @@ import {
|
|
|
21
21
|
renderFreeOverlay,
|
|
22
22
|
type CatalogModel,
|
|
23
23
|
} from "../engine-native/ompOverlay";
|
|
24
|
+
import { FAST_ON_TIER, toggleDeployedOpenAiFast } from "../engine-native/ompFastMode";
|
|
25
|
+
import { ompPaths } from "../engine-native/ompPaths";
|
|
24
26
|
|
|
25
27
|
const model = Flag.String("model").pipe(
|
|
26
28
|
Flag.withDescription("Free model selector to use and remember for omp sessions"),
|
|
@@ -30,6 +32,12 @@ const pick = Flag.Boolean("pick").pipe(
|
|
|
30
32
|
Flag.withDescription("Choose the free model interactively"),
|
|
31
33
|
Flag.withDefault(false),
|
|
32
34
|
);
|
|
35
|
+
const fast = Flag.Boolean("fast").pipe(
|
|
36
|
+
Flag.withDescription(
|
|
37
|
+
"Toggle fast mode (tier.openai priority/none) for OpenAI and Codex models in the deployed omp config, then exit",
|
|
38
|
+
),
|
|
39
|
+
Flag.withDefault(false),
|
|
40
|
+
);
|
|
33
41
|
const args: Argument.Argument<ReadonlyArray<string>> = Argument.String("args").pipe(
|
|
34
42
|
Argument.withDescription("Arguments forwarded verbatim to omp"),
|
|
35
43
|
Argument.variadic(),
|
|
@@ -163,12 +171,35 @@ const pickLevels = (catalogModel: CatalogModel) =>
|
|
|
163
171
|
return { thinking, advisorThinking };
|
|
164
172
|
});
|
|
165
173
|
|
|
166
|
-
export const ompCommand = Command.make("omp", { model, pick, args }, (config) =>
|
|
174
|
+
export const ompCommand = Command.make("omp", { model, pick, fast, args }, (config) =>
|
|
167
175
|
Effect.gen(function* () {
|
|
168
176
|
if (Option.isSome(config.model) && config.pick) {
|
|
169
177
|
return yield* bail("Pass either --model <selector> or --pick, not both");
|
|
170
178
|
}
|
|
171
179
|
|
|
180
|
+
if (config.fast) {
|
|
181
|
+
if (Option.isSome(config.model) || config.pick || config.args.length > 0) {
|
|
182
|
+
return yield* bail("--fast toggles fast mode and exits; pass it alone");
|
|
183
|
+
}
|
|
184
|
+
const configPath = p(
|
|
185
|
+
ompPaths({ home: engineHome(process.env), env: process.env, platform: process.platform })
|
|
186
|
+
.agentDir,
|
|
187
|
+
"config.yml",
|
|
188
|
+
);
|
|
189
|
+
const toggle = yield* Effect.try({
|
|
190
|
+
try: () => toggleDeployedOpenAiFast(configPath),
|
|
191
|
+
catch: (error) => (error instanceof Error ? error.message : String(error)),
|
|
192
|
+
}).pipe(Effect.catch((message) => bail(message)));
|
|
193
|
+
const state = toggle.next === FAST_ON_TIER ? "ON" : "OFF";
|
|
194
|
+
yield* Console.log(
|
|
195
|
+
`omp fast mode ${state} for OpenAI/Codex models: tier.openai ${toggle.previous} -> ${toggle.next} in ${configPath}`,
|
|
196
|
+
);
|
|
197
|
+
yield* Console.log(
|
|
198
|
+
"New omp sessions use it; in a running session, use /fast on|off or restart omp.",
|
|
199
|
+
);
|
|
200
|
+
return;
|
|
201
|
+
}
|
|
202
|
+
|
|
172
203
|
const omp = yield* Effect.sync(() => which("omp"));
|
|
173
204
|
if (omp === "") {
|
|
174
205
|
return yield* bail("omp not found on PATH; install omp, then retry", 1);
|
|
@@ -274,6 +305,6 @@ export const ompCommand = Command.make("omp", { model, pick, args }, (config) =>
|
|
|
274
305
|
}),
|
|
275
306
|
).pipe(
|
|
276
307
|
Command.withDescription(
|
|
277
|
-
