Merge branch 'main' of github.com:NousResearch/hermes-agent into feat/ink-refactor

agent/anthropic_adapter.py

@@ -298,6 +298,33 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     return _anthropic_sdk.Anthropic(**kwargs)
 
 
+def build_anthropic_bedrock_client(region: str):
+    """Create an AnthropicBedrock client for Bedrock Claude models.
+
+    Uses the Anthropic SDK's native Bedrock adapter, which provides full
+    Claude feature parity: prompt caching, thinking budgets, adaptive
+    thinking, fast mode — features not available via the Converse API.
+
+    Auth uses the boto3 default credential chain (IAM roles, SSO, env vars).
+    """
+    if _anthropic_sdk is None:
+        raise ImportError(
+            "The 'anthropic' package is required for the Bedrock provider. "
+            "Install it with: pip install 'anthropic>=0.39.0'"
+        )
+    if not hasattr(_anthropic_sdk, "AnthropicBedrock"):
+        raise ImportError(
+            "anthropic.AnthropicBedrock not available. "
+            "Upgrade with: pip install 'anthropic>=0.39.0'"
+        )
+    from httpx import Timeout
+
+    return _anthropic_sdk.AnthropicBedrock(
+        aws_region=region,
+        timeout=Timeout(timeout=900.0, connect=10.0),
+    )
+
+
 def read_claude_code_credentials() -> Optional[Dict[str, Any]]:
     """Read refreshable Claude Code OAuth credentials from ~/.claude/.credentials.json.
 

agent/auxiliary_client.py

@@ -775,6 +775,21 @@ def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
 
 
 def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
+    # Check cross-session rate limit guard before attempting Nous —
+    # if another session already recorded a 429, skip Nous entirely
+    # to avoid piling more requests onto the tapped RPH bucket.
+    try:
+        from agent.nous_rate_guard import nous_rate_limit_remaining
+        _remaining = nous_rate_limit_remaining()
+        if _remaining is not None and _remaining > 0:
+            logger.debug(
+                "Auxiliary: skipping Nous Portal (rate-limited, resets in %.0fs)",
+                _remaining,
+            )
+            return None, None
+    except Exception:
+        pass
+
     nous = _read_nous_auth()
     if not nous:
         return None, None
@@ -899,6 +914,51 @@ def _current_custom_base_url() -> str:
     return custom_base or ""
 
 
+def _validate_proxy_env_urls() -> None:
+    """Fail fast with a clear error when proxy env vars have malformed URLs.
+
+    Common cause: shell config (e.g. .zshrc) with a typo like
+    ``export HTTP_PROXY=http://127.0.0.1:6153export NEXT_VAR=...``
+    which concatenates 'export' into the port number.  Without this
+    check the OpenAI/httpx client raises a cryptic ``Invalid port``
+    error that doesn't name the offending env var.
+    """
+    from urllib.parse import urlparse
+
+    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY",
+                "https_proxy", "http_proxy", "all_proxy"):
+        value = str(os.environ.get(key) or "").strip()
+        if not value:
+            continue
+        try:
+            parsed = urlparse(value)
+            if parsed.scheme:
+                _ = parsed.port          # raises ValueError for e.g. '6153export'
+        except ValueError as exc:
+            raise RuntimeError(
+                f"Malformed proxy environment variable {key}={value!r}. "
+                "Fix or unset your proxy settings and try again."
+            ) from exc
+
+
+def _validate_base_url(base_url: str) -> None:
+    """Reject obviously broken custom endpoint URLs before they reach httpx."""
+    from urllib.parse import urlparse
+
+    candidate = str(base_url or "").strip()
+    if not candidate or candidate.startswith("acp://"):
+        return
+    try:
+        parsed = urlparse(candidate)
+        if parsed.scheme in {"http", "https"}:
+            _ = parsed.port              # raises ValueError for malformed ports
+    except ValueError as exc:
+        raise RuntimeError(
+            f"Malformed custom endpoint URL: {candidate!r}. "
+            "Run `hermes setup` or `hermes model` and enter a valid http(s) base URL."
+        ) from exc
+
+
 def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:
     runtime = _resolve_custom_runtime()
     if len(runtime) == 2:
@@ -1299,6 +1359,7 @@ def resolve_provider_client(
     Returns:
         (client, resolved_model) or (None, None) if auth is unavailable.
     """
+    _validate_proxy_env_urls()
     # Normalise aliases
     provider = _normalize_aux_provider(provider)
 

agent/error_classifier.py

@@ -112,6 +112,10 @@ _RATE_LIMIT_PATTERNS = [
     "please retry after",
     "resource_exhausted",
     "rate increased too quickly",  # Alibaba/DashScope throttling
+    # AWS Bedrock throttling
+    "throttlingexception",
+    "too many concurrent requests",
+    "servicequotaexceededexception",
 ]
 
 # Usage-limit patterns that need disambiguation (could be billing OR rate_limit)
@@ -171,6 +175,11 @@ _CONTEXT_OVERFLOW_PATTERNS = [
     # Chinese error messages (some providers return these)
     "超过最大长度",
     "上下文长度",
+    # AWS Bedrock Converse API error patterns
+    "input is too long",
+    "max input token",
+    "input token",
+    "exceeds the maximum number of input tokens",
 ]
 
 # Model not found patterns

agent/model_metadata.py

@@ -1012,6 +1012,16 @@ def get_model_context_length(
         if ctx:
             return ctx
 
+    # 4b. AWS Bedrock — use static context length table.
+    # Bedrock's ListFoundationModels doesn't expose context window sizes,
+    # so we maintain a curated table in bedrock_adapter.py.
+    if provider == "bedrock" or (base_url and "bedrock-runtime" in base_url):
+        try:
+            from agent.bedrock_adapter import get_bedrock_context_length
+            return get_bedrock_context_length(model)
+        except ImportError:
+            pass  # boto3 not installed — fall through to generic resolution
+
     # 5. Provider-aware lookups (before generic OpenRouter cache)
     # These are provider-specific and take priority over the generic OR cache,
     # since the same model can have different context limits per provider

