bullswarm 0.26.0 → 0.27.0

package/AGENTS.md

@@ -20,37 +20,31 @@ content. Published as `bullswarm` on npm.
 5. Workflow dispatches must honor the same guarantees as single runs:
    `BULLSWARM_DEPTH` is propagated, burst-gated pools are excluded, and
    auth verdicts quarantine the pool + append to the shared decision log
-   (R6/R7/R8 in `src/workflow/runtime.js`).
-6. Adversarial verification is a first-class primitive: a `verify` step
-   reads a prior outFile and demands a JSON `{ok, concerns, summary}`
-   verdict before downstream steps can trust the work (R-skeptic).
-7. Workflows can be built incrementally from the shell
-   (`bullswarm workflow draft create/phase/step/set/...`). Drafts are
-   stored under `~/.bullswarm/drafts/<name>/` and are runnable by name
-   without an upfront JSON. JSON is still the durable artifact — drafts
-   are JSON documents, just built one mutation at a time.
-8. New goal workflows are caller-planned programs in a shared workspace.
+   (R6/R7/R8 in `src/workflow/v2-dispatch.js`).
+6. Adversarial verification is a first-class primitive: an action naming
+   requirements in `evidenceFor` is dispatched under an evidence contract and
+   judges them from the durable artifact, so a requirement is only verified by
+   work someone else inspected (R-skeptic).
+7. New goal workflows are caller-planned programs in a shared workspace.
    `bullswarm workflow goal --program` executes the graph; `--orchestrator`
    explicitly delegates planning. File territories are advisory scheduling
    hints, and the graph finishes without automatic gap rounds. `verified`
    separately records requirement evidence. `--isolation` opts into strict
    per-worker worktrees. Saved V2 runs preserve their original semantics.
+8. Historical authored-graph runs remain visible as read-only `legacy` rows.
+   Their executor was removed in 0.27.0; driving commands fail closed before
+   dispatch and historical run directories remain untouched.
 
