fix: follow-up for salvaged PR #8952

- Rename provider_contracts.py -> volcengine_byteplus.py for explicitness
- Consolidate duplicate host-to-provider mappings: provider_for_base_url()
  now uses the canonical _URL_TO_PROVIDER from model_metadata.py instead of
  maintaining a separate 20-entry dict
- Add volcengine/byteplus to runtime_provider.py model-dependent base URL
  resolution (kimi-style special case) so manually-edited configs resolve
  the coding-plan base URL correctly
- Remove volcengine/byteplus from _API_KEY_PROVIDER_AUX_MODELS — the
  main-model-first design in _resolve_auto() handles these providers
  already; entries were dead code in the normal flow
- Add VOLCENGINE_API_KEY and BYTEPLUS_API_KEY to OPTIONAL_ENV_VARS in
  config.py so they appear in hermes setup
- Update docs: environment-variables.md, fallback-providers.md,
  configuration.md

README.md

@@ -13,7 +13,7 @@
 
 **The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.
 
-Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
+Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [Volcengine](https://www.volcengine.com/product/ark), [BytePlus](https://www.byteplus.com/en/product/modelark), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
 
 <table>
 <tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr>

agent/auxiliary_client.py

@@ -74,6 +74,10 @@ _PROVIDER_ALIASES = {
     "minimax_cn": "minimax-cn",
     "claude": "anthropic",
     "claude-code": "anthropic",
+    "volcengine-coding-plan": "volcengine",
+    "volcengine_coding_plan": "volcengine",
+    "byteplus-coding-plan": "byteplus",
+    "byteplus_coding_plan": "byteplus",
 }
 
 

agent/model_metadata.py

@@ -14,8 +14,8 @@ from urllib.parse import urlparse
 import requests
 import yaml
 
+from hermes_cli.volcengine_byteplus import model_context_window
 from utils import base_url_host_matches, base_url_hostname
-
 from hermes_constants import OPENROUTER_MODELS_URL
 
 logger = logging.getLogger(__name__)
@@ -30,6 +30,10 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "qwen-oauth",
     "xiaomi",
     "arcee",
+    "volcengine",
+    "volcengine-coding-plan",
+    "byteplus",
+    "byteplus-coding-plan",
     "custom", "local",
     # Common aliases
     "google", "google-gemini", "google-ai-studio",
@@ -257,6 +261,8 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.xiaomimimo.com": "xiaomi",
     "xiaomimimo.com": "xiaomi",
     "ollama.com": "ollama-cloud",
+    "ark.cn-beijing.volces.com": "volcengine",
+    "ark.ap-southeast.bytepluses.com": "byteplus",
 }
 
 
@@ -1119,12 +1125,20 @@ def get_model_context_length(
         ctx = _resolve_nous_context_length(model)
         if ctx:
             return ctx
+    if effective_provider in {"volcengine", "byteplus"}:
+        ctx = model_context_window(model)
+        if ctx:
+            return ctx
     if effective_provider:
         from agent.models_dev import lookup_models_dev_context
         ctx = lookup_models_dev_context(effective_provider, model)
         if ctx:
             return ctx
 
+    ctx = model_context_window(model)
+    if ctx:
+        return ctx
+
     # 6. OpenRouter live API metadata (provider-unaware fallback)
     metadata = fetch_model_metadata()
     if model in metadata:

gateway/run.py

@@ -5690,6 +5690,7 @@ class GatewayRunner:
         from hermes_cli.models import (
             list_available_providers,
             normalize_provider,
+            provider_for_base_url,
             _PROVIDER_LABELS,
         )
 
@@ -5718,7 +5719,10 @@ class GatewayRunner:
         # Detect custom endpoint from config base_url
         if current_provider == "openrouter":
             _cfg_base = model_cfg.get("base_url", "") if isinstance(model_cfg, dict) else ""
-            if _cfg_base and "openrouter.ai" not in _cfg_base:
+            inferred_provider = provider_for_base_url(_cfg_base)
+            if inferred_provider:
+                current_provider = inferred_provider
+            elif _cfg_base and "openrouter.ai" not in _cfg_base:
                 current_provider = "custom"
 
         current_label = _PROVIDER_LABELS.get(current_provider, current_provider)

hermes_cli/auth.py

@@ -39,6 +39,13 @@ import httpx
 import yaml
 
 from hermes_cli.config import get_hermes_home, get_config_path, read_raw_config
+from hermes_cli.volcengine_byteplus import (
+    VOLCENGINE_PROVIDER,
+    BYTEPLUS_PROVIDER,
+    VOLCENGINE_STANDARD_BASE_URL,
+    BYTEPLUS_STANDARD_BASE_URL,
+    base_url_for_provider_model,
+)
 from hermes_constants import OPENROUTER_BASE_URL
 
 logger = logging.getLogger(__name__)
@@ -307,6 +314,20 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("XIAOMI_API_KEY",),
         base_url_env_var="XIAOMI_BASE_URL",
     ),
+    "volcengine": ProviderConfig(
+        id=VOLCENGINE_PROVIDER,
+        name="Volcengine",
+        auth_type="api_key",
+        inference_base_url=VOLCENGINE_STANDARD_BASE_URL,
+        api_key_env_vars=("VOLCENGINE_API_KEY",),
+    ),
+    "byteplus": ProviderConfig(
+        id=BYTEPLUS_PROVIDER,
+        name="BytePlus",
+        auth_type="api_key",
+        inference_base_url=BYTEPLUS_STANDARD_BASE_URL,
+        api_key_env_vars=("BYTEPLUS_API_KEY",),
+    ),
     "ollama-cloud": ProviderConfig(
         id="ollama-cloud",
         name="Ollama Cloud",
@@ -1015,6 +1036,10 @@ def resolve_provider(
         "hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
         "mimo": "xiaomi", "xiaomi-mimo": "xiaomi",
         "aws": "bedrock", "aws-bedrock": "bedrock", "amazon-bedrock": "bedrock", "amazon": "bedrock",
+        "volcengine-coding-plan": "volcengine",
+        "volcengine_coding_plan": "volcengine",
+        "byteplus-coding-plan": "byteplus",
+        "byteplus_coding_plan": "byteplus",
         "go": "opencode-go", "opencode-go-sub": "opencode-go",
         "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
         # Local server aliases — route through the generic custom provider
@@ -1157,6 +1182,21 @@ def _qwen_cli_auth_path() -> Path:
     return Path.home() / ".qwen" / "oauth_creds.json"
 
 
+def _current_model_for_provider(provider_id: str) -> str:
+    """Return the currently configured model when it belongs to the provider."""
+    try:
+        config = read_raw_config()
+    except Exception:
+        return ""
+
+    model_cfg = config.get("model")
+    if isinstance(model_cfg, dict):
+        configured_provider = str(model_cfg.get("provider") or "").strip().lower()
+        if configured_provider == provider_id:
+            return str(model_cfg.get("default") or model_cfg.get("model") or "").strip()
+    return ""
+
+
 def _read_qwen_cli_tokens() -> Dict[str, Any]:
     auth_path = _qwen_cli_auth_path()
     if not auth_path.exists():
@@ -2555,7 +2595,11 @@ def get_api_key_provider_status(provider_id: str) -> Dict[str, Any]:
     if pconfig.base_url_env_var:
         env_url = os.getenv(pconfig.base_url_env_var, "").strip()
 
-    if provider_id in ("kimi-coding", "kimi-coding-cn"):
+    active_model = _current_model_for_provider(provider_id)
+
+    if provider_id in {VOLCENGINE_PROVIDER, BYTEPLUS_PROVIDER}:
+        base_url = base_url_for_provider_model(provider_id, active_model) or pconfig.inference_base_url
+    elif provider_id in ("kimi-coding", "kimi-coding-cn"):
         base_url = _resolve_kimi_base_url(api_key, pconfig.inference_base_url, env_url)
     elif env_url:
         base_url = env_url
@@ -2650,7 +2694,11 @@ def resolve_api_key_provider_credentials(provider_id: str) -> Dict[str, Any]:
     if pconfig.base_url_env_var:
         env_url = os.getenv(pconfig.base_url_env_var, "").strip()
 
-    if provider_id in ("kimi-coding", "kimi-coding-cn"):
+    active_model = _current_model_for_provider(provider_id)
+
+    if provider_id in {VOLCENGINE_PROVIDER, BYTEPLUS_PROVIDER}:
+        base_url = base_url_for_provider_model(provider_id, active_model) or pconfig.inference_base_url
+    elif provider_id in ("kimi-coding", "kimi-coding-cn"):
         base_url = _resolve_kimi_base_url(api_key, pconfig.inference_base_url, env_url)
     elif provider_id == "zai":
         base_url = _resolve_zai_base_url(api_key, pconfig.inference_base_url, env_url)

hermes_cli/config.py

@@ -1281,6 +1281,20 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
+    "VOLCENGINE_API_KEY": {
+        "description": "Volcengine API key for Doubao / Seed models (standard + Coding Plan catalogs)",
+        "prompt": "Volcengine API Key",
+        "url": "https://www.volcengine.com/product/ark",
+        "password": True,
+        "category": "provider",
+    },
+    "BYTEPLUS_API_KEY": {
+        "description": "BytePlus API key for Seed / Dola models (standard + Coding Plan catalogs)",
+        "prompt": "BytePlus API Key",
+        "url": "https://www.byteplus.com/en/product/modelark",
+        "password": True,
+        "category": "provider",
+    },
     "AWS_REGION": {
         "description": "AWS region for Bedrock API calls (e.g. us-east-1, eu-central-1)",
         "prompt": "AWS Region",

hermes_cli/main.py

@@ -1570,6 +1570,8 @@ def select_provider_and_model(args=None):
         _model_flow_stepfun(config, current_model)
     elif selected_provider == "bedrock":
         _model_flow_bedrock(config, current_model)
+    elif selected_provider in ("volcengine", "byteplus"):
+        _model_flow_contract_provider(config, selected_provider, current_model)
     elif selected_provider in (
         "gemini",
         "deepseek",
@@ -1954,7 +1956,7 @@ def _aux_flow_custom_endpoint(task: str, task_cfg: dict) -> None:
     print(f"{display_name}: custom ({short_url})" + (f" · {model}" if model else ""))
 
 
-def _prompt_provider_choice(choices, *, default=0):
+def _prompt_provider_choice(choices, *, default=0, title="Select provider:"):
     """Show provider selection menu with curses arrow-key navigation.
 
     Falls back to a numbered list when curses is unavailable (e.g. piped
@@ -1963,8 +1965,7 @@ def _prompt_provider_choice(choices, *, default=0):
     """
     try:
         from hermes_cli.setup import _curses_prompt_choice
-
-        idx = _curses_prompt_choice("Select provider:", choices, default)
+        idx = _curses_prompt_choice(title, choices, default)
         if idx >= 0:
             print()
             return idx
@@ -1972,7 +1973,7 @@ def _prompt_provider_choice(choices, *, default=0):
         pass
 
     # Fallback: numbered list
-    print("Select provider:")
+    print(title)
     for i, c in enumerate(choices, 1):
         marker = "→" if i - 1 == default else " "
         print(f"  {marker} {i}. {c}")
@@ -2944,6 +2945,10 @@ def _model_flow_named_custom(config, provider_info):
 
 # Curated model lists for direct API-key providers — single source in models.py
 from hermes_cli.models import _PROVIDER_MODELS
+from hermes_cli.volcengine_byteplus import (
+    base_url_for_provider_model,
+    provider_models,
+)
 
 
 def _current_reasoning_effort(config) -> str:
@@ -4033,6 +4038,70 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
         print("No change.")
 
 
+def _model_flow_contract_provider(config, provider_id, current_model=""):
+    """Provider flow for Volcengine / BytePlus contract-backed catalogs."""
+    from hermes_cli.auth import (
+        PROVIDER_REGISTRY,
+        _prompt_model_selection,
+        _save_model_choice,
+        deactivate_provider,
+    )
+    from hermes_cli.config import get_env_value, load_config, save_config, save_env_value
+
+    pconfig = PROVIDER_REGISTRY[provider_id]
+    key_env = pconfig.api_key_env_vars[0] if pconfig.api_key_env_vars else ""
+    existing_key = ""
+    for env_var in pconfig.api_key_env_vars:
+        existing_key = get_env_value(env_var) or os.getenv(env_var, "")
+        if existing_key:
+            break
+
+    if not existing_key:
+        print(f"No {pconfig.name} API key configured.")
+        if key_env:
+            try:
+                import getpass
+
+                new_key = getpass.getpass(f"{key_env} (or Enter to cancel): ").strip()
+            except (KeyboardInterrupt, EOFError):
+                print()
+                return
+            if not new_key:
+                print("Cancelled.")
+                return
+            save_env_value(key_env, new_key)
+            print("API key saved.")
+            print()
+    else:
+        print(f"  {pconfig.name} API key: {existing_key[:8]}... ✓")
+        print()
+
+    model_list = provider_models(provider_id)
+    if not model_list:
+        print(f"No curated model catalog found for {pconfig.name}.")
+        return
+
+    selected = _prompt_model_selection(model_list, current_model=current_model)
+    if not selected:
+        print("No change.")
+        return
+
+    _save_model_choice(selected)
+
+    cfg = load_config()
+    model = cfg.get("model")
+    if not isinstance(model, dict):
+        model = {"default": model} if model else {}
+        cfg["model"] = model
+    model["provider"] = provider_id
+    model["base_url"] = base_url_for_provider_model(provider_id, selected)
+    model.pop("api_mode", None)
+    save_config(cfg)
+    deactivate_provider()
+
+    print(f"Default model set to: {selected} (via {pconfig.name})")
+
+
 def _run_anthropic_oauth_flow(save_env_value):
     """Run the Claude OAuth setup-token flow. Returns True if credentials were saved."""
     from agent.anthropic_adapter import (

hermes_cli/model_normalize.py

@@ -97,6 +97,8 @@ _MATCHING_PREFIX_STRIP_PROVIDERS: frozenset[str] = frozenset({
     "xiaomi",
     "arcee",
     "ollama-cloud",
+    "volcengine",
+    "byteplus",
     "custom",
 })
 
@@ -423,4 +425,3 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
 # ---------------------------------------------------------------------------
 # Batch / convenience helpers
 # ---------------------------------------------------------------------------
-

hermes_cli/models.py

@@ -22,6 +22,12 @@ from hermes_cli import __version__ as _HERMES_VERSION
 # Check (error 1010) don't reject the default ``Python-urllib/*`` signature.
 _HERMES_USER_AGENT = f"hermes-cli/{_HERMES_VERSION}"
 
+from hermes_cli.volcengine_byteplus import (
+    BYTEPLUS_PROVIDER,
+    VOLCENGINE_PROVIDER,
+    provider_models,
+)
+
 COPILOT_BASE_URL = "https://api.githubcopilot.com"
 COPILOT_MODELS_URL = f"{COPILOT_BASE_URL}/models"
 COPILOT_EDITOR_VERSION = "vscode/1.104.1"
@@ -356,6 +362,8 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "us.meta.llama4-maverick-17b-instruct-v1:0",
         "us.meta.llama4-scout-17b-instruct-v1:0",
     ],
+    VOLCENGINE_PROVIDER: provider_models(VOLCENGINE_PROVIDER),
+    BYTEPLUS_PROVIDER: provider_models(BYTEPLUS_PROVIDER),
 }
 
 # Vercel AI Gateway: derive the bare-model-id catalog from the curated
@@ -690,6 +698,8 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway (200+ models, $5 free credit, no markup)"),
     ProviderEntry("anthropic",      "Anthropic",                "Anthropic (Claude models — API key or Claude Code)"),
     ProviderEntry("openai-codex",   "OpenAI Codex",             "OpenAI Codex"),
+    ProviderEntry(VOLCENGINE_PROVIDER, "Volcengine",            "Volcengine (standard + Coding Plan catalogs)"),
+    ProviderEntry(BYTEPLUS_PROVIDER, "BytePlus",                "BytePlus (standard + Coding Plan catalogs)"),
     ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
     ProviderEntry("nvidia",         "NVIDIA NIM",               "NVIDIA NIM (Nemotron models — build.nvidia.com or local NIM)"),
     ProviderEntry("qwen-oauth",     "Qwen OAuth (Portal)",      "Qwen OAuth (reuses local Qwen CLI login)"),
@@ -719,7 +729,6 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
 _PROVIDER_LABELS = {p.slug: p.label for p in CANONICAL_PROVIDERS}
 _PROVIDER_LABELS["custom"] = "Custom endpoint"  # special case: not a named provider
 
-
 _PROVIDER_ALIASES = {
     "glm": "zai",
     "z-ai": "zai",
@@ -782,6 +791,10 @@ _PROVIDER_ALIASES = {
     "nemotron": "nvidia",
     "ollama": "custom",  # bare "ollama" = local; use "ollama-cloud" for cloud
     "ollama_cloud": "ollama-cloud",
+    "volcengine-coding-plan": VOLCENGINE_PROVIDER,
+    "volcengine_coding_plan": VOLCENGINE_PROVIDER,
+    "byteplus-coding-plan": BYTEPLUS_PROVIDER,
+    "byteplus_coding_plan": BYTEPLUS_PROVIDER,
 }
 
 
@@ -1242,7 +1255,6 @@ def list_available_providers() -> list[dict[str, str]]:
     """
     # Derive display order from canonical list + custom
     provider_order = [p.slug for p in CANONICAL_PROVIDERS] + ["custom"]
-
     # Build reverse alias map
     aliases_for: dict[str, list[str]] = {}
     for alias, canonical in _PROVIDER_ALIASES.items():
@@ -1258,7 +1270,7 @@ def list_available_providers() -> list[dict[str, str]]:
             from hermes_cli.auth import get_auth_status, has_usable_secret
             if pid == "custom":
                 custom_base_url = _get_custom_base_url() or ""
-                has_creds = bool(custom_base_url.strip())
+                has_creds = bool(custom_base_url.strip()) and provider_for_base_url(custom_base_url) is None
             elif pid == "openrouter":
                 has_creds = has_usable_secret(os.getenv("OPENROUTER_API_KEY", ""))
             else:
@@ -1324,6 +1336,29 @@ def _get_custom_base_url() -> str:
     return ""
 
 
+def provider_for_base_url(base_url: str) -> Optional[str]:
+    """Return a known built-in provider for a configured base URL, if any.
+
+    Uses the canonical _URL_TO_PROVIDER mapping from model_metadata plus
+    additional entries for providers not in that dict.
+    """
+    normalized = str(base_url or "").strip().rstrip("/")
+    if not normalized or "openrouter.ai" in normalized.lower():
+        return None
+
+    url_lower = normalized.lower()
+
+    # Primary source — shared with context-length resolution
+    from agent.model_metadata import _URL_TO_PROVIDER
+
+    for host, provider_id in _URL_TO_PROVIDER.items():
+        if host in url_lower:
+            canonical = normalize_provider(provider_id)
+            if canonical in _PROVIDER_LABELS and canonical != "custom":
+                return canonical
+    return None
+
+
 def curated_models_for_provider(
     provider: Optional[str],
     *,

hermes_cli/providers.py

@@ -23,6 +23,12 @@ import logging
 from dataclasses import dataclass
 from typing import Any, Dict, List, Optional, Tuple
 