agent/nous_rate_guard.py

@@ -0,0 +1,182 @@
+"""Cross-session rate limit guard for Nous Portal.
+
+Writes rate limit state to a shared file so all sessions (CLI, gateway,
+cron, auxiliary) can check whether Nous Portal is currently rate-limited
+before making requests.  Prevents retry amplification when RPH is tapped.
+
+Each 429 from Nous triggers up to 9 API calls per conversation turn
+(3 SDK retries x 3 Hermes retries), and every one of those calls counts
+against RPH.  By recording the rate limit state on first 429 and checking
+it before subsequent attempts, we eliminate the amplification effect.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import tempfile
+import time
+from typing import Any, Mapping, Optional
+
+logger = logging.getLogger(__name__)
+
+_STATE_SUBDIR = "rate_limits"
+_STATE_FILENAME = "nous.json"
+
+
+def _state_path() -> str:
+    """Return the path to the Nous rate limit state file."""
+    try:
+        from hermes_constants import get_hermes_home
+        base = get_hermes_home()
+    except ImportError:
+        base = os.path.join(os.path.expanduser("~"), ".hermes")
+    return os.path.join(base, _STATE_SUBDIR, _STATE_FILENAME)
+
+
+def _parse_reset_seconds(headers: Optional[Mapping[str, str]]) -> Optional[float]:
+    """Extract the best available reset-time estimate from response headers.
+
+    Priority:
+      1. x-ratelimit-reset-requests-1h  (hourly RPH window — most useful)
+      2. x-ratelimit-reset-requests     (per-minute RPM window)
+      3. retry-after                     (generic HTTP header)
+
+    Returns seconds-from-now, or None if no usable header found.
+    """
+    if not headers:
+        return None
+
+    lowered = {k.lower(): v for k, v in headers.items()}
+
+    for key in (
+        "x-ratelimit-reset-requests-1h",
+        "x-ratelimit-reset-requests",
+        "retry-after",
+    ):
+        raw = lowered.get(key)
+        if raw is not None:
+            try:
+                val = float(raw)
+                if val > 0:
+                    return val
+            except (TypeError, ValueError):
+                pass
+
+    return None
+
+
+def record_nous_rate_limit(
+    *,
+    headers: Optional[Mapping[str, str]] = None,
+    error_context: Optional[dict[str, Any]] = None,
+    default_cooldown: float = 300.0,
+) -> None:
+    """Record that Nous Portal is rate-limited.
+
+    Parses the reset time from response headers or error context.
+    Falls back to ``default_cooldown`` (5 minutes) if no reset info
+    is available.  Writes to a shared file that all sessions can read.
+
+    Args:
+        headers: HTTP response headers from the 429 error.
+        error_context: Structured error context from _extract_api_error_context().
+        default_cooldown: Fallback cooldown in seconds when no header data.
+    """
+    now = time.time()
+    reset_at = None
+
+    # Try headers first (most accurate)
+    header_seconds = _parse_reset_seconds(headers)
+    if header_seconds is not None:
+        reset_at = now + header_seconds
+
+    # Try error_context reset_at (from body parsing)
+    if reset_at is None and isinstance(error_context, dict):
+        ctx_reset = error_context.get("reset_at")
+        if isinstance(ctx_reset, (int, float)) and ctx_reset > now:
+            reset_at = float(ctx_reset)
+
+    # Default cooldown
+    if reset_at is None:
+        reset_at = now + default_cooldown
+
+    path = _state_path()
+    try:
+        state_dir = os.path.dirname(path)
+        os.makedirs(state_dir, exist_ok=True)
+
+        state = {
+            "reset_at": reset_at,
+            "recorded_at": now,
+            "reset_seconds": reset_at - now,
+        }
+
+        # Atomic write: write to temp file + rename
+        fd, tmp_path = tempfile.mkstemp(dir=state_dir, suffix=".tmp")
+        try:
+            with os.fdopen(fd, "w") as f:
+                json.dump(state, f)
+            os.replace(tmp_path, path)
+        except Exception:
+            # Clean up temp file on failure
+            try:
+                os.unlink(tmp_path)
+            except OSError:
+                pass
+            raise
+
+        logger.info(
+            "Nous rate limit recorded: resets in %.0fs (at %.0f)",
+            reset_at - now, reset_at,
+        )
+    except Exception as exc:
+        logger.debug("Failed to write Nous rate limit state: %s", exc)
+
+
+def nous_rate_limit_remaining() -> Optional[float]:
+    """Check if Nous Portal is currently rate-limited.
+
+    Returns:
+        Seconds remaining until reset, or None if not rate-limited.
+    """
+    path = _state_path()
+    try:
+        with open(path) as f:
+            state = json.load(f)
+        reset_at = state.get("reset_at", 0)
+        remaining = reset_at - time.time()
+        if remaining > 0:
+            return remaining
+        # Expired — clean up
+        try:
+            os.unlink(path)
+        except OSError:
+            pass
+        return None
+    except (FileNotFoundError, json.JSONDecodeError, KeyError, TypeError):
+        return None
+
+
+def clear_nous_rate_limit() -> None:
+    """Clear the rate limit state (e.g., after a successful Nous request)."""
+    try:
+        os.unlink(_state_path())
+    except FileNotFoundError:
+        pass
+    except OSError as exc:
+        logger.debug("Failed to clear Nous rate limit state: %s", exc)
+
+
+def format_remaining(seconds: float) -> str:
+    """Format seconds remaining into human-readable duration."""
+    s = max(0, int(seconds))
+    if s < 60:
+        return f"{s}s"
+    if s < 3600:
+        m, sec = divmod(s, 60)
+        return f"{m}m {sec}s" if sec else f"{m}m"
+    h, remainder = divmod(s, 3600)
+    m = remainder // 60
+    return f"{h}h {m}m" if m else f"{h}h"

agent/redact.py

@@ -93,6 +93,17 @@ _DB_CONNSTR_RE = re.compile(
     re.IGNORECASE,
 )
 
+# JWT tokens: header.payload[.signature] — always start with "eyJ" (base64 for "{")
+# Matches 1-part (header only), 2-part (header.payload), and full 3-part JWTs.
+_JWT_RE = re.compile(
+    r"eyJ[A-Za-z0-9_-]{10,}"           # Header (always starts with eyJ)
+    r"(?:\.[A-Za-z0-9_=-]{4,}){0,2}"   # Optional payload and/or signature
+)
+
+# Discord user/role mentions: <@123456789012345678> or <@!123456789012345678>
+# Snowflake IDs are 17-20 digit integers that resolve to specific Discord accounts.
+_DISCORD_MENTION_RE = re.compile(r"<@!?(\d{17,20})>")
+
 # E.164 phone numbers: +<country><number>, 7-15 digits
 # Negative lookahead prevents matching hex strings or identifiers
 _SIGNAL_PHONE_RE = re.compile(r"(\+[1-9]\d{6,14})(?![A-Za-z0-9])")
@@ -159,6 +170,12 @@ def redact_sensitive_text(text: str) -> str:
     # Database connection string passwords
     text = _DB_CONNSTR_RE.sub(lambda m: f"{m.group(1)}***{m.group(3)}", text)
 
