hermes-taskflow 0.3.0-beta.1 → 0.3.0-beta.1.2

package/README.md

@@ -21,7 +21,7 @@
 
 **taskflow is a declarative runtime for coding-agent workflows.** It turns a graph into a verifiable execution contract, runs phases in isolation, and keeps intermediate work out of the host conversation. In the 0.3 candidate, the contract also describes the effects a phase is allowed to propose.
 
-> **Status: 0.3.0-beta.1 Trusted Effects beta — beta channel, not GA.** This release candidate is prepared for npm's `beta` channel; the beta ships the Trusted Effects MVP described below. The 0.3-C Control Plane remains a follow-on candidate track; it is not a shipped beta surface.
+> **Status: 0.3.0-beta.1.2 Trusted Effects beta — beta channel, not GA.** This release candidate is prepared for npm's `beta` channel; the beta ships the Trusted Effects MVP described below. The 0.3-C Control Plane remains a follow-on candidate track; it is not a shipped beta surface.
 
 ## The 0.3 idea
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "hermes-taskflow",
-  "version": "0.3.0-beta.1",
+  "version": "0.3.0-beta.1.2",
   "description": "Run taskflow on Hermes Agent: a Hermes subagent runner plus an MCP server (and a config scaffold) that exposes the taskflow_* tools to Hermes users.",
   "keywords": [
     "hermes",
@@ -50,9 +50,9 @@
     "access": "public"
   },
   "dependencies": {
-    "taskflow-core": "0.3.0-beta.1",
-    "taskflow-hosts": "0.3.0-beta.1",
-    "taskflow-mcp-core": "0.3.0-beta.1"
+    "taskflow-core": "0.3.0-beta.1.2",
+    "taskflow-hosts": "0.3.0-beta.1.2",
+    "taskflow-mcp-core": "0.3.0-beta.1.2"
   },
   "scripts": {
     "build": "rm -rf dist && tsc -p tsconfig.build.json && node ../../scripts/copy-readme.mjs hermes-taskflow"

package/plugin/hermes.config.snippet.yaml

@@ -14,7 +14,7 @@
 
 taskflow:
   command: "npx"
-  args: ["-y", "-p", "hermes-taskflow@0.3.0-beta.1", "hermes-taskflow-mcp"]
+  args: ["-y", "-p", "hermes-taskflow@0.3.0-beta.1.2", "hermes-taskflow-mcp"]
   env:
     # Uncomment for mutating agent phases (terminal / file write).
     # Leave unset for verify/plan/script-only flows.

package/plugin/skills/taskflow/SKILL.md

@@ -163,6 +163,24 @@ large definition on every call and keeps a durable draft you can diff. Falls
 back cleanly: precedence is `define` (inline) > `defineFile` (disk) > `name`
 (saved flow).
 