+from hermes_cli.volcengine_byteplus import (
+    BYTEPLUS_PROVIDER,
+    BYTEPLUS_STANDARD_BASE_URL,
+    VOLCENGINE_PROVIDER,
+    VOLCENGINE_STANDARD_BASE_URL,
+)
 from utils import base_url_host_matches, base_url_hostname
 
 logger = logging.getLogger(__name__)
@@ -163,6 +169,16 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         transport="openai_chat",
         base_url_env_var="OLLAMA_BASE_URL",
     ),
+    VOLCENGINE_PROVIDER: HermesOverlay(
+        transport="openai_chat",
+        extra_env_vars=("VOLCENGINE_API_KEY",),
+        base_url_override=VOLCENGINE_STANDARD_BASE_URL,
+    ),
+    BYTEPLUS_PROVIDER: HermesOverlay(
+        transport="openai_chat",
+        extra_env_vars=("BYTEPLUS_API_KEY",),
+        base_url_override=BYTEPLUS_STANDARD_BASE_URL,
+    ),
 }
 
 
@@ -273,6 +289,10 @@ ALIASES: Dict[str, str] = {
     # xiaomi
     "mimo": "xiaomi",
     "xiaomi-mimo": "xiaomi",
+    "volcengine-coding-plan": VOLCENGINE_PROVIDER,
+    "volcengine_coding_plan": VOLCENGINE_PROVIDER,
+    "byteplus-coding-plan": BYTEPLUS_PROVIDER,
+    "byteplus_coding_plan": BYTEPLUS_PROVIDER,
 
     # bedrock
     "aws": "bedrock",
@@ -306,6 +326,8 @@ _LABEL_OVERRIDES: Dict[str, str] = {
     "copilot-acp": "GitHub Copilot ACP",
     "stepfun": "StepFun Step Plan",
     "xiaomi": "Xiaomi MiMo",
+    VOLCENGINE_PROVIDER: "Volcengine",
+    BYTEPLUS_PROVIDER: "BytePlus",
     "local": "Local endpoint",
     "bedrock": "AWS Bedrock",
     "ollama-cloud": "Ollama Cloud",

hermes_cli/runtime_provider.py

@@ -643,7 +643,7 @@ def _resolve_explicit_runtime(
 
         base_url = explicit_base_url
         if not base_url:
-            if provider in ("kimi-coding", "kimi-coding-cn"):
+            if provider in ("kimi-coding", "kimi-coding-cn", "volcengine", "byteplus"):
                 creds = resolve_api_key_provider_credentials(provider)
                 base_url = creds.get("base_url", "").rstrip("/")
             else:

hermes_cli/volcengine_byteplus.py

@@ -0,0 +1,134 @@
+"""Source-of-truth contracts for built-in providers without models.dev catalogs."""
+
+from __future__ import annotations
+
+from typing import Dict, List, Tuple
+
+VOLCENGINE_PROVIDER = "volcengine"
+BYTEPLUS_PROVIDER = "byteplus"
+
+VOLCENGINE_STANDARD_BASE_URL = "https://ark.cn-beijing.volces.com/api/v3"
+VOLCENGINE_CODING_PLAN_BASE_URL = "https://ark.cn-beijing.volces.com/api/coding/v3"
+BYTEPLUS_STANDARD_BASE_URL = "https://ark.ap-southeast.bytepluses.com/api/v3"
+BYTEPLUS_CODING_PLAN_BASE_URL = "https://ark.ap-southeast.bytepluses.com/api/coding/v3"
+
+VOLCENGINE_STANDARD_MODELS: Tuple[str, ...] = (
+    "doubao-seed-2-0-pro-260215",
+    "doubao-seed-2-0-lite-260215",
+    "doubao-seed-2-0-mini-260215",
+    "doubao-seed-2-0-code-preview-260215",
+    "kimi-k2-5-260127",
+    "glm-4-7-251222",
+    "deepseek-v3-2-251201",
+)
+
+VOLCENGINE_CODING_PLAN_MODELS: Tuple[str, ...] = (
+    "doubao-seed-2.0-code",
+    "doubao-seed-2.0-pro",
+    "doubao-seed-2.0-lite",
+    "doubao-seed-code",
+    "minimax-m2.5",
+    "glm-4.7",
+    "deepseek-v3.2",
+    "kimi-k2.5",
+)
+
+BYTEPLUS_STANDARD_MODELS: Tuple[str, ...] = (
+    "seed-2-0-pro-260328",
+    "seed-2-0-lite-260228",
+    "seed-2-0-mini-260215",
+    "kimi-k2-5-260127",
+    "glm-4-7-251222",
+)
+
+BYTEPLUS_CODING_PLAN_MODELS: Tuple[str, ...] = (
+    "dola-seed-2.0-pro",
+    "dola-seed-2.0-lite",
+    "bytedance-seed-code",
+    "glm-4.7",
+    "kimi-k2.5",
+    "gpt-oss-120b",
+)
+
+VOLCENGINE_STANDARD_MODEL_REFS: Tuple[str, ...] = tuple(
+    f"{VOLCENGINE_PROVIDER}/{model_id}" for model_id in VOLCENGINE_STANDARD_MODELS
+)
+VOLCENGINE_CODING_PLAN_MODEL_REFS: Tuple[str, ...] = tuple(
+    f"{VOLCENGINE_PROVIDER}-coding-plan/{model_id}" for model_id in VOLCENGINE_CODING_PLAN_MODELS
+)
+BYTEPLUS_STANDARD_MODEL_REFS: Tuple[str, ...] = tuple(
+    f"{BYTEPLUS_PROVIDER}/{model_id}" for model_id in BYTEPLUS_STANDARD_MODELS
+)
+BYTEPLUS_CODING_PLAN_MODEL_REFS: Tuple[str, ...] = tuple(
+    f"{BYTEPLUS_PROVIDER}-coding-plan/{model_id}" for model_id in BYTEPLUS_CODING_PLAN_MODELS
+)
+
+PROVIDER_MODEL_CATALOGS: Dict[str, Tuple[str, ...]] = {
+    VOLCENGINE_PROVIDER: VOLCENGINE_STANDARD_MODEL_REFS + VOLCENGINE_CODING_PLAN_MODEL_REFS,
+    BYTEPLUS_PROVIDER: BYTEPLUS_STANDARD_MODEL_REFS + BYTEPLUS_CODING_PLAN_MODEL_REFS,
+}
+
+MODEL_CONTEXT_WINDOWS: Dict[str, int] = {
+    "doubao-seed-2-0-pro-260215": 256000,
+    "doubao-seed-2-0-lite-260215": 256000,
+    "doubao-seed-2-0-mini-260215": 256000,
+    "doubao-seed-2-0-code-preview-260215": 256000,
+    "kimi-k2-5-260127": 256000,
+    "glm-4-7-251222": 200000,
+    "deepseek-v3-2-251201": 128000,
+    "doubao-seed-2.0-code": 256000,
+    "doubao-seed-2.0-pro": 256000,
+    "doubao-seed-2.0-lite": 256000,
+    "doubao-seed-code": 256000,
+    "minimax-m2.5": 200000,
+    "glm-4.7": 200000,
+    "deepseek-v3.2": 128000,
+    "kimi-k2.5": 256000,
+    "seed-2-0-pro-260328": 256000,
+    "seed-2-0-lite-260228": 256000,
+    "seed-2-0-mini-260215": 256000,
+}
+
+
+def provider_models(provider_id: str) -> List[str]:
+    """Return the full user-facing model catalog for a provider."""
+    return list(PROVIDER_MODEL_CATALOGS.get(provider_id, ()))
+
+
+def _bare_model_name(model_name: str) -> str:
+    value = (model_name or "").strip()
+    if not value:
+        return ""
+    if "/" in value:
+        return value.split("/", 1)[1].strip()
+    return value
+
+
+def is_coding_plan_model(provider_id: str, model_name: str) -> bool:
+    """Return True when a model belongs to the coding-plan catalog."""
+    raw = (model_name or "").strip()
+    bare = _bare_model_name(raw)
+    if provider_id == VOLCENGINE_PROVIDER:
+        return raw in VOLCENGINE_CODING_PLAN_MODEL_REFS or bare in VOLCENGINE_CODING_PLAN_MODELS
+    if provider_id == BYTEPLUS_PROVIDER:
+        return raw in BYTEPLUS_CODING_PLAN_MODEL_REFS or bare in BYTEPLUS_CODING_PLAN_MODELS
+    return False
+
+
+def base_url_for_provider_model(provider_id: str, model_name: str) -> str:
+    """Resolve the source-of-truth base URL for a provider+model pair."""
+    if provider_id == VOLCENGINE_PROVIDER:
+        if is_coding_plan_model(provider_id, model_name):
+            return VOLCENGINE_CODING_PLAN_BASE_URL
+        return VOLCENGINE_STANDARD_BASE_URL
+    if provider_id == BYTEPLUS_PROVIDER:
+        if is_coding_plan_model(provider_id, model_name):
+            return BYTEPLUS_CODING_PLAN_BASE_URL
+        return BYTEPLUS_STANDARD_BASE_URL
+    return ""
+
+
+def model_context_window(model_name: str) -> int | None:
+    """Return a known context window for a model, if specified by the contract."""
+    bare = _bare_model_name(model_name)
+    return MODEL_CONTEXT_WINDOWS.get(bare)

hermes_state.py

@@ -256,136 +256,109 @@ class SessionDB:
                 self._conn.close()
                 self._conn = None
 
-    @staticmethod
-    def _parse_schema_columns(schema_sql: str) -> Dict[str, Dict[str, str]]:
-        """Extract expected columns per table from SCHEMA_SQL.
-
-        Uses an in-memory SQLite database to parse the SQL — SQLite itself
-        handles all syntax (DEFAULT expressions with commas, inline
-        REFERENCES, CHECK constraints, etc.) so there are zero regex
-        edge cases.  The in-memory DB is opened, the schema DDL is
-        executed, and PRAGMA table_info extracts the column metadata.
-
-        Adding a column to SCHEMA_SQL is all that's needed; the
-        reconciliation loop picks it up automatically.
-        """
-        ref = sqlite3.connect(":memory:")
-        try:
-            ref.executescript(schema_sql)
-            table_columns: Dict[str, Dict[str, str]] = {}
-            for (tbl,) in ref.execute(
-                "SELECT name FROM sqlite_master "
-                "WHERE type='table' AND name NOT LIKE 'sqlite_%'"
-            ).fetchall():
-                cols: Dict[str, str] = {}
-                for row in ref.execute(
-                    f'PRAGMA table_info("{tbl}")'
-                ).fetchall():
-                    # row: (cid, name, type, notnull, dflt_value, pk)
-                    col_name = row[1]
-                    col_type = row[2] or ""
-                    notnull = row[3]
-                    default = row[4]
-                    pk = row[5]
-                    # Reconstruct the type expression for ALTER TABLE ADD COLUMN
-                    parts = [col_type] if col_type else []
-                    if notnull and not pk:
-                        parts.append("NOT NULL")
-                    if default is not None:
-                        parts.append(f"DEFAULT {default}")
-                    cols[col_name] = " ".join(parts)
-                table_columns[tbl] = cols
-            return table_columns
-        finally:
-            ref.close()
-
-    def _reconcile_columns(self, cursor: sqlite3.Cursor) -> None:
-        """Ensure live tables have every column declared in SCHEMA_SQL.
-
-        Follows the Beets/sqlite-utils pattern: the CREATE TABLE definition
-        in SCHEMA_SQL is the single source of truth for the desired schema.
-        On every startup this method diffs the live columns (via PRAGMA
-        table_info) against the declared columns, and ADDs any that are
-        missing.
-
-        This makes column additions a declarative operation — just add
-        the column to SCHEMA_SQL and it appears on the next startup.
-        Version-gated migration blocks are no longer needed for ADD COLUMN.
-        """
-        expected = self._parse_schema_columns(SCHEMA_SQL)
-        for table_name, declared_cols in expected.items():
-            # Get current columns from the live table
-            try:
-                rows = cursor.execute(
-                    f'PRAGMA table_info("{table_name}")'
-                ).fetchall()
-            except sqlite3.OperationalError:
-                continue  # Table doesn't exist yet (shouldn't happen after executescript)
-            live_cols = set()
-            for row in rows:
-                # PRAGMA table_info returns (cid, name, type, notnull, dflt_value, pk)
-                name = row[1] if isinstance(row, (tuple, list)) else row["name"]
-                live_cols.add(name)
-
-            for col_name, col_type in declared_cols.items():
-                if col_name not in live_cols:
-                    safe_name = col_name.replace('"', '""')
-                    try:
-                        cursor.execute(
-                            f'ALTER TABLE "{table_name}" ADD COLUMN "{safe_name}" {col_type}'
-                        )
-                    except sqlite3.OperationalError as exc:
-                        # Expected: "duplicate column name" from a race or
-                        # re-run.  Unexpected: "Cannot add a NOT NULL column
-                        # with default value NULL" from a schema mistake.
-                        # Log at DEBUG so it's visible in agent.log.
-                        logger.debug(
-                            "reconcile %s.%s: %s", table_name, col_name, exc,
-                        )
-
     def _init_schema(self):
-        """Create tables and FTS if they don't exist, reconcile columns.
-
-        Schema management follows the declarative reconciliation pattern
-        (Beets, sqlite-utils): SCHEMA_SQL is the single source of truth.
-        On existing databases, _reconcile_columns() diffs live columns
-        against SCHEMA_SQL and ADDs any missing ones.  This eliminates
-        the version-gated migration chain for column additions, making
-        it impossible for reordered or inserted migrations to skip columns.
-
-        The schema_version table is retained for future data migrations
-        (transforming existing rows) which cannot be handled declaratively.
-        """
+        """Create tables and FTS if they don't exist, run migrations."""
         cursor = self._conn.cursor()
 
         cursor.executescript(SCHEMA_SQL)
 
-        # ── Declarative column reconciliation ──────────────────────────
-        # Diff live tables against SCHEMA_SQL and ADD any missing columns.
-        # This is idempotent and self-healing: even if a version-gated
-        # migration was skipped (e.g. due to version renumbering), the
-        # column gets created here.
-        self._reconcile_columns(cursor)
-
-        # ── Schema version bookkeeping ─────────────────────────────────
-        # Bump to current so future data migrations (if any) can gate on
-        # version.  No version-gated column additions remain.
+        # Check schema version and run migrations
         cursor.execute("SELECT version FROM schema_version LIMIT 1")
         row = cursor.fetchone()
         if row is None:
-            cursor.execute(
-                "INSERT INTO schema_version (version) VALUES (?)",
-                (SCHEMA_VERSION,),
-            )
+            cursor.execute("INSERT INTO schema_version (version) VALUES (?)", (SCHEMA_VERSION,))
         else:
             current_version = row["version"] if isinstance(row, sqlite3.Row) else row[0]
-            if current_version < SCHEMA_VERSION:
-                cursor.execute(
-                    "UPDATE schema_version SET version = ?",
-                    (SCHEMA_VERSION,),
-                )
+            if current_version < 2:
+                # v2: add finish_reason column to messages
+                try:
+                    cursor.execute("ALTER TABLE messages ADD COLUMN finish_reason TEXT")
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 2")
+            if current_version < 3:
+                # v3: add title column to sessions
+                try:
+                    cursor.execute("ALTER TABLE sessions ADD COLUMN title TEXT")
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 3")
+            if current_version < 4:
+                # v4: add unique index on title (NULLs allowed, only non-NULL must be unique)
+                try:
+                    cursor.execute(
+                        "CREATE UNIQUE INDEX IF NOT EXISTS idx_sessions_title_unique "
+                        "ON sessions(title) WHERE title IS NOT NULL"
+                    )
+                except sqlite3.OperationalError:
+                    pass  # Index already exists
+                cursor.execute("UPDATE schema_version SET version = 4")
+            if current_version < 5:
+                new_columns = [
+                    ("cache_read_tokens", "INTEGER DEFAULT 0"),
+                    ("cache_write_tokens", "INTEGER DEFAULT 0"),
+                    ("reasoning_tokens", "INTEGER DEFAULT 0"),
+                    ("billing_provider", "TEXT"),
+                    ("billing_base_url", "TEXT"),
+                    ("billing_mode", "TEXT"),
+                    ("estimated_cost_usd", "REAL"),
+                    ("actual_cost_usd", "REAL"),
+                    ("cost_status", "TEXT"),
+                    ("cost_source", "TEXT"),
+                    ("pricing_version", "TEXT"),
+                ]
+                for name, column_type in new_columns:
+                    try:
+                        # name and column_type come from the hardcoded tuple above,
+                        # not user input. Double-quote identifier escaping is applied
+                        # as defense-in-depth; SQLite DDL cannot be parameterized.
+                        safe_name = name.replace('"', '""')
+                        cursor.execute(f'ALTER TABLE sessions ADD COLUMN "{safe_name}" {column_type}')
+                    except sqlite3.OperationalError:
+                        pass
+                cursor.execute("UPDATE schema_version SET version = 5")
+            if current_version < 6:
+                # v6: add reasoning columns to messages table — preserves assistant
+                # reasoning text and structured reasoning_details across gateway
+                # session turns.  Without these, reasoning chains are lost on
+                # session reload, breaking multi-turn reasoning continuity for
+                # providers that replay reasoning (OpenRouter, OpenAI, Nous).
+                for col_name, col_type in [
+                    ("reasoning", "TEXT"),
+                    ("reasoning_details", "TEXT"),
+                    ("codex_reasoning_items", "TEXT"),
+                ]:
+                    try:
+                        safe = col_name.replace('"', '""')
+                        cursor.execute(
+                            f'ALTER TABLE messages ADD COLUMN "{safe}" {col_type}'
+                        )
+                    except sqlite3.OperationalError:
+                        pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 6")
+            if current_version < 7:
+                # v7: preserve provider-native reasoning_content separately from
+                # normalized reasoning text. Kimi/Moonshot replay can require
+                # this field on assistant tool-call messages when thinking is on.
+                try:
+                    cursor.execute('ALTER TABLE messages ADD COLUMN "reasoning_content" TEXT')
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 7")
+            if current_version < 8:
+                # v8: add api_call_count column to sessions — tracks the number
+                # of individual LLM API calls made within a session (as opposed
+                # to the session count itself).
+                try:
+                    cursor.execute(
+                        'ALTER TABLE sessions ADD COLUMN "api_call_count" INTEGER DEFAULT 0'
+                    )
+                except sqlite3.OperationalError:
+                    pass  # Column already exists
+                cursor.execute("UPDATE schema_version SET version = 8")
 