+    # JWT tokens (eyJ... — base64-encoded JSON headers)
+    text = _JWT_RE.sub(lambda m: _mask_token(m.group(0)), text)
+
+    # Discord user/role mentions (<@snowflake_id>)
+    text = _DISCORD_MENTION_RE.sub(lambda m: f"<@{'!' if '!' in m.group(0) else ''}***>", text)
+
     # E.164 phone numbers (Signal, WhatsApp)
     def _redact_phone(m):
         phone = m.group(1)

agent/usage_pricing.py

@@ -284,6 +284,80 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://ai.google.dev/pricing",
         pricing_version="google-pricing-2026-03-16",
     ),
+    # AWS Bedrock — pricing per the Bedrock pricing page.
+    # Bedrock charges the same per-token rates as the model provider but
+    # through AWS billing.  These are the on-demand prices (no commitment).
+    # Source: https://aws.amazon.com/bedrock/pricing/
+    (
+        "bedrock",
+        "anthropic.claude-opus-4-6",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("15.00"),
+        output_cost_per_million=Decimal("75.00"),
+        source="official_docs_snapshot",
+        source_url="https://aws.amazon.com/bedrock/pricing/",
+        pricing_version="bedrock-pricing-2026-04",
+    ),
+    (
+        "bedrock",
+        "anthropic.claude-sonnet-4-6",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("3.00"),
+        output_cost_per_million=Decimal("15.00"),
+        source="official_docs_snapshot",
+        source_url="https://aws.amazon.com/bedrock/pricing/",
+        pricing_version="bedrock-pricing-2026-04",
+    ),
+    (
+        "bedrock",
+        "anthropic.claude-sonnet-4-5",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("3.00"),
+        output_cost_per_million=Decimal("15.00"),
+        source="official_docs_snapshot",
+        source_url="https://aws.amazon.com/bedrock/pricing/",
+        pricing_version="bedrock-pricing-2026-04",
+    ),
+    (
+        "bedrock",
+        "anthropic.claude-haiku-4-5",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.80"),
+        output_cost_per_million=Decimal("4.00"),
+        source="official_docs_snapshot",
+        source_url="https://aws.amazon.com/bedrock/pricing/",
+        pricing_version="bedrock-pricing-2026-04",
+    ),
+    (
+        "bedrock",
+        "amazon.nova-pro",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.80"),
+        output_cost_per_million=Decimal("3.20"),
+        source="official_docs_snapshot",
+        source_url="https://aws.amazon.com/bedrock/pricing/",
+        pricing_version="bedrock-pricing-2026-04",
+    ),
+    (
+        "bedrock",
+        "amazon.nova-lite",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.06"),
+        output_cost_per_million=Decimal("0.24"),
+        source="official_docs_snapshot",
+        source_url="https://aws.amazon.com/bedrock/pricing/",
+        pricing_version="bedrock-pricing-2026-04",
+    ),
+    (
+        "bedrock",
+        "amazon.nova-micro",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.035"),
+        output_cost_per_million=Decimal("0.14"),
+        source="official_docs_snapshot",
+        source_url="https://aws.amazon.com/bedrock/pricing/",
+        pricing_version="bedrock-pricing-2026-04",
+    ),
 }
 
 

gateway/config.py

@@ -554,6 +554,12 @@ def load_gateway_config() -> GatewayConfig:
                     bridged["mention_patterns"] = platform_cfg["mention_patterns"]
                 if plat == Platform.DISCORD and "channel_skill_bindings" in platform_cfg:
                     bridged["channel_skill_bindings"] = platform_cfg["channel_skill_bindings"]
+                if "channel_prompts" in platform_cfg:
+                    channel_prompts = platform_cfg["channel_prompts"]
+                    if isinstance(channel_prompts, dict):
+                        bridged["channel_prompts"] = {str(k): v for k, v in channel_prompts.items()}
+                    else:
+                        bridged["channel_prompts"] = channel_prompts
                 if not bridged:
                     continue
                 plat_data = platforms_data.setdefault(plat.value, {})

gateway/platforms/base.py

@@ -683,6 +683,10 @@ class MessageEvent:
     # Discord channel_skill_bindings).  A single name or ordered list.
     auto_skill: Optional[str | list[str]] = None
 
+    # Per-channel ephemeral system prompt (e.g. Discord channel_prompts).
+    # Applied at API call time and never persisted to transcript history.
+    channel_prompt: Optional[str] = None
+    
     # Internal flag — set for synthetic events (e.g. background process
     # completion notifications) that must bypass user authorization checks.
     internal: bool = False
@@ -776,6 +780,36 @@ _RETRYABLE_ERROR_PATTERNS = (
 MessageHandler = Callable[[MessageEvent], Awaitable[Optional[str]]]
 
 
+def resolve_channel_prompt(
+    config_extra: dict,
+    channel_id: str,
+    parent_id: str | None = None,
+) -> str | None:
+    """Resolve a per-channel ephemeral prompt from platform config.
+
+    Looks up ``channel_prompts`` in the adapter's ``config.extra`` dict.
+    Prefers an exact match on *channel_id*; falls back to *parent_id*
+    (useful for forum threads / child channels inheriting a parent prompt).
+
+    Returns the prompt string, or None if no match is found.  Blank/whitespace-
+    only prompts are treated as absent.
+    """
+    prompts = config_extra.get("channel_prompts") or {}
+    if not isinstance(prompts, dict):
+        return None
+
+    for key in (channel_id, parent_id):
+        if not key:
+            continue
+        prompt = prompts.get(key)
+        if prompt is None:
+            continue
+        prompt = str(prompt).strip()
+        if prompt:
+            return prompt
+    return None
+
+
 class BasePlatformAdapter(ABC):
     """
     Base class for platform adapters.

gateway/platforms/discord.py

@@ -1992,11 +1992,14 @@ class DiscordAdapter(BasePlatformAdapter):
         )
 
         msg_type = MessageType.COMMAND if text.startswith("/") else MessageType.TEXT
+        channel_id = str(interaction.channel_id)
+        parent_id = str(getattr(getattr(interaction, "channel", None), "parent_id", "") or "")
         return MessageEvent(
             text=text,
             message_type=msg_type,
             source=source,
             raw_message=interaction,
+            channel_prompt=self._resolve_channel_prompt(channel_id, parent_id or None),
         )
 
     # ------------------------------------------------------------------
@@ -2067,14 +2070,17 @@ class DiscordAdapter(BasePlatformAdapter):
             chat_topic=chat_topic,
         )
 
-        _parent_id = str(getattr(getattr(interaction, "channel", None), "parent_id", "") or "")
+        _parent_channel = self._thread_parent_channel(getattr(interaction, "channel", None))
+        _parent_id = str(getattr(_parent_channel, "id", "") or "")
         _skills = self._resolve_channel_skills(thread_id, _parent_id or None)
+        _channel_prompt = self._resolve_channel_prompt(thread_id, _parent_id or None)
         event = MessageEvent(
             text=text,
             message_type=MessageType.TEXT,
             source=source,
             raw_message=interaction,
             auto_skill=_skills,
+            channel_prompt=_channel_prompt,
         )
         await self.handle_message(event)
 
@@ -2103,6 +2109,11 @@ class DiscordAdapter(BasePlatformAdapter):
                     return list(dict.fromkeys(skills))  # dedup, preserve order
         return None
 