"Start omp with every model role overridden to the remembered free model for this run only (no deployed configuration is changed; --model or --pick remembers a new free default).",
|
|
308
|
+
"Start omp with every model role overridden to the remembered free model for this run only (no deployed configuration is changed; --model or --pick remembers a new free default). --fast instead toggles OpenAI/Codex fast mode in the deployed omp config and exits.",
|
|
278
309
|
),
|
|
279
310
|
);
|
|
@@ -15,7 +15,7 @@ import {
|
|
|
15
15
|
import { payloadDisplayPath } from "../payload";
|
|
16
16
|
import { PLUGIN_TABLE_HEADER } from "./codexConfig";
|
|
17
17
|
import { isTomlHeaderLine } from "./codexToml";
|
|
18
|
-
import { p, spawnProcess } from "./exec";
|
|
18
|
+
import { p, processFailureSummary, spawnProcess } from "./exec";
|
|
19
19
|
import { recordFailure } from "./failures";
|
|
20
20
|
import type { Ctx } from "./index";
|
|
21
21
|
import { compareCodepoints, isObject, jqStringify, parseJson, type Json } from "./jq";
|
|
@@ -271,10 +271,9 @@ export async function syncPlugins(ctx: Ctx, sotConfigText: string): Promise<void
|
|
|
271
271
|
);
|
|
272
272
|
failed++;
|
|
273
273
|
} else {
|
|
274
|
-
const failureLine = addOut.split("\n")[0] ?? "";
|
|
275
274
|
recordFailure(
|
|
276
275
|
ctx,
|
|
277
|
-
`Codex plugin refresh failed for ${pluginId}: ${
|
|
276
|
+
`Codex plugin refresh failed for ${pluginId}: ${processFailureSummary(res)}; run manually: codex plugin add ${pluginId}`,
|
|
278
277
|
);
|
|
279
278
|
failed++;
|
|
280
279
|
}
|
|
@@ -72,6 +72,23 @@ export interface AsyncProcessResult {
|
|
|
72
72
|
readonly error?: Error;
|
|
73
73
|
}
|
|
74
74
|
|
|
75
|
+
/**
|
|
76
|
+
* One-line failure text for a warning. A harness CLI that wraps git puts its own
|
|
77
|
+
* message first, and the first line alone is often only git's `Cloning into`
|
|
78
|
+
* line. Keep the first line and add the first later `fatal:` or `error:` line,
|
|
79
|
+
* or the last line when no such line exists, because the CLI can print more
|
|
80
|
+
* text after git's error.
|
|
81
|
+
*/
|
|
82
|
+
export function processFailureSummary(result: AsyncProcessResult): string {
|
|
83
|
+
const lines = [...result.stdout.split("\n"), ...result.stderr.split("\n")]
|
|
84
|
+
.map((line) => line.trim())
|
|
85
|
+
.filter((line) => line !== "");
|
|
86
|
+
const [first, ...rest] = lines;
|
|
87
|
+
if (first === undefined) return result.error?.message ?? "unknown error";
|
|
88
|
+
const cause = rest.find((line) => /^(fatal|error):/i.test(line)) ?? rest.at(-1);
|
|
89
|
+
return cause === undefined ? first : `${first} | ${cause}`;
|
|
90
|
+
}
|
|
91
|
+
|
|
75
92
|
export interface AsyncProcessOptions {
|
|
76
93
|
readonly stdio?: SpawnOptions["stdio"];
|
|
77
94
|
/** Host whose executable resolution and argv shaping apply; tests inject it. */
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* `docks-kit omp --fast` toggles omp's OpenAI service tier in the deployed
|
|
3
|
+
* config.yml. `tier.openai: priority` is what omp's `/fast on` selects for
|
|
4
|
+
* OpenAI and OpenAI-Codex models; `none` omits `service_tier`. The SoT does not
|
|
5
|
+
* declare `tier.openai`, so the additive sync merge keeps the toggled value.