 ## Development
 
 ```bash
 npm test            # full suite, no network needed (meters read from cache)
 node bin/bullswarm.js doctor --json   # readiness report
-node bin/bullswarm.js workflow list   # discover workflows
+node bin/bullswarm.js workflow goal "Fix the failing tests" --program plan.json
 node bin/bullswarm.js workflow runs   # ongoing workflow instances
 node bin/bullswarm.js workflow runs --all   # including historical
-node bin/bullswarm.js workflow validate <file>  # dry-run
-BULLSWARM_HOME=/tmp/bs node bin/bullswarm.js workflow run <file>   # sandboxed run
-# Build a workflow from the shell:
-bullswarm workflow draft create my-audit
-bullswarm workflow draft phase add my-audit discover
-bullswarm workflow draft step add my-audit discover list-files --type run --prompt 'List files'
-bullswarm workflow draft run my-audit
+# Validate a caller-authored program before launch:
+bullswarm workflow plan validate "Fix the failing tests" --program plan.json
 # Operate on a run by shortId (6 chars) or full runId (`wf-...`):
 bullswarm workflow runs show <shortId>
 bullswarm workflow runs delete <shortId> --yes

package/CHANGELOG.md

@@ -1,5 +1,94 @@
 # bullswarm changelog
 
+## 0.27.0 — one workflow engine
+
+- Fixed: a worker that floods its stdout could kill the kernel. Every chunk of a
+  worker's stdout and stderr was appended to one string; a command-code worker
+  whose transcript outgrew Node's maximum string length threw
+  `RangeError: Invalid string length` inside the stream handler, the kernel died
+  as an uncaught exception, and every worker it supervised died with it (seen
+  twice on the same action in one day; the trace is in
+  `~/.bullswarm/goals/<runId>/stderr.log`). Streams are now captured through a
+  bounded buffer that keeps the first and last 16 MiB of each stream, counts what
+  it dropped (`captureTruncated` on the attempt observation), and any exception
+  raised while reading a worker now fails that attempt instead of the kernel.
+  Fatal-signature matching already looked only at the last 4,000 characters, so
+  quota and auth detection are unchanged.
+
+- There is now one workflow engine. The authored-graph verbs `workflow run`,
+  `validate`, `list`, `draft`, `inspect` and `approval` are gone — each falls to
+  the workflow-level unknown-verb message, exits 2 and spawns nothing — and with
+  them the eleven V1 modules they drove: `runtime.js` (1,902 lines),
+  `runner.js` (1,304), `draft-cli.js` (434), `validate.js` (366),
+  `decision.js` (357), `tui.js` (297), `draft.js` (268), `result.js` (239),
+  `template.js` (146), `schema.js` (81) and `semaphore.js` (56). The V1 panel
+  model, timeline and orchestrator-detail twins came out of `dashboard.js`
+  (−965), the V1 branches out of `cli.js` (−291), `runs-cli.js` (−141),
+  `short-id.js` (−127) and `watch-cli.js` (−132). `src/workflow/*.js` goes from
+  16,941 lines to 10,257. Also deleted: the five saved definitions
+  `workflows/adaptive-code-review.json`, `agent-model-comparison.json`,
+  `connector-audit.json`, `smoke-two-step.json` and `verify-and-cap.json`
+  (257 lines) together with the `workflows/` entry in package.json `files`;
+  `scripts/sanity-multi-claude.mjs` (131), which only exercised `runWorkflow`;
+  and two more tools that could only reach deleted modules —
+  `bin/check-output-schema.js` (30, the V1 `outputSchema` worker preflight) and
+  `scripts/planner-contract-probe.mjs` (175, a probe for the V1 `decide`
+  planner). `workflow capabilities` now reports `engines.authoredGraphs` as
+  `{ retired: '0.27.0', command: null }` instead of advertising a verb that
+  exits 2. `bullswarm workflow --help` describes one engine.
+
+- `newRunId` moved from `runner.js` into `src/workflow/short-id.js`, same
+  behaviour, exported; `v2-runtime.js` imports it from there.
+
+- Removed the last V1 remnants that no gate caught because they named no
+  deleted symbol: the dead authored-graph planner prompt in
+  `src/workflow/goal.js` (`AUTONOMOUS_ORCHESTRATOR_PROMPT`,
+  `PLANNER_RULES_SECTION`, `PLANNER_EXAMPLES_SECTION` — 36 lines whose only
+  consumer was the deleted `runtime.js`, and which still taught `type`,
+  `stepTemplate`, `itemsFrom`, `outputSchema`, `covers` and `completion.when`
+  to a planner the V2 validator would reject), and the permanently-zero
+  `fanout: { total, ok, failed }` counter that `dashboard.js` still put on every
+  row and rendered behind an unreachable branch. `outputSchema`, `itemsFrom` and
+  `stepTemplate` now appear nowhere in `src/`. The `skill/references/operations.md`
+  "Adversarial verification" section described the removed `{ok, concerns,
+  summary}` verify verdict; it now documents the `bullswarm.workflow.evidence.v2`
+  envelope the kernel actually enforces. `AGENTS.md` doctrine item 5 pointed at
+  the deleted `runtime.js` and now points at `v2-dispatch.js`.
+
+- Historical authored-graph runs stay readable, read-only, and nothing tries to
+  drive them. A run directory whose `state.json` lacks
+  `schemaVersion: 'bullswarm.workflow.state.v2'` is a legacy run: `workflow runs`
+  (with `--all` and `--json`) lists it as one row — short id, run id, name or
+  goal, status, age — marked `legacy`, reading only those five fields and never
+  throwing on a missing one, and the workflow home lists the same row. Every
+  driving command — `runs show`, `runs result`, `watch`, `cancel`, `resume`,
+  `steer`, `action show`, `tui <runId>` — prints exactly one line, `legacy
+  authored-graph run <shortId>: its executor was removed in 0.27.0; files remain
+  under <dir>`, and exits 2 before touching anything — including on the older
+  directories that hold only a `workflow.json` and never had a `state.json` at
+  all; the workflow home shows
+  that same line in its detail pane. `events <runId>` still replays the durable
+  JSONL and `runs delete <id> --yes` still removes the directory. Historical
+  directories are never modified. The stale-owner reconciliation that used to
+  run before every dispatch is gone with the V1 liveness model it served.
+
+- Tests: 818 -> 661. Six V1-only files were deleted
+  (`workflow-adaptive`, `workflow-gaps`, `workflow-draft`, `workflow-schema`,
+  `workflow-validate`, `workflow-run` — 151 tests); `workflow-runs`,
+  `workflow-watch`, `assignments`, `workflow-interruption`, `workflow-steering`
+  and `workflow-goal` were rewritten onto the V2 kernel keeping every assertion
+  about shared behaviour; `workflow-dashboard` went from 48 cases to 35 — 21
+  V1-only cases removed and 2 added with the rewrite, then 6 re-added against V2
+  fixtures for the rendering behaviours the removal had dropped (blocked-action
+  naming, one segment header per phase or dependency level, the mid-segment
+  continuation header, parallel levels grouped in declared order, the narrow
+  layout, and auto-follow); and a new `workflow-legacy-runs` (11 tests) proves
+  the legacy contract against a synthetic legacy `state.json`.
+  `tests/manual-dynamic-real.mjs` (330 lines), a
+  manual real-provider matrix for authored `run`/`decide` graphs, went with the
+  executor; it was never part of the suite count. No test dispatches a real
+  provider.
+
 ## 0.26.0 — two entry points, kinds and rungs
 
 - There are now exactly two ways to start work, and `bullswarm delegate` is

package/README.md

@@ -30,8 +30,8 @@ without initializing state or executing the command:
 