+    def _resolve_channel_prompt(self, channel_id: str, parent_id: str | None = None) -> str | None:
+        """Resolve a Discord per-channel prompt, preferring the exact channel over its parent."""
+        from gateway.platforms.base import resolve_channel_prompt
+        return resolve_channel_prompt(self.config.extra, channel_id, parent_id)
+
     def _thread_parent_channel(self, channel: Any) -> Any:
         """Return the parent text channel when invoked from a thread."""
         return getattr(channel, "parent", None) or channel
@@ -2654,6 +2665,7 @@ class DiscordAdapter(BasePlatformAdapter):
         _parent_id = str(getattr(_chan, "parent_id", "") or "")
         _chan_id = str(getattr(_chan, "id", ""))
         _skills = self._resolve_channel_skills(_chan_id, _parent_id or None)
+        _channel_prompt = self._resolve_channel_prompt(_chan_id, _parent_id or None)
 
         reply_to_id = None
         reply_to_text = None
@@ -2674,6 +2686,7 @@ class DiscordAdapter(BasePlatformAdapter):
             reply_to_text=reply_to_text,
             timestamp=message.created_at,
             auto_skill=_skills,
+            channel_prompt=_channel_prompt,
         )
 
         # Track thread participation so the bot won't require @mention for

gateway/platforms/mattermost.py

@@ -718,6 +718,12 @@ class MattermostAdapter(BasePlatformAdapter):
             thread_id=thread_id,
         )
 
+        # Per-channel ephemeral prompt
+        from gateway.platforms.base import resolve_channel_prompt
+        _channel_prompt = resolve_channel_prompt(
+            self.config.extra, channel_id, None,
+        )
+
         msg_event = MessageEvent(
             text=message_text,
             message_type=msg_type,
@@ -726,6 +732,7 @@ class MattermostAdapter(BasePlatformAdapter):
             message_id=post_id,
             media_urls=media_urls if media_urls else None,
             media_types=media_types if media_types else None,
+            channel_prompt=_channel_prompt,
         )
 
         await self.handle_message(msg_event)

gateway/platforms/slack.py

@@ -1167,6 +1167,12 @@ class SlackAdapter(BasePlatformAdapter):
             thread_id=thread_ts,
         )
 
+        # Per-channel ephemeral prompt
+        from gateway.platforms.base import resolve_channel_prompt
+        _channel_prompt = resolve_channel_prompt(
+            self.config.extra, channel_id, None,
+        )
+
         msg_event = MessageEvent(
             text=text,
             message_type=msg_type,
@@ -1176,6 +1182,7 @@ class SlackAdapter(BasePlatformAdapter):
             media_urls=media_urls,
             media_types=media_types,
             reply_to_message_id=thread_ts if thread_ts != ts else None,
+            channel_prompt=_channel_prompt,
         )
 
         # Only react when bot is directly addressed (DM or @mention).

gateway/platforms/telegram.py

@@ -2775,6 +2775,15 @@ class TelegramAdapter(BasePlatformAdapter):
             reply_to_id = str(message.reply_to_message.message_id)
             reply_to_text = message.reply_to_message.text or message.reply_to_message.caption or None
 
+        # Per-channel/topic ephemeral prompt
+        from gateway.platforms.base import resolve_channel_prompt
+        _chat_id_str = str(chat.id)
+        _channel_prompt = resolve_channel_prompt(
+            self.config.extra,
+            thread_id_str or _chat_id_str,
+            _chat_id_str if thread_id_str else None,
+        )
+
         return MessageEvent(
             text=message.text or "",
             message_type=msg_type,
@@ -2784,6 +2793,7 @@ class TelegramAdapter(BasePlatformAdapter):
             reply_to_message_id=reply_to_id,
             reply_to_text=reply_to_text,
             auto_skill=topic_skill,
+            channel_prompt=_channel_prompt,
             timestamp=message.date,
         )
 

gateway/run.py

@@ -2891,6 +2891,7 @@ class GatewayRunner:
                         message_type=_MT.TEXT,
                         source=event.source,
                         message_id=event.message_id,
+                        channel_prompt=event.channel_prompt,
                     )
                     adapter._pending_messages[_quick_key] = queued_event
                 return "Queued for the next turn."
@@ -3875,6 +3876,7 @@ class GatewayRunner:
                 session_id=session_entry.session_id,
                 session_key=session_key,
                 event_message_id=event.message_id,
+                channel_prompt=event.channel_prompt,
             )
 
             # Stop persistent typing indicator now that the agent is done
@@ -5186,6 +5188,7 @@ class GatewayRunner:
             message_type=MessageType.TEXT,
             source=source,
             raw_message=event.raw_message,
+            channel_prompt=event.channel_prompt,
         )
         
         # Let the normal message handler process it
@@ -8166,6 +8169,7 @@ class GatewayRunner:
         session_key: str = None,
         _interrupt_depth: int = 0,
         event_message_id: Optional[str] = None,
+        channel_prompt: Optional[str] = None,
     ) -> Dict[str, Any]:
         """
         Run the agent with the given message and context.
@@ -8520,8 +8524,12 @@ class GatewayRunner:
             # Platform.LOCAL ("local") maps to "cli"; others pass through as-is.
             platform_key = "cli" if source.platform == Platform.LOCAL else source.platform.value
             
-            # Combine platform context with user-configured ephemeral system prompt
+            # Combine platform context, per-channel context, and the user-configured
+            # ephemeral system prompt.
             combined_ephemeral = context_prompt or ""
+            event_channel_prompt = (channel_prompt or "").strip()
+            if event_channel_prompt:
+                combined_ephemeral = (combined_ephemeral + "\n\n" + event_channel_prompt).strip()
             if self._ephemeral_system_prompt:
                 combined_ephemeral = (combined_ephemeral + "\n\n" + self._ephemeral_system_prompt).strip()
 
@@ -9473,6 +9481,7 @@ class GatewayRunner:
                     session_key=session_key,
                     _interrupt_depth=_interrupt_depth + 1,
                     event_message_id=next_message_id,
+                    channel_prompt=pending_event.channel_prompt,
                 )
         finally:
             # Stop progress sender, interrupt monitor, and notification task

hermes_cli/auth.py

@@ -274,6 +274,14 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("XIAOMI_API_KEY",),
         base_url_env_var="XIAOMI_BASE_URL",
     ),
+    "bedrock": ProviderConfig(
+        id="bedrock",
+        name="AWS Bedrock",
+        auth_type="aws_sdk",
+        inference_base_url="https://bedrock-runtime.us-east-1.amazonaws.com",
+        api_key_env_vars=(),
+        base_url_env_var="BEDROCK_BASE_URL",
+    ),
 }
 
 
@@ -924,6 +932,7 @@ def resolve_provider(
         "qwen-portal": "qwen-oauth", "qwen-cli": "qwen-oauth", "qwen-oauth": "qwen-oauth",
         "hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
         "mimo": "xiaomi", "xiaomi-mimo": "xiaomi",
+        "aws": "bedrock", "aws-bedrock": "bedrock", "amazon-bedrock": "bedrock", "amazon": "bedrock",
         "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
@@ -980,6 +989,15 @@ def resolve_provider(
             if has_usable_secret(os.getenv(env_var, "")):
                 return pid
 
