owenloop 0.5.1 → 0.5.3
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/CHANGELOG.md +30 -0
- package/README.md +9 -2
- package/dist/packages/work/src/agent/brief.d.ts +21 -0
- package/dist/packages/work/src/agent/brief.js +42 -1
- package/dist/packages/work/src/agent/capability-model.d.ts +123 -0
- package/dist/packages/work/src/agent/capability-model.js +148 -0
- package/dist/packages/work/src/agent/loop.d.ts +47 -4
- package/dist/packages/work/src/agent/loop.js +83 -53
- package/dist/packages/work/src/exec/loop.d.ts +17 -0
- package/dist/packages/work/src/exec/loop.js +195 -34
- package/dist/packages/work/src/exec/runner.js +15 -5
- package/dist/packages/work/src/harness/claude.js +69 -9
- package/dist/packages/work/src/harness/codex.js +56 -8
- package/dist/packages/work/src/harness/contract.d.ts +65 -1
- package/dist/packages/work/src/harness/contract.js +56 -0
- package/dist/packages/work/src/harness/session-store.d.ts +3 -1
- package/dist/packages/work/src/harness/session-store.js +46 -22
- package/dist/packages/work/src/hold/mcp.js +9 -2
- package/dist/packages/work/src/hub/client.d.ts +7 -1
- package/dist/packages/work/src/hub/client.js +1 -0
- package/dist/packages/work/src/hub/types.d.ts +71 -3
- package/dist/packages/work/src/roles/agent-run.js +8 -9
- package/dist/packages/work/src/roles/hold.d.ts +2 -0
- package/dist/packages/work/src/roles/hold.js +39 -8
- package/dist/packages/work/src/roles/settings.js +18 -6
- package/dist/packages/work/src/roles/shift.js +13 -1
- package/dist/packages/work/src/settings/settings.d.ts +60 -7
- package/dist/packages/work/src/settings/settings.js +69 -22
- package/dist/packages/work/src/shift/logretention.d.ts +253 -0
- package/dist/packages/work/src/shift/logretention.js +407 -0
- package/dist/packages/work/src/shift/logsink.d.ts +14 -0
- package/dist/packages/work/src/shift/logsink.js +98 -0
- package/dist/packages/work/src/shift/loop.d.ts +18 -1
- package/dist/packages/work/src/shift/loop.js +250 -12
- package/dist/packages/work/src/shift/protocol.d.ts +124 -1
- package/dist/packages/work/src/shift/protocol.js +14 -0
- package/dist/packages/work/src/shift/runtime.d.ts +14 -0
- package/dist/packages/work/src/shift/runtime.js +229 -6
- package/dist/packages/work/src/shift/server.d.ts +13 -0
- package/dist/packages/work/src/shift/server.js +61 -36
- package/dist/packages/work/src/shift/spawn.d.ts +78 -5
- package/dist/packages/work/src/shift/spawn.js +158 -12
- package/dist/packages/work/src/shift/state.d.ts +25 -0
- package/dist/packages/work/src/shift/state.js +29 -5
- package/dist/packages/work/src/shift/truncate.d.ts +35 -0
- package/dist/packages/work/src/shift/truncate.js +73 -0
- package/dist/packages/work/src/submit-proof.d.ts +31 -6
- package/dist/packages/work/src/submit-proof.js +33 -7
- package/dist/packages/work/src/submit-value.d.ts +48 -0
- package/dist/packages/work/src/submit-value.js +118 -0
- package/dist/packages/work/src/usage.d.ts +1 -1
- package/dist/packages/work/src/usage.js +11 -0
- package/dist/src/bundle/runtime.d.ts +1 -1
- package/dist/src/bundle/runtime.js +9 -0
- package/dist/src/capabilities.d.ts +93 -0
- package/dist/src/capabilities.js +101 -0
- package/dist/src/cli.js +37 -11
- package/dist/src/crypto/records.d.ts +3 -0
- package/dist/src/crypto/records.js +11 -0
- package/dist/src/defs.js +192 -4
- package/dist/src/engine.d.ts +112 -3