 ```bash
 bullswarm --help
-bullswarm workflow run --help
-bullswarm workflow draft step add --help
+bullswarm workflow goal --help
+bullswarm workflow runs show --help
 ```
 
 `workflow goal` launches a durable background runner, prints operating commands,
@@ -112,19 +112,11 @@ bullswarm health   # re-judge saved outputs; catch gate failures
 | `pools` | Show each pool's meter state, pace position, 5-hour utilization (`5h=<n>%`, flagged `NEAR-5H-LIMIT` at or above 75%), quarantine status |
 | `strategy` | Interactive provider/model control center with live high/medium/low route previews and an agent-facing JSON API |
 | `doctor` | Machine-readable readiness report; self-heals on first call |
-| `workflow` | Start an autonomous goal, or run / validate / draft / inspect explicit workflows and their live instances. |
+| `workflow` | Plan, execute, observe, and operate one autonomous workflow engine and its live instances. |
 | `runs` | Short alias for `workflow runs`, including list, show, result, delete, and cleanup operations. |
 | `version` / `--version` | Print the installed Bullswarm version. |
 | `release` | Run the guarded local version-bump, commit, and tag workflow used before CI publishes to npm. |
 
-Discover and validate workflow definitions without executing them:
-
-```bash
-bullswarm workflow list
-bullswarm workflow list --json
-bullswarm workflow validate workflows/my-workflow.json
-```
-
 `workflow goal --request <path>` and `--run-id <id>` are internal detached-runner
 resume plumbing. Normal callers should provide a goal or use `--resume <shortId|runId>`.
 
@@ -141,7 +133,7 @@ bullswarm strategy routes --json           # compact effective choices
 bullswarm strategy set-provider codex off --yes
 bullswarm strategy set-model opencode2 kaihk/gpt-5.6-luna \
   --tiers high,medium,low --yes
-bullswarm strategy configure --file strategy.json --yes  # atomic agent-authored policy
+bullswarm strategy configure --file strategy.json --yes  # atomic agent-created policy
 bullswarm strategy reset-tier low --yes     # restore one tier to automatic
 bullswarm strategy set-reasoning --tier high --level xhigh --yes
 bullswarm strategy set-reasoning --tier high --level high --pool codex --yes
@@ -202,8 +194,8 @@ any routing change. Press `Y` to apply them or `N` to retain the current policy.
 The analysis selects at most one default model for each provider and effort
 tier. It uses OpenRouter's agentic, coding, and intelligence indices as quality
 signals and API-equivalent pricing as the budget signal. A repository-owned
-GitHub Actions job (`.github/workflows/refresh-benchmarks.yml`) refreshes two
-public assets on the rolling `benchmark-data-latest` GitHub Release:
+benchmark refresh job refreshes two public assets on the rolling
+`benchmark-data-latest` GitHub Release:
 `openrouter-benchmarks.json` from the authenticated OpenRouter APIs, and
 `epoch-benchmarks.json` from Epoch AI's CC BY 4.0 benchmark export, which is
 what `strategy rungs` reads for per-model-per-reasoning-level evidence.
@@ -321,7 +313,7 @@ phase/step/attempt tree.
 
 ## One-command autonomous goals
 
-For normal multi-step work, give Bullswarm the goal and the program you authored
+For normal multi-step work, give Bullswarm the goal and the program you author
 for it—not a JSON graph of phases:
 