+    # AWS Bedrock — detect via boto3 credential chain (IAM roles, SSO, env vars).
+    # This runs after API-key providers so explicit keys always win.
+    try:
+        from agent.bedrock_adapter import has_aws_credentials
+        if has_aws_credentials():
+            return "bedrock"
+    except ImportError:
+        pass  # boto3 not installed — skip Bedrock auto-detection
+
     raise AuthError(
         "No inference provider configured. Run 'hermes model' to choose a "
         "provider and model, or set an API key (OPENROUTER_API_KEY, "
@@ -2446,6 +2464,13 @@ def get_auth_status(provider_id: Optional[str] = None) -> Dict[str, Any]:
     pconfig = PROVIDER_REGISTRY.get(target)
     if pconfig and pconfig.auth_type == "api_key":
         return get_api_key_provider_status(target)
+    # AWS SDK providers (Bedrock) — check via boto3 credential chain
+    if pconfig and pconfig.auth_type == "aws_sdk":
+        try:
+            from agent.bedrock_adapter import has_aws_credentials
+            return {"logged_in": has_aws_credentials(), "provider": target}
+        except ImportError:
+            return {"logged_in": False, "provider": target, "error": "boto3 not installed"}
     return {"logged_in": False}
 
 

hermes_cli/auth_commands.py

@@ -368,6 +368,27 @@ def _interactive_auth() -> None:
     print("=" * 50)
 
     auth_list_command(SimpleNamespace(provider=None))
+
+    # Show AWS Bedrock credential status (not in the pool — uses boto3 chain)
+    try:
+        from agent.bedrock_adapter import has_aws_credentials, resolve_aws_auth_env_var, resolve_bedrock_region
+        if has_aws_credentials():
+            auth_source = resolve_aws_auth_env_var() or "unknown"
+            region = resolve_bedrock_region()
+            print(f"bedrock (AWS SDK credential chain):")
+            print(f"  Auth: {auth_source}")
+            print(f"  Region: {region}")
+            try:
+                import boto3
+                sts = boto3.client("sts", region_name=region)
+                identity = sts.get_caller_identity()
+                arn = identity.get("Arn", "unknown")
+                print(f"  Identity: {arn}")
+            except Exception:
+                print(f"  Identity: (could not resolve — boto3 STS call failed)")
+            print()
+    except ImportError:
+        pass  # boto3 or bedrock_adapter not available
     print()
 
     # Main menu

hermes_cli/config.py

@@ -419,6 +419,27 @@ DEFAULT_CONFIG = {
         "protect_last_n": 20,         # minimum recent messages to keep uncompressed
 
     },
+
+    # AWS Bedrock provider configuration.
+    # Only used when model.provider is "bedrock".
+    "bedrock": {
+        "region": "",  # AWS region for Bedrock API calls (empty = AWS_REGION env var → us-east-1)
+        "discovery": {
+            "enabled": True,           # Auto-discover models via ListFoundationModels
+            "provider_filter": [],     # Only show models from these providers (e.g. ["anthropic", "amazon"])
+            "refresh_interval": 3600,  # Cache discovery results for this many seconds
+        },
+        "guardrail": {
+            # Amazon Bedrock Guardrails — content filtering and safety policies.
+            # Create a guardrail in the Bedrock console, then set the ID and version here.
+            # See: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html
+            "guardrail_identifier": "",  # e.g. "abc123def456"
+            "guardrail_version": "",     # e.g. "1" or "DRAFT"
+            "stream_processing_mode": "async",  # "sync" or "async"
+            "trace": "disabled",         # "enabled", "disabled", or "enabled_full"
+        },
+    },
+
     "smart_model_routing": {
         "enabled": False,
         "max_simple_chars": 160,
@@ -638,6 +659,7 @@ DEFAULT_CONFIG = {
         "allowed_channels": "",        # If set, bot ONLY responds in these channel IDs (whitelist)
         "auto_thread": True,           # Auto-create threads on @mention in channels (like Slack)
         "reactions": True,             # Add 👀/✅/❌ reactions to messages during processing
+        "channel_prompts": {},         # Per-channel ephemeral system prompts (forum parents apply to child threads)
     },
 
     # WhatsApp platform settings (gateway mode)
@@ -648,6 +670,21 @@ DEFAULT_CONFIG = {
         # Supports \n for newlines, e.g. "🤖 *My Bot*\n──────\n"
     },
 
+    # Telegram platform settings (gateway mode)
+    "telegram": {
+        "channel_prompts": {},         # Per-chat/topic ephemeral system prompts (topics inherit from parent group)
+    },
+
+    # Slack platform settings (gateway mode)
+    "slack": {
+        "channel_prompts": {},         # Per-channel ephemeral system prompts
+    },
+
+    # Mattermost platform settings (gateway mode)
+    "mattermost": {
+        "channel_prompts": {},         # Per-channel ephemeral system prompts
+    },
+
     # Approval mode for dangerous commands:
     #   manual — always prompt the user (default)
     #   smart  — use auxiliary LLM to auto-approve low-risk commands, prompt for high-risk
@@ -703,7 +740,7 @@ DEFAULT_CONFIG = {
     },
 
     # Config schema version - bump this when adding new required fields
-    "_config_version": 17,
+    "_config_version": 18,
 }
 
 # =============================================================================
@@ -974,6 +1011,22 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
+    "AWS_REGION": {
+        "description": "AWS region for Bedrock API calls (e.g. us-east-1, eu-central-1)",
+        "prompt": "AWS Region",
+        "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-regions.html",
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
+    "AWS_PROFILE": {
+        "description": "AWS named profile for Bedrock authentication (from ~/.aws/credentials)",
+        "prompt": "AWS Profile",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
 
     # ── Tool API keys ──
     "EXA_API_KEY": {

hermes_cli/doctor.py

@@ -860,6 +860,31 @@ def run_doctor(args):
             except Exception as _e:
                 print(f"\r  {color('⚠', Colors.YELLOW)} {_label} {color(f'({_e})', Colors.DIM)}           ")
 
+    # -- AWS Bedrock --
+    # Bedrock uses the AWS SDK credential chain, not API keys.
+    try:
+        from agent.bedrock_adapter import has_aws_credentials, resolve_aws_auth_env_var, resolve_bedrock_region
+        if has_aws_credentials():
+            _auth_var = resolve_aws_auth_env_var()
+            _region = resolve_bedrock_region()
+            _label = "AWS Bedrock".ljust(20)
+            print(f"  Checking AWS Bedrock...", end="", flush=True)
+            try:
+                import boto3
+                _br_client = boto3.client("bedrock", region_name=_region)
+                _br_resp = _br_client.list_foundation_models()
+                _model_count = len(_br_resp.get("modelSummaries", []))
+                print(f"\r  {color('✓', Colors.GREEN)} {_label} {color(f'({_auth_var}, {_region}, {_model_count} models)', Colors.DIM)}           ")
+            except ImportError:
+                print(f"\r  {color('⚠', Colors.YELLOW)} {_label} {color('(boto3 not installed — pip install hermes-agent[bedrock])', Colors.DIM)}           ")
+                issues.append("Install boto3 for Bedrock: pip install hermes-agent[bedrock]")
+            except Exception as _e:
+                _err_name = type(_e).__name__
+                print(f"\r  {color('⚠', Colors.YELLOW)} {_label} {color(f'({_err_name}: {_e})', Colors.DIM)}           ")
+                issues.append(f"AWS Bedrock: {_err_name} — check IAM permissions for bedrock:ListFoundationModels")
+    except ImportError:
+        pass  # bedrock_adapter not available — skip silently
+
     # =========================================================================
     # Check: Submodules
     # =========================================================================

