owenloop 0.5.23 → 0.5.25

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.
@@ -123,16 +123,47 @@ The Claude Code adapter refuses a `read-only` allow-list containing anything out
123
123
 
124
124
  ## Owenloop control-plane exception
125
125
 
126
- `network: owenloop-only` means that the Step Agent may reach only the born-bound Owenloop MCP control plane for the held order. The exception exists so the Step Agent can call `get_order` and `submit`; without those calls the Step Agent cannot inspect or complete the order.
126
+ `network: owenloop-only` means that the Step Agent may reach only the born-bound Owenloop MCP control plane for the held order. The exception exists so the Step Agent can call `get_order`, `submit`, and `ask`; without those calls the Step Agent cannot inspect, complete, or honestly hold an impossible order.
127
127
 
128
- For Claude Code isolation, the adapter sets `settingSources: []`, `strictMcpConfig: true`, disables skills, excludes hooks and external MCP servers, and mounts only the worker-created `owenloop` MCP server. The restricted MCP child positively registers exactly `get_order` and `submit`; the restricted MCP child does not register `reject`. A future work-holder tool therefore does not enter restricted sessions unless the adapter explicitly adds the tool to the positive registration list. The adapter also restricts built-in tools to an audited no-network set. The same option construction runs for cold start and resume.
128
+ For Claude Code isolation, the adapter sets `settingSources: []`, `strictMcpConfig: true`, disables skills, excludes hooks and external MCP servers, and mounts only the worker-created `owenloop` MCP server. The restricted MCP child positively registers exactly `get_order`, `submit`, and `ask`; the restricted MCP child does not register `reject`. A future work-holder tool therefore does not enter restricted sessions unless the adapter explicitly adds the tool to the positive registration list. The adapter also restricts built-in tools to an audited no-network set. The same option construction runs for cold start and resume.
129
129
 
130
- The born-bound Owenloop MCP server is created by the worker from the live workflow, run, origin, account, Shift, and held claim. Workflow extension data cannot replace that mount. During isolation, the adapter adds `mcp__owenloop__get_order` and `mcp__owenloop__submit` to `allowedTools` so both control calls execute without an unattended permission prompt. `allowedTools` controls permission automation; `allowedTools` does not filter the MCP server's `tools/list` response. The positive registration list on the MCP child is the visibility boundary. The adapter also adds `mcp__owenloop__reject` to `disallowedTools` as defense in depth. A direct deny or an MCP wildcard deny that blocks Owenloop `get_order` or `submit` is refused.
130
+ The born-bound Owenloop MCP server is created by the worker from the live workflow, run, origin, account, Shift, and held claim. Workflow extension data cannot replace that mount. During isolation, the adapter adds `mcp__owenloop__get_order`, `mcp__owenloop__submit`, and `mcp__owenloop__ask` to `allowedTools` so those control calls execute without an unattended permission prompt. `allowedTools` controls permission automation; `allowedTools` does not filter the MCP server's `tools/list` response. The positive registration list on the MCP child is the visibility boundary. The adapter also adds `mcp__owenloop__reject` to `disallowedTools` as defense in depth. A direct deny or an MCP wildcard deny that blocks Owenloop `get_order`, `submit`, or `ask` is refused.
131
131
 
132
132
  Outside Claude Code isolation, the default work-holder MCP child continues to register `get_order`, `submit`, and `reject`.
133
133
 
134
134
  ## Security boundary
135
135
 
136
+ ### Claude exact work root
137
+
138
+ A dedicated audit Shift may enable `OWENLOOP_CLAUDE_EXACT_WORKDIR=1` in the
139
+ host environment. It is a host-only setting: it is removed before the Claude
140
+ child is launched and is not carried in prompts, events, provider options, or
141
+ durable session records. Absence leaves existing workflows unchanged; any other
142
+ present value fails configuration before a provider query starts.
143
+
144
+ This profile requires an explicit or derived built-in surface containing only
145
+ `Read`, `Glob`, and `Grep` (an explicit `tools: []` remains valid). It forces
146
+ the same isolated settings/MCP/skills profile described above, rejects an
147
+ incompatible authored surface rather than silently filtering it, and keeps the
148
+ born-bound `get_order`, `submit`, and `ask` controls headless.
149
+
150
+ Every path-bearing built-in is intercepted by a host-owned `PreToolUse` guard
151
+ before the SDK's bare `allowedTools` approval can run. A well-formed lexical
152
+ path inside the exact step directory proceeds headlessly. Outside, malformed,
153
+ or SDK-blocked paths are final fixed-message denials: they never create a human
154
+ tool approval, and the agent must work inside the directory or use `ask` when
155
+ the order is impossible there. The callback retains the same final-deny check
156
+ as defense in depth.
157
+
158
+ For a configured model, both cold and resumed strict turns require the provider
159
+ to confirm the identical literal model name. Missing identity, a different
160
+ model, an unavailable model, or a structured fallback event fails the turn
161
+ instead of accepting a substitute. No fallback model is configured.
162
+
163
+ The boundary is lexical containment only; it does not claim to defeat symlinks
164
+ or special files. Snapshot construction remains responsible for those separate
165
+ checks.
166
+
136
167
  `x.harness` permission fields are enforced policy. Adapter preflight must prove that the selected adapter can implement each authored restriction exactly; unsupported policy fails closed.
137
168
 