 ```bash
@@ -433,9 +425,7 @@ The planner does not author phases or declare success/failure. The kernel
 derives stable presentation stages for the TUI and computes the final V2
 result. Saved V2 runs retain their original execution and workspace policy on
 resume. V1 autonomous run directories are not migrated or resumed;
-explicitly naming one fails before any paid dispatch. Fixed JSON workflows and
-drafts remain a separate authored-graph feature with their existing step
-types.
+explicitly naming one fails before any paid dispatch.
 
 The detached response includes a short ID and exact observation commands:
 
@@ -570,33 +560,6 @@ runs still support their original gap boundaries and `--exhausted` submissions.
 the caller plans against a real survey; scout units are advisory for a caller
 planner.
 
-Use an explicit draft when the graph itself is a durable contract and should
-not be planner-defined. `bullswarm workflow draft ...` lets you assemble it one
-mutation at a time. No upfront JSON required. Drafts persist under
-`~/.bullswarm/drafts/<name>/` and become first-class workflows
-(discoverable, runnable by name) the moment they exist.
-
-```bash
-bullswarm workflow draft create audit-code \
-    --description "Audit the source code" --input targetDir=.
-bullswarm workflow draft phase add audit-code discover
-bullswarm workflow draft phase add audit-code review
-bullswarm workflow draft step add audit-code discover list-files \
-    --type run --lane chore --prompt "List every .js file in src/" \
-    --add-dir '{{inputs.targetDir}}'
-bullswarm workflow draft step add audit-code review per-file \
-    --type fanout --items-from 'outputs.list-files.outFile' \
-    --lane analyze --concurrency 2 \
-    --step-template '{"lane":"analyze","addDir":"{{inputs.targetDir}}","prompt":"Review {{item}}"}'
-bullswarm workflow draft show audit-code    # inspect the JSON
-bullswarm workflow draft run audit-code     # execute it
-bullswarm workflow draft export audit-code workflows/audit-code.json   # promote to file
-```
-
-`step add` re-validates after every mutation; partial drafts (zero
-phases, etc.) are treated as building, not invalid. `set` and
-`step set` patch fields in place. `delete` requires `--yes`.
-
 ## Operating on workflow runs
 