- package/dist/src/engine.js +224 -28
- package/dist/src/hub.d.ts +27 -11
- package/dist/src/hub.js +24 -18
- package/dist/src/index.d.ts +3 -1
- package/dist/src/index.js +4 -1
- package/dist/src/mcp/serve.js +11 -4
- package/dist/src/model.d.ts +36 -0
- package/dist/src/model.js +46 -0
- package/dist/src/schemas/index.d.ts +17 -0
- package/dist/src/schemas/order.v1.schema.json +17 -3
- package/dist/src/store.d.ts +33 -1
- package/dist/src/store.js +57 -4
- package/dist/src/types.d.ts +102 -2
- package/docs/agent-runner.md +26 -1
- package/docs/authoring.md +7 -0
- package/docs/bundles.md +103 -3
- package/docs/cli.md +127 -9
- package/docs/crypto.md +23 -7
- package/docs/shift-logs.md +642 -0
- package/docs/wire-contracts.md +34 -19
- package/package.json +1 -1
- package/plugins/claude-code/plugin/.claude-plugin/plugin.json +1 -1
- package/plugins/claude-code/plugin/.mcp.json +1 -1
- package/plugins/codex/plugins/owenloop/.codex-plugin/plugin.json +1 -1
- package/plugins/codex/plugins/owenloop/.mcp.json +1 -1
- package/dist/packages/work/src/agent/model-policy.d.ts +0 -49
- package/dist/packages/work/src/agent/model-policy.js +0 -138
package/docs/cli.md
CHANGED
|
@@ -179,7 +179,7 @@ The execution settings file is `$XDG_CONFIG_HOME/owenloop/settings.json` when
|
|
|
179
179
|
```text
|
|
180
180
|
owenloop shift start <crew...> [--all] [--origin <url>] [--as <account>] [--name <n>]
|
|
181
181
|
[--cap <n>] [--max-agents <n>] [--poll-interval <ms>] [--once]
|
|
182
|
-
[--cache-dir <p>] [--state-dir <p>]
|
|
182
|
+
[--cache-dir <p>] [--state-dir <p>] [--log-dir <p>] [--log-max-age <ms>]
|
|
183
183
|
```
|
|
184
184
|
|
|
185
185
|
At least one named crew is required unless `--all` is present. `--all` and
|
|
@@ -199,6 +199,92 @@ one loop sweep and exits instead of keeping the foreground daemon running.
|
|
|
199
199
|
| `--once` | run one loop sweep and exit; without it, keep the daemon in the foreground |
|
|
200
200
|
| `--cache-dir <p>` | cache root; precedence is flag, then `OWENLOOP_CACHE_DIR`, then `settings.cacheDir`, then `$XDG_CACHE_HOME/owenloop`, then `$HOME/.cache/owenloop` |
|
|
201
201
|
| `--state-dir <p>` | socket and child-state root; precedence is flag, then `OWENLOOP_STATE_DIR`, then `settings.stateDir`, then `$XDG_STATE_HOME/owenloop/exec`, then `$HOME/.local/state/owenloop/exec`; the socket is `shift.sock` inside this directory |
|
|
202
|
+
| `--log-dir <p>` | where `shift.log` and each `<run>.log` are written; precedence is flag, then `OWENLOOP_SHIFT_LOG_DIR`, then `settings.shiftLogDir`, then the resolved state directory |
|
|
203
|
+
| `--log-max-age <ms>` | worker-log retention, swept once at startup; precedence is flag, then `OWENLOOP_SHIFT_LOG_MAX_AGE_MS`, then `settings.shiftLogMaxAgeMs`, then `1209600000` (14 days). `0` reaps every completed run's log at the next startup; there is no value that disables the sweep, and `shift.log` is never reaped |
|
|
204
|
+
|
|
205
|
+
**On-disk logs.** A running shift appends its dispatch record to
|
|
206
|
+
`<log-dir>/shift.log` as JSON Lines, and gives each dispatched worker's stdout
|
|
207
|
+
and stderr their own `<log-dir>/<run>.log`. Both files outlive the shift
|
|
208
|
+
process. A log directory that cannot be created costs the logs, never the
|
|
209
|
+
dispatch: the shift reports it once on stderr and serves with logging disabled.