-        # Unique title index — always ensure it exists
+        # Unique title index — always ensure it exists (safe to run after migrations
+        # since the title column is guaranteed to exist at this point)
         try:
             cursor.execute(
                 "CREATE UNIQUE INDEX IF NOT EXISTS idx_sessions_title_unique "

scripts/release.py

@@ -105,6 +105,7 @@ AUTHOR_MAP = {
     "134848055+UNLINEARITY@users.noreply.github.com": "UNLINEARITY",
     "ben.burtenshaw@gmail.com": "burtenshaw",
     "roopaknijhara@gmail.com": "rnijhara",
+    "Maaannnn@users.noreply.github.com": "Maaannnn",
     # contributors (manual mapping from git names)
     "ahmedsherif95@gmail.com": "asheriif",
     "liujinkun@bytedance.com": "liujinkun2025",

tests/agent/test_auxiliary_client.py

@@ -782,6 +782,45 @@ def test_resolve_api_key_provider_skips_unconfigured_anthropic(monkeypatch):
 # ---------------------------------------------------------------------------
 
 
+class TestModelDefaultElimination:
+    """_resolve_api_key_provider must skip providers without known aux models."""
+
+    def test_unknown_provider_skipped(self, monkeypatch):
+        """Providers not in _API_KEY_PROVIDER_AUX_MODELS are skipped, not sent model='default'."""
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+
+        # Verify our known providers have entries
+        assert "gemini" in _API_KEY_PROVIDER_AUX_MODELS
+        assert "kimi-coding" in _API_KEY_PROVIDER_AUX_MODELS
+
+        # A random provider_id not in the dict should return None
+        assert _API_KEY_PROVIDER_AUX_MODELS.get("totally-unknown-provider") is None
+
+    def test_known_provider_gets_real_model(self):
+        """Known providers get a real model name, not 'default'."""
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+
+        for provider_id, model in _API_KEY_PROVIDER_AUX_MODELS.items():
+            assert model != "default", f"{provider_id} should not map to 'default'"
+            assert isinstance(model, str) and model.strip(), \
+                f"{provider_id} should have a non-empty model string"
+
+    def test_volcengine_byteplus_use_main_model_first(self):
+        """Volcengine/BytePlus use main-model-first — no entry in _API_KEY_PROVIDER_AUX_MODELS."""
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+
+        assert "volcengine" not in _API_KEY_PROVIDER_AUX_MODELS
+        assert "byteplus" not in _API_KEY_PROVIDER_AUX_MODELS
+
+
+class TestContractProviderAliases:
+    def test_coding_plan_aliases_normalize_to_canonical_provider(self):
+        from agent.auxiliary_client import _normalize_aux_provider
+
+        assert _normalize_aux_provider("volcengine-coding-plan") == "volcengine"
+        assert _normalize_aux_provider("byteplus-coding-plan") == "byteplus"
+
+
 # ---------------------------------------------------------------------------
 # _try_payment_fallback reason parameter (#7512 bug 3)
 # ---------------------------------------------------------------------------

tests/agent/test_model_metadata.py

@@ -222,6 +222,22 @@ class TestGetModelContextLength:
         mock_fetch.return_value = {}
         assert get_model_context_length("unknown/never-heard-of-this") == CONTEXT_PROBE_TIERS[0]
 
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_volcengine_contract_model_uses_contract_context_length(self, mock_fetch):
+        mock_fetch.return_value = {}
+        assert get_model_context_length(
+            "volcengine/doubao-seed-2-0-pro-260215",
+            provider="volcengine",
+        ) == 256000
+
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_byteplus_contract_model_infers_provider_from_url(self, mock_fetch):
+        mock_fetch.return_value = {}
+        assert get_model_context_length(
+            "byteplus-coding-plan/kimi-k2.5",
+            base_url="https://ark.ap-southeast.bytepluses.com/api/coding/v3",
+        ) == 256000
+
     @patch("agent.model_metadata.fetch_model_metadata")
     def test_partial_match_in_defaults(self, mock_fetch):
         mock_fetch.return_value = {}

tests/hermes_cli/test_api_key_providers.py

@@ -42,6 +42,8 @@ class TestProviderRegistry:
         ("minimax-cn", "MiniMax (China)", "api_key"),
         ("ai-gateway", "Vercel AI Gateway", "api_key"),
         ("kilocode", "Kilo Code", "api_key"),
+        ("volcengine", "Volcengine", "api_key"),
+        ("byteplus", "BytePlus", "api_key"),
     ])
     def test_provider_registered(self, provider_id, name, auth_type):
         assert provider_id in PROVIDER_REGISTRY
@@ -111,6 +113,16 @@ class TestProviderRegistry:
         assert pconfig.api_key_env_vars == ("HF_TOKEN",)
         assert pconfig.base_url_env_var == "HF_BASE_URL"
 
+    def test_volcengine_env_vars(self):
+        pconfig = PROVIDER_REGISTRY["volcengine"]
+        assert pconfig.api_key_env_vars == ("VOLCENGINE_API_KEY",)
+        assert pconfig.base_url_env_var == ""
+
+    def test_byteplus_env_vars(self):
+        pconfig = PROVIDER_REGISTRY["byteplus"]
+        assert pconfig.api_key_env_vars == ("BYTEPLUS_API_KEY",)
+        assert pconfig.base_url_env_var == ""
+
     def test_base_urls(self):
         assert PROVIDER_REGISTRY["copilot"].inference_base_url == "https://api.githubcopilot.com"
         assert PROVIDER_REGISTRY["copilot-acp"].inference_base_url == "acp://copilot"
@@ -122,6 +134,8 @@ class TestProviderRegistry:
         assert PROVIDER_REGISTRY["ai-gateway"].inference_base_url == "https://ai-gateway.vercel.sh/v1"
         assert PROVIDER_REGISTRY["kilocode"].inference_base_url == "https://api.kilo.ai/api/gateway"
         assert PROVIDER_REGISTRY["huggingface"].inference_base_url == "https://router.huggingface.co/v1"
+        assert PROVIDER_REGISTRY["volcengine"].inference_base_url == "https://ark.cn-beijing.volces.com/api/v3"
+        assert PROVIDER_REGISTRY["byteplus"].inference_base_url == "https://ark.ap-southeast.bytepluses.com/api/v3"
 
     def test_oauth_providers_unchanged(self):
         """Ensure we didn't break the existing OAuth providers."""
@@ -147,6 +161,7 @@ PROVIDER_ENV_VARS = (
     "NOUS_API_KEY", "GITHUB_TOKEN", "GH_TOKEN",
     "OPENAI_BASE_URL", "HERMES_COPILOT_ACP_COMMAND", "COPILOT_CLI_PATH",
     "HERMES_COPILOT_ACP_ARGS", "COPILOT_ACP_BASE_URL",
+    "VOLCENGINE_API_KEY", "BYTEPLUS_API_KEY",
 )
 
 
@@ -232,6 +247,14 @@ class TestResolveProvider:
         assert resolve_provider("github-copilot-acp") == "copilot-acp"
         assert resolve_provider("copilot-acp-agent") == "copilot-acp"
 
+    def test_alias_volcengine_coding_plan(self):
+        assert resolve_provider("volcengine-coding-plan") == "volcengine"
+        assert resolve_provider("volcengine_coding_plan") == "volcengine"
+
+    def test_alias_byteplus_coding_plan(self):
+        assert resolve_provider("byteplus-coding-plan") == "byteplus"
+        assert resolve_provider("byteplus_coding_plan") == "byteplus"
+
     def test_explicit_huggingface(self):
         assert resolve_provider("huggingface") == "huggingface"
 
@@ -339,6 +362,23 @@ class TestApiKeyProviderStatus:
         assert status["configured"] is True
         assert status["base_url"] == STEPFUN_STEP_PLAN_CN_BASE_URL
 
+    def test_volcengine_status_uses_coding_plan_base_url(self, monkeypatch):
+        monkeypatch.setenv("VOLCENGINE_API_KEY", "volc-test-key")
+        monkeypatch.setattr(
+            "hermes_cli.auth.read_raw_config",
+            lambda: {
+                "model": {
+                    "provider": "volcengine",
+                    "default": "volcengine-coding-plan/doubao-seed-2.0-code",
+                }
+            },
+        )
+
+        status = get_api_key_provider_status("volcengine")
+
+        assert status["configured"] is True
+        assert status["base_url"] == "https://ark.cn-beijing.volces.com/api/coding/v3"
+
     def test_copilot_status_uses_gh_cli_token(self, monkeypatch):
         monkeypatch.setattr("hermes_cli.copilot_auth._try_gh_cli_token", lambda: "gho_gh_cli_token")
         status = get_api_key_provider_status("copilot")
@@ -394,6 +434,25 @@ class TestResolveApiKeyProviderCredentials:
         assert creds["base_url"] == "https://api.z.ai/api/paas/v4"
         assert creds["source"] == "GLM_API_KEY"
 
+    def test_resolve_byteplus_with_coding_plan_model_uses_coding_base_url(self, monkeypatch):
+        monkeypatch.setenv("BYTEPLUS_API_KEY", "byteplus-secret-key")
+        monkeypatch.setattr(
+            "hermes_cli.auth.read_raw_config",
+            lambda: {
+                "model": {
+                    "provider": "byteplus",
+                    "default": "byteplus-coding-plan/dola-seed-2.0-pro",
+                }
+            },
+        )
+
+        creds = resolve_api_key_provider_credentials("byteplus")
+
+        assert creds["provider"] == "byteplus"
+        assert creds["api_key"] == "byteplus-secret-key"
+        assert creds["base_url"] == "https://ark.ap-southeast.bytepluses.com/api/coding/v3"
+        assert creds["source"] == "BYTEPLUS_API_KEY"
+
     def test_resolve_copilot_with_github_token(self, monkeypatch):
         monkeypatch.setenv("GITHUB_TOKEN", "gh-env-secret")
         creds = resolve_api_key_provider_credentials("copilot")

tests/hermes_cli/test_model_normalize.py

@@ -179,6 +179,19 @@ class TestIssue6211NativeProviderPrefixNormalization:
         assert normalize_model_for_provider(model, target_provider) == expected
 
 
+class TestContractProviderPrefixNormalization:
+    @pytest.mark.parametrize("model,target_provider,expected", [
+        ("volcengine/doubao-seed-2-0-pro-260215", "volcengine", "doubao-seed-2-0-pro-260215"),
+        ("volcengine-coding-plan/doubao-seed-2.0-code", "volcengine", "doubao-seed-2.0-code"),
+        ("byteplus/seed-2-0-pro-260328", "byteplus", "seed-2-0-pro-260328"),
+        ("byteplus-coding-plan/dola-seed-2.0-pro", "byteplus", "dola-seed-2.0-pro"),
+    ])
+    def test_contract_provider_prefixes_strip_to_native_model(
+        self, model, target_provider, expected
+    ):
+        assert normalize_model_for_provider(model, target_provider) == expected
+
+
 # ── detect_vendor ──────────────────────────────────────────────────────
 
 class TestDetectVendor:

tests/hermes_cli/test_model_provider_persistence.py

@@ -102,6 +102,31 @@ class TestProviderPersistsAfterModelSave:
         )
         assert model.get("default") == "kimi-k2.5"
 
+    def test_volcengine_contract_provider_persists_coding_plan_model(self, config_home, monkeypatch):
+        """Volcengine should persist a prefixed coding-plan model and matching base URL."""
+        monkeypatch.setenv("VOLCENGINE_API_KEY", "volc-test-key")
+
+        from hermes_cli.main import _model_flow_contract_provider
+        from hermes_cli.config import load_config
+
+        with patch(
+            "hermes_cli.auth._prompt_model_selection",
+            return_value="volcengine-coding-plan/doubao-seed-2.0-code",
+        ), patch(
+            "hermes_cli.auth.deactivate_provider",
+        ):
+            _model_flow_contract_provider(load_config(), "volcengine", "old-model")
+
+        import yaml
+
+        config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
+        model = config.get("model")
+        assert isinstance(model, dict), f"model should be dict, got {type(model)}"
+        assert model.get("provider") == "volcengine"
+        assert model.get("default") == "volcengine-coding-plan/doubao-seed-2.0-code"
+        assert model.get("base_url") == "https://ark.cn-beijing.volces.com/api/coding/v3"
+        assert "api_mode" not in model
+
     def test_copilot_provider_saved_when_selected(self, config_home):
         """_model_flow_copilot should persist provider/base_url/model together."""
         from hermes_cli.main import _model_flow_copilot

tests/hermes_cli/test_models.py

@@ -6,6 +6,7 @@ from hermes_cli.models import (
     OPENROUTER_MODELS, fetch_openrouter_models, model_ids, detect_provider_for_model,
     is_nous_free_tier, partition_nous_models_by_tier,
     check_nous_free_tier, _FREE_TIER_CACHE_TTL,
+    list_available_providers, provider_for_base_url,
 )
 import hermes_cli.models as _models_mod
 
@@ -291,6 +292,41 @@ class TestDetectProviderForModel:
         assert result is not None
         assert result[0] not in ("nous",)  # nous has claude models but shouldn't be suggested
 
+    def test_volcengine_coding_plan_model_detected(self):
+        result = detect_provider_for_model(
+            "volcengine-coding-plan/doubao-seed-2.0-code",
+            "openrouter",
+        )
+        assert result == ("volcengine", "volcengine-coding-plan/doubao-seed-2.0-code")
+
+    def test_byteplus_standard_model_detected(self):
+        result = detect_provider_for_model(
+            "byteplus/seed-2-0-pro-260328",
+            "openrouter",
+        )
+        assert result == ("byteplus", "byteplus/seed-2-0-pro-260328")
+
+
+class TestConfiguredBaseUrlProviderDetection:
+    def test_provider_for_base_url_detects_volcengine(self):
+        assert provider_for_base_url("https://ark.cn-beijing.volces.com/api/v3") == "volcengine"
+
+    def test_provider_for_base_url_detects_byteplus_coding(self):
+        assert provider_for_base_url("https://ark.ap-southeast.bytepluses.com/api/coding/v3") == "byteplus"
+
+    def test_known_builtin_endpoint_is_not_listed_as_custom(self, monkeypatch):
+        monkeypatch.setattr("hermes_cli.models._get_custom_base_url", lambda: "https://ark.cn-beijing.volces.com/api/v3")
+        monkeypatch.setattr(
+            "hermes_cli.auth.get_auth_status",
+            lambda pid: {"configured": pid == "volcengine", "logged_in": pid == "volcengine"},
+        )
+        monkeypatch.setattr("hermes_cli.auth.has_usable_secret", lambda value: False)
+
+        providers = {p["id"]: p for p in list_available_providers()}
+
+        assert providers["volcengine"]["authenticated"] is True
+        assert providers["custom"]["authenticated"] is False
+
 
 class TestIsNousFreeTier:
     """Tests for is_nous_free_tier — account tier detection."""

tests/test_hermes_state.py

@@ -1254,144 +1254,6 @@ class TestSchemaInit:
 
         migrated_db.close()
 
-    def test_reconciliation_adds_missing_columns(self, tmp_path):
-        """Columns present in SCHEMA_SQL but missing from the live table
-        are added by _reconcile_columns regardless of schema_version.
-
-        Regression test: commit a7d78d3b inserted a new v7 migration
-        (reasoning_content) and renumbered the old v7 (api_call_count)
-        to v8.  Users already at the old v7 had schema_version >= 7,
-        so the new v7 block was skipped and reasoning_content was never
-        created — causing 'no such column' on /continue.
-        """
-        import sqlite3
-
-        db_path = tmp_path / "gap_test.db"
-        conn = sqlite3.connect(str(db_path))
-        # Simulate the old v7 state: api_call_count exists, reasoning_content does NOT
-        conn.executescript("""
-            CREATE TABLE schema_version (version INTEGER NOT NULL);
-            INSERT INTO schema_version (version) VALUES (7);
-
-            CREATE TABLE sessions (
-                id TEXT PRIMARY KEY,
-                source TEXT NOT NULL,
-                user_id TEXT,
-                model TEXT,
-                model_config TEXT,
-                system_prompt TEXT,
-                parent_session_id TEXT,
-                started_at REAL NOT NULL,
-                ended_at REAL,
-                end_reason TEXT,
-                message_count INTEGER DEFAULT 0,
-                tool_call_count INTEGER DEFAULT 0,
-                input_tokens INTEGER DEFAULT 0,
-                output_tokens INTEGER DEFAULT 0,
-                cache_read_tokens INTEGER DEFAULT 0,
-                cache_write_tokens INTEGER DEFAULT 0,
-                reasoning_tokens INTEGER DEFAULT 0,
-                billing_provider TEXT,
-                billing_base_url TEXT,
-                billing_mode TEXT,
-                estimated_cost_usd REAL,
-                actual_cost_usd REAL,
-                cost_status TEXT,
-                cost_source TEXT,
-                pricing_version TEXT,
-                title TEXT,
-                api_call_count INTEGER DEFAULT 0
-            );
-
-            CREATE TABLE messages (
-                id INTEGER PRIMARY KEY AUTOINCREMENT,
-                session_id TEXT NOT NULL,
-                role TEXT NOT NULL,
-                content TEXT,
-                tool_call_id TEXT,
-                tool_calls TEXT,
-                tool_name TEXT,
-                timestamp REAL NOT NULL,
-                token_count INTEGER,
-                finish_reason TEXT,
-                reasoning TEXT,
-                reasoning_details TEXT,
-                codex_reasoning_items TEXT
-            );
-        """)
-        conn.execute(
-            "INSERT INTO sessions (id, source, started_at) VALUES (?, ?, ?)",
-            ("s1", "cli", 1000.0),
-        )
-        conn.execute(
-            "INSERT INTO messages (session_id, role, content, timestamp) "
-            "VALUES (?, ?, ?, ?)",
-            ("s1", "assistant", "hello", 1001.0),
-        )
-        conn.commit()
-        # Verify reasoning_content is absent
-        cols = {r[1] for r in conn.execute("PRAGMA table_info(messages)").fetchall()}
-        assert "reasoning_content" not in cols
-        conn.close()
-
-        # Open with SessionDB — reconciliation should add the missing column
-        migrated_db = SessionDB(db_path=db_path)
-
-        msg_cols = {
-            r[1]
-            for r in migrated_db._conn.execute("PRAGMA table_info(messages)").fetchall()
-        }
-        assert "reasoning_content" in msg_cols
-
-        # The query that used to crash must now work
-        cursor = migrated_db._conn.execute(
-            "SELECT role, content, reasoning, reasoning_content, "
-            "reasoning_details, codex_reasoning_items "
-            "FROM messages WHERE session_id = ?",
-            ("s1",),
-        )
-        row = cursor.fetchone()
-        assert row is not None
-        assert row[0] == "assistant"
-        assert row[3] is None  # reasoning_content NULL for old rows
-
-        migrated_db.close()
-
-    def test_reconciliation_is_idempotent(self, tmp_path):
-        """Opening the same database twice doesn't error or duplicate columns."""
-        db_path = tmp_path / "idempotent.db"
-        db1 = SessionDB(db_path=db_path)
-        cols1 = {r[1] for r in db1._conn.execute("PRAGMA table_info(messages)").fetchall()}
-        db1.close()
-
-        db2 = SessionDB(db_path=db_path)
-        cols2 = {r[1] for r in db2._conn.execute("PRAGMA table_info(messages)").fetchall()}
-        db2.close()
-
-        assert cols1 == cols2
-
-    def test_schema_sql_is_source_of_truth(self, db):
-        """Every column in SCHEMA_SQL exists in the live database.
-
-        This is the architectural invariant: SCHEMA_SQL declares the
-        desired schema, _reconcile_columns ensures it matches reality.
-        """
-        from hermes_state import SCHEMA_SQL
-
-        expected = SessionDB._parse_schema_columns(SCHEMA_SQL)
-        for table_name, declared_cols in expected.items():
-            live_cols = {
-                r[1]
-                for r in db._conn.execute(
-                    f'PRAGMA table_info("{table_name}")'
-                ).fetchall()
-            }
-            for col_name in declared_cols:
-                assert col_name in live_cols, (
-                    f"Column {col_name} declared in SCHEMA_SQL for {table_name} "
-                    f"but missing from live DB. Live columns: {live_cols}"
-                )
-
 
 class TestTitleUniqueness:
     """Tests for unique title enforcement and title-based lookups."""