 Every run gets a 6-character shortId (Crockford-style alphabet,
@@ -615,11 +578,13 @@ bullswarm workflow runs show <shortId>     # state + report + summary
 bullswarm workflow runs result <shortId> --json  # stable result for the calling agent
 bullswarm runs show <shortId>              # top-level shorthand
 bullswarm workflow runs delete <shortId> --yes    # remove the run dir
-
-# Resume by shortId — runs the same logic as the full runId
-bullswarm workflow run audit-code --resume <shortId>
 ```
 
+Legacy authored-graph runs are listed as read-only rows marked `legacy`. Every
+driving command prints `legacy authored-graph run <shortId>: its executor was
+removed in 0.27.0; files remain under <dir>` and exits 2; historical directories
+are untouched.
+
 Run-history time filters always compare when the workflow was initiated
 (`startedAt`), never when it finished. `--since` is inclusive and `--until` is
 exclusive; `--started-after`/`--from` and `--started-before`/`--to` are aliases.
@@ -635,8 +600,7 @@ usage, and verification qualification. New programs include `executionMode:
 "program"` and a `workspace` report with `changedFiles`, `baselineChangedFiles`,
 and warnings. This is a Git status inventory, not attribution to individual
 workers; files stay in the target directory. A completed program may be
-unverified and contain negative evidence. Fixed authored workflows retain their existing
-result envelope. `runs show` remains the low-level debugging surface.
+unverified and contain negative evidence. `runs show` remains the low-level debugging surface.
 Goal launch output includes an `instructions` handoff with four named paths:
 `agentInspect` for a machine-readable snapshot, `watch` for low-noise progress,
 `humanTui` for the interactive browser, and `result` for the terminal delivery.
@@ -661,10 +625,9 @@ periodic heartbeat is off unless you pass `--heartbeat <seconds>`;
 `--stall-after <seconds>` (default 300) reports a running agent that has
 gone silent. Pass `--classic` to force the older heartbeat-based watcher
 instead (the transition-on-change snapshot stream plus a periodic
-heartbeat, every 60 seconds unless `--heartbeat <seconds>` is given) —
-legacy (non-V2) runs already behave this way and `--classic` is a no-op for
-them; `--classic` cannot combine with `--next`, which exists only for event
-mode. `--next` prints no attach line and
+heartbeat, every 60 seconds unless `--heartbeat <seconds>` is given).
+`--classic` applies only to V2 runs and cannot combine with `--next`, which
+exists only for event mode. `--next` prints no attach line and
 exits after the first notable event so a background terminal can wake the
 caller; relaunch until the outcome line reports a pause or a terminal
 status (exit 0 while the run continues or delivered, 1 when it ended
@@ -684,9 +647,9 @@ prints). `--jsonl` emits one JSON object per notable event with a stable
 `interrupted`, and with `--verbose` `action.started`, `attempt.retrying`,
 `steering.delivered`); in that mode the relaunch line is not printed and
 every object instead carries the `sequence` it was emitted at, which is the
-value to pass as `--after`. `--once` still prints one current snapshot. Legacy
-(non-V2) runs keep the compact transition-plus-heartbeat stream unchanged,
-the same stream `--classic` opts a V2 run into.
+value to pass as `--after`. `--once` still prints one current snapshot. A legacy
+(pre-0.27.0 authored-graph) run cannot be watched at all: the watcher prints
+the legacy line and exits 2 before it polls anything.
 
