docs: updated graph agent docs to reflect improved llm node failure behavior

Graph-Agents.md

@@ -428,17 +428,18 @@ whitelist is enforced against global tools, agent custom tools, and MCP
 alike. Each entry is validated at startup against the active agent's tool
 list; an unknown entry is a startup error.
 
-### Tolerant-fail routing
+### Failure routing
 
-| Outcome                                  | Routes to                  |
+| Outcome                                  | Behavior                                                                                  |
-|------------------------------------------|----------------------------|
+|------------------------------------------|-------------------------------------------------------------------------------------------|
-| Success                                  | `next`                     |
+| Success                                  | Routes via `next`.                                                                        |
-| Failure WITH `fallback` set              | `fallback`                 |
+| Failure with `fallback` set              | Routes via `fallback`; `state_updates` are still applied; `{{output}}` holds the error.   |
-| Failure WITHOUT `fallback`               | `next` (output is "LLM node failed: ...") |
+| Failure without `fallback`               | **Graph fails at this node** with a clear error message naming the underlying cause.      |
 
-`state_updates` are always applied (success or failure). On failure,
+`state_updates` are always applied when the node has a `fallback` route
-`{{output}}` resolves to an error description so downstream nodes can detect
+(success or failure). On failure with no `fallback`, the graph aborts before
-it.
+downstream nodes run, so downstream `{{output}}` references never see error
+strings; the upstream cause is reported instead.
 
 ### Retries (`max_attempts`)
 
@@ -746,22 +747,24 @@ Nodes route via three mechanisms in priority order:
 | `script`    | Either `_next` from script output OR static `next` (or `fallback` on failure). Error if neither.  | Yes (when `_next` is not emitted) |
 | `approval`  | No - routing is via `routes` and `on_other`. `next` is ignored.                                   | No - forbidden by validator       |
 | `input`     | **Yes** - `next` is the success route.                                                            | No - forbidden by validator       |
-| `llm`       | **Yes** - `next` is the success route (and the default for failures without `fallback`).          | Yes (success path; failure with `fallback` routes to single target) |
+| `llm`       | **Yes** - `next` is the success route. Failures without `fallback` halt the graph.                | Yes (success path; failure with `fallback` routes to single target) |
 | `rag`       | **Yes** - `next` is required. Error at runtime if missing.                                        | Yes                               |
 | `map`       | **Yes** - `next` is where the parent super-step continues after the map collects.                 | Yes                               |
 | `end`       | No - terminal.                                                                                    | n/a                               |
 
-### Tolerant-fail contract
+### Failure-handling contract
 
-Currently honored by `script` and `llm` nodes:
+| Node type                  | Success                     | Failure with `fallback` | Failure without `fallback`                                |
+|----------------------------|-----------------------------|-------------------------|-----------------------------------------------------------|
+| `llm`                      | Routes via `next`           | Routes via `fallback`   | **Graph fails at this node** (use `fallback:` to recover) |
+| `script`                   | Routes via `next`           | Routes via `fallback`   | Routes via `next`; `{{output}}` holds the error           |
+| `agent` / `input`          | Routes via `next`           | n/a (no `fallback`)     | Graph fails at this node                                  |
+| `rag` / `map` / `approval` | Routes via configured edges | n/a                     | Graph fails at this node                                  |
 
-- Success -> default routing
+**Note:** LLM node failures halt the graph with
-- Failure with `fallback` set -> `fallback` target
+a clear error message. This prevents downstream nodes from running against
-- Failure without `fallback` -> default routing, with the error description
+garbage state when an upstream LLM call fails (HTTP 4xx/5xx, timeout,
-  exposed in state so the next node can react
+structured-extraction error, etc.).
-
-`agent` and `input` nodes do NOT have a tolerant-fail `fallback` path;
-their failures propagate as graph failures.
 
 ---
 
@@ -1127,8 +1130,9 @@ Schema:
 
 ### Tolerant-fail for extraction
 
-- **LLM node**: extraction failure = node failure -> routes via `fallback`
+- **LLM node**: extraction failure = node failure. Routes via `fallback`
-  or `next`.
+  if declared; otherwise the graph fails at this node with the extractor
+  error message.
 - **Agent node**: extraction failure propagates as a graph error (agent
   nodes have no `fallback`).