|
|
210
|
+
Full field-by-field contract, retention rules, and uploader notes in
|
|
211
|
+
[`docs/shift-logs.md`](shift-logs.md).
|
|
212
|
+
|
|
213
|
+
**One harness per shift.** A shift has no per-order harness switch and no
|
|
214
|
+
`--harness` flag. It never puts `--harness` on a worker's command line; each
|
|
215
|
+
`agent-run` child resolves its own adapter, in this order:
|
|
216
|
+
|
|
217
|
+
1. its own `--harness` flag — which a shift never supplies;
|
|
218
|
+
2. `OWENLOOP_HARNESS` in the environment the child inherits, which is the
|
|
219
|
+
shift's environment;
|
|
220
|
+
3. the `harness:` field on the verified step definition;
|
|
221
|
+
4. the first registered adapter.
|
|
222
|
+
|
|
223
|
+
Rank 2 is the operator's control. Export `OWENLOOP_HARNESS` in the shell that
|
|
224
|
+
starts the shift and every agent order that shift dispatches runs on that
|
|
225
|
+
adapter. To run two adapters at once, start two shifts:
|
|
226
|
+
|
|
227
|
+
```bash
|
|
228
|
+
OWENLOOP_HARNESS=claude-code XDG_CONFIG_HOME=~/.config/owenloop-shifts/claude owenloop shift start build --state-dir ~/.local/state/owenloop/claude
|
|
229
|
+
```
|
|
230
|
+
|
|
231
|
+
```bash
|
|
232
|
+
OWENLOOP_HARNESS=codex XDG_CONFIG_HOME=~/.config/owenloop-shifts/codex owenloop shift start build --state-dir ~/.local/state/owenloop/codex
|
|
233
|
+
```
|
|
234
|
+
|
|
235
|
+
Both shifts may serve the SAME crew. The hub does not route by harness — it
|
|
236
|
+
offers an order to any shift whose crew is bound to the order's capability, and
|
|
237
|
+
whichever shift claims it first runs it on its own adapter.
|
|
238
|
+
|
|
239
|
+
**Per-shift `XDG_CONFIG_HOME` is not optional when the adapters differ.** The
|
|
240
|
+
settings file resolves from `XDG_CONFIG_HOME` (see above), and it carries
|
|
241
|
+
`capabilityModels` — a map of composed capability to `{model, effort}` whose
|
|
242
|
+
model ids are strings the SHIFT'S OWN adapter accepts. Two shifts on different
|
|
243
|
+
adapters need different model ids for the same capability, so they need
|
|
244
|
+
different settings files, so they need different `XDG_CONFIG_HOME` values. A
|
|
245
|
+
shared config directory would give both shifts one adapter's model ids, and the
|
|
246
|
+
shift holding the wrong adapter fails at the vendor API on its first order.
|
|
247
|
+
|
|
248
|
+
Give each shift its own `--state-dir` as well. The state directory holds the
|
|
249
|
+
control socket (`shift.sock`), and a second shift starting against a socket
|
|
250
|
+
another shift already owns is refused.
|
|
251
|
+
|
|
252
|
+
**`capabilityModels` — which model serves which capability.** The hub decides
|
|
253
|
+
WHAT grade of work an order is; it composes the step's capability with the run's
|
|
254
|
+
depth modifier and stamps the result on the order (`builder` at the `deep`
|
|
255
|
+
modifier becomes `builder:deep`). It never decides which model serves that
|
|
256
|
+
grade. That decision is local, and this map is where the operator makes it:
|
|
257
|
+
|
|
258
|
+
```json
|
|
259
|
+
{
|
|
260
|
+
"capabilityModels": {
|
|
261
|
+
"builder:deep": { "model": "claude-opus-5", "effort": "xhigh" },
|
|
262
|
+
"builder": { "model": "claude-sonnet-5", "effort": "high" },
|
|
263
|
+
"wise": { "model": "claude-fable-5", "effort": "xhigh" }
|
|
264
|
+
}
|
|
265
|
+
}
|
|
266
|
+
```
|
|
267
|
+
|
|
268
|
+
Lookup runs two passes over the order's capabilities: every EXACT composed key
|
|
269
|
+
first, then every BARE name part. `builder:deep` takes the first row above;
|
|
270
|
+
`builder:express` has no exact row and falls back to the `builder` row.