ui-tui/src/__tests__/subagentTree.test.ts

@@ -1,410 +0,0 @@
-import { describe, expect, it } from 'vitest'
-
-import {
-  buildSubagentTree,
-  descendantIds,
-  flattenTree,
-  fmtCost,
-  fmtDuration,
-  fmtTokens,
-  formatSummary,
-  hotnessBucket,
-  peakHotness,
-  sparkline,
-  topLevelSubagents,
-  treeTotals,
-  widthByDepth
-} from '../lib/subagentTree.js'
-import type { SubagentProgress } from '../types.js'
-
-const makeItem = (overrides: Partial<SubagentProgress> & Pick<SubagentProgress, 'id' | 'index'>): SubagentProgress => ({
-  depth: 0,
-  goal: overrides.id,
-  notes: [],
-  parentId: null,
-  status: 'running',
-  taskCount: 1,
-  thinking: [],
-  toolCount: 0,
-  tools: [],
-  ...overrides
-})
-
-describe('aggregate: tokens, cost, files, hotness', () => {
-  it('sums tokens and cost across subtree', () => {
-    const items = [
-      makeItem({ costUsd: 0.01, id: 'p', index: 0, inputTokens: 1000, outputTokens: 500 }),
-      makeItem({
-        costUsd: 0.005,
-        depth: 1,
-        id: 'c1',
-        index: 0,
-        inputTokens: 500,
-        outputTokens: 100,
-        parentId: 'p'
-      }),
-      makeItem({
-        costUsd: 0.008,
-        depth: 1,
-        id: 'c2',
-        index: 1,
-        inputTokens: 300,
-        outputTokens: 200,
-        parentId: 'p'
-      })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.aggregate).toMatchObject({
-      costUsd: 0.023,
-      inputTokens: 1800,
-      outputTokens: 800
-    })
-  })
-
-  it('counts files read + written across subtree', () => {
-    const items = [
-      makeItem({ filesRead: ['a.ts', 'b.ts'], id: 'p', index: 0 }),
-      makeItem({ depth: 1, filesWritten: ['c.ts'], id: 'c', index: 0, parentId: 'p' })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.aggregate.filesTouched).toBe(3)
-  })
-
-  it('hotness = totalTools / totalDuration', () => {
-    const items = [
-      makeItem({
-        durationSeconds: 10,
-        id: 'p',
-        index: 0,
-        status: 'completed',
-        toolCount: 20
-      })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.aggregate.hotness).toBeCloseTo(2)
-  })
-
-  it('hotness is zero when duration is zero', () => {
-    const items = [makeItem({ id: 'p', index: 0, toolCount: 10 })]
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.aggregate.hotness).toBe(0)
-  })
-})
-
-describe('hotnessBucket + peakHotness', () => {
-  it('peakHotness walks subtree', () => {
-    const items = [
-      makeItem({ durationSeconds: 100, id: 'p', index: 0, status: 'completed', toolCount: 1 }),
-      makeItem({
-        depth: 1,
-        durationSeconds: 1,
-        id: 'c',
-        index: 0,
-        parentId: 'p',
-        status: 'completed',
-        toolCount: 5
-      })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(peakHotness(tree)).toBeGreaterThan(2)
-  })
-
-  it('hotnessBucket clamps and normalizes', () => {
-    expect(hotnessBucket(0, 10, 4)).toBe(0)
-    expect(hotnessBucket(10, 10, 4)).toBe(3)
-    expect(hotnessBucket(5, 10, 4)).toBe(2)
-    expect(hotnessBucket(100, 10, 4)).toBe(3) // clamped
-    expect(hotnessBucket(5, 0, 4)).toBe(0) // guard against divide-by-zero
-  })
-})
-
-describe('fmtCost + fmtTokens', () => {
-  it('fmtCost handles ranges', () => {
-    expect(fmtCost(0)).toBe('')
-    expect(fmtCost(0.001)).toBe('<$0.01')
-    expect(fmtCost(0.42)).toBe('$0.42')
-    expect(fmtCost(1.23)).toBe('$1.23')
-    expect(fmtCost(12.5)).toBe('$12.5')
-  })
-
-  it('fmtTokens handles ranges', () => {
-    expect(fmtTokens(0)).toBe('0')
-    expect(fmtTokens(542)).toBe('542')
-    expect(fmtTokens(1234)).toBe('1.2k')
-    expect(fmtTokens(45678)).toBe('46k')
-  })
-})
-
-describe('formatSummary with tokens + cost', () => {
-  it('includes token + cost when present', () => {
-    expect(
-      formatSummary({
-        activeCount: 0,
-        costUsd: 0.42,
-        descendantCount: 3,
-        filesTouched: 0,
-        hotness: 0,
-        inputTokens: 8000,
-        maxDepthFromHere: 2,
-        outputTokens: 2000,
-        totalDuration: 30,
-        totalTools: 14
-      })
-    ).toBe('d2 · 3 agents · 14 tools · 30s · 10k tok · $0.42')
-  })
-})
-
-describe('buildSubagentTree', () => {
-  it('returns empty list for empty input', () => {
-    expect(buildSubagentTree([])).toEqual([])
-  })
-
-  it('treats flat list as top-level when no parentId is given', () => {
-    const items = [makeItem({ id: 'a', index: 0 }), makeItem({ id: 'b', index: 1 }), makeItem({ id: 'c', index: 2 })]
-
-    const tree = buildSubagentTree(items)
-    expect(tree).toHaveLength(3)
-    expect(tree.map(n => n.item.id)).toEqual(['a', 'b', 'c'])
-    expect(tree.every(n => n.children.length === 0)).toBe(true)
-  })
-
-  it('nests children under their parent by subagent_id', () => {
-    const items = [
-      makeItem({ id: 'parent', index: 0 }),
-      makeItem({ depth: 1, id: 'child-1', index: 0, parentId: 'parent' }),
-      makeItem({ depth: 1, id: 'child-2', index: 1, parentId: 'parent' })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree).toHaveLength(1)
-    expect(tree[0]!.children).toHaveLength(2)
-    expect(tree[0]!.children.map(n => n.item.id)).toEqual(['child-1', 'child-2'])
-  })
-
-  it('builds multi-level nesting', () => {
-    const items = [
-      makeItem({ id: 'p', index: 0 }),
-      makeItem({ depth: 1, id: 'c', index: 0, parentId: 'p' }),
-      makeItem({ depth: 2, id: 'gc', index: 0, parentId: 'c' })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.children[0]!.children[0]!.item.id).toBe('gc')
-    expect(tree[0]!.aggregate.maxDepthFromHere).toBe(2)
-    expect(tree[0]!.aggregate.descendantCount).toBe(2)
-  })
-
-  it('promotes orphaned children (missing parent) to top level', () => {
-    const items = [makeItem({ id: 'a', index: 0 }), makeItem({ depth: 1, id: 'orphan', index: 1, parentId: 'ghost' })]
-
-    const tree = buildSubagentTree(items)
-    expect(tree).toHaveLength(2)
-    expect(tree.map(n => n.item.id)).toEqual(['a', 'orphan'])
-  })
-
-  it('stable sort: children ordered by (depth, index) not insert order', () => {
-    const items = [
-      makeItem({ id: 'p', index: 0 }),
-      makeItem({ depth: 1, id: 'c3', index: 2, parentId: 'p' }),
-      makeItem({ depth: 1, id: 'c1', index: 0, parentId: 'p' }),
-      makeItem({ depth: 1, id: 'c2', index: 1, parentId: 'p' })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.children.map(n => n.item.id)).toEqual(['c1', 'c2', 'c3'])
-  })
-})
-
-describe('aggregate', () => {
-  it('sums tool counts and durations across subtree', () => {
-    const items = [
-      makeItem({ durationSeconds: 10, id: 'p', index: 0, status: 'completed', toolCount: 5 }),
-      makeItem({ depth: 1, durationSeconds: 4, id: 'c1', index: 0, parentId: 'p', status: 'completed', toolCount: 3 }),
-      makeItem({ depth: 1, durationSeconds: 2, id: 'c2', index: 1, parentId: 'p', status: 'completed', toolCount: 1 })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.aggregate).toMatchObject({
-      activeCount: 0,
-      descendantCount: 2,
-      totalDuration: 16,
-      totalTools: 9
-    })
-  })
-
-  it('counts queued + running as active', () => {
-    const items = [
-      makeItem({ id: 'p', index: 0, status: 'running' }),
-      makeItem({ depth: 1, id: 'c1', index: 0, parentId: 'p', status: 'queued' }),
-      makeItem({ depth: 1, id: 'c2', index: 1, parentId: 'p', status: 'completed' })
-    ]
-
-    const tree = buildSubagentTree(items)
-    expect(tree[0]!.aggregate.activeCount).toBe(2)
-  })
-})
-
-describe('widthByDepth', () => {
-  it('returns empty array for empty tree', () => {
-    expect(widthByDepth([])).toEqual([])
-  })
-
-  it('tallies nodes at each depth', () => {
-    const items = [
-      makeItem({ id: 'p1', index: 0 }),
-      makeItem({ id: 'p2', index: 1 }),
-      makeItem({ depth: 1, id: 'c1', index: 0, parentId: 'p1' }),
-      makeItem({ depth: 1, id: 'c2', index: 1, parentId: 'p1' }),
-      makeItem({ depth: 1, id: 'c3', index: 0, parentId: 'p2' }),
-      makeItem({ depth: 2, id: 'gc1', index: 0, parentId: 'c1' })
-    ]
-
-    expect(widthByDepth(buildSubagentTree(items))).toEqual([2, 3, 1])
-  })
-})
-
-describe('treeTotals', () => {
-  it('folds a full tree into a single rollup', () => {
-    const items = [
-      makeItem({ id: 'p1', index: 0, toolCount: 5 }),
-      makeItem({ id: 'p2', index: 1, toolCount: 2 }),
-      makeItem({ depth: 1, id: 'c', index: 0, parentId: 'p1', toolCount: 3 })
-    ]
-
-    const totals = treeTotals(buildSubagentTree(items))
-    expect(totals.descendantCount).toBe(3)
-    expect(totals.totalTools).toBe(10)
-    expect(totals.maxDepthFromHere).toBe(2)
-  })
-
-  it('returns zeros for empty tree', () => {
-    expect(treeTotals([])).toEqual({
-      activeCount: 0,
-      costUsd: 0,
-      descendantCount: 0,
-      filesTouched: 0,
-      hotness: 0,
-      inputTokens: 0,
-      maxDepthFromHere: 0,
-      outputTokens: 0,
-      totalDuration: 0,
-      totalTools: 0
-    })
-  })
-})
-
-describe('flattenTree + descendantIds', () => {
-  const items = [
-    makeItem({ id: 'p', index: 0 }),
-    makeItem({ depth: 1, id: 'c1', index: 0, parentId: 'p' }),
-    makeItem({ depth: 2, id: 'gc', index: 0, parentId: 'c1' }),
-    makeItem({ depth: 1, id: 'c2', index: 1, parentId: 'p' })
-  ]
-
-  it('flattens in visit order (depth-first, pre-order)', () => {
-    const tree = buildSubagentTree(items)
-    expect(flattenTree(tree).map(n => n.item.id)).toEqual(['p', 'c1', 'gc', 'c2'])
-  })
-
-  it('collects descendant ids excluding the node itself', () => {
-    const tree = buildSubagentTree(items)
-    expect(descendantIds(tree[0]!)).toEqual(['c1', 'gc', 'c2'])
-  })
-})
-
-describe('sparkline', () => {
-  it('returns empty string for empty input', () => {
-    expect(sparkline([])).toBe('')
-  })
-
-  it('renders zeroes as spaces (not bottom glyph)', () => {
-    expect(sparkline([0, 0])).toBe('  ')
-  })
-
-  it('scales to the max value', () => {
-    const out = sparkline([1, 8])
-    expect(out).toHaveLength(2)
-    expect(out[1]).toBe('█')
-  })
-
-  it('sparse widths render as expected', () => {
-    const out = sparkline([2, 3, 7, 4])
-    expect(out).toHaveLength(4)
-    expect([...out].every(ch => /[\s▁-█]/.test(ch))).toBe(true)
-  })
-})
-
-describe('formatSummary', () => {
-  const emptyTotals = {
-    activeCount: 0,
-    costUsd: 0,
-    descendantCount: 0,
-    filesTouched: 0,
-    hotness: 0,
-    inputTokens: 0,
-    maxDepthFromHere: 0,
-    outputTokens: 0,
-    totalDuration: 0,
-    totalTools: 0
-  }
-
-  it('collapses zero-valued components', () => {
-    expect(formatSummary({ ...emptyTotals, descendantCount: 1 })).toBe('d0 · 1 agent')
-  })
-
-  it('emits rich summary with all pieces', () => {
-    expect(
-      formatSummary({
-        ...emptyTotals,
-        activeCount: 2,
-        descendantCount: 7,
-        maxDepthFromHere: 3,
-        totalDuration: 134,
-        totalTools: 124
-      })
-    ).toBe('d3 · 7 agents · 124 tools · 2m 14s · ⚡2')
-  })
-})
-
-describe('fmtDuration', () => {
-  it('formats under a minute as plain seconds', () => {
-    expect(fmtDuration(0)).toBe('0s')
-    expect(fmtDuration(42)).toBe('42s')
-    expect(fmtDuration(59.4)).toBe('59s')
-  })
-
-  it('formats whole minutes without trailing seconds', () => {
-    expect(fmtDuration(60)).toBe('1m')
-    expect(fmtDuration(180)).toBe('3m')
-  })
-
-  it('mixes minutes and seconds', () => {
-    expect(fmtDuration(134)).toBe('2m 14s')
-    expect(fmtDuration(605)).toBe('10m 5s')
-  })
-})
-
-describe('topLevelSubagents', () => {
-  it('returns items with no parent', () => {
-    const items = [makeItem({ id: 'a', index: 0 }), makeItem({ id: 'b', index: 1 })]
-    expect(topLevelSubagents(items).map(s => s.id)).toEqual(['a', 'b'])
-  })
-
-  it('excludes children whose parent is present', () => {
-    const items = [
-      makeItem({ id: 'p', index: 0 }),
-      makeItem({ depth: 1, id: 'c', index: 0, parentId: 'p' })
-    ]
-
-    expect(topLevelSubagents(items).map(s => s.id)).toEqual(['p'])
-  })
-
-  it('promotes orphans whose parent is missing', () => {
-    const items = [makeItem({ id: 'a', index: 0 }), makeItem({ depth: 1, id: 'orphan', index: 1, parentId: 'ghost' })]
-    expect(topLevelSubagents(items).map(s => s.id)).toEqual(['a', 'orphan'])
-  })
-})

ui-tui/src/app/createGatewayEventHandler.ts

@@ -1,13 +1,11 @@
 import { STREAM_BATCH_MS } from '../config/timing.js'
 import { buildSetupRequiredSections, SETUP_REQUIRED_TITLE } from '../content/setup.js'
-import type { CommandsCatalogResponse, DelegationStatusResponse, GatewayEvent, GatewaySkin } from '../gatewayTypes.js'
+import type { CommandsCatalogResponse, GatewayEvent, GatewaySkin } from '../gatewayTypes.js'
 import { rpcErrorMessage } from '../lib/rpc.js'
-import { topLevelSubagents } from '../lib/subagentTree.js'
 import { formatToolCall, stripAnsi } from '../lib/text.js'
 import { fromSkin } from '../theme.js'
 import type { Msg, SubagentProgress } from '../types.js'
 
-import { applyDelegationStatus, getDelegationState } from './delegationStore.js'
 import type { GatewayEventHandlerContext } from './interfaces.js'
 import { patchOverlayState } from './overlayStore.js'
 import { turnController } from './turnController.js'
@@ -55,55 +53,6 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
   let pendingThinkingStatus = ''
   let thinkingStatusTimer: null | ReturnType<typeof setTimeout> = null
 
-  // Inject the disk-save callback into turnController so recordMessageComplete
-  // can fire-and-forget a persist without having to plumb a gateway ref around.
-  turnController.persistSpawnTree = async (subagents, sessionId) => {
-    try {
-      const startedAt = subagents.reduce<number>((min, s) => {
-        if (!s.startedAt) {
-          return min
-        }
-
-        return min === 0 ? s.startedAt : Math.min(min, s.startedAt)
-      }, 0)
-
-      const top = topLevelSubagents(subagents)
-        .map(s => s.goal)
-        .filter(Boolean)
-        .slice(0, 2)
-
-      const label = top.length ? top.join(' · ') : `${subagents.length} subagents`
-
-      await rpc('spawn_tree.save', {
-        finished_at: Date.now() / 1000,
-        label: label.slice(0, 120),
-        session_id: sessionId ?? 'default',
-        started_at: startedAt ? startedAt / 1000 : null,
-        subagents
-      })
-    } catch {
-      // Persistence is best-effort; in-memory history is the authoritative
-      // same-session source.  A write failure doesn't block the turn.
-    }
-  }
-
-  // Refresh delegation caps at most every 5s so the status bar HUD can
-  // render a /warning close to the configured cap without spamming the RPC.
-  let lastDelegationFetchAt = 0
-
-  const refreshDelegationStatus = (force = false) => {
-    const now = Date.now()
-
-    if (!force && now - lastDelegationFetchAt < 5000) {
-      return
-    }
-
-    lastDelegationFetchAt = now
-    rpc<DelegationStatusResponse>('delegation.status', {})
-      .then(r => applyDelegationStatus(r))
-      .catch(() => {})
-  }
-
   const setStatus = (status: string) => {
     pendingThinkingStatus = ''
 
@@ -136,12 +85,7 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
     }, ms)
   }
 