hermes_cli/gateway.py

@@ -222,7 +222,7 @@ def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = Fals
                     current_cmd = ""
         else:
             result = subprocess.run(
-                ["ps", "eww", "-ax", "-o", "pid=,command="],
+                ["ps", "-A", "eww", "-o", "pid=,command="],
                 capture_output=True,
                 text=True,
                 timeout=10,

hermes_cli/main.py

@@ -1370,6 +1370,8 @@ def select_provider_and_model(args=None):
         _model_flow_anthropic(config, current_model)
     elif selected_provider == "kimi-coding":
         _model_flow_kimi(config, current_model)
+    elif selected_provider == "bedrock":
+        _model_flow_bedrock(config, current_model)
     elif selected_provider in ("gemini", "deepseek", "xai", "zai", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface", "xiaomi", "arcee"):
         _model_flow_api_key_provider(config, selected_provider, current_model)
 
@@ -2656,6 +2658,252 @@ def _model_flow_kimi(config, current_model=""):
         print("No change.")
 
 
+def _model_flow_bedrock_api_key(config, region, current_model=""):
+    """Bedrock API Key mode — uses the OpenAI-compatible bedrock-mantle endpoint.
+
+    For developers who don't have an AWS account but received a Bedrock API Key
+    from their AWS admin. Works like any OpenAI-compatible endpoint.
+    """
+    from hermes_cli.auth import _prompt_model_selection, _save_model_choice, deactivate_provider
+    from hermes_cli.config import load_config, save_config, get_env_value, save_env_value
+    from hermes_cli.models import _PROVIDER_MODELS
+
+    mantle_base_url = f"https://bedrock-mantle.{region}.api.aws/v1"
+
+    # Prompt for API key
+    existing_key = get_env_value("AWS_BEARER_TOKEN_BEDROCK") or ""
+    if existing_key:
+        print(f"  Bedrock API Key: {existing_key[:12]}... ✓")
+    else:
+        print(f"  Endpoint: {mantle_base_url}")
+        print()
+        try:
+            import getpass
+            api_key = getpass.getpass("  Bedrock API Key: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            print()
+            return
+        if not api_key:
+            print("  Cancelled.")
+            return
+        save_env_value("AWS_BEARER_TOKEN_BEDROCK", api_key)
+        existing_key = api_key
+        print("  ✓ API key saved.")
+    print()
+
+    # Model selection — use static list (mantle doesn't need boto3 for discovery)
+    model_list = _PROVIDER_MODELS.get("bedrock", [])
+    print(f"  Showing {len(model_list)} curated models")
+
+    if model_list:
+        selected = _prompt_model_selection(model_list, current_model=current_model)
+    else:
+        try:
+            selected = input("  Model ID: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            selected = None
+
+    if selected:
+        _save_model_choice(selected)
+
+        # Save as custom provider pointing to bedrock-mantle
+        cfg = load_config()
+        model = cfg.get("model")
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = "custom"
+        model["base_url"] = mantle_base_url
+        model.pop("api_mode", None)  # chat_completions is the default
+
+        # Also save region in bedrock config for reference
+        bedrock_cfg = cfg.get("bedrock", {})
+        if not isinstance(bedrock_cfg, dict):
+            bedrock_cfg = {}
+        bedrock_cfg["region"] = region
+        cfg["bedrock"] = bedrock_cfg
+
+        # Save the API key env var name so hermes knows where to find it
+        save_env_value("OPENAI_API_KEY", existing_key)
+        save_env_value("OPENAI_BASE_URL", mantle_base_url)
+
+        save_config(cfg)
+        deactivate_provider()
+
+        print(f"  Default model set to: {selected} (via Bedrock API Key, {region})")
+        print(f"  Endpoint: {mantle_base_url}")
+    else:
+        print("  No change.")
+
+
+def _model_flow_bedrock(config, current_model=""):
+    """AWS Bedrock provider: verify credentials, pick region, discover models.
+
+    Uses the native Converse API via boto3 — not the OpenAI-compatible endpoint.
+    Auth is handled by the AWS SDK default credential chain (env vars, profile,
+    instance role), so no API key prompt is needed.
+    """
+    from hermes_cli.auth import _prompt_model_selection, _save_model_choice, deactivate_provider
+    from hermes_cli.config import load_config, save_config
+    from hermes_cli.models import _PROVIDER_MODELS
+
+    # 1. Check for AWS credentials
+    try:
+        from agent.bedrock_adapter import (
+            has_aws_credentials,
+            resolve_aws_auth_env_var,
+            resolve_bedrock_region,
+            discover_bedrock_models,
+        )
+    except ImportError:
+        print("  ✗ boto3 is not installed. Install it with:")
+        print("    pip install boto3")
+        print()
+        return
+
+    if not has_aws_credentials():
+        print("  ⚠ No AWS credentials detected via environment variables.")
+        print("  Bedrock will use boto3's default credential chain (IMDS, SSO, etc.)")
+        print()
+
+    auth_var = resolve_aws_auth_env_var()
+    if auth_var:
+        print(f"  AWS credentials: {auth_var} ✓")
+    else:
+        print("  AWS credentials: boto3 default chain (instance role / SSO)")
+    print()
+
+    # 2. Region selection
+    current_region = resolve_bedrock_region()
+    try:
+        region_input = input(f"  AWS Region [{current_region}]: ").strip()
+    except (KeyboardInterrupt, EOFError):
+        print()
+        return
+    region = region_input or current_region
+
+    # 2b. Authentication mode
+    print("  Choose authentication method:")
+    print()
+    print("    1. IAM credential chain (recommended)")
+    print("       Works with EC2 instance roles, SSO, env vars, aws configure")
+    print("    2. Bedrock API Key")
+    print("       Enter your Bedrock API Key directly — also supports")
+    print("       team scenarios where an admin distributes keys")
+    print()
+    try:
+        auth_choice = input("  Choice [1]: ").strip()
+    except (KeyboardInterrupt, EOFError):
+        print()
+        return
+
+    if auth_choice == "2":
+        _model_flow_bedrock_api_key(config, region, current_model)
+        return
+
+    # 3. Model discovery — try live API first, fall back to static list
+    print(f"  Discovering models in {region}...")
+    live_models = discover_bedrock_models(region)
+
+    if live_models:
+        _EXCLUDE_PREFIXES = (
+            "stability.", "cohere.embed", "twelvelabs.", "us.stability.",
+            "us.cohere.embed", "us.twelvelabs.", "global.cohere.embed",
+            "global.twelvelabs.",
+        )
+        _EXCLUDE_SUBSTRINGS = ("safeguard", "voxtral", "palmyra-vision")
+        filtered = []
+        for m in live_models:
+            mid = m["id"]
+            if any(mid.startswith(p) for p in _EXCLUDE_PREFIXES):
+                continue
+            if any(s in mid.lower() for s in _EXCLUDE_SUBSTRINGS):
+                continue
+            filtered.append(m)
+
+        # Deduplicate: prefer inference profiles (us.*, global.*) over bare
+        # foundation model IDs.
+        profile_base_ids = set()
+        for m in filtered:
+            mid = m["id"]
+            if mid.startswith(("us.", "global.")):
+                base = mid.split(".", 1)[1] if "." in mid[3:] else mid
+                profile_base_ids.add(base)
+
+        deduped = []
+        for m in filtered:
+            mid = m["id"]
+            if not mid.startswith(("us.", "global.")) and mid in profile_base_ids:
+                continue
+            deduped.append(m)
+
+        _RECOMMENDED = [
+            "us.anthropic.claude-sonnet-4-6",
+            "us.anthropic.claude-opus-4-6",
+            "us.anthropic.claude-haiku-4-5",
+            "us.amazon.nova-pro",
+            "us.amazon.nova-lite",
+            "us.amazon.nova-micro",
+            "deepseek.v3",
+            "us.meta.llama4-maverick",
+            "us.meta.llama4-scout",
+        ]
+
+        def _sort_key(m):
+            mid = m["id"]
+            for i, rec in enumerate(_RECOMMENDED):
+                if mid.startswith(rec):
+                    return (0, i, mid)
+            if mid.startswith("global."):
+                return (1, 0, mid)
+            return (2, 0, mid)
+
+        deduped.sort(key=_sort_key)
+        model_list = [m["id"] for m in deduped]
+        print(f"  Found {len(model_list)} text model(s) (filtered from {len(live_models)} total)")
+    else:
+        model_list = _PROVIDER_MODELS.get("bedrock", [])
+        if model_list:
+            print(f"  Using {len(model_list)} curated models (live discovery unavailable)")
+        else:
+            print("  No models found. Check IAM permissions for bedrock:ListFoundationModels.")
+            return
+
+    # 4. Model selection
+    if model_list:
+        selected = _prompt_model_selection(model_list, current_model=current_model)
+    else:
+        try:
+            selected = input("  Model ID: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            selected = None
+
+    if selected:
+        _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"] = "bedrock"
+        model["base_url"] = f"https://bedrock-runtime.{region}.amazonaws.com"
+        model.pop("api_mode", None)  # bedrock_converse is auto-detected
+
+        bedrock_cfg = cfg.get("bedrock", {})
+        if not isinstance(bedrock_cfg, dict):
+            bedrock_cfg = {}
+        bedrock_cfg["region"] = region
+        cfg["bedrock"] = bedrock_cfg
+
+        save_config(cfg)
+        deactivate_provider()
+
+        print(f"  Default model set to: {selected} (via AWS Bedrock, {region})")
+    else:
+        print("  No change.")
+
+
 def _model_flow_api_key_provider(config, provider_id, current_model=""):
     """Generic flow for API-key providers (z.ai, MiniMax, OpenCode, etc.)."""
     from hermes_cli.auth import (