|
|
271
|
+
`effort` must be one of `low`, `medium`, `high`, `xhigh`, `max`. The model id is
|
|
272
|
+
never checked against a list — owenloop keeps no registry of which models exist,
|
|
273
|
+
so a model released after your owenloop build still works.
|
|
274
|
+
|
|
275
|
+
A capability with no exact row and no bare row is REFUSED, not run on a default:
|
|
276
|
+
the worker releases the claim, reports the refusal to the hub, and exits `1`. An
|
|
277
|
+
order carrying no capabilities at all is not refused — it runs on the adapter's
|
|
278
|
+
own default model, which is how capability-silent steps have always run.
|
|
279
|
+
|
|
280
|
+
**Migrating from `tierMap` / `tierProfiles`.** Both keys are removed. A settings
|
|
281
|
+
file that still contains either one fails to load with an error naming
|
|
282
|
+
`capabilityModels`; the shift does not start. This is deliberate — a shift that
|
|
283
|
+
ignored the old keys would have no capability map at all and would refuse every
|
|
284
|
+
order it claimed, hours later and far from the cause. Rewrite the tier rungs as
|
|
285
|
+
capability rows: whatever `tierProfiles.strongest` pointed at becomes the
|
|
286
|
+
`{model, effort}` of your `:deep` rows, and whatever `standard` pointed at
|
|
287
|
+
becomes the bare rows.
|
|
202
288
|
|
|
203
289
|
A clean start or `--once` completion exits `0`. `owenloop shift --help` also
|
|
204
290
|
exits `0`. Runtime failures such as credential reads or socket/runtime setup
|
|
@@ -260,14 +346,46 @@ returns promptly when an event is queued, the wait expires, or the shift
|
|
|
260
346
|
explicitly ends. A normal timeout exits `0` and prints the current capacity
|
|
261
347
|
object, for example `{ "cap": 3, "free": 3, "running": 0, "events": [] }`.
|
|
262
348
|
Successful responses use the same capacity shape and may include queued event
|
|
263
|
-
objects.
|
|
264
|
-
|
|
349
|
+
objects.
|
|
350
|
+
|
|
351
|
+
**Every event carries the same three envelope fields**, in addition to whatever
|
|
352
|
+
its own `type` defines:
|
|
353
|
+
|
|
354
|
+
| field | meaning |
|
|
355
|
+
|---|---|
|
|
356
|
+
| `ts` | ISO-8601 UTC with milliseconds, e.g. `2026-08-13T18:04:11.412Z` |
|
|
357
|
+
| `shift` | the shift's human name — `clock_in` can change it between events |
|
|
358
|
+
| `shiftId` | `shf_<uuid>`, the shift process incarnation; stable for the process |
|
|
359
|
+
|
|
360
|
+
The envelope is omitted from the per-type examples below for brevity; it is
|
|
361
|
+
never omitted on the wire. For `dispatched`, `reaped`, and `failed`, `kind` is
|
|
362
|
+
either `exec` or `agent-run`:
|
|
265
363
|
|
|
266
364
|
- `dispatched`: `{ "type": "dispatched", "workflow": "...", "run": "...", "step": "...", "kind": "exec", "pid": 123 }`
|
|
267
365
|
- `reaped`: `{ "type": "reaped", "workflow": "...", "run": "...", "kind": "exec", "pid": 123 }`
|
|
268
366
|
- `failed`: `{ "type": "failed", "workflow": "...", "run": "...", "step": "...", "kind": "exec", "message": "..." }`
|
|
367
|
+
- `bundle-miss`: `{ "type": "bundle-miss", "workflow": "...", "def": "..." }` — a legacy order named a def with no cached bundle, so it was left for hub pickup
|
|
368
|
+
- `order-dropped`: `{ "type": "order-dropped", "workflow": "...", "run": "...", "step": "...", "reason": "unsupported-worker", "message": "..." }` — the shift refused one order. Match on `reason` (`malformed-digest`, `malformed-worker`, `unsupported-worker`, `verification-failed`, `metadata-unavailable`); display `message`
|
|
269
369
|
- `ended`: `{ "type": "ended" }`, delivered to a parked `next` when `shift end` explicitly shuts down the daemon
|
|
270
370
|
|
|
371
|
+
Every event above is also appended to `<log-dir>/shift.log` as JSON Lines, which
|
|
372
|
+
is how they survive the daemon. **Four further record types exist in
|
|
373
|
+
`shift.log` and are never delivered over the socket** — `parked`, `capacity`,
|
|
374
|
+
`hub-error`, and `event-queue-overflow`.