-  // Terminal statuses are never overwritten by late-arriving live events —
-  // otherwise a stale `subagent.start` / `spawn_requested` can clobber a
-  // `failed` or `interrupted` terminal state (Copilot review #14045).
-  const isTerminalStatus = (s: SubagentProgress['status']) => s === 'completed' || s === 'failed' || s === 'interrupted'
-
-  const keepTerminalElseRunning = (s: SubagentProgress['status']) => (isTerminalStatus(s) ? s : 'running')
+  const keepCompletedElseRunning = (s: SubagentProgress['status']) => (s === 'completed' ? s : 'running')
 
   const handleReady = (skin?: GatewaySkin) => {
     if (skin) {
@@ -316,28 +260,32 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
         turnController.recordToolStart(ev.payload.tool_id, ev.payload.name ?? 'tool', ev.payload.context ?? '')
 
         return
-      case 'tool.complete': {
-        const inlineDiffText =
-          ev.payload.inline_diff && getUiState().inlineDiffs ? stripAnsi(String(ev.payload.inline_diff)).trim() : ''
 
-        turnController.recordToolComplete(
-          ev.payload.tool_id,
-          ev.payload.name,
-          ev.payload.error,
-          inlineDiffText ? '' : ev.payload.summary
-        )
+      case 'tool.complete':
+        {
+          const inlineDiffText =
+            ev.payload.inline_diff && getUiState().inlineDiffs ? stripAnsi(String(ev.payload.inline_diff)).trim() : ''
+
+          turnController.recordToolComplete(
+            ev.payload.tool_id,
+            ev.payload.name,
+            ev.payload.error,
+            inlineDiffText ? '' : ev.payload.summary
+          )
+
+          if (!inlineDiffText) {
+            return
+          }
+
+          // Keep inline diffs attached to the assistant completion body so
+          // they render in the same message flow, not as a standalone system
+          // artifact that can look out-of-place around tool rows.
+          turnController.queueInlineDiff(inlineDiffText)
 
-        if (!inlineDiffText) {
           return
         }
 
-        // Keep inline diffs attached to the assistant completion body so
-        // they render in the same message flow, not as a standalone system
-        // artifact that can look out-of-place around tool rows.
-        turnController.queueInlineDiff(inlineDiffText)
-
         return
-      }
 
       case 'clarify.request':
         patchOverlayState({
@@ -381,23 +329,8 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
 
         return
 
-      case 'subagent.spawn_requested':
-        // Child built but not yet running (waiting on ThreadPoolExecutor slot).
-        // Preserve completed state if a later event races in before this one.
-        turnController.upsertSubagent(ev.payload, c => (isTerminalStatus(c.status) ? {} : { status: 'queued' }))
-
-        // Prime the status-bar HUD: fetch caps (once every 5s) so we can
-        // warn as depth/concurrency approaches the configured ceiling.
-        if (getDelegationState().maxSpawnDepth === null) {
-          refreshDelegationStatus(true)
-        } else {
-          refreshDelegationStatus()
-        }
-
-        return
-
       case 'subagent.start':
-        turnController.upsertSubagent(ev.payload, c => (isTerminalStatus(c.status) ? {} : { status: 'running' }))
+        turnController.upsertSubagent(ev.payload, () => ({ status: 'running' }))
 
         return
       case 'subagent.thinking': {
@@ -407,16 +340,10 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
           return
         }
 
-        // Update-only: never resurrect subagents whose spawn_requested/start
-        // we missed or that already flushed via message.complete.
-        turnController.upsertSubagent(
-          ev.payload,
-          c => ({
-            status: keepTerminalElseRunning(c.status),
-            thinking: pushThinking(c.thinking, text)
-          }),
-          { createIfMissing: false }
-        )
+        turnController.upsertSubagent(ev.payload, c => ({
+          status: keepCompletedElseRunning(c.status),
+          thinking: pushThinking(c.thinking, text)
+        }))
 
         return
       }
@@ -427,14 +354,10 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
           ev.payload.tool_preview ?? ev.payload.text ?? ''
         )
 
-        turnController.upsertSubagent(
-          ev.payload,
-          c => ({
-            status: keepTerminalElseRunning(c.status),
-            tools: pushTool(c.tools, line)
-          }),
-          { createIfMissing: false }
-        )
+        turnController.upsertSubagent(ev.payload, c => ({
+          status: keepCompletedElseRunning(c.status),
+          tools: pushTool(c.tools, line)
+        }))
 
         return
       }
@@ -446,28 +369,20 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
           return
         }
 
-        turnController.upsertSubagent(
-          ev.payload,
-          c => ({
-            notes: pushNote(c.notes, text),
-            status: keepTerminalElseRunning(c.status)
-          }),
-          { createIfMissing: false }
-        )
+        turnController.upsertSubagent(ev.payload, c => ({
+          notes: pushNote(c.notes, text),
+          status: keepCompletedElseRunning(c.status)
+        }))
 
         return
       }
 
       case 'subagent.complete':
-        turnController.upsertSubagent(
-          ev.payload,
-          c => ({
-            durationSeconds: ev.payload.duration_seconds ?? c.durationSeconds,
-            status: ev.payload.status ?? 'completed',
-            summary: ev.payload.summary || ev.payload.text || c.summary
-          }),
-          { createIfMissing: false }
-        )
+        turnController.upsertSubagent(ev.payload, c => ({
+          durationSeconds: ev.payload.duration_seconds ?? c.durationSeconds,
+          status: ev.payload.status ?? 'completed',
+          summary: ev.payload.summary || ev.payload.text || c.summary
+        }))
 
         return
 

ui-tui/src/app/delegationStore.ts

@@ -1,77 +0,0 @@
-import { atom } from 'nanostores'
-
-import type { DelegationStatusResponse } from '../gatewayTypes.js'
-
-export interface DelegationState {
-  // Last known caps from `delegation.status` RPC.  null until fetched.
-  maxConcurrentChildren: null | number
-  maxSpawnDepth: null | number
-  // True when spawning is globally paused (see tools/delegate_tool.py).
-  paused: boolean
-  // Monotonic clock of the last successful status fetch.
-  updatedAt: null | number
-}
-
-const buildState = (): DelegationState => ({
-  maxConcurrentChildren: null,
-  maxSpawnDepth: null,
-  paused: false,
-  updatedAt: null
-})
-
-export const $delegationState = atom<DelegationState>(buildState())
-
-export const getDelegationState = () => $delegationState.get()
-
-export const patchDelegationState = (next: Partial<DelegationState>) =>
-  $delegationState.set({ ...$delegationState.get(), ...next })
-
-export const resetDelegationState = () => $delegationState.set(buildState())
-
-// ── Overlay accordion open-state ──────────────────────────────────────
-//
-// Lifted out of OverlaySection's local useState so collapse choices
-// survive:
-//   - navigating to a different subagent (Detail remounts)
-//   - switching list ↔ detail mode (Detail unmounts in list mode)
-//   - walking history (←/→)
-// Keyed by section title; missing entries fall back to the section's
-// `defaultOpen` prop.
-
-export const $overlaySectionsOpen = atom<Record<string, boolean>>({})
-
-export const toggleOverlaySection = (title: string, defaultOpen: boolean) => {
-  const state = $overlaySectionsOpen.get()
-  const current = title in state ? state[title]! : defaultOpen
-
-  $overlaySectionsOpen.set({ ...state, [title]: !current })
-}
-
-export const getOverlaySectionOpen = (title: string, defaultOpen: boolean): boolean => {
-  const state = $overlaySectionsOpen.get()
-
-  return title in state ? state[title]! : defaultOpen
-}
-
-/** Merge a raw RPC response into the store.  Tolerant of partial/omitted fields. */
-export const applyDelegationStatus = (r: DelegationStatusResponse | null | undefined) => {
-  if (!r) {
-    return
-  }
-
-  const patch: Partial<DelegationState> = { updatedAt: Date.now() }
-
-  if (typeof r.max_spawn_depth === 'number') {
-    patch.maxSpawnDepth = r.max_spawn_depth
-  }
-
-  if (typeof r.max_concurrent_children === 'number') {
-    patch.maxConcurrentChildren = r.max_concurrent_children
-  }
-
-  if (typeof r.paused === 'boolean') {
-    patch.paused = r.paused
-  }
-
-  patchDelegationState(patch)
-}

ui-tui/src/app/interfaces.ts

@@ -53,8 +53,6 @@ export interface GatewayProviderProps {
 }
 
 export interface OverlayState {
-  agents: boolean
-  agentsInitialHistoryIndex: number
   approval: ApprovalReq | null
   clarify: ClarifyReq | null
   confirm: ConfirmReq | null

ui-tui/src/app/overlayStore.ts

@@ -3,8 +3,6 @@ import { atom, computed } from 'nanostores'
 import type { OverlayState } from './interfaces.js'
 
 const buildOverlayState = (): OverlayState => ({
-  agents: false,
-  agentsInitialHistoryIndex: 0,
   approval: null,
   clarify: null,
   confirm: null,
@@ -20,8 +18,8 @@ export const $overlayState = atom<OverlayState>(buildOverlayState())
 
 export const $isBlocked = computed(
   $overlayState,
-  ({ agents, approval, clarify, confirm, modelPicker, pager, picker, secret, skillsHub, sudo }) =>
-    Boolean(agents || approval || clarify || confirm || modelPicker || pager || picker || secret || skillsHub || sudo)
+  ({ approval, clarify, confirm, modelPicker, pager, picker, secret, skillsHub, sudo }) =>
+    Boolean(approval || clarify || confirm || modelPicker || pager || picker || secret || skillsHub || sudo)
 )
 
 export const getOverlayState = () => $overlayState.get()
@@ -29,23 +27,4 @@ export const getOverlayState = () => $overlayState.get()
 export const patchOverlayState = (next: Partial<OverlayState> | ((state: OverlayState) => OverlayState)) =>
   $overlayState.set(typeof next === 'function' ? next($overlayState.get()) : { ...$overlayState.get(), ...next })
 
-/** Full reset — used by session/turn teardown and tests. */
 export const resetOverlayState = () => $overlayState.set(buildOverlayState())
-
-/**
- * Soft reset: drop FLOW-scoped overlays (approval / clarify / confirm / sudo
- * / secret / pager) but PRESERVE user-toggled ones — agents dashboard, model
- * picker, skills hub, session picker.  Those are opened deliberately and
- * shouldn't vanish when a turn ends.  Called from turnController.idle() on
- * every turn completion / interrupt; the old "reset everything" behaviour
- * silently closed /agents the moment delegation finished.
- */
-export const resetFlowOverlays = () =>
-  $overlayState.set({
-    ...buildOverlayState(),
-    agents: $overlayState.get().agents,
-    agentsInitialHistoryIndex: $overlayState.get().agentsInitialHistoryIndex,
-    modelPicker: $overlayState.get().modelPicker,
-    picker: $overlayState.get().picker,
-    skillsHub: $overlayState.get().skillsHub
-  })

ui-tui/src/app/slash/commands/ops.ts

@@ -1,14 +1,6 @@
-import type {
-  DelegationPauseResponse,
-  SlashExecResponse,
-  SpawnTreeListResponse,
-  SpawnTreeLoadResponse,
-  ToolsConfigureResponse
-} from '../../../gatewayTypes.js'
+import type { SlashExecResponse, ToolsConfigureResponse } from '../../../gatewayTypes.js'
 import type { PanelSection } from '../../../types.js'
-import { applyDelegationStatus, getDelegationState } from '../../delegationStore.js'
 import { patchOverlayState } from '../../overlayStore.js'
-import { getSpawnHistory, pushDiskSnapshot, setDiffPair, type SpawnSnapshot } from '../../spawnHistoryStore.js'
 import type { SlashCommand } from '../types.js'
 
 interface SkillInfo {
@@ -50,163 +42,6 @@ interface SkillsBrowseResponse {
 }
 
 export const opsCommands: SlashCommand[] = [
-  {
-    aliases: ['tasks'],
-    help: 'open the spawn-tree dashboard (live audit + kill/pause controls)',
-    name: 'agents',
-    run: (arg, ctx) => {
-      const sub = arg.trim().toLowerCase()
-
-      // Stay compatible with the gateway `/agents [pause|resume|status]` CLI —
-      // explicit subcommands skip the overlay and act directly so scripts and
-      // multi-step flows can drive it without entering interactive mode.
-      if (sub === 'pause' || sub === 'resume' || sub === 'unpause') {
-        const paused = sub === 'pause'
-        ctx.gateway.gw
-          .request<DelegationPauseResponse>('delegation.pause', { paused })
-          .then(r => {
-            applyDelegationStatus({ paused: r?.paused })
-            ctx.transcript.sys(`delegation · ${r?.paused ? 'paused' : 'resumed'}`)
-          })
-          .catch(ctx.guardedErr)
-
-        return
-      }
-
-      if (sub === 'status') {
-        const d = getDelegationState()
-        ctx.transcript.sys(
-          `delegation · ${d.paused ? 'paused' : 'active'} · caps d${d.maxSpawnDepth ?? '?'}/${d.maxConcurrentChildren ?? '?'}`
-        )
-
-        return
-      }
-
-      patchOverlayState({ agents: true, agentsInitialHistoryIndex: 0 })
-    }
-  },
-
-  {
-    help: 'replay a completed spawn tree · `/replay [N|last|list|load <path>]`',
-    name: 'replay',
-    run: (arg, ctx) => {
-      const history = getSpawnHistory()
-      const raw = arg.trim()
-      const lower = raw.toLowerCase()
-
-      // ── Disk-backed listing ─────────────────────────────────────
-      if (lower === 'list' || lower === 'ls') {
-        ctx.gateway
-          .rpc<SpawnTreeListResponse>('spawn_tree.list', {
-            limit: 30,
-            session_id: ctx.sid ?? 'default'
-          })
-          .then(
-            ctx.guarded<SpawnTreeListResponse>(r => {
-              const entries = r.entries ?? []
-
-              if (!entries.length) {
-                return ctx.transcript.sys('no archived spawn trees on disk for this session')
-              }
-
-              const rows: [string, string][] = entries.map(e => {
-                const ts = e.finished_at ? new Date(e.finished_at * 1000).toLocaleString() : '?'
-                const label = e.label || `${e.count} subagents`
-
-                return [`${ts} · ${e.count}×`, `${label}\n  ${e.path}`]
-              })
-
-              ctx.transcript.panel('Archived spawn trees', [{ rows }])
-            })
-          )
-          .catch(ctx.guardedErr)
-
-        return
-      }
-
-      // ── Disk-backed load by path ─────────────────────────────────
-      if (lower.startsWith('load ')) {
-        const path = raw.slice(5).trim()
-
-        if (!path) {
-          return ctx.transcript.sys('usage: /replay load <path>')
-        }
-
-        ctx.gateway
-          .rpc<SpawnTreeLoadResponse>('spawn_tree.load', { path })
-          .then(
-            ctx.guarded<SpawnTreeLoadResponse>(r => {
-              if (!r.subagents?.length) {
-                return ctx.transcript.sys('snapshot empty or unreadable')
-              }
-
-              // Push onto the in-memory history so the overlay picks it up
-              // by index 1 just like any other snapshot.
-              pushDiskSnapshot(r, path)
-              patchOverlayState({ agents: true, agentsInitialHistoryIndex: 1 })
-            })
-          )
-          .catch(ctx.guardedErr)
-
-        return
-      }
-
-      // ── In-memory nav (same-session) ─────────────────────────────
-      if (!history.length) {
-        return ctx.transcript.sys('no completed spawn trees this session · try /replay list')
-      }
-
-      let index = 1
-
-      if (raw && lower !== 'last') {
-        const parsed = parseInt(raw, 10)
-
-        if (Number.isNaN(parsed) || parsed < 1 || parsed > history.length) {
-          return ctx.transcript.sys(`replay: index out of range 1..${history.length} · use /replay list for disk`)
-        }
-
-        index = parsed
-      }
-
-      patchOverlayState({ agents: true, agentsInitialHistoryIndex: index })
-    }
-  },
-
-  {
-    help: 'diff two completed spawn trees · `/replay-diff <baseline> <candidate>` (indexes from /replay list or history N)',
-    name: 'replay-diff',
-    run: (arg, ctx) => {
-      const parts = arg.trim().split(/\s+/).filter(Boolean)
-
-      if (parts.length !== 2) {
-        return ctx.transcript.sys('usage: /replay-diff <a> <b>  (e.g. /replay-diff 1 2 for last two)')
-      }
-
-      const [a, b] = parts
-      const history = getSpawnHistory()
-
-      const resolve = (token: string): null | SpawnSnapshot => {
-        const n = parseInt(token!, 10)
-
-        if (Number.isFinite(n) && n >= 1 && n <= history.length) {
-          return history[n - 1] ?? null
-        }
-
-        return null
-      }
-
-      const baseline = resolve(a!)
-      const candidate = resolve(b!)
-
-      if (!baseline || !candidate) {
-        return ctx.transcript.sys(`replay-diff: could not resolve indices · history has ${history.length} entries`)
-      }
-
-      setDiffPair({ baseline, candidate })
-      patchOverlayState({ agents: true, agentsInitialHistoryIndex: 0 })
-    }
-  },
-
   {
     help: 'browse, inspect, install skills',
     name: 'skills',