138
169
  `advisory.tools` is model guidance only. `advisory.tools` does not configure an adapter, does not remove a provider tool, and is not a security boundary.
package/docs/authoring.md CHANGED
@@ -566,6 +566,27 @@ capability in the resulting judge list just as it does for an ordinary step
566
566
  producer nor judge supplies capabilities, the judge remains capability-silent,
567
567
  and there is nothing to compose.
568
568
 
569
+ ### Modifier-scoped judges
570
+
571
+ Workflow `modifiers:` still controls routing for every step. A native judge
572
+ may additionally opt into an exact subset of that declared vocabulary with
573
+ `modifiers: [deep]` on the judge entry. Omitting the key is fully compatible:
574
+ that judge is active for every run. A scoped judge is active only when the
575
+ instance's stored modifier exactly matches one listed name; an instance with no
576
+ current modifier activates no scoped judge. Per-step escalation does not change
577
+ this decision.
578
+
579
+ Every scope name must be a declared top-level modifier; empty, duplicate,
580
+ whitespace-containing, `:`-containing, unknown, and unscoped-workflow lists
581
+ are definition errors. A mixed panel is allowed: its unscoped judges remain
582
+ required at every modifier while scoped judges join only on matching runs. An
583
+ inactive judge creates no order, pending approval, receipt, or completion debt,
584
+ but an active judge keeps normal capability composition (for example
585
+ `review-rigor:deep`). If the workflow binds its modifier from an artifact,
586
+ every producer with a scoped judge must consume a path strictly downstream of
587
+ that binding artifact; a sibling output on the binder cannot safely use a
588
+ scoped judge because it could commit before the binding settles.
589
+
569
590
  Author `x:` on the producer step, not on individual judge entries. Every native
570
591
  judge synthesized from that producer inherits the producer's complete parsed
571
592
  `x:` map. Each judge receives an independent deep clone, so runner-side
@@ -581,7 +602,7 @@ through the normal pipeline, with its own throttles (`cadence:`,
581
602
  `report`, it lands `submitted` (not `green`) instead — schema-valid, but
582
603
  waiting on sign-off. Each judge evaluates it and calls the *same*
583
604
  `green`/`reject` verbs you already use, targeted at `report` — no new CLI
584
- surface. Once every declared judge has approved the current version, `report`
605
+ surface. Once every active judge has approved the current version, `report`
585
606
  goes `green`. A single reject sends it straight to `rejected` and re-arms
586
607
  `researcher`; a rebuild starts every judge's ledger fresh, so a sibling
587
608
  judge's earlier approval never carries over to a new version.
package/docs/design.md CHANGED
@@ -724,7 +724,7 @@ this version yet.
724
724
  - **Reads as OUTSTANDING for completion** — `OUTSTANDING_STATES = DEBT_STATES
725
725
  ∪ { submitted }` (§5). A workflow is not `done` while any artifact sits in
726
726
  `submitted`, even though the producer itself has no further debt.
727
- - Artifacts whose `produces` entry declares no `judges:` never enter
727
+ - Artifacts whose `produces` entry declares no active `judges:` never enter
728
728
  `submitted` — a plain commit lands `green` exactly as before. This is fully
729
729
  backward compatible: no judges declared, zero behavior change.
730
730
 
@@ -744,6 +744,8 @@ named `${producerStep}.${producedStem}.judges.${judgeName}`. Each judge step:
744
744
  - `judges: <judgedStem>` — the marker field that makes it a judge (mirrors
745
745
  `calls:`'s marker-field pattern), read by both layers:
746
746
  `eligibleFirings`/`applyOutcome` (model.ts) and `green()` (engine.ts).
747
+ - `judgeModifiers?: string[]` — the internal compiled carrier for the
748
+ authored judge's optional scope; it is not a general conditional-step key.
747
749
  - The producer step's complete parsed `x:` extension carrier is deep-cloned
748
750
  onto every synthesized judge. Judge entries do not author their own `x:`;
749
751
  inheritance happens after the producer has been fully parsed. Every judge
@@ -773,7 +775,7 @@ sign-off ledger, present only while relevant (`undefined` once an artifact is
773
775
  `green`/`rejected` cleanly, cleared on every reject/retry/fresh-submit).
774
776
 