|
|
375
|
+
|
|
376
|
+
An idle `shift next` must block until there is work to report, and each of those
|
|
377
|
+
four would satisfy it with news that no work moved: a startup record, a report
|
|
378
|
+
that the shift is full, a failed call to the hub, or a record about the socket
|
|
379
|
+
queue itself. `parked` and `capacity` are also redundant on the wire — the
|
|
380
|
+
response above already carries live `cap`, `free`, and `running`, which is
|
|
381
|
+
exactly what a `capacity` record restates. `hub-error` is level-triggered at the
|
|
382
|
+
poll interval, so an unreachable hub would otherwise fill the 1000-slot socket
|
|
383
|
+
FIFO and evict the `dispatched`, `failed` and `reaped` records a parked client
|
|
384
|
+
is actually waiting for. In `shift.log`, which is append-only and unbounded, all
|
|
385
|
+
four are load-bearing: they are the only way to tell an idle shift from a
|
|
386
|
+
saturated one, and the only record of every failed hub call. See
|
|
387
|
+
[`docs/shift-logs.md`](shift-logs.md).
|
|
388
|
+
|
|
271
389
|
`gate` is a reserved protocol shape for a future local representation of a
|
|
272
390
|
pending hub gate. Production code does not construct live hub gate events yet;
|
|
273
391
|
the local FIFO test and drill scope are recorded in
|
|
@@ -1691,7 +1809,7 @@ allowed) re-reads the route table as it stands at that moment.
|
|
|
1691
1809
|
- **Adding.** Running `capability bind` on a capability that is **already bound** ADDS the
|
|
1692
1810
|
named crew — it never displaces a crew already bound. Adding widens who can
|
|
1693
1811
|
serve the capability, live at the next poll of every in-flight run using it. Re-adding
|
|
1694
|
-
a pair that is already there is a normal success, not an error (`
|
|
1812
|
+
a pair that is already there is a normal success, not an error (`alreadyBound:
|
|
1695
1813
|
true`).
|
|
1696
1814
|
- **Removing.** Running `capability unbind` removes exactly ONE pair. If the capability still
|
|
1697
1815
|
has other live routes, it simply routes to a narrower set and nothing pauses.
|
|
@@ -1718,9 +1836,9 @@ id; the CLI does no crew lookup and performs no client-side validation of either
|
|
|
1718
1836
|
argument (the hub is the enforcement of record).
|
|
1719
1837
|
|
|
1720
1838
|
**Adding is idempotent per pair.** Re-adding a `(capability, crew)` pair that is
|
|
1721
|
-
already bound is a normal success — the hub answers `200` with `
|
|
1839
|
+
already bound is a normal success — the hub answers `200` with `alreadyBound:
|
|
1722
1840
|
true` and changes nothing (the original row keeps its creator and timestamp).
|
|
1723
|
-
`
|
|
1841
|
+
`boundCrewCount` reports how many **live** crews the capability binds after the write.