ui-tui/src/app/spawnHistoryStore.ts

@@ -1,139 +0,0 @@
-import { atom } from 'nanostores'
-
-import type { SpawnTreeLoadResponse } from '../gatewayTypes.js'
-import type { SubagentProgress } from '../types.js'
-
-export interface SpawnSnapshot {
-  finishedAt: number
-  fromDisk?: boolean
-  id: string
-  label: string
-  path?: string
-  sessionId: null | string
-  startedAt: number
-  subagents: SubagentProgress[]
-}
-
-export interface SpawnDiffPair {
-  baseline: SpawnSnapshot
-  candidate: SpawnSnapshot
-}
-
-const HISTORY_LIMIT = 10
-
-export const $spawnHistory = atom<SpawnSnapshot[]>([])
-export const $spawnDiff = atom<null | SpawnDiffPair>(null)
-
-export const getSpawnHistory = () => $spawnHistory.get()
-export const getSpawnDiff = () => $spawnDiff.get()
-
-export const clearSpawnHistory = () => $spawnHistory.set([])
-export const clearDiffPair = () => $spawnDiff.set(null)
-export const setDiffPair = (pair: SpawnDiffPair) => $spawnDiff.set(pair)
-
-/**
- * Commit a finished turn's spawn tree to history.  Keeps the last 10
- * non-empty snapshots — empty turns (no subagents) are dropped.
- *
- * Why in-memory?  The primary investigation loop is "I just ran a fan-out,
- * it misbehaved, let me look at what happened" — same-session debugging.
- * Disk persistence across process restarts is a natural extension but
- * adds RPC surface for a less-common path.
- */
-export const pushSnapshot = (
-  subagents: readonly SubagentProgress[],
-  meta: { sessionId?: null | string; startedAt?: null | number }
-) => {
-  if (!subagents.length) {
-    return
-  }
-
-  const now = Date.now()
-  const started = meta.startedAt ?? Math.min(...subagents.map(s => s.startedAt ?? now))
-
-  const snap: SpawnSnapshot = {
-    finishedAt: now,
-    id: `snap-${now.toString(36)}`,
-    label: summarizeLabel(subagents),
-    sessionId: meta.sessionId ?? null,
-    startedAt: Number.isFinite(started) ? started : now,
-    subagents: subagents.map(item => ({ ...item }))
-  }
-
-  const next = [snap, ...$spawnHistory.get()].slice(0, HISTORY_LIMIT)
-  $spawnHistory.set(next)
-}
-
-function summarizeLabel(subagents: readonly SubagentProgress[]): string {
-  const top = subagents
-    .filter(s => s.parentId == null || subagents.every(o => o.id !== s.parentId))
-    .slice(0, 2)
-    .map(s => s.goal || 'subagent')
-    .join(' · ')
-
-  return top || `${subagents.length} agent${subagents.length === 1 ? '' : 's'}`
-}
-
-/**
- * Push a disk-loaded snapshot onto the front of the history stack so the
- * overlay can pick it up at index 1 via /replay load.  Normalises the
- * server payload (arbitrary list) into the same SubagentProgress shape
- * used for live data — defensive against cross-version reads.
- */
-export const pushDiskSnapshot = (r: SpawnTreeLoadResponse, path: string) => {
-  const raw = Array.isArray(r.subagents) ? r.subagents : []
-  const normalised = raw.map(normaliseSubagent)
-
-  if (!normalised.length) {
-    return
-  }
-
-  const snap: SpawnSnapshot = {
-    finishedAt: (r.finished_at ?? Date.now() / 1000) * 1000,
-    fromDisk: true,
-    id: `disk-${path}`,
-    label: r.label || `${normalised.length} subagents`,
-    path,
-    sessionId: r.session_id ?? null,
-    startedAt: (r.started_at ?? r.finished_at ?? Date.now() / 1000) * 1000,
-    subagents: normalised
-  }
-
-  const next = [snap, ...$spawnHistory.get()].slice(0, HISTORY_LIMIT)
-  $spawnHistory.set(next)
-}
-
-function normaliseSubagent(raw: unknown): SubagentProgress {
-  const o = raw as Record<string, unknown>
-  const s = (v: unknown) => (typeof v === 'string' ? v : undefined)
-  const n = (v: unknown) => (typeof v === 'number' ? v : undefined)
-  const arr = <T>(v: unknown): T[] | undefined => (Array.isArray(v) ? (v as T[]) : undefined)
-
-  return {
-    apiCalls: n(o.apiCalls),
-    costUsd: n(o.costUsd),
-    depth: typeof o.depth === 'number' ? o.depth : 0,
-    durationSeconds: n(o.durationSeconds),
-    filesRead: arr<string>(o.filesRead),
-    filesWritten: arr<string>(o.filesWritten),
-    goal: s(o.goal) ?? 'subagent',
-    id: s(o.id) ?? `sa-${Math.random().toString(36).slice(2, 8)}`,
-    index: typeof o.index === 'number' ? o.index : 0,
-    inputTokens: n(o.inputTokens),
-    iteration: n(o.iteration),
-    model: s(o.model),
-    notes: (arr<string>(o.notes) ?? []).filter(x => typeof x === 'string'),
-    outputTail: arr(o.outputTail) as SubagentProgress['outputTail'],
-    outputTokens: n(o.outputTokens),
-    parentId: s(o.parentId) ?? null,
-    reasoningTokens: n(o.reasoningTokens),
-    startedAt: n(o.startedAt),
-    status: (s(o.status) as SubagentProgress['status']) ?? 'completed',
-    summary: s(o.summary),
-    taskCount: typeof o.taskCount === 'number' ? o.taskCount : 1,
-    thinking: (arr<string>(o.thinking) ?? []).filter(x => typeof x === 'string'),
-    toolCount: typeof o.toolCount === 'number' ? o.toolCount : 0,
-    tools: (arr<string>(o.tools) ?? []).filter(x => typeof x === 'string'),
-    toolsets: arr<string>(o.toolsets)
-  }
-}

ui-tui/src/app/turnController.ts

@@ -10,9 +10,8 @@ import {
 } from '../lib/text.js'
 import type { ActiveTool, ActivityItem, Msg, SubagentProgress } from '../types.js'
 
-import { resetFlowOverlays } from './overlayStore.js'
-import { pushSnapshot } from './spawnHistoryStore.js'
-import { getTurnState, patchTurnState, resetTurnState } from './turnStore.js'
+import { resetOverlayState } from './overlayStore.js'
+import { patchTurnState, resetTurnState } from './turnStore.js'
 import { getUiState, patchUiState } from './uiStore.js'
 
 const INTERRUPT_COOLDOWN_MS = 1500
@@ -42,7 +41,6 @@ class TurnController {
   lastStatusNote = ''
   pendingInlineDiffs: string[] = []
   persistedToolLabels = new Set<string>()
-  persistSpawnTree?: (subagents: SubagentProgress[], sessionId: null | string) => Promise<void>
   protocolWarned = false
   reasoningText = ''
   segmentMessages: Msg[] = []
@@ -92,7 +90,7 @@ class TurnController {
       turnTrail: []
     })
     patchUiState({ busy: false })
-    resetFlowOverlays()
+    resetOverlayState()
   }
 
   interruptTurn({ appendMessage, gw, sid, sys }: InterruptDeps) {
@@ -191,7 +189,9 @@ class TurnController {
     // leading "┊ review diff" header written by `_emit_inline_diff` for the
     // terminal printer). That header only makes sense as stdout dressing,
     // not inside a markdown ```diff block.
-    const text = diffText.replace(/^\s*┊[^\n]*\n?/, '').trim()
+    const text = diffText
+      .replace(/^\s*┊[^\n]*\n?/, '')
+      .trim()
 
     if (!text || this.pendingInlineDiffs.includes(text)) {
       return
@@ -249,15 +249,12 @@ class TurnController {
     // markdown fence of its own — otherwise we render two stacked diff
     // blocks for the same edit.
     const assistantAlreadyHasDiff = /```(?:diff|patch)\b/i.test(finalText)
-
     const remainingInlineDiffs = assistantAlreadyHasDiff
       ? []
       : this.pendingInlineDiffs.filter(diff => !finalText.includes(diff))
-
     const inlineDiffBlock = remainingInlineDiffs.length
       ? `\`\`\`diff\n${remainingInlineDiffs.join('\n\n')}\n\`\`\``
       : ''
-
     const mergedText = [finalText, inlineDiffBlock].filter(Boolean).join('\n\n')
     const existingReasoning = this.reasoningText.trim() || String(payload.reasoning ?? '').trim()
     const savedReasoning = [existingReasoning, existingReasoning ? '' : split.reasoning].filter(Boolean).join('\n\n')
@@ -279,20 +276,6 @@ class TurnController {
 
     const wasInterrupted = this.interrupted
 
-    // Archive the turn's spawn tree to history BEFORE idle() drops subagents
-    // from turnState.  Lets /replay and the overlay's history nav pull up
-    // finished fan-outs without a round-trip to disk.
-    const finishedSubagents = getTurnState().subagents
-    const sessionId = getUiState().sid
-
-    if (finishedSubagents.length > 0) {
-      pushSnapshot(finishedSubagents, { sessionId, startedAt: null })
-      // Fire-and-forget disk persistence so /replay survives process restarts.
-      // The same snapshot lives in memory via spawnHistoryStore for immediate
-      // recall — disk is the long-term archive.
-      void this.persistSpawnTree?.(finishedSubagents, sessionId)
-    }
-
     this.idle()
     this.clearReasoning()
     this.turnTools = []
@@ -460,82 +443,33 @@ class TurnController {
     patchTurnState({ activity: [], outcome: '', subagents: [], toolTokens: 0, tools: [], turnTrail: [] })
   }
 
-  upsertSubagent(
-    p: SubagentEventPayload,
-    patch: (current: SubagentProgress) => Partial<SubagentProgress>,
-    opts: { createIfMissing?: boolean } = { createIfMissing: true }
-  ) {
-    // Stable id: prefer the server-issued subagent_id (survives nested
-    // grandchildren + cross-tree joins).  Fall back to the composite key
-    // for older gateways that omit the field — those produce a flat list.
-    const id = p.subagent_id || `sa:${p.task_index}:${p.goal || 'subagent'}`
+  upsertSubagent(p: SubagentEventPayload, patch: (current: SubagentProgress) => Partial<SubagentProgress>) {
+    const id = `sa:${p.task_index}:${p.goal || 'subagent'}`
 
     patchTurnState(state => {
       const existing = state.subagents.find(item => item.id === id)
 
-      // Late events (subagent.complete/tool/progress arriving after message.complete
-      // has already fired idle()) would otherwise resurrect a finished
-      // subagent into turn.subagents and block the "finished" title on the
-      // /agents overlay.  When `createIfMissing` is false we drop silently.
-      if (!existing && !opts.createIfMissing) {
-        return state
-      }
-
       const base: SubagentProgress = existing ?? {
-        depth: p.depth ?? 0,
         goal: p.goal,
         id,
         index: p.task_index,
-        model: p.model,
         notes: [],
-        parentId: p.parent_id ?? null,
-        startedAt: Date.now(),
         status: 'running',
         taskCount: p.task_count ?? 1,
         thinking: [],
-        toolCount: p.tool_count ?? 0,
-        tools: [],
-        toolsets: p.toolsets
+        tools: []
       }
 
-      // Map snake_case payload keys onto camelCase state.  Only overwrite
-      // when the event actually carries the field; `??` preserves prior
-      // values across streaming events that emit partial payloads.
-      const outputTail = p.output_tail
-        ? p.output_tail.map(e => ({
-            isError: Boolean(e.is_error),
-            preview: String(e.preview ?? ''),
-            tool: String(e.tool ?? 'tool')
-          }))
-        : base.outputTail
-
       const next: SubagentProgress = {
         ...base,
-        apiCalls: p.api_calls ?? base.apiCalls,
-        costUsd: p.cost_usd ?? base.costUsd,
-        depth: p.depth ?? base.depth,
-        filesRead: p.files_read ?? base.filesRead,
-        filesWritten: p.files_written ?? base.filesWritten,
         goal: p.goal || base.goal,
-        inputTokens: p.input_tokens ?? base.inputTokens,
-        iteration: p.iteration ?? base.iteration,
-        model: p.model ?? base.model,
-        outputTail,
-        outputTokens: p.output_tokens ?? base.outputTokens,
-        parentId: p.parent_id ?? base.parentId,
-        reasoningTokens: p.reasoning_tokens ?? base.reasoningTokens,
         taskCount: p.task_count ?? base.taskCount,
-        toolCount: p.tool_count ?? base.toolCount,
-        toolsets: p.toolsets ?? base.toolsets,
         ...patch(base)
       }
 
-      // Stable order: by spawn (depth, parent, index) rather than insert time.
-      // Without it, grandchildren can shuffle relative to siblings when
-      // events arrive out of order under high concurrency.
       const subagents = existing
         ? state.subagents.map(item => (item.id === id ? next : item))
-        : [...state.subagents, next].sort((a, b) => a.depth - b.depth || a.index - b.index)
+        : [...state.subagents, next].sort((a, b) => a.index - b.index)
 
       return { ...state, subagents }
     })

ui-tui/src/app/useInputHandlers.ts

@@ -74,10 +74,6 @@ export function useInputHandlers(ctx: InputHandlerContext): InputHandlerResult {
     if (overlay.picker) {
       return patchOverlayState({ picker: false })
     }
-
-    if (overlay.agents) {
-      return patchOverlayState({ agents: false })
-    }
   }
 
   const cycleQueue = (dir: 1 | -1) => {
@@ -184,7 +180,6 @@ export function useInputHandlers(ctx: InputHandlerContext): InputHandlerResult {
         if (isCtrl(key, ch, 'c')) {
           cancelOverlayFromCtrlC()
         }
-
         return
       }
 
@@ -295,7 +290,6 @@ export function useInputHandlers(ctx: InputHandlerContext): InputHandlerResult {
     if (key.upArrow && !cState.inputBuf.length) {
       const inputSel = getInputSelection()
       const cursor = inputSel && inputSel.start === inputSel.end ? inputSel.start : null
-
       const noLineAbove =
         !cState.input || (cursor !== null && cState.input.lastIndexOf('\n', Math.max(0, cursor - 1)) < 0)
 

ui-tui/src/components/appChrome.tsx

@@ -1,14 +1,10 @@
 import { Box, type ScrollBoxHandle, Text } from '@hermes/ink'
-import { useStore } from '@nanostores/react'
-import { type ReactNode, type RefObject, useCallback, useEffect, useMemo, useState, useSyncExternalStore } from 'react'
+import { type ReactNode, type RefObject, useCallback, useEffect, useState, useSyncExternalStore } from 'react'
 
-import { $delegationState } from '../app/delegationStore.js'
-import { $turnState } from '../app/turnStore.js'
 import { FACES } from '../content/faces.js'
 import { VERBS } from '../content/verbs.js'
 import { fmtDuration } from '../domain/messages.js'
 import { stickyPromptFromViewport } from '../domain/viewport.js'
-import { buildSubagentTree, treeTotals, widthByDepth } from '../lib/subagentTree.js'
 import { fmtK } from '../lib/text.js'
 import type { Theme } from '../theme.js'
 import type { Msg, Usage } from '../types.js'
@@ -64,67 +60,6 @@ function ctxBar(pct: number | undefined, w = 10) {
   return '█'.repeat(filled) + '░'.repeat(w - filled)
 }
 
-function SpawnHud({ t }: { t: Theme }) {
-  // Tight HUD that only appears when the session is actually fanning out.
-  // Colour escalates to warn/error as depth or concurrency approaches the cap.
-  const delegation = useStore($delegationState)
-  const turn = useStore($turnState)
-
-  const tree = useMemo(() => buildSubagentTree(turn.subagents), [turn.subagents])
-  const totals = useMemo(() => treeTotals(tree), [tree])
-
-  if (!totals.descendantCount && !delegation.paused) {
-    return null
-  }
-
-  const maxDepth = delegation.maxSpawnDepth
-  const maxConc = delegation.maxConcurrentChildren
-  const depth = Math.max(0, totals.maxDepthFromHere)
-  const active = totals.activeCount
-
-  // `max_concurrent_children` is a per-parent cap, not a global one.
-  // `activeCount` sums every running agent across the tree and would
-  // over-warn for multi-orchestrator runs.  The widest level of the tree
-  // is a closer proxy to "most concurrent spawns that could be hitting a
-  // single parent's slot budget".
-  const widestLevel = widthByDepth(tree).reduce((a, b) => Math.max(a, b), 0)
-  const depthRatio = maxDepth ? depth / maxDepth : 0
-  const concRatio = maxConc ? widestLevel / maxConc : 0
-  const ratio = Math.max(depthRatio, concRatio)
-
-  const color = delegation.paused || ratio >= 1 ? t.color.error : ratio >= 0.66 ? t.color.warn : t.color.dim
-
-  const pieces: string[] = []
-
-  if (delegation.paused) {
-    pieces.push('⏸ paused')
-  }
-
-  if (totals.descendantCount > 0) {
-    const depthLabel = maxDepth ? `${depth}/${maxDepth}` : `${depth}`
-    pieces.push(`d${depthLabel}`)
-
-    if (active > 0) {
-      // Label pairs the widest-level count (drives concRatio above) with
-      // the total active count for context.  `W/cap` triggers the warn,
-      // `+N` is everything else currently running across the tree.
-      const extra = Math.max(0, active - widestLevel)
-      const widthLabel = maxConc ? `${widestLevel}/${maxConc}` : `${widestLevel}`
-      const suffix = extra > 0 ? `+${extra}` : ''
-      pieces.push(`⚡${widthLabel}${suffix}`)
-    }
-  }
-
-  const atCap = depthRatio >= 1 || concRatio >= 1
-
-  return (
-    <Text color={color}>
-      {atCap ? ' │ ⚠ ' : ' │ '}
-      {pieces.join(' ')}
-    </Text>
-  )
-}
-
 function SessionDuration({ startedAt }: { startedAt: number }) {
   const [now, setNow] = useState(() => Date.now())
 
@@ -210,7 +145,6 @@ export function StatusRule({
               <SessionDuration startedAt={sessionStartedAt} />
             </Text>
           ) : null}
-          <SpawnHud t={t} />
           {voiceLabel ? <Text color={t.color.dim}> │ {voiceLabel}</Text> : null}
           {bgCount > 0 ? <Text color={t.color.dim}> │ {bgCount} bg</Text> : null}
           {showCost && typeof usage.cost_usd === 'number' ? (

ui-tui/src/components/appLayout.tsx

@@ -2,15 +2,13 @@ import { AlternateScreen, Box, NoSelect, ScrollBox, Text } from '@hermes/ink'
 import { useStore } from '@nanostores/react'
 import { memo } from 'react'
 
-import { useGateway } from '../app/gatewayContext.js'
 import type { AppLayoutProgressProps, AppLayoutProps } from '../app/interfaces.js'
-import { $isBlocked, $overlayState, patchOverlayState } from '../app/overlayStore.js'
+import { $isBlocked } from '../app/overlayStore.js'
 import { $uiState } from '../app/uiStore.js'
 import { PLACEHOLDER } from '../content/placeholders.js'
 import type { Theme } from '../theme.js'
 import type { DetailsMode } from '../types.js'
 
-import { AgentsOverlay } from './agentsOverlay.js'
 import { GoodVibesHeart, StatusRule, StickyPromptTracker, TranscriptScrollbar } from './appChrome.js'
 import { FloatingOverlays, PromptZone } from './appOverlays.js'
 import { Banner, Panel, SessionPanel } from './branding.js'
@@ -258,21 +256,6 @@ const ComposerPane = memo(function ComposerPane({
   )
 })
 
-const AgentsOverlayPane = memo(function AgentsOverlayPane() {
-  const { gw } = useGateway()
-  const ui = useStore($uiState)
-  const overlay = useStore($overlayState)
-
-  return (
-    <AgentsOverlay
-      gw={gw}
-      initialHistoryIndex={overlay.agentsInitialHistoryIndex}
-      onClose={() => patchOverlayState({ agents: false, agentsInitialHistoryIndex: 0 })}
-      t={ui.theme}
-    />
-  )
-})
-
 export const AppLayout = memo(function AppLayout({
   actions,
   composer,
@@ -281,30 +264,22 @@ export const AppLayout = memo(function AppLayout({
   status,
   transcript
 }: AppLayoutProps) {
-  const overlay = useStore($overlayState)
-
   return (
     <AlternateScreen mouseTracking={mouseTracking}>
       <Box flexDirection="column" flexGrow={1}>
         <Box flexDirection="row" flexGrow={1}>
-          {overlay.agents ? (
-            <AgentsOverlayPane />
-          ) : (
-            <TranscriptPane actions={actions} composer={composer} progress={progress} transcript={transcript} />
-          )}
+          <TranscriptPane actions={actions} composer={composer} progress={progress} transcript={transcript} />
         </Box>
 