|
|
6
|
+
*/
|
|
7
|
+
import { chmodSync, existsSync, readFileSync, renameSync, writeFileSync } from "node:fs";
|
|
8
|
+
import { isMap, parseDocument } from "yaml";
|
|
9
|
+
|
|
10
|
+
export const FAST_ON_TIER = "priority";
|
|
11
|
+
export const FAST_OFF_TIER = "none";
|
|
12
|
+
|
|
13
|
+
export interface FastToggle {
|
|
14
|
+
/** The deployed `tier.openai` value before the toggle; omp's default `none` when unset. */
|
|
15
|
+
readonly previous: string;
|
|
16
|
+
readonly next: typeof FAST_ON_TIER | typeof FAST_OFF_TIER;
|
|
17
|
+
readonly text: string;
|
|
18
|
+
}
|
|
19
|
+
|
|
20
|
+
/**
|
|
21
|
+
* Pure toggle over config.yml text; edits only `tier.openai`. Only `priority`
|
|
22
|
+
* counts as on, so any other tier, `ultrafast` included, switches to plain fast.
|
|
23
|
+
*/
|
|
24
|
+
export function toggleOpenAiFast(configText: string): FastToggle {
|
|
25
|
+
const doc = parseDocument(configText);
|
|
26
|
+
const parseError = doc.errors[0];
|
|
27
|
+
if (parseError !== undefined) {
|
|
28
|
+
throw new Error(`Invalid omp config.yml YAML: ${parseError.message}`);
|
|
29
|
+
}
|
|
30
|
+
if (doc.contents !== null && !isMap(doc.contents)) {
|
|
31
|
+
throw new Error("omp config.yml root must be a mapping");
|
|
32
|
+
}
|
|
33
|
+
const tier = doc.get("tier", true);
|
|
34
|
+
if (tier !== undefined && tier !== null && !isMap(tier)) {
|
|
35
|
+
throw new Error("omp config.yml key 'tier' must be a mapping");
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
const current = doc.getIn(["tier", "openai"]);
|
|
39
|
+
const previous = typeof current === "string" && current !== "" ? current : FAST_OFF_TIER;
|
|
40
|
+
const next = previous === FAST_ON_TIER ? FAST_OFF_TIER : FAST_ON_TIER;
|
|
41
|
+
doc.setIn(["tier", "openai"], next);
|
|
42
|
+
return { previous, next, text: doc.toString() };
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
/** Toggle `tier.openai` in the deployed config.yml with an atomic 0600 write. */
|
|
46
|
+
export function toggleDeployedOpenAiFast(configPath: string): FastToggle {
|
|
47
|
+
if (!existsSync(configPath)) {
|
|
48
|
+
throw new Error(`${configPath} does not exist; run 'docks-kit sync omp' first`);
|
|
49
|
+
}
|
|
50
|
+
const toggle = toggleOpenAiFast(readFileSync(configPath, "utf8"));
|
|
51
|
+
const temporary = `${configPath}.tmp`;
|
|
52
|
+
writeFileSync(temporary, toggle.text, { mode: 0o600 });
|
|
53
|
+
chmodSync(temporary, 0o600);
|
|
54
|
+
renameSync(temporary, configPath);
|
|
55
|
+
return toggle;
|
|
56
|
+
}
|
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
/**
|
|
2
2
|
* EngineNative omp marketplace pass: registry detection plus register, adopt,
|
|
3
3
|
* and refresh flows. Split from ompSync.ts; the orchestration still lives
|
|
4
|
-
* there.
|
|
4
|
+
* there.