|
|
1724
1842
|
|
|
1725
1843
|
### `capability unbind <capability> <crew>`
|
|
1726
1844
|
|
|
@@ -1781,7 +1899,7 @@ works. Human progress lines (the two `capability unbind` warnings) go to stderr
|
|
|
1781
1899
|
|
|
1782
1900
|
| subcommand | stdout |
|
|
1783
1901
|
|---|---|
|
|
1784
|
-
| `capability bind` | `{ "ok": true, "hub": "<origin>", "capability": "gpu", "crew": "ml-crew", "
|
|
1902
|
+
| `capability bind` | `{ "ok": true, "hub": "<origin>", "capability": "gpu", "crew": "ml-crew", "alreadyBound": false, "boundCrewCount": 2 }` |
|
|
1785
1903
|
| `capability unbind` | `{ "ok": true, "hub": "<origin>", "capability": "gpu", "crewId": "crw_1", "removed": true, "remainingCrewIds": ["crw_2"] }` |
|
|
1786
1904
|
| `capability list` | `{ "ok": true, "hub": "<origin>", "routes": [ { "capability": "gpu", "crewId": "crw_1", "crewName": "ml-crew", "createdBy": "u_1", "createdAt": 1738000000000 } ] }` |
|
|
1787
1905
|
|
|
@@ -1789,9 +1907,9 @@ Every added field carries the **hub's own name**, verbatim — the same words it
|
|
|
1789
1907
|
audit log and the web console use — so correlating stdout against them never
|
|
1790
1908
|
needs a translation step.
|
|
1791
1909
|
|
|
1792
|
-
- `
|
|
1910
|
+
- `alreadyBound` (`capability bind`) — was this exact `(capability, crew)` pair already
|
|
1793
1911
|
bound before the call? `false` means the pair was created by it.
|
|
1794
|
-
- `
|
|
1912
|
+
- `boundCrewCount` (`capability bind`) — how many **live** crews the capability binds
|
|
1795
1913
|
after the write. A dangling route routes nothing and is not counted.
|
|
1796
1914
|
- `removed` (`capability unbind`) — did this call actually remove a pair? `false` is the
|
|
1797
1915
|
tolerant "it was never bound" case, not an error.
|
package/docs/crypto.md
CHANGED
|
@@ -164,13 +164,29 @@ canonical JSON payload with `dsseSignSubmission` under the
|
|
|
164
164
|
`owenloop-dsse-v1` namespace. The target `proof` request field is the serialized
|
|
165
165
|
DSSE envelope for that one submitted artifact path.
|
|
166
166
|
|
|
167
|
-
A judge approval may sign the existing judged version from the claim fingerprint
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
167
|
+
A judge approval may sign the existing judged version from the claim fingerprint,
|
|
168
|
+
because the approval attests that version and does not allocate a new one.
|
|
169
|
+
|
|
170
|
+
A producer submit signs `owes[].version`, the target version the hub issues for
|
|
171
|
+
that owed output. The target is the version the next successful commit will
|
|
172
|
+
land (claim-time committed version + 1) — exactly the version the downstream
|
|
173
|
+
consumer passes to `verifyConsumed` as `expectedVersion`. It is never inferred
|
|
174
|
+
from process-local state.
|
|
175
|
+
|
|
176
|
+
Retry-safety is a property of where the target is computed, not of the client.
|
|
177
|
+
The engine computes it inside the claim transaction and persists it with the
|
|
178
|
+
immutable order, so every read of that claim — a reconnect, a retried submit
|
|
179
|
+
after a lost response, a restarted holder — yields the same number. Engine
|
|
180
|
+
refusal paths that leave the run open (a schema reject) do not bump the
|
|
181
|
+
artifact, so the target survives in-claim retries; a refinement is a new claim
|
|
182
|
+
and receives a newly issued target. A stale target fails the consumer's version
|
|
183
|
+
check, which is a refusal, never an admitted unverified value.
|
|
184
|
+
|
|
185
|
+
A target is authoritative only when it is a positive integer: the smallest
|
|
186
|
+
commit any producer can land is v1. An absent target, a `0`, or a non-integer
|
|
187
|
+
is treated as no authoritative metadata — the driver submits without a proof
|
|
188
|
+
and warns once per process, rather than signing a number the consumer is
|
|
189
|
+
guaranteed to reject.
|
|
174
190
|
|
|
175
191
|
The engine does not sign: local `Engine.green` is synchronous and commits inside
|
|
176
192
|
a synchronous store transaction. `owenloop green` remains deliberately unsigned
|