-        {!overlay.agents && (
-          <PromptZone
-            cols={composer.cols}
-            onApprovalChoice={actions.answerApproval}
-            onClarifyAnswer={actions.answerClarify}
-            onSecretSubmit={actions.answerSecret}
-            onSudoSubmit={actions.answerSudo}
-          />
-        )}
+        <PromptZone
+          cols={composer.cols}
+          onApprovalChoice={actions.answerApproval}
+          onClarifyAnswer={actions.answerClarify}
+          onSecretSubmit={actions.answerSecret}
+          onSudoSubmit={actions.answerSudo}
+        />
 
-        {!overlay.agents && <ComposerPane actions={actions} composer={composer} status={status} />}
+        <ComposerPane actions={actions} composer={composer} status={status} />
       </Box>
     </AlternateScreen>
   )

ui-tui/src/components/textInput.tsx

@@ -615,7 +615,14 @@ export function TextInput({
         return
       }
 
-      if ((k.ctrl && inp === 'c') || k.tab || (k.shift && k.tab) || k.pageUp || k.pageDown || k.escape) {
+      if (
+        (k.ctrl && inp === 'c') ||
+        k.tab ||
+        (k.shift && k.tab) ||
+        k.pageUp ||
+        k.pageDown ||
+        k.escape
+      ) {
         return
       }
 

ui-tui/src/components/thinking.tsx

@@ -1,19 +1,8 @@
 import { Box, NoSelect, Text } from '@hermes/ink'
-import { memo, type ReactNode, useEffect, useMemo, useState } from 'react'
+import { memo, useEffect, useMemo, useState, type ReactNode } from 'react'
 import spinners, { type BrailleSpinnerName } from 'unicode-animations'
 
 import { THINKING_COT_MAX } from '../config/limits.js'
-import {
-  buildSubagentTree,
-  fmtCost,
-  fmtTokens,
-  formatSummary as formatSpawnSummary,
-  hotnessBucket,
-  peakHotness,
-  sparkline,
-  treeTotals,
-  widthByDepth
-} from '../lib/subagentTree.js'
 import {
   compactPreview,
   estimateTokensRough,
@@ -25,7 +14,7 @@ import {
   toolTrailLabel
 } from '../lib/text.js'
 import type { Theme } from '../theme.js'
-import type { ActiveTool, ActivityItem, DetailsMode, SubagentNode, SubagentProgress, ThinkingMode } from '../types.js'
+import type { ActiveTool, ActivityItem, DetailsMode, SubagentProgress, ThinkingMode } from '../types.js'
 
 const THINK: BrailleSpinnerName[] = ['helix', 'breathe', 'orbit', 'dna', 'waverows', 'snake', 'pulse']
 const TOOL: BrailleSpinnerName[] = ['cascade', 'scan', 'diagswipe', 'fillsweep', 'rain', 'columns', 'sparkle']
@@ -117,8 +106,6 @@ function TreeNode({
   header,
   open,
   rails = [],
-  stemColor,
-  stemDim,
   t
 }: {
   branch: TreeBranch
@@ -126,13 +113,11 @@ function TreeNode({
   header: ReactNode
   open: boolean
   rails?: TreeRails
-  stemColor?: string
-  stemDim?: boolean
   t: Theme
 }) {
   return (
     <Box flexDirection="column">
-      <TreeRow branch={branch} rails={rails} stemColor={stemColor} stemDim={stemDim} t={t}>
+      <TreeRow branch={branch} rails={rails} t={t}>
         {header}
       </TreeRow>
       {open ? children?.(nextTreeRails(rails, branch)) : null}
@@ -254,31 +239,16 @@ function Chevron({
   )
 }
 
-function heatColor(node: SubagentNode, peak: number, theme: Theme): string | undefined {
-  const palette = [theme.color.bronze, theme.color.amber, theme.color.gold, theme.color.warn, theme.color.error]
-  const idx = hotnessBucket(node.aggregate.hotness, peak, palette.length)
-
-  // Below the median bucket we keep the default dim stem so cool branches
-  // fade into the chrome — only "hot" branches draw the eye.
-  if (idx < 2) {
-    return undefined
-  }
-
-  return palette[idx]
-}
-
 function SubagentAccordion({
   branch,
   expanded,
-  node,
-  peak,
+  item,
   rails = [],
   t
 }: {
   branch: TreeBranch
   expanded: boolean
-  node: SubagentNode
-  peak: number
+  item: SubagentProgress
   rails?: TreeRails
   t: Theme
 }) {
@@ -287,7 +257,6 @@ function SubagentAccordion({
   const [openThinking, setOpenThinking] = useState(expanded)
   const [openTools, setOpenTools] = useState(expanded)
   const [openNotes, setOpenNotes] = useState(expanded)
-  const [openKids, setOpenKids] = useState(expanded)
 
   useEffect(() => {
     if (!expanded) {
@@ -299,7 +268,6 @@ function SubagentAccordion({
     setOpenThinking(true)
     setOpenTools(true)
     setOpenNotes(true)
-    setOpenKids(true)
   }, [expanded])
 
   const expandAll = () => {
@@ -308,13 +276,8 @@ function SubagentAccordion({
     setOpenThinking(true)
     setOpenTools(true)
     setOpenNotes(true)
-    setOpenKids(true)
   }
 
-  const item = node.item
-  const children = node.children
-  const aggregate = node.aggregate
-
   const statusTone: 'dim' | 'error' | 'warn' =
     item.status === 'failed' ? 'error' : item.status === 'interrupted' ? 'warn' : 'dim'
 
@@ -323,60 +286,10 @@ function SubagentAccordion({
   const title = `${prefix}${open ? goalLabel : compactPreview(goalLabel, 60)}`
   const summary = compactPreview((item.summary || '').replace(/\s+/g, ' ').trim(), 72)
 
-  // Suffix packs branch rollup: status · elapsed · per-branch tool/agent/token/cost.
-  // Emphasises the numbers the user can't easily eyeball from a flat list.
-  const statusLabel = item.status === 'queued' ? 'queued' : item.status === 'running' ? 'running' : String(item.status)
-
-  const rollupBits: string[] = [statusLabel]
-
-  if (item.durationSeconds) {
-    rollupBits.push(fmtElapsed(item.durationSeconds * 1000))
-  }
-
-  const localTools = item.toolCount ?? 0
-  const subtreeTools = aggregate.totalTools - localTools
-
-  if (localTools > 0) {
-    rollupBits.push(`${localTools} tool${localTools === 1 ? '' : 's'}`)
-  }
-
-  const localTokens = (item.inputTokens ?? 0) + (item.outputTokens ?? 0)
-
-  if (localTokens > 0) {
-    rollupBits.push(`${fmtTokens(localTokens)} tok`)
-  }
-
-  const localCost = item.costUsd ?? 0
-
-  if (localCost > 0) {
-    rollupBits.push(fmtCost(localCost))
-  }
-
-  const filesLocal = (item.filesWritten?.length ?? 0) + (item.filesRead?.length ?? 0)
-
-  if (filesLocal > 0) {
-    rollupBits.push(`⎘${filesLocal}`)
-  }
-
-  if (children.length > 0) {
-    rollupBits.push(`${aggregate.descendantCount}↓`)
-
-    if (subtreeTools > 0) {
-      rollupBits.push(`+${subtreeTools}t sub`)
-    }
-
-    const subCost = aggregate.costUsd - localCost
-
-    if (subCost >= 0.01) {
-      rollupBits.push(`+${fmtCost(subCost)} sub`)
-    }
-
-    if (aggregate.activeCount > 0 && item.status !== 'running') {
-      rollupBits.push(`⚡${aggregate.activeCount}`)
-    }
-  }
-
-  const suffix = rollupBits.join(' · ')
+  const suffix =
+    item.status === 'running'
+      ? 'running'
+      : `${item.status}${item.durationSeconds ? ` · ${fmtElapsed(item.durationSeconds * 1000)}` : ''}`
 
   const thinkingText = item.thinking.join('\n')
   const hasThinking = Boolean(thinkingText)
@@ -505,50 +418,6 @@ function SubagentAccordion({
     })
   }
 
-  if (children.length > 0) {
-    // Nested grandchildren — rendered recursively via SubagentAccordion,
-    // sharing the same keybindings / expand semantics as top-level nodes.
-    sections.push({
-      header: (
-        <Chevron
-          count={children.length}
-          onClick={shift => {
-            if (shift) {
-              expandAll()
-            } else {
-              setOpenKids(v => !v)
-            }
-          }}
-          open={showChildren || openKids}
-          suffix={`d${item.depth + 1} · ${aggregate.descendantCount} total`}
-          t={t}
-          title="Spawned"
-        />
-      ),
-      key: 'subagents',
-      open: showChildren || openKids,
-      render: childRails => (
-        <Box flexDirection="column">
-          {children.map((child, i) => (
-            <SubagentAccordion
-              branch={i === children.length - 1 ? 'last' : 'mid'}
-              expanded={expanded || deep}
-              key={child.item.id}
-              node={child}
-              peak={peak}
-              rails={childRails}
-              t={t}
-            />
-          ))}
-        </Box>
-      )
-    })
-  }
-
-  // Heatmap: amber→error gradient on the stem when this branch is "hot"
-  // (high tools/sec) relative to the whole tree's peak.
-  const stem = heatColor(node, peak, t)
-
   return (
     <TreeNode
       branch={branch}
@@ -578,8 +447,6 @@ function SubagentAccordion({
       }
       open={open}
       rails={rails}
-      stemColor={stem}
-      stemDim={stem == null}
       t={t}
     >
       {childRails => (
@@ -731,16 +598,6 @@ export const ToolTrail = memo(function ToolTrail({
 
   const cot = useMemo(() => thinkingPreview(reasoning, 'full', THINKING_COT_MAX), [reasoning])
 
-  // Spawn-tree derivations must live above any early return so React's
-  // rules-of-hooks sees a stable call order.  Cheap O(N) builds memoised
-  // by subagent-list identity.
-  const spawnTree = useMemo(() => buildSubagentTree(subagents), [subagents])
-  const spawnPeak = useMemo(() => peakHotness(spawnTree), [spawnTree])
-  const spawnTotals = useMemo(() => treeTotals(spawnTree), [spawnTree])
-  const spawnWidths = useMemo(() => widthByDepth(spawnTree), [spawnTree])
-  const spawnSpark = useMemo(() => sparkline(spawnWidths), [spawnWidths])
-  const spawnSummaryLabel = useMemo(() => formatSpawnSummary(spawnTotals), [spawnTotals])
-
   if (
     !busy &&
     !trail.length &&
@@ -896,13 +753,12 @@ export const ToolTrail = memo(function ToolTrail({
 
   const renderSubagentList = (rails: boolean[]) => (
     <Box flexDirection="column">
-      {spawnTree.map((node, index) => (
+      {subagents.map((item, index) => (
         <SubagentAccordion
-          branch={index === spawnTree.length - 1 ? 'last' : 'mid'}
+          branch={index === subagents.length - 1 ? 'last' : 'mid'}
           expanded={detailsMode === 'expanded' || deepSubagents}
-          key={node.item.id}
-          node={node}
-          peak={spawnPeak}
+          item={item}
+          key={item.id}
           rails={rails}
           t={t}
         />
@@ -1025,14 +881,10 @@ export const ToolTrail = memo(function ToolTrail({
   }
 
   if (hasSubagents && !inlineDelegateKey) {
-    // Spark + summary give a one-line read on the branch shape before
-    // opening the subtree.  `/agents` opens the full-screen audit overlay.
-    const suffix = spawnSpark ? `${spawnSummaryLabel}  ${spawnSpark}  (/agents)` : `${spawnSummaryLabel}  (/agents)`
-
     sections.push({
       header: (
         <Chevron
-          count={spawnTotals.descendantCount}
+          count={subagents.length}
           onClick={shift => {
             if (shift) {
               expandAll()
@@ -1043,9 +895,8 @@ export const ToolTrail = memo(function ToolTrail({
             }
           }}
           open={detailsMode === 'expanded' || openSubagents}
-          suffix={suffix}
           t={t}
-          title="Spawn tree"
+          title="Subagents"
         />
       ),
       key: 'subagents',

ui-tui/src/gatewayTypes.ts

@@ -280,85 +280,15 @@ export interface ReloadMcpResponse {
 // ── Subagent events ──────────────────────────────────────────────────
 
 export interface SubagentEventPayload {
-  api_calls?: number
-  cost_usd?: number
-  depth?: number
   duration_seconds?: number
-  files_read?: string[]
-  files_written?: string[]
   goal: string
-  input_tokens?: number
-  iteration?: number
-  model?: string
-  output_tail?: { is_error?: boolean; preview?: string; tool?: string }[]
-  output_tokens?: number
-  parent_id?: null | string
-  reasoning_tokens?: number
-  status?: 'completed' | 'failed' | 'interrupted' | 'queued' | 'running'
-  subagent_id?: string
+  status?: 'completed' | 'failed' | 'interrupted' | 'running'
   summary?: string
   task_count?: number
   task_index: number
   text?: string
-  tool_count?: number
   tool_name?: string
   tool_preview?: string
-  toolsets?: string[]
-}
-
-// ── Delegation control RPCs ──────────────────────────────────────────
-
-export interface DelegationStatusResponse {
-  active?: {
-    depth?: number
-    goal?: string
-    model?: null | string
-    parent_id?: null | string
-    started_at?: number
-    status?: string
-    subagent_id?: string
-    tool_count?: number
-  }[]
-  max_concurrent_children?: number
-  max_spawn_depth?: number
-  paused?: boolean
-}
-
-export interface DelegationPauseResponse {
-  paused?: boolean
-}
-
-export interface SubagentInterruptResponse {
-  found?: boolean
-  subagent_id?: string
-}
-
-// ── Spawn-tree snapshots ─────────────────────────────────────────────
-
-export interface SpawnTreeListEntry {
-  count: number
-  finished_at?: number
-  label?: string
-  path: string
-  session_id?: string
-  started_at?: number | null
-}
-
-export interface SpawnTreeListResponse {
-  entries?: SpawnTreeListEntry[]
-}
-
-export interface SpawnTreeLoadResponse {
-  finished_at?: number
-  label?: string
-  session_id?: string
-  started_at?: null | number
-  subagents?: unknown[]
-}
-
-export interface SpawnTreeSaveResponse {
-  path?: string
-  session_id?: string
 }
 
 export type GatewayEvent =
@@ -390,7 +320,6 @@ export type GatewayEvent =
   | { payload: { env_var: string; prompt: string; request_id: string }; session_id?: string; type: 'secret.request' }
   | { payload: { task_id: string; text: string }; session_id?: string; type: 'background.complete' }
   | { payload: { text: string }; session_id?: string; type: 'btw.complete' }
-  | { payload: SubagentEventPayload; session_id?: string; type: 'subagent.spawn_requested' }
   | { payload: SubagentEventPayload; session_id?: string; type: 'subagent.start' }
   | { payload: SubagentEventPayload; session_id?: string; type: 'subagent.thinking' }
   | { payload: SubagentEventPayload; session_id?: string; type: 'subagent.tool' }