hermes_cli/models.py

@@ -303,6 +303,22 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "XiaomiMiMo/MiMo-V2-Flash",
         "moonshotai/Kimi-K2-Thinking",
     ],
+    # AWS Bedrock — static fallback list used when dynamic discovery is
+    # unavailable (no boto3, no credentials, or API error).  The agent
+    # prefers live discovery via ListFoundationModels + ListInferenceProfiles.
+    # Use inference profile IDs (us.*) since most models require them.
+    "bedrock": [
+        "us.anthropic.claude-sonnet-4-6",
+        "us.anthropic.claude-opus-4-6-v1",
+        "us.anthropic.claude-haiku-4-5-20251001-v1:0",
+        "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
+        "us.amazon.nova-pro-v1:0",
+        "us.amazon.nova-lite-v1:0",
+        "us.amazon.nova-micro-v1:0",
+        "deepseek.v3.2",
+        "us.meta.llama4-maverick-17b-instruct-v1:0",
+        "us.meta.llama4-scout-17b-instruct-v1:0",
+    ],
 }
 
 # ---------------------------------------------------------------------------
@@ -536,6 +552,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("opencode-zen",   "OpenCode Zen",             "OpenCode Zen (35+ curated models, pay-as-you-go)"),
     ProviderEntry("opencode-go",    "OpenCode Go",              "OpenCode Go (open models, $10/month subscription)"),
     ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway (200+ models, pay-per-use)"),
+    ProviderEntry("bedrock",        "AWS Bedrock",              "AWS Bedrock (Claude, Nova, Llama, DeepSeek — IAM or API key)"),
 ]
 
 # Derived dicts — used throughout the codebase
@@ -587,6 +604,10 @@ _PROVIDER_ALIASES = {
     "huggingface-hub": "huggingface",
     "mimo": "xiaomi",
     "xiaomi-mimo": "xiaomi",
+    "aws": "bedrock",
+    "aws-bedrock": "bedrock",
+    "amazon-bedrock": "bedrock",
+    "amazon": "bedrock",
     "grok": "xai",
     "x-ai": "xai",
     "x.ai": "xai",
@@ -1955,6 +1976,42 @@ def validate_requested_model(
 
     # api_models is None — couldn't reach API.  Accept and persist,
     # but warn so typos don't silently break things.
+
+    # Bedrock: use our own discovery instead of HTTP /models endpoint.
+    # Bedrock's bedrock-runtime URL doesn't support /models — it uses the
+    # AWS SDK control plane (ListFoundationModels + ListInferenceProfiles).
+    if normalized == "bedrock":
+        try:
+            from agent.bedrock_adapter import discover_bedrock_models, resolve_bedrock_region
+            region = resolve_bedrock_region()
+            discovered = discover_bedrock_models(region)
+            discovered_ids = {m["id"] for m in discovered}
+            if requested in discovered_ids:
+                return {
+                    "accepted": True,
+                    "persist": True,
+                    "recognized": True,
+                    "message": None,
+                }
+            # Not in discovered list — still accept (user may have custom
+            # inference profiles or cross-account access), but warn.
+            suggestions = get_close_matches(requested, list(discovered_ids), n=3, cutoff=0.4)
+            suggestion_text = ""
+            if suggestions:
+                suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
+            return {
+                "accepted": True,
+                "persist": True,
+                "recognized": False,
+                "message": (
+                    f"Note: `{requested}` was not found in Bedrock model discovery for {region}. "
+                    f"It may still work with custom inference profiles or cross-account access."
+                    f"{suggestion_text}"
+                ),
+            }
+        except Exception:
+            pass  # Fall through to generic warning
+
     provider_label = _PROVIDER_LABELS.get(normalized, normalized)
     return {
         "accepted": False,

hermes_cli/providers.py

@@ -236,6 +236,12 @@ ALIASES: Dict[str, str] = {
     "mimo": "xiaomi",
     "xiaomi-mimo": "xiaomi",
 