|
|
5
5
|
*/
|
|
6
6
|
import { existsSync, readFileSync } from "node:fs";
|
|
7
7
|
|
|
8
|
-
import {
|
|
8
|
+
import { processFailureSummary, spawnProcess } from "./exec";
|
|
9
9
|
import { recordFailure } from "./failures";
|
|
10
10
|
import type { Ctx } from "./index";
|
|
11
11
|
import { isObject, parseJson } from "./jq";
|
|
@@ -36,11 +36,6 @@ function registryHasDocks(registryFile: string): boolean {
|
|
|
36
36
|
return entries.some((entry) => isObject(entry) && entry["name"] === MARKETPLACE_NAME);
|
|
37
37
|
}
|
|
38
38
|
|
|
39
|
-
export function firstOutputLine(result: AsyncProcessResult): string {
|
|
40
|
-
const output = `${result.stdout}${result.stderr}`;
|
|
41
|
-
return output.split("\n")[0] || "unknown error";
|
|
42
|
-
}
|
|
43
|
-
|
|
44
39
|
/**
|
|
45
40
|
* Three states, because upstream `getMarketplacesRegistryPath` copies a legacy
|
|
46
41
|
* `configRoot` registry forward the first time it resolves an XDG data root:
|
|
@@ -89,7 +84,7 @@ export async function syncMarketplace(
|
|
|
89
84
|
} else {
|
|
90
85
|
recordFailure(
|
|
91
86
|
ctx,
|
|
92
|
-
`omp docks marketplace registration failed: ${
|
|
87
|
+
`omp docks marketplace registration failed: ${processFailureSummary(result)}; run manually: omp plugin marketplace add ${MARKETPLACE_SOURCE}`,
|
|
93
88
|
);
|
|
94
89
|
}
|
|
95
90
|
return;
|
|
@@ -114,7 +109,7 @@ export async function syncMarketplace(
|
|
|
114
109
|
} else {
|
|
115
110
|
recordFailure(
|
|
116
111
|
ctx,
|
|
117
|
-
`omp docks marketplace adoption failed: ${
|
|
112
|
+
`omp docks marketplace adoption failed: ${processFailureSummary(listed)}; run manually: omp plugin marketplace list`,
|
|
118
113
|
);
|
|
119
114
|
}
|
|
120
115
|
return;
|
|
@@ -130,7 +125,7 @@ export async function syncMarketplace(
|
|
|
130
125
|
} else {
|
|
131
126
|
recordFailure(
|
|
132
127
|
ctx,
|
|
133
|
-
`omp docks marketplace update failed: ${
|
|
128
|
+
`omp docks marketplace update failed: ${processFailureSummary(result)}; run manually: omp plugin marketplace update ${MARKETPLACE_NAME}`,
|
|
134
129
|
);
|
|
135
130
|
}
|
|
136
131
|
}
|
|
@@ -3,11 +3,10 @@
|
|
|
3
3
|
* pinned pi-intercom npm plugin. Split from ompSync.ts; the orchestration
|
|
4
4
|
* still lives there.
|
|
5
5
|
*/
|
|
6
|
-
import { spawnProcess } from "./exec";
|
|
6
|
+
import { processFailureSummary, spawnProcess } from "./exec";
|
|
7
7
|
import { recordFailure } from "./failures";
|
|
8
8
|
import type { Ctx } from "./index";
|
|
9
9
|
import { isObject, parseJson } from "./jq";
|
|
10
|
-
import { firstOutputLine } from "./ompMarketplace";
|
|
11
10
|
import { field } from "./toolchain";
|
|
12
11
|
|
|
13
12
|
const MARKETPLACE_PLUGIN_IDS = ["docks@docks", "plan-lifecycle@docks"] as const;
|
|
@@ -69,7 +68,7 @@ async function runPluginCommand(
|
|
|
69
68
|
|
|
70
69
|
recordFailure(
|
|
71
70
|
ctx,
|
|
72
|
-
`omp plugin operation failed for ${plugin}: ${
|
|
71
|
+
`omp plugin operation failed for ${plugin}: ${processFailureSummary(result)}; run manually: omp ${args.join(" ")}`,
|
|
73
72
|
);
|
|
74
73
|
return false;
|
|
75
74
|
}
|
|
@@ -1,7 +1,7 @@
|
|
|
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 = "0.20.