+### Long instructions: `taskFile` (load-time include, not `context`)
+
+A phase or parallel branch may set `taskFile` **instead of** `task`. Trusted
+loaders (`defineFile` / saved flow) resolve the **literal** path against the
+definition directory — same class of source as `scriptCwd: "flow"` — inline the
+UTF-8 body into `task`, and **delete** `taskFile` before validate / interpolate
+/ cache / FlowIR. Runtime never sees `taskFile`.
+
+- XOR with `task`. Path is a static import: **not interpolated**, no `..`, no
+  symlink leaf, must stay physically inside the flow directory. Cap 256 KiB.
+- Inline leftover → `TF_TASKFILE_NO_PROVENANCE`. Generated sub-flows →
+  `TF_DYNAMIC_RESOURCE_FORBIDDEN`.
+- Do **not** put durable instructions in `context`. `context` is cwd-relative,
+  default-truncated at 8k, wrapped as `## File:`, marked unreplayable, and
+  forbidden in dynamic sub-flows.
+- TS DSL: `agent({ taskFile: "prompts/x.md" })`. `taskflow-dsl check` / erase
+  emit the field and do **not** read the file.
+
 ### DSL shape
 
 ```jsonc

package/plugin/skills/taskflow/configuration.md

@@ -47,7 +47,7 @@ Top-level keys of the taskflow definition object.
 | `concurrency` | number | `8` | Default fan-out / same-layer parallelism cap. See §4. |
 | `idleTimeout` | number | host default (`300000`) | Flow-level idle watchdog in ms (≥ 1000, or `0` to disable) for all agent-running phases that don't set their own. `0` disables the watchdog but then **every** agent-running phase MUST declare a finite wall `timeout` (≥ 1000) so the flow can never hang. A per-phase `idleTimeout` overrides this. |
 | `agentScope` | `user`\|`project`\|`both` | `user` | Which agent dirs to load. See §6. |
-| `scriptCwd` | `invocation`\|`flow` | `invocation` | Default cwd policy for `script` phases. `flow` requires trusted saved-flow/`defineFile` provenance; explicit phase `cwd` wins, and inherited cwd-bridge boundaries still constrain the resolved source directory. |
+| `scriptCwd` | `invocation`\|`flow` | `invocation` | Default cwd policy for `script` phases. `flow` requires trusted saved-flow/`defineFile` provenance; explicit phase `cwd` wins, and inherited cwd-bridge boundaries still constrain the resolved source directory. `taskFile` is the same class of load-time trusted source (see §2). |
 | `args` | record | `{}` | Declared invocation arguments. See §3. |
 | `hooks` | object | — | **0.2.7.** Terminal fire-and-forget notifications: `onComplete` / `onFail` / `onBlocked` arrays of `{type:"webhook"\|"file"\|"command", …}`. Payload is summary-only (`taskflow.hook.v1`) — never transcripts. Hook failure never changes run status. `https` or `http://127.0.0.1\|localhost` for webhooks; `command.run` is argv-only (no shell string). |
 | `phases` | array | — | **Required.** The phase DAG. See §2. |
@@ -89,10 +89,11 @@ Keys of each object in `phases[]`. Some only apply to specific `type`s.
 | `id` | all | — | **Required, unique.** Used in `{steps.<id>…}`. |
 | `type` | all | `agent` | One of the **12** phase types (agent, parallel, map, gate, reduce, approval, flow, loop, tournament, script, **race**, **expand**). |
 | `agent` | all | first available | Agent name; resolved from the scoped pool. |
-| `task` | agent, gate, map, reduce | — | Prompt; supports interpolation. Required for these types. |
+| `task` | agent, gate, map, reduce | — | Prompt; supports interpolation. Required for these types unless `taskFile` is set. |
+| `taskFile` | agent, gate, map, reduce, parallel/race branch | — | Load-time include. Literal path relative to the flow definition directory. Trusted loaders inline UTF-8 into `task` and delete the field. XOR with `task`. Path is **not** interpolated. Cap 256 KiB. Not `context`. |
 | `over` | map | — | **Required for map.** Must resolve to an array. |
 | `as` | map | `item` | Loop variable bound per item. |
-| `branches` | parallel, race | — | **Required** (≥1 for parallel; ≥2 for race). `[{task, agent?}]`. |
+| `branches` | parallel, race | — | **Required** (≥1 for parallel; ≥2 for race). `[{task, agent?}]` or `{taskFile, agent?}`. |
 | `cancelLosers` | race | `true` | Abort in-flight losers after first **success** (best-effort AbortSignal). |
 | `from` | reduce | — | **Required for reduce.** Phase ids whose outputs are aggregated. `{previous.output}` resolves to **all completed `from[]` outputs** in from-array order (one → raw; many → `### <id>\n\n<output>` sections joined by `\n\n---\n\n`). |
 | `reduceStrategy` | reduce | `one-shot` | `one-shot` = a single reducer call over all aggregated inputs. `tree` = batched intermediate reducer rounds (see `batchSize`); useful when aggregated input would exceed one prompt. `tree` forces the imperative runtime (event kernel falls back). |