 ```bash
 bullswarm workflow watch <shortId>
@@ -736,16 +699,14 @@ bullswarm workflow tui --json --all           # ongoing + historical runs
 bullswarm workflow tui --json <shortId>       # inspect one run
 bullswarm workflow tui --json --cancel <id>   # request cooperative stop
 bullswarm workflow capabilities --json       # pools, lanes, models, meters, limits
-bullswarm workflow inspect <file-or-name>     # workflow shape and semantics
 bullswarm workflow events --json <id> --after 20
 bullswarm workflow steer <id> --message "Prefer focused tests before another full suite"
 bullswarm workflow action show --json <id> <actionId>
-bullswarm workflow approval approve --json <id>  # then resume the run
 ```
 
 Cancellation stops active delegates and commits `cancelled`. V2 goal workflows
 keep the operator request in a separate durable file so kernel progress cannot
-overwrite it; authored V1 graphs additionally expose a `cancelling` state.
+overwrite it.
 `SIGTERM` and `SIGINT` stop delegate process groups and commit a resumable
 `interrupted` state. A V2 resume holds an exclusive kernel lease, stops recorded
 surviving delegates from the previous kernel, and finishes post-processing from
@@ -817,71 +778,6 @@ runtime value and uses its matching connector rate metadata for the attempt's
 cost estimate. Unknown or provider-hidden model identity remains explicitly
 unknown.
 
-### Authored adaptive graphs
-
-This is part of the separately authored fixed-graph engine, not the autonomous
-V2 `workflow goal` path. A graph may add an explicit `decide` step, advisory
-resource targets, and structural expansion limits:
-
-```json
-{
-  "mode": "adaptive",
-  "settings": {
-    "maxAgents": 12,
-    "maxExpansionRounds": 3,
-    "maxActions": 20,
-    "maxItemsPerExpansion": 8,
-    "maxWorkflowSeconds": 1800
-  },
-  "phases": [{
-    "name": "review",
-    "steps": [
-      { "id": "initial", "type": "run", "prompt": "Inspect the code." },
-      {
-        "id": "planner",
-        "type": "decide",
-        "requiresCapabilities": ["workflow-planning", "strong-analysis"],
-        "prompt": "Judge sufficiency and propose only bounded missing work."
-      }
-    ]
-  }]
-}
-```
-
-For an authored adaptive graph, `maxAgents`, `maxWorkflowSeconds`, and
-`maxExpansionRounds` are advisory inputs to its decide step. Approaching them
-strongly biases that step toward
-consolidating existing artifacts and returning the best useful outcome;
-crossing them is recorded but never stops a worker, skips verification, or
-fails a run. `maxActions` and `maxItemsPerExpansion` remain hard structural
-safeguards. Reaching one returns a qualified outcome when useful work exists,
-rather than discarding the run as a blanket failure. Delegates have no
-implicit wall-clock timeout; set a step's `timeoutSec` (or direct-run
-`--timeout`) only when an operator explicitly wants a hard termination timer.
-
-Within this authored-graph engine, `complete` remains strictly verified. A
-decide-step `stop` still
-delivers a completed outcome when a useful delivery exists: unresolved
-verification concerns and the stopping reason ride along as `outcome.concerns`
-and `outcome.reason`, attributes of that completed outcome rather than a
-separate terminal status. `stop` produces `blocked` only when no useful
-delivery exists. `workflow runs result` treats the completed outcome as ready
-while reporting `verified:false`. The status value `completed_with_concerns`
-still appears on some runs — including legacy ones recorded before this
-framing — and every consumer reads it exactly like `completed`: a delivered
-result with concerns to review, never a failure.
-
-The planner returns versioned JSON. It may propose `needs_more_work` with
-bounded `run`, inline-`fanout`, or `verify` actions. The deterministic runtime
-validates IDs, dependencies, operation types, capabilities, and budgets before
-appending anything. It executes ready actions, observes their durable results,
-and calls the planner again. `events.jsonl`, `state.json`, the TUI, and JSON
-inspection expose the same plan, actions, attempts, decisions, budgets, and
-artifacts. See `workflows/adaptive-code-review.json` for a complete example.
-Planner actions cannot set `pool`, `model`, `addDir`, or `taskFile`. If those need to be
-fixed by the initiator, declare them under the `decide` step's `actionDefaults`;
-otherwise eligible capable pools are ranked by live quota surplus.
-
 ## The verdict
 
 ```json

package/docs/workflow-design.md

@@ -1,6 +1,10 @@
 # bullswarm Dynamic Workflows — Design
 
-**Status:** implemented; historical design rationale retained · **Created:** 2026-08-21
+**Status:** historical. The authored-graph engine this document describes —
+`workflow run`, `workflow validate`, `workflow draft`, the `bullswarm.workflow.v1`
+document, its `decide` step and the `check-output-schema` preflight — was removed in
+0.27.0. The program-based V2 goal engine is the only workflow engine; see README.md.
+Kept for design rationale only · **Created:** 2026-08-21
 
 ## Problem
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bullswarm",
-  "version": "0.26.0",
+  "version": "0.27.0",
   "description": "Route work across coding-agent CLI subscriptions — paced by live quota meters, verified by content, never trusting exit codes.",
   "type": "module",
   "bin": {
@@ -14,7 +14,6 @@
     "bin/",
     "src/",
     "connectors/",
-    "workflows/",
     "skill/",
     "mcp/",
     "fixtures/",

package/skill/SKILL.md

@@ -151,4 +151,4 @@ always inspect the returned status.
 