|
|
4
|
+
export const GENERATED_PACKAGE_VERSION = "0.20.4"
|
|
5
5
|
|
|
6
6
|
export const GENERATED_PAYLOAD_TEXT = {
|
|
7
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",
|
|
@@ -18,7 +18,7 @@ export const GENERATED_PAYLOAD_TEXT = {
|
|
|
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\": \"plan-lifecycle\",\n \"source\": {\n \"source\": \"git-subdir\",\n \"url\": \"https://github.com/DocksDocks/docks.git\",\n \"path\": \"./plugins/plan-lifecycle\",\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
|
"SoT/.omp/AGENTS.md": "# Global OMP guidance\n\n- Verify unfamiliar or version-sensitive APIs and configuration against current official documentation before implementation.\n- When the user asks for an assessment rather than a change, report findings without editing.\n- For Docks plan reviews, cross-company review is standing-authorized; host security policy still applies.\n- Please remove all mannered prose.\n\n## Asking me things\n\nA question typed in prose is just text I may or may not act on. The `ask` tool renders a\nblocking picker, waits indefinitely (`ask.timeout = 0`), and records my answer in the\ntranscript. If you actually need an answer, it MUST go through `ask`.\n\nMUST use `ask` before:\n- Anything irreversible or destructive: deleting/overwriting files or data you did not create,\n force-push, history rewrite, dropping tables, running migrations, mass rename, touching\n secrets/credentials, or publishing outward (release, upstream PR, issue, comment).\n- Two or more viable approaches whose tradeoffs are mine to own: schema/API/protocol shape,\n adding a dependency, or establishing a convention this repo does not already have.\n- A fact only I hold: intended semantics of an ambiguous requirement, which of several\n conflicting existing patterns is canonical, or which environment/account/target to use.\n- A request that contradicts the repo: surface the conflict and let me resolve it; never\n silently pick one side.\n\nIf `ask` is not registered — subagent, headless, or `-p` print runs, where `hasUI` is false —\nthe MUST above cannot be satisfied: do not fabricate the call and do not stall on it. Take the\nconservative reversible option and put the question, plus the assumption you made, in your\nfinal report so whoever spawned you can decide.\n\nNEVER use `ask` for:\n- Permission to begin, or to confirm scope already stated in the request.\n- Anything a tool, grep, or doc can answer — go read it.\n- A cheap reversible choice — take the conservative option and say which you took.\n- Something already answered earlier in the conversation.\n\nBatch every open question into one `ask` call with multiple questions; do not serialize\nround trips. Being overruled ends the discussion — execute my call without relitigating.\n\n## Output Standard\n\nApply Simplified Technical English to all agent text. This includes responses, messages,\ndocumentation, comments, and interface text.\n\nReply in the language I use, and apply every rule below to that language.\n\nA rule that names English grammar applies only to English. The contraction ban is one\nsuch rule. In another language, follow the normal grammar of that language. Portuguese,\nSpanish, French, Italian, and German merge a preposition with an article, and that merge\nis required, not optional.\n\nTreat the word limits as approximate outside English. Some languages need more words to\ncarry the same content.\n\n- Use the simplest precise technical term.\n- Use each term consistently.\n- Expand an abbreviation at its first occurrence.\n- Explain a technical term when I ask for an explanation.\n- Write complete and grammatically correct sentences.\n- Use active voice and identify the actor.\n- Use the imperative form for instructions.\n- Put only one action in each instruction sentence.\n- Put a necessary condition before its instruction.\n- Use simple verb tenses.\n- Do not use contractions, idioms, or slang. Avoid humor and rhetorical questions.\n- Keep procedural sentences to 20 words or fewer.\n- Keep descriptive sentences to 25 words or fewer.\n- Keep each paragraph to one topic and six sentences or fewer.\n- Do not use more than three nouns together.\n- Use vertical lists for complex information.\n- Put a warning or caution before a related hazardous instruction.\n\n### Naming\n\n- Say what the thing does before you name it. Put the technical term after the plain\n description, once, in parentheses.\n- Do not use a technical term as the only name for something you just introduced.\n- Prefer the short common word. Use \"use\", not \"utilize\". Use \"set up\", not \"provision\".\n- Do not explain by metaphor alone. A metaphor may follow a literal statement.\n",