ui-tui/src/lib/subagentTree.ts

@@ -1,355 +0,0 @@
-import type { SubagentAggregate, SubagentNode, SubagentProgress } from '../types.js'
-
-const ROOT_KEY = '__root__'
-
-/**
- * Reconstruct the subagent spawn tree from a flat event-ordered list.
- *
- * Grouping is by `parentId`; a missing `parentId` (or one pointing at an
- * unknown subagent) is treated as a top-level spawn of the current turn.
- * Children within a parent are sorted by `depth` then `index` — same key
- * used in `turnController.upsertSubagent`, so render order matches spawn
- * order regardless of network reordering of gateway events.
- *
- * Older gateways omit `parentId`; every subagent is then a top-level node
- * and the tree renders flat — matching pre-observability behaviour.
- */
-export function buildSubagentTree(items: readonly SubagentProgress[]): SubagentNode[] {
-  if (!items.length) {
-    return []
-  }
-
-  const byParent = new Map<string, SubagentProgress[]>()
-  const known = new Set<string>()
-
-  for (const item of items) {
-    known.add(item.id)
-  }
-
-  for (const item of items) {
-    const parentKey = item.parentId && known.has(item.parentId) ? item.parentId : ROOT_KEY
-    const bucket = byParent.get(parentKey) ?? []
-    bucket.push(item)
-    byParent.set(parentKey, bucket)
-  }
-
-  for (const bucket of byParent.values()) {
-    bucket.sort((a, b) => a.depth - b.depth || a.index - b.index)
-  }
-
-  const build = (item: SubagentProgress): SubagentNode => {
-    const kids = byParent.get(item.id) ?? []
-    const children = kids.map(build)
-
-    return { aggregate: aggregate(item, children), children, item }
-  }
-
-  return (byParent.get(ROOT_KEY) ?? []).map(build)
-}
-
-/**
- * Roll up counts for a node's whole subtree.  Kept pure so the live view
- * and the post-hoc replay can share the same renderer unchanged.
- *
- * `hotness` = tools per second across the subtree — a crude proxy for
- * "how much work is happening in this branch".  Used to colour tree rails
- * in the overlay / inline view so the eye spots the expensive branch.
- */
-export function aggregate(item: SubagentProgress, children: readonly SubagentNode[]): SubagentAggregate {
-  let totalTools = item.toolCount ?? 0
-  let totalDuration = item.durationSeconds ?? 0
-  let descendantCount = 0
-  let activeCount = isRunning(item) ? 1 : 0
-  let maxDepthFromHere = 0
-  let inputTokens = item.inputTokens ?? 0
-  let outputTokens = item.outputTokens ?? 0
-  let costUsd = item.costUsd ?? 0
-  let filesTouched = (item.filesRead?.length ?? 0) + (item.filesWritten?.length ?? 0)
-
-  for (const child of children) {
-    totalTools += child.aggregate.totalTools
-    totalDuration += child.aggregate.totalDuration
-    descendantCount += child.aggregate.descendantCount + 1
-    activeCount += child.aggregate.activeCount
-    maxDepthFromHere = Math.max(maxDepthFromHere, child.aggregate.maxDepthFromHere + 1)
-    inputTokens += child.aggregate.inputTokens
-    outputTokens += child.aggregate.outputTokens
-    costUsd += child.aggregate.costUsd
-    filesTouched += child.aggregate.filesTouched
-  }
-
-  const hotness = totalDuration > 0 ? totalTools / totalDuration : 0
-
-  return {
-    activeCount,
-    costUsd,
-    descendantCount,
-    filesTouched,
-    hotness,
-    inputTokens,
-    maxDepthFromHere,
-    outputTokens,
-    totalDuration,
-    totalTools
-  }
-}
-
-/**
- * Count of subagents at each depth level, indexed by depth (0 = top level).
- * Drives the inline sparkline (`▁▃▇▅`) and the status-bar HUD.
- */
-export function widthByDepth(tree: readonly SubagentNode[]): number[] {
-  const widths: number[] = []
-
-  const walk = (nodes: readonly SubagentNode[], depth: number) => {
-    if (!nodes.length) {
-      return
-    }
-
-    widths[depth] = (widths[depth] ?? 0) + nodes.length
-
-    for (const node of nodes) {
-      walk(node.children, depth + 1)
-    }
-  }
-
-  walk(tree, 0)
-
-  return widths
-}
-
-/**
- * Flat totals across the full tree — feeds the summary chip header.
- */
-export function treeTotals(tree: readonly SubagentNode[]): SubagentAggregate {
-  let totalTools = 0
-  let totalDuration = 0
-  let descendantCount = 0
-  let activeCount = 0
-  let maxDepthFromHere = 0
-  let inputTokens = 0
-  let outputTokens = 0
-  let costUsd = 0
-  let filesTouched = 0
-
-  for (const node of tree) {
-    totalTools += node.aggregate.totalTools
-    totalDuration += node.aggregate.totalDuration
-    descendantCount += node.aggregate.descendantCount + 1
-    activeCount += node.aggregate.activeCount
-    maxDepthFromHere = Math.max(maxDepthFromHere, node.aggregate.maxDepthFromHere + 1)
-    inputTokens += node.aggregate.inputTokens
-    outputTokens += node.aggregate.outputTokens
-    costUsd += node.aggregate.costUsd
-    filesTouched += node.aggregate.filesTouched
-  }
-
-  const hotness = totalDuration > 0 ? totalTools / totalDuration : 0
-
-  return {
-    activeCount,
-    costUsd,
-    descendantCount,
-    filesTouched,
-    hotness,
-    inputTokens,
-    maxDepthFromHere,
-    outputTokens,
-    totalDuration,
-    totalTools
-  }
-}
-
-/**
- * Flatten the tree into visit order — useful for keyboard navigation and
- * for "kill subtree" walks that fire one RPC per descendant.
- */
-export function flattenTree(tree: readonly SubagentNode[]): SubagentNode[] {
-  const out: SubagentNode[] = []
-
-  const walk = (nodes: readonly SubagentNode[]) => {
-    for (const node of nodes) {
-      out.push(node)
-      walk(node.children)
-    }
-  }
-
-  walk(tree)
-
-  return out
-}
-
-/**
- * Collect every descendant's id for a given node (excluding the node itself).
- */
-export function descendantIds(node: SubagentNode): string[] {
-  const ids: string[] = []
-
-  const walk = (children: readonly SubagentNode[]) => {
-    for (const child of children) {
-      ids.push(child.item.id)
-      walk(child.children)
-    }
-  }
-
-  walk(node.children)
-
-  return ids
-}
-
-export function isRunning(item: Pick<SubagentProgress, 'status'>): boolean {
-  return item.status === 'running' || item.status === 'queued'
-}
-
-const SPARK_RAMP = ['▁', '▂', '▃', '▄', '▅', '▆', '▇', '█'] as const
-
-/**
- * 8-step unicode bar sparkline from a positive-integer array.  Zeroes render
- * as spaces so a sparse tree doesn't read as equal activity at every depth.
- */
-export function sparkline(values: readonly number[]): string {
-  if (!values.length) {
-    return ''
-  }
-
-  const max = Math.max(...values)
-
-  if (max <= 0) {
-    return ' '.repeat(values.length)
-  }
-
-  return values
-    .map(v => {
-      if (v <= 0) {
-        return ' '
-      }
-
-      const idx = Math.min(SPARK_RAMP.length - 1, Math.max(0, Math.ceil((v / max) * (SPARK_RAMP.length - 1))))
-
-      return SPARK_RAMP[idx]
-    })
-    .join('')
-}
-
-/**
- * Format totals into a compact one-line summary: `d2 · 7 agents · 124 tools · 2m 14s`
- */
-export function formatSummary(totals: SubagentAggregate): string {
-  const pieces = [`d${Math.max(0, totals.maxDepthFromHere)}`]
-  pieces.push(`${totals.descendantCount} agent${totals.descendantCount === 1 ? '' : 's'}`)
-
-  if (totals.totalTools > 0) {
-    pieces.push(`${totals.totalTools} tool${totals.totalTools === 1 ? '' : 's'}`)
-  }
-
-  if (totals.totalDuration > 0) {
-    pieces.push(fmtDuration(totals.totalDuration))
-  }
-
-  const tokens = totals.inputTokens + totals.outputTokens
-
-  if (tokens > 0) {
-    pieces.push(`${fmtTokens(tokens)} tok`)
-  }
-
-  if (totals.costUsd > 0) {
-    pieces.push(fmtCost(totals.costUsd))
-  }
-
-  if (totals.activeCount > 0) {
-    pieces.push(`⚡${totals.activeCount}`)
-  }
-
-  return pieces.join(' · ')
-}
-
-/** Compact dollar amount: `$0.02`, `$1.34`, `$12.4` — never > 5 chars beyond the `$`. */
-export function fmtCost(usd: number): string {
-  if (!Number.isFinite(usd) || usd <= 0) {
-    return ''
-  }
-
-  if (usd < 0.01) {
-    return '<$0.01'
-  }
-
-  if (usd < 10) {
-    return `$${usd.toFixed(2)}`
-  }
-
-  return `$${usd.toFixed(1)}`
-}
-
-/** Compact token count: `12k`, `1.2k`, `542`. */
-export function fmtTokens(n: number): string {
-  if (!Number.isFinite(n) || n <= 0) {
-    return '0'
-  }
-
-  if (n < 1000) {
-    return String(Math.round(n))
-  }
-
-  if (n < 10_000) {
-    return `${(n / 1000).toFixed(1)}k`
-  }
-
-  return `${Math.round(n / 1000)}k`
-}
-
-/**
- * `Ns` / `Nm` / `Nm Ss` formatter for seconds.  Shared with the agents
- * overlay so the timeline + list + summary all speak the same dialect.
- */
-export function fmtDuration(seconds: number): string {
-  if (seconds < 60) {
-    return `${Math.max(0, Math.round(seconds))}s`
-  }
-
-  const m = Math.floor(seconds / 60)
-  const s = Math.round(seconds - m * 60)
-
-  return s === 0 ? `${m}m` : `${m}m ${s}s`
-}
-
-/**
- * A subagent is top-level if it has no `parentId`, or its parent isn't in
- * the same snapshot (orphaned by a pruned mid-flight root).  Same rule
- * `buildSubagentTree` uses — keep call sites consistent across the live
- * view, disk label, and diff pane.
- */
-export function topLevelSubagents(items: readonly SubagentProgress[]): SubagentProgress[] {
-  const ids = new Set(items.map(s => s.id))
-
-  return items.filter(s => !s.parentId || !ids.has(s.parentId))
-}
-
-/**
- * Normalize a node's hotness into a palette index 0..N-1 where N = buckets.
- * Higher hotness = "hotter" colour. Normalized against the tree's peak hotness
- * so a uniformly slow tree still shows gradient across its busiest branches.
- */
-export function hotnessBucket(hotness: number, peakHotness: number, buckets: number): number {
-  if (!Number.isFinite(hotness) || hotness <= 0 || peakHotness <= 0 || buckets <= 1) {
-    return 0
-  }
-
-  const ratio = Math.min(1, hotness / peakHotness)
-
-  return Math.min(buckets - 1, Math.max(0, Math.round(ratio * (buckets - 1))))
-}
-
-export function peakHotness(tree: readonly SubagentNode[]): number {
-  let peak = 0
-
-  const walk = (nodes: readonly SubagentNode[]) => {
-    for (const node of nodes) {
-      peak = Math.max(peak, node.aggregate.hotness)
-      walk(node.children)
-    }
-  }
-
-  walk(tree)
-
-  return peak
-}

ui-tui/src/theme.ts

@@ -94,12 +94,7 @@ export const DARK_THEME: Theme = {
     amber: '#FFBF00',
     bronze: '#CD7F32',
     cornsilk: '#FFF8DC',
-    // Bumped from the old `#B8860B` darkgoldenrod (~53% luminance) which
-    // read as barely-visible on dark terminals for long body text.  The
-    // new value sits ~60% luminance — readable without losing the "muted /
-    // secondary" semantic.  Field labels still use `label` (65%) which
-    // stays brighter so hierarchy holds.
-    dim: '#CC9B1F',
+    dim: '#B8860B',
     completionBg: '#FFFFFF',
     completionCurrentBg: mix('#FFFFFF', '#FFBF00', 0.25),
 
@@ -109,11 +104,8 @@ export const DARK_THEME: Theme = {
     warn: '#ffa726',
 
     prompt: '#FFF8DC',
-    // sessionLabel/sessionBorder intentionally track the `dim` value — they
-    // are "same role, same colour" by design.  fromSkin's banner_dim fallback
-    // relies on this pairing (#11300).
-    sessionLabel: '#CC9B1F',
-    sessionBorder: '#CC9B1F',
+    sessionLabel: '#B8860B',
+    sessionBorder: '#B8860B',
 
     statusBg: '#1a1a2e',
     statusFg: '#C0C0C0',

ui-tui/src/types.ts

@@ -12,72 +12,16 @@ export interface ActivityItem {
 }
 
 export interface SubagentProgress {
-  apiCalls?: number
-  costUsd?: number
-  depth: number
   durationSeconds?: number
-  filesRead?: string[]
-  filesWritten?: string[]
   goal: string
   id: string
   index: number
-  inputTokens?: number
-  iteration?: number
-  model?: string
   notes: string[]
-  outputTail?: SubagentOutputEntry[]
-  outputTokens?: number
-  parentId: null | string
-  reasoningTokens?: number
-  startedAt?: number
-  status: 'completed' | 'failed' | 'interrupted' | 'queued' | 'running'
+  status: 'completed' | 'failed' | 'interrupted' | 'running'
   summary?: string
   taskCount: number
   thinking: string[]
-  toolCount: number
   tools: string[]
-  toolsets?: string[]
-}
-
-export interface SubagentOutputEntry {
-  isError: boolean
-  preview: string
-  tool: string
-}
-
-export interface SubagentNode {
-  aggregate: SubagentAggregate
-  children: SubagentNode[]
-  item: SubagentProgress
-}
-
-export interface SubagentAggregate {
-  activeCount: number
-  costUsd: number
-  descendantCount: number
-  filesTouched: number
-  hotness: number
-  inputTokens: number
-  maxDepthFromHere: number
-  outputTokens: number
-  totalDuration: number
-  totalTools: number
-}
-
-export interface DelegationStatus {
-  active: {
-    depth?: number
-    goal?: string
-    model?: null | string
-    parent_id?: null | string
-    started_at?: number
-    status?: string
-    subagent_id?: string
-    tool_count?: number
-  }[]
-  max_concurrent_children?: number
-  max_spawn_depth?: number
-  paused: boolean
 }
 
 export interface ApprovalReq {

website/docs/integrations/providers.md

@@ -30,6 +30,8 @@ You need at least one way to connect to an LLM. Use `hermes model` to switch pro
 | **Alibaba Cloud** | `DASHSCOPE_API_KEY` in `~/.hermes/.env` (provider: `alibaba`, aliases: `dashscope`, `qwen`) |
 | **Kilo Code** | `KILOCODE_API_KEY` in `~/.hermes/.env` (provider: `kilocode`) |
 | **Xiaomi MiMo** | `XIAOMI_API_KEY` in `~/.hermes/.env` (provider: `xiaomi`, aliases: `mimo`, `xiaomi-mimo`) |
+| **Volcengine** | `hermes model` or `VOLCENGINE_API_KEY` in `~/.hermes/.env` (provider: `volcengine`) |
+| **BytePlus** | `hermes model` or `BYTEPLUS_API_KEY` in `~/.hermes/.env` (provider: `byteplus`) |
 | **OpenCode Zen** | `OPENCODE_ZEN_API_KEY` in `~/.hermes/.env` (provider: `opencode-zen`) |
 | **OpenCode Go** | `OPENCODE_GO_API_KEY` in `~/.hermes/.env` (provider: `opencode-go`) |
 | **DeepSeek** | `DEEPSEEK_API_KEY` in `~/.hermes/.env` (provider: `deepseek`) |
@@ -274,17 +276,59 @@ hermes chat --provider xiaomi --model mimo-v2-pro
 # Arcee AI (Trinity models)
 hermes chat --provider arcee --model trinity-large-thinking
 # Requires: ARCEEAI_API_KEY in ~/.hermes/.env
+
+# Volcengine
+hermes chat --provider volcengine --model volcengine/doubao-seed-2-0-pro-260215
+# Requires: VOLCENGINE_API_KEY in ~/.hermes/.env
+
+# Volcengine Coding Plan catalog (same provider, same API key)
+hermes chat --provider volcengine --model volcengine-coding-plan/doubao-seed-2.0-code
+
+# BytePlus
+hermes chat --provider byteplus --model byteplus/seed-2-0-pro-260328
+# Requires: BYTEPLUS_API_KEY in ~/.hermes/.env
+
+# BytePlus Coding Plan catalog (same provider, same API key)
+hermes chat --provider byteplus --model byteplus-coding-plan/dola-seed-2.0-pro
 ```
 
 Or set the provider permanently in `config.yaml`:
 ```yaml
 model:
-  provider: "zai"       # or: kimi-coding, kimi-coding-cn, minimax, minimax-cn, alibaba, xiaomi, arcee
+  provider: "zai"       # or: kimi-coding, kimi-coding-cn, minimax, minimax-cn, alibaba, xiaomi, arcee, volcengine, byteplus
   default: "glm-5"
 ```
 
 Base URLs can be overridden with `GLM_BASE_URL`, `KIMI_BASE_URL`, `MINIMAX_BASE_URL`, `MINIMAX_CN_BASE_URL`, `DASHSCOPE_BASE_URL`, or `XIAOMI_BASE_URL` environment variables.
 
+### Volcengine and BytePlus Contract Catalogs
+
+Hermes exposes **two** built-in providers for these integrations:
+
+- `volcengine`
+- `byteplus`
+
+Each provider includes both its standard catalog and its Coding Plan catalog. The selected model ID determines the runtime base URL automatically:
+
+- `volcengine/...` -> `https://ark.cn-beijing.volces.com/api/v3`
+- `volcengine-coding-plan/...` -> `https://ark.cn-beijing.volces.com/api/coding/v3`
+- `byteplus/...` -> `https://ark.ap-southeast.bytepluses.com/api/v3`
+- `byteplus-coding-plan/...` -> `https://ark.ap-southeast.bytepluses.com/api/coding/v3`
+
+In `hermes model`, the setup flow is:
+
+1. Enter API key
+2. Select a model
+
+If you pick a `volcengine-coding-plan/...` or `byteplus-coding-plan/...` model, Hermes automatically uses the corresponding coding-plan base URL.
+
+The API key is shared per provider:
+
+- `VOLCENGINE_API_KEY` works for both `volcengine/...` and `volcengine-coding-plan/...`
+- `BYTEPLUS_API_KEY` works for both `byteplus/...` and `byteplus-coding-plan/...`
+
+Use `hermes model` to pick from the built-in curated catalogs. Hermes saves the canonical prefixed model ID in `config.yaml`, so standard and Coding Plan variants remain unambiguous.
+
 :::note Z.AI Endpoint Auto-Detection
 When using the Z.AI / GLM provider, Hermes automatically probes multiple endpoints (global, China, coding variants) to find one that accepts your API key. You don't need to set `GLM_BASE_URL` manually — the working endpoint is detected and cached automatically.
 :::

website/docs/reference/environment-variables.md

@@ -44,6 +44,8 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `KILOCODE_BASE_URL` | Override Kilo Code base URL (default: `https://api.kilo.ai/api/gateway`) |
 | `XIAOMI_API_KEY` | Xiaomi MiMo API key ([platform.xiaomimimo.com](https://platform.xiaomimimo.com)) |
 | `XIAOMI_BASE_URL` | Override Xiaomi MiMo base URL (default: `https://api.xiaomimimo.com/v1`) |
+| `VOLCENGINE_API_KEY` | Volcengine API key for Doubao / Seed models ([volcengine.com/product/ark](https://www.volcengine.com/product/ark)) |
+| `BYTEPLUS_API_KEY` | BytePlus API key for Seed / Dola models ([byteplus.com/en/product/modelark](https://www.byteplus.com/en/product/modelark)) |
 | `HF_TOKEN` | Hugging Face token for Inference Providers ([huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)) |
 | `HF_BASE_URL` | Override Hugging Face base URL (default: `https://router.huggingface.co/v1`) |
 | `GOOGLE_API_KEY` | Google AI Studio API key ([aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey)) |

website/docs/user-guide/configuration.md

@@ -628,7 +628,7 @@ Every model slot in Hermes — auxiliary tasks, compression, fallback — uses t
 
 When `base_url` is set, Hermes ignores the provider and calls that endpoint directly (using `api_key` or `OPENAI_API_KEY` for auth). When only `provider` is set, Hermes uses that provider's built-in auth and base URL.
 
-Available providers for auxiliary tasks: `auto`, `main`, plus any provider in the [provider registry](/docs/reference/environment-variables) — `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `gemini`, `google-gemini-cli`, `qwen-oauth`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `deepseek`, `nvidia`, `xai`, `ollama-cloud`, `alibaba`, `bedrock`, `huggingface`, `arcee`, `xiaomi`, `kilocode`, `opencode-zen`, `opencode-go`, `ai-gateway` — or any named custom provider from your `custom_providers` list (e.g. `provider: "beans"`).
+Available providers for auxiliary tasks: `auto`, `main`, plus any provider in the [provider registry](/docs/reference/environment-variables) — `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `gemini`, `google-gemini-cli`, `qwen-oauth`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `deepseek`, `nvidia`, `xai`, `ollama-cloud`, `alibaba`, `bedrock`, `huggingface`, `arcee`, `xiaomi`, `volcengine`, `byteplus`, `kilocode`, `opencode-zen`, `opencode-go`, `ai-gateway` — or any named custom provider from your `custom_providers` list (e.g. `provider: "beans"`).
 
 :::warning `"main"` is for auxiliary tasks only
 The `"main"` provider option means "use whatever provider my main agent uses" — it's only valid inside `auxiliary:`, `compression:`, and `fallback_model:` configs. It is **not** a valid value for your top-level `model.provider` setting. If you use a custom OpenAI-compatible endpoint, set `provider: custom` in your `model:` section. See [AI Providers](/docs/integrations/providers) for all main model provider options.

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

@@ -58,6 +58,8 @@ Both `provider` and `model` are **required**. If either is missing, the fallback
 | OpenCode Go | `opencode-go` | `OPENCODE_GO_API_KEY` |
 | Kilo Code | `kilocode` | `KILOCODE_API_KEY` |
 | Xiaomi MiMo | `xiaomi` | `XIAOMI_API_KEY` |
+| Volcengine | `volcengine` | `VOLCENGINE_API_KEY` |
+| BytePlus | `byteplus` | `BYTEPLUS_API_KEY` |
 | Arcee AI | `arcee` | `ARCEEAI_API_KEY` |
 | Alibaba / DashScope | `alibaba` | `DASHSCOPE_API_KEY` |
 | Hugging Face | `huggingface` | `HF_TOKEN` |