feat(workflows): add stage introspection and control actions

packages/workflows/CHANGELOG.md

@@ -6,6 +6,10 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+### Added
+
+- Added workflow tool stage introspection and control actions (`stages`, `stage`, `transcript`, `send`, `pause`, and `reload`) for inspecting stage state, reading transcripts, answering prompts, controlling live stages, pausing runs, and reloading workflow resources ([#1023](https://github.com/flora131/atomic/issues/1023)).
+
 ### Changed
 
 - Added a final Ralph PR-preparation phase that reviews changes against the configured base branch, tries available GitHub credentials using local git identity as a hint, posts implementation notes as a PR comment, and creates a pull request when possible.
@@ -15,6 +19,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 ### Fixed
 
 - Removed biasing stage-output and iteration-count context from Ralph reviewer prompts while making the comparison base branch explicit ([#1037](https://github.com/flora131/atomic/issues/1037)).
+- Ordered snapshot transcript fallback entries chronologically before applying `tail`/`limit`, preserving terminal result/error entries after tools for missing or tied timestamps ([#1023](https://github.com/flora131/atomic/issues/1023)).
+- Reloaded workflow resources directly for `workflow({ action: "reload" })` instead of queuing a literal `/workflow reload` follow-up ([#1023](https://github.com/flora131/atomic/issues/1023)).
+- Kept pending prompts unresolved when `workflow({ action: "send" })` omits `text`, `response`, and `message`, while preserving explicit empty-string answers ([#1023](https://github.com/flora131/atomic/issues/1023)).
 - Included `deep-research-codebase` discovery-stage handoff files in the persisted run manifest.
 - Persisted `deep-research-codebase` final reports as dated Markdown research docs while retaining file-only handoffs for bounded aggregation.
 - Prevented `deep-research-codebase` aggregation from inlining large specialist transcripts by using file-only handoff artifacts ([#1016](https://github.com/flora131/atomic/issues/1016)).

packages/workflows/README.md

@@ -192,6 +192,7 @@ registry.get("alpha"); // compiled workflow definition | undefined
 | `/workflow interrupt [run-id\|--all]` | Pause active/named/all active runs so they can resume    |
 | `/workflow kill [run-id\|--all]`      | Kill and remove active/named/all active runs from status |
 | `/workflow resume <run-id>`           | Resume paused work or re-open a run snapshot             |
+| `/workflow reload`                    | Reload discovered workflow resources in-process          |
 | `/workflow inputs <name>`             | Print the input schema for a workflow                    |
 
 Input overrides are bare `key=value` tokens (no leading `--`). Values are JSON-parsed when possible, so numbers, booleans, and quoted strings work as expected (e.g. `count=3`, `flag=true`, `prompt="multi word value"`). A whole-object override can be passed as a single JSON token (e.g. `{"prompt":"...","count":3}`).
@@ -207,18 +208,31 @@ Workflows always run as **background tasks** — the chat editor stays free whil
   "parameters": {
     "workflow": "string (optional) — workflow ID or normalized name",
     "inputs": "object (optional) — key/value map of workflow inputs",
-    "action": "'run' | 'list' | 'get' | 'inputs' | 'status' | 'interrupt' | 'kill' | 'resume'",
-    "runId": "optional run id or unique prefix; interrupt/kill default to the active run; use '--all' or all:true for interrupt/kill all",
-    "stageId": "optional stage id, prefix, or name for resume",
-    "message": "optional resume message",
-    "all": "optional boolean for interrupt/kill all",
+    "action": "'run' | 'list' | 'get' | 'inputs' | 'status' | 'stages' | 'stage' | 'transcript' | 'send' | 'pause' | 'interrupt' | 'kill' | 'resume' | 'reload'",
+    "runId": "optional run id or unique prefix; control actions default to the active run where safe; use '--all' or all:true for pause/interrupt/kill all",
+    "stageId": "optional stage id, prefix, or name for stage-scoped actions; cannot be combined with all:true",
+    "statusFilter": "optional stages filter: pending/running/awaiting_input/paused/blocked/completed/failed/skipped/all",
+    "format": "optional agent-facing output format: text or json",
+    "limit": "transcript-only maximum number of most recent entries; default 50",
+    "tail": "transcript-only last-N entry count; overrides limit",
+    "includeToolOutput": "transcript-only flag for snapshot tool-event output; live transcripts may not expose tool output",
+    "text": "optional string payload for send/resume; explicit empty text answers pending prompts",
+    "response": "optional structured payload for answering pending prompts; explicit empty response is valid",
+    "message": "optional string payload for send/resume when text is not provided",
+    "delivery": "optional send delivery mode: auto, answer, prompt, steer, followUp, or resume; auto prioritizes answer, then resume, steer, followUp",
+    "promptId": "optional pending prompt identifier for send/answer",
+    "reason": "optional human-readable reload reason",
+    "all": "optional boolean for pause/interrupt/kill all; cannot be combined with stageId",
     "task/tasks/chain": "optional direct workflow-native orchestration modes"
   }
 }
 ```
 
 - **`renderCall`** — renders a compact workflow call summary in the chat scroll.
 - **`renderResult`** — renders the result or dispatch banner; live progress continues through the widget and graph viewer. Named workflow runs are background-oriented.
+- **`transcript`** — uses a registered live stage handle when one exists, even before live messages arrive; otherwise it falls back to stored stage snapshots. Snapshot entries are ordered chronologically before `tail`/`limit` is applied, with terminal result/error entries kept after tool entries when timestamps are missing or tied. `includeToolOutput` applies to snapshot tool events; live session transcripts may not expose tool output.
+- **`send`** — answers pending stage prompts only when `text`, `response`, or `message` is present; an explicit empty string is a valid answer, while an omitted payload is a no-op. `delivery: "auto"` answers pending prompts first, then resumes paused stages, steers streaming stages, or queues a follow-up.
+- **`reload`** — refreshes workflow resources directly in-process instead of queuing a literal `/workflow reload` chat follow-up.
 
 ### F2 keyboard shortcut