775
777
  - **Judge approve**: `approvals[judgeName] = artifact.version`. If every
776
- declared judge name now maps to the artifact's *current* version, the
778
+ active judge name now maps to the artifact's *current* version, the
777
779
  artifact transitions `submitted → green`. Otherwise it stays `submitted`
778
780
  with a partial ledger.
779
781
  - **Judge reject**: any single reject wins immediately —
@@ -913,6 +915,7 @@ steps:
913
915
  model: strong # optional, per-judge model
914
916
  inputs: true # optional, default false — judge also
915
917
  # reads the producer's inputs (question)
918
+ modifiers: [deep] # optional exact workflow-modifier scope
916
919
  maxAttempts: 8 # optional, §6 — overrides the step default below
917
920
  # just for `report`; absent caps still inherit
918
921
  maxAttempts: 5 # producer's cap (default for every produce on this step)
@@ -933,6 +936,22 @@ steps:
933
936
  inputs, for criteria that need "what was asked for" as context.
934
937
  - `cadence:` / `maxRunsPerDay:` — optional throttles, same meaning as on
935
938
  steps; firing is event-driven (on submit), the throttles just cap the rate.
939
+ - `modifiers:` — optional non-empty set of exact workflow modifier names. The
940
+ names must be declared in the workflow's top-level `modifiers:` vocabulary.
941
+ Unscoped judges stay unconditional; a scoped judge is inactive without a
942
+ matching stored instance modifier. `activeJudgesForStem(def, stem, modifier)`
943
+ is the shared derivation used by eligibility, pending status, producer and
944
+ verdict commits, rejection, groups, terminal timing, and model checking.
945
+ Inactive judges create no order, approval ledger slot, routing receipt, or
946
+ completion debt.
947
+
948
+ When a definition binds `modifier` from a produced artifact, scoped-judge
949
+ producers must be strictly downstream of that artifact under the same exact
950
+ consume/produce matching used by routing lint. This rules out the binder itself
951
+ and sibling branches, which might commit before the stored modifier is known.
952
+ Definitions with no modifier bind remain valid: their instance modifier is
953
+ chosen at create time (or absent), and active judge orders retain ordinary
954
+ capability composition.
936
955
 
937
956
  See `examples/workflows/judged-research.yaml` for a runnable end-to-end
938
957
  example (mirrors this shape exactly, plus `examples/workflows/judges/rigor.md`
@@ -1147,6 +1166,12 @@ at `create` time. `CheckOptions.assumeProvided` (library level, when calling
1147
1166
  library default is unchanged by the CLI change below, and is what the
1148
1167
  `modelCheck` unit tests calling it directly still rely on.
1149
1168
 
1169
+ `CheckOptions.modifier` selects one concrete stored-modifier variant for the
1170
+ pure checker. Call `modelCheck(def, { modifier: 'deep', assumeProvided: true })`
1171
+ for each declared variant; inactive synthesized judge steps are omitted from
1172
+ that variant's dead/unreached accounting, while active judges are checked
1173
+ normally.
1174
+
1150
1175
  `owenloop check` (the CLI command), however, now defaults to
1151
1176
  `assumeProvided: true` — seedOwed inputs are seeded green by default,
1152
1177
  modeling "the operator already ran `provide` at `create`." This dissolves
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "owenloop",
3
- "version": "0.5.23",
3
+ "version": "0.5.25",
4
4
  "description": "Deterministic rails for agentic workflows. Declare steps and dependencies; the engine guarantees order, redoes what changes invalidate, and stops what keeps failing — instead of hoping the agent follows through.",
5
5
  "license": "Apache-2.0",
6
6
  "author": "typicalday",
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "owenloop",
3
- "version": "0.5.23",
3
+ "version": "0.5.25",
4
4
  "description": "Claude Code driver for owenloop — cross-harness shift and conduct skills driven by the owenloop CLI, plus one hub control-plane MCP server backing an author skill and a fallback worker, for conducting and authoring workflows against your hosted owenloop server.",
5
5
  "author": {
6
6
  "name": "Typical Day"
@@ -7,7 +7,7 @@
7
7
  "mcp"
8
8
  ],
9
9
  "env": {
10
- "OWENLOOP_PLUGIN_VERSION": "0.5.23"
10
+ "OWENLOOP_PLUGIN_VERSION": "0.5.25"
11
11
  }
12
12
  }
13
13
  }
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "owenloop",
3
- "version": "0.5.23",
3
+ "version": "0.5.25",
4
4
  "description": "Codex plugin for the owenloop workflow engine.",
5
5
  "skills": "./skills/",
6
6
  "mcpServers": "./.mcp.json"
@@ -6,7 +6,7 @@
6
6
  "mcp"
7
7
  ],
8
8
  "env": {
9
- "OWENLOOP_PLUGIN_VERSION": "0.5.23"
9
+ "OWENLOOP_PLUGIN_VERSION": "0.5.25"
10
10
  },
11
11
  "env_vars": [
12
12
  "HOME",