|
|
21
|
-
"SoT/.omp/config.yml": "statusLine:\n compactThinkingLevel: false\n\ndefaultThinkingLevel: high\n\ncycleOrder:\n - smol\n - default\n - slow\n - fable\n - astra\n\ntier:\n
|
|
21
|
+
"SoT/.omp/config.yml": "statusLine:\n compactThinkingLevel: false\n\ndefaultThinkingLevel: high\n\ncycleOrder:\n - smol\n - default\n - slow\n - fable\n - astra\n\ntier:\n anthropic: none\n\nadvisor:\n enabled: true\n syncBacklog: \"1\"\n\ngithub:\n enabled: true\n\nfind:\n enabled: true\n\ntask:\n eager: always\n showResolvedModelBadge: true\n softRequestBudget: 200\n softRequestBudgetNotice: true\n batch: true\n enableLsp: true\n enableEffort: true\n maxEffort: xhigh\n maxConcurrency: 16\n maxRecursionDepth: 2\n maxRuntimeMs: 3600000\n agentModelOverrides:\n reviewer: \"@task\"\n security-reviewer: \"@task\"\n code-reviewer: \"@task\"\n plan-reviewer: \"@task\"\n\nmodelRoles:\n smol: openai-codex/gpt-6-luna:medium\n advisor: anthropic/claude-opus-5-5:medium\n designer: anthropic/claude-opus-5-5:high\n plan: anthropic/claude-opus-5-5:xhigh\n commit: openai-codex/gpt-6-luna:medium\n task: anthropic/claude-opus-5-5:high\n vision: anthropic/claude-opus-5-5:medium\n tiny: openai-codex/gpt-6-luna:low\n default: anthropic/claude-opus-5-5:high\n slow: anthropic/claude-opus-5-5:xhigh\n fable: anthropic/claude-fable-5-1:medium\n switch_fable: anthropic/claude-fable-5-1:medium\n astra: openai-codex/gpt-6-astra:xhigh\n web: web/firecrawl\n\nmodelTags:\n fable:\n name: Fable 5.1\n switch_fable:\n name: Fable switch default\n hidden: true\n astra:\n name: GPT-6 Astra\n\ndisplay:\n showTokenUsage: true\n\nproviders:\n anthropic:\n serverSideFallback: false\n fetch: auto\n webSearchTimeoutSeconds: 30\n\nretry:\n usageAwareFallback: true\n fallbackChains:\n default:\n - openai-codex/gpt-6.1-sol:high\n advisor: []\n task:\n - openai-codex/gpt-6.1-sol:high\n vision:\n - openai-codex/gpt-6.1-sol:medium\n smol:\n - anthropic/claude-opus-5-5:low\n tiny:\n - anthropic/claude-opus-5-5:low\n commit:\n - anthropic/claude-opus-5-5:medium\n switch_fable: []\n fable:\n - openai-codex/gpt-6-astra:xhigh\n astra:\n - anthropic/claude-fable-5-1:medium\n web:\n - web/exa\n - web/perplexity\n - openai-codex/gpt-6-luna\n - web/parallel\n - web/zai\n - web/tinyfish\n - web/jina\n - web/kagi\n - web/tavily\n - web/brave\n - web/kimi\n - web/synthetic\n - web/ollama\n - web/searxng\n - web/startpage\n - web/duckduckgo\n - web/ecosia\n - web/google\n - web/mojeek\n - web/public\n\nincludeWorkspaceTree: false\n\nbranchSummary:\n enabled: true\n\ncommands:\n enableOpencodeProject: false\n enableOpencodeUser: false\n\nskills:\n enableClaudeUser: false\n enableCodexUser: false\n enableAgentsUser: true\n\nsteeringMode: all\n\ndev:\n autoqa: false\n autoqaConsent: denied\n\ncompaction:\n thresholdTokens: -1\n idleEnabled: true\n handoffSaveToDisk: true\n\ndoubleEscapeAction: tree\ntextVerbosity: low\n\nfeatures:\n unexpectedStopDetection: smart\n\ncodexResets:\n autoRedeem: \"no\"\n\nstartup:\n quiet: true\n\ntools:\n approvalMode: yolo\n",
|
|
22
22
|
"SoT/.omp/intercom.json": "{\n \"brokerCommand\": \"bun\",\n \"brokerArgs\": []\n}\n",
|
|
23
23
|
"SoT/.omp/mcp.json": "{\n \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n \"disabledServers\": [\n \"chrome-devtools\",\n \"context7:context7\",\n \"openaiDeveloperDocs\"\n ]\n}\n",
|
|
24
24
|
"SoT/.omp/models.yml": "providers:\n openai-codex:\n modelOverrides:\n gpt-6-astra:\n thinking:\n mode: effort\n efforts:\n - low\n - medium\n - high\n - xhigh\n - max\n defaultLevel: xhigh\n"
|
|
@@ -50,4 +50,4 @@ export const GENERATED_PAYLOAD_PATHS = [
|
|
|
50
50
|
"notification.mp3"
|
|
51
51
|
] as const
|
|
52
52
|
|
|
53
|
-
export const GENERATED_PAYLOAD_HASH = "
|
|
53
|
+
export const GENERATED_PAYLOAD_HASH = "404ea9eb15770181e21e248c73930522050b5c096a82e5d5b6726b27ef8e6a30"
|
package/package.json
CHANGED