 Read [operations.md](references/operations.md) only when you need **steering,
 cancellation, resume, scouting, a dispatched planner, explicit isolation,
-routing diagnosis, or fixed drafts**. Ordinary work needs only the flow above.
+routing diagnosis**. Ordinary work needs only the flow above.

package/skill/references/operations.md

@@ -76,10 +76,12 @@ Resume keeps the run's durable planner mode, routing pins, and settings;
 `--program`, `--orchestrator`, `--scout`, and `--suggested-plan` are rejected
 there (use `workflow plan submit` for a caller program). Autonomous resume is
 V2-only. An old autonomous run ID fails before dispatch; there is no migration
-or fallback executor. Fixed authored workflows and drafts remain a separate
-product surface. `bullswarm workflow goal --resume <shortId>` and
+or fallback executor. `bullswarm workflow goal --resume <shortId>` and
 `bullswarm workflow tui --cancel <shortId>` remain as aliases.
 
+Legacy authored-graph runs are listed as read-only rows marked `legacy`; driving
+commands fail closed with their short ID and retained run directory.
+
 ## Program actions: `kind`, `defaults`, and advisories
 
 An action's `kind` names what the work IS and derives its `lane` and `effort`,
@@ -168,16 +170,18 @@ must list exact files in `ownedFiles`; undeclared files can fail the action and
 are not integrated. An unrestricted writer with `ownedFiles: []` is invalid.
 Existing runs preserve their saved mode on resume.
 
-## Fixed graphs, fan-out, and adversarial verification
-
-Use `workflow draft` only when exact phases and dependencies are user-authored
-requirements. Drafts support `run`, `fanout`, and `verify` steps. A verify must
-return JSON `{ok, concerns, summary}` and is successful only when it parses and
-`ok` is true.
+## Adversarial verification
 
-For data-driven fan-out, make discovery return a JSON array or a schema-backed
-object, then use `itemsFrom`. Put `outputSchema` only on worker output that a
-later action consumes structurally; ordinary prose should not have a schema.
+An action that names requirement IDs in `evidenceFor` is dispatched under the
+kernel-owned evidence contract and writes a
+`bullswarm.workflow.evidence.v2` envelope — `requirements: { <id>: { status,
+evidence, concerns } }` — to the durable path the task file names. It judges the
+artifact its dependency produced, so give it `dependsOn` and no `ownedFiles`;
+the kernel validates the envelope after dispatch and a schema-invalid one gets
+one bounded correction. Do not ask a worker to return a `{ok, concerns,
+summary}` verdict or any other hand-rolled JSON shape: the program validator
+rejects response-format directives, and that older verdict shape is refused
+outright. `kind: 'adversarial-acceptance'` routes such an action to analyze/high.
 
 ## Routing and model policy
 
@@ -215,6 +219,8 @@ bullswarm workflow runs show <id> --json   # routing reason + candidates
   `remainingMinutes`. An empty list with work apparently running means the
   dispatching process never registered it; a stale-looking entry is pruned on
   the next read once its process is gone.
+- Legacy authored-graph rows are read-only. Every driving command fails closed
+  with the executor-removed message and leaves the historical run directory untouched.
 - `bullswarm pools` carries `inflight=<n>` next to each pool's `5h=<n>%`
   reading; `--json` adds the full `inflight` block (`count`, elapsed
   `minutes`, `remainingMinutes`, `unknownExpected`, `records[]`) and each