docs+defaults: declare delegation.fallback_providers in config surfaces

Adopted from PR #80421 with the author's explicit go-ahead on #80450
('Please proceed!'): config_defaults entry, cli-config.yaml.example
block, and user-guide docs for the delegation-scoped fallback chain.

Co-authored-by: Andrex Ibiza, MBA <84248988+andrexibiza@users.noreply.github.com>

cli-config.yaml.example

@@ -1662,6 +1662,9 @@ delegation:
   #                                           # delegation.model to an inexpensive one — children carry the
   #                                           # vast majority of tokens, so this is where spend is cut while
   #                                           # planning quality stays with the frontier parent.
+  # fallback_providers:                       # Fallback chain for delegated children (same entry format as the
+  #   - provider: "openrouter"                # top-level fallback_providers list). Unset = inherit the parent
+  #     model: "deepseek/deepseek-chat"       # agent's chain; [] = disable child fallback entirely (#65038).
 
 # =============================================================================
 # Honcho Integration (Cross-Session User Modeling)

hermes_cli/config_defaults.py

@@ -1211,6 +1211,11 @@ DEFAULT_CONFIG = {
     "delegation": {
         "model": "",  # e.g. "google/gemini-3-flash-preview" (empty = inherit parent)
         "provider": "",  # e.g. "openrouter" (empty = inherit parent provider + credentials)
+        # Fallback chain for delegated children (same entry format as the top-level list).
+        # For an unpinned child, null = inherit the parent chain; [] = disable fallback.
+        # A child pinned by provider, endpoint, or model gets no fallback unless this
+        # setting declares one explicitly.
+        "fallback_providers": None,
         "base_url": "",  # direct OpenAI-compatible endpoint for subagents
         "api_key": "",  # key for delegation.base_url (falls back to OPENAI_API_KEY)
         # Wire protocol for delegation.base_url: "chat_completions" | "codex_responses" |

website/docs/user-guide/configuration.md

@@ -2704,6 +2704,8 @@ delegation:
 
 **Subagent provider:model override:** By default, subagents inherit the parent agent's provider and model. Set `delegation.provider` and `delegation.model` to route subagents to a different provider:model pair — e.g., use a cheap/fast model for narrowly-scoped subtasks while your primary agent runs an expensive reasoning model.
 
+**Subagent fallback chain:** Set `delegation.fallback_providers` to give workers their own chain (same entry shape as the top-level list). An explicitly pinned child (by provider, endpoint, or model) uses that chain only when it is declared; otherwise it fails loudly instead of borrowing the parent agent's route. For an unpinned child, an absent or `null` setting preserves parent-chain inheritance. Use `fallback_providers: []` under `delegation:` to disable child fallback entirely.
+
 **Direct endpoint override:** If you want the obvious custom-endpoint path, set `delegation.base_url`, `delegation.api_key`, and `delegation.model`. That sends subagents directly to that OpenAI-compatible endpoint and takes precedence over `delegation.provider`. If `delegation.api_key` is omitted, Hermes falls back to `OPENAI_API_KEY` only. When `delegation.provider` is set alongside `delegation.base_url`, the explicit endpoint and key still win, but that provider's request settings (`extra_body` overrides and max output tokens from your `custom_providers` entry) are carried into the subagent.
 
 **Per-child request settings (`request_overrides`):** `delegation.request_overrides` is a dict of request settings sent on every subagent API call. Top-level keys are API kwargs (e.g. `service_tier`); an `extra_body` sub-dict is merged into the request's `extra_body`. It is honored on **all three** resolution branches — direct `base_url`, named `provider`, and pure inherit — so the key always takes effect. Precedence: explicit `request_overrides` values merge **over** any runtime- or parent-derived overrides — top-level explicit keys win, and `extra_body` is deep-merged one level so runtime `extra_body` keys (e.g. a provider's `thinking: {type: disabled}` personality) survive unless your key redefines them. The canonical use case is OpenRouter routing hints for delegation children:
@@ -2718,7 +2720,6 @@ delegation:
       provider:
         sort: throughput   # route children to the fastest OpenRouter provider
 ```
-
 **Wire protocol (`api_mode`):** Hermes auto-detects the wire protocol from `delegation.base_url` (e.g. paths ending in `/anthropic` → `anthropic_messages`; Codex / native Anthropic / Kimi-coding hostnames keep their existing detection). For endpoints the heuristic can't classify — for example Azure AI Foundry, MiniMax, Zhipu GLM, or LiteLLM proxies fronting an Anthropic-shaped backend — set `delegation.api_mode` explicitly to one of `chat_completions`, `codex_responses`, or `anthropic_messages`. Leave it empty (the default) to keep auto-detection.
 
 The delegation provider uses the same credential resolution as CLI/gateway startup. All configured providers are supported: `openrouter`, `nous`, `copilot`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`. When a provider is set, the system automatically resolves the correct base URL, API key, and API mode — no manual credential wiring needed.

website/docs/user-guide/features/fallback-providers.md

@@ -185,7 +185,7 @@ fallback_providers:
 |---------|-------------------|
 | CLI sessions | ✔ |
 | Messaging gateway (Telegram, Discord, etc.) | ✔ |
-| Subagent delegation | ✔ (subagents inherit the parent fallback chain) |
+| Subagent delegation | ✔ (`delegation.fallback_providers` when set; otherwise inherit parent chain; `[]` disables) |
 | Cron jobs | ✔ (cron agents inherit configured fallback providers) |
 | Auxiliary tasks on `provider: auto` | ✔ (try per-task fallback, then the main fallback chain before built-in aux discovery) |