+    # bedrock
+    "aws": "bedrock",
+    "aws-bedrock": "bedrock",
+    "amazon-bedrock": "bedrock",
+    "amazon": "bedrock",
+
     # arcee
     "arcee-ai": "arcee",
     "arceeai": "arcee",
@@ -262,6 +268,7 @@ _LABEL_OVERRIDES: Dict[str, str] = {
     "copilot-acp": "GitHub Copilot ACP",
     "xiaomi": "Xiaomi MiMo",
     "local": "Local endpoint",
+    "bedrock": "AWS Bedrock",
 }
 
 
@@ -271,6 +278,7 @@ TRANSPORT_TO_API_MODE: Dict[str, str] = {
     "openai_chat": "chat_completions",
     "anthropic_messages": "anthropic_messages",
     "codex_responses": "codex_responses",
+    "bedrock_converse": "bedrock_converse",
 }
 
 
@@ -388,6 +396,10 @@ def determine_api_mode(provider: str, base_url: str = "") -> str:
     if pdef is not None:
         return TRANSPORT_TO_API_MODE.get(pdef.transport, "chat_completions")
 
+    # Direct provider checks for providers not in HERMES_OVERLAYS
+    if provider == "bedrock":
+        return "bedrock_converse"
+
     # URL-based heuristics for custom / unknown providers
     if base_url:
         url_lower = base_url.rstrip("/").lower()
@@ -395,6 +407,8 @@ def determine_api_mode(provider: str, base_url: str = "") -> str:
             return "anthropic_messages"
         if "api.openai.com" in url_lower:
             return "codex_responses"
+        if "bedrock-runtime" in url_lower and "amazonaws.com" in url_lower:
+            return "bedrock_converse"
 
     return "chat_completions"
 

hermes_cli/runtime_provider.py

@@ -124,7 +124,7 @@ def _copilot_runtime_api_mode(model_cfg: Dict[str, Any], api_key: str) -> str:
         return "chat_completions"
 
 
-_VALID_API_MODES = {"chat_completions", "codex_responses", "anthropic_messages"}
+_VALID_API_MODES = {"chat_completions", "codex_responses", "anthropic_messages", "bedrock_converse"}
 
 
 def _parse_api_mode(raw: Any) -> Optional[str]:
@@ -836,6 +836,77 @@ def resolve_runtime_provider(
             "requested_provider": requested_provider,
         }
 
+    # AWS Bedrock (native Converse API via boto3)
+    if provider == "bedrock":
+        from agent.bedrock_adapter import (
+            has_aws_credentials,
+            resolve_aws_auth_env_var,
+            resolve_bedrock_region,
+            is_anthropic_bedrock_model,
+        )
+        # When the user explicitly selected bedrock (not auto-detected),
+        # trust boto3's credential chain — it handles IMDS, ECS task roles,
+        # Lambda execution roles, SSO, and other implicit sources that our
+        # env-var check can't detect.
+        is_explicit = requested_provider in ("bedrock", "aws", "aws-bedrock", "amazon-bedrock", "amazon")
+        if not is_explicit and not has_aws_credentials():
+            raise AuthError(
+                "No AWS credentials found for Bedrock. Configure one of:\n"
+                "  - AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY\n"
+                "  - AWS_PROFILE (for SSO / named profiles)\n"
+                "  - IAM instance role (EC2, ECS, Lambda)\n"
+                "Or run 'aws configure' to set up credentials.",
+                code="no_aws_credentials",
+            )
+        # Read bedrock-specific config from config.yaml
+        from hermes_cli.config import load_config as _load_bedrock_config
+        _bedrock_cfg = _load_bedrock_config().get("bedrock", {})
+        # Region priority: config.yaml bedrock.region → env var → us-east-1
+        region = (_bedrock_cfg.get("region") or "").strip() or resolve_bedrock_region()
+        auth_source = resolve_aws_auth_env_var() or "aws-sdk-default-chain"
+        # Build guardrail config if configured
+        _gr = _bedrock_cfg.get("guardrail", {})
+        guardrail_config = None
+        if _gr.get("guardrail_identifier") and _gr.get("guardrail_version"):
+            guardrail_config = {
+                "guardrailIdentifier": _gr["guardrail_identifier"],
+                "guardrailVersion": _gr["guardrail_version"],
+            }
+            if _gr.get("stream_processing_mode"):
+                guardrail_config["streamProcessingMode"] = _gr["stream_processing_mode"]
+            if _gr.get("trace"):
+                guardrail_config["trace"] = _gr["trace"]
+        # Dual-path routing: Claude models use AnthropicBedrock SDK for full
+        # feature parity (prompt caching, thinking budgets, adaptive thinking).
+        # Non-Claude models use the Converse API for multi-model support.
+        _current_model = str(model_cfg.get("default") or "").strip()
+        if is_anthropic_bedrock_model(_current_model):
+            # Claude on Bedrock → AnthropicBedrock SDK → anthropic_messages path
+            runtime = {
+                "provider": "bedrock",
+                "api_mode": "anthropic_messages",
+                "base_url": f"https://bedrock-runtime.{region}.amazonaws.com",
+                "api_key": "aws-sdk",
+                "source": auth_source,
+                "region": region,
+                "bedrock_anthropic": True,  # Signal to use AnthropicBedrock client
+                "requested_provider": requested_provider,
+            }
+        else:
+            # Non-Claude (Nova, DeepSeek, Llama, etc.) → Converse API
+            runtime = {
+                "provider": "bedrock",
+                "api_mode": "bedrock_converse",
+                "base_url": f"https://bedrock-runtime.{region}.amazonaws.com",
+                "api_key": "aws-sdk",
+                "source": auth_source,
+                "region": region,
+                "requested_provider": requested_provider,
+            }
+        if guardrail_config:
+            runtime["guardrail_config"] = guardrail_config
+        return runtime
+
     # API-key providers (z.ai/GLM, Kimi, MiniMax, MiniMax-CN)
     pconfig = PROVIDER_REGISTRY.get(provider)
     if pconfig and pconfig.auth_type == "api_key":

plugins/memory/honcho/client.py

@@ -58,8 +58,7 @@ def resolve_config_path() -> Path:
 
     Resolution order:
       1. $HERMES_HOME/honcho.json      (profile-local, if it exists)
-      2. ~/.hermes/honcho.json          (default profile — shared host blocks live here)
+      2. ~/.honcho/config.json          (global, cross-app interop)
-      3. ~/.honcho/config.json          (global, cross-app interop)
 
     Returns the global path if none exist (for first-time setup writes).
     """
@@ -67,11 +66,6 @@ def resolve_config_path() -> Path:
     if local_path.exists():
         return local_path
 
-    # Default profile's config — host blocks accumulate here via setup/clone
-    default_path = Path.home() / ".hermes" / "honcho.json"
-    if default_path != local_path and default_path.exists():
-        return default_path
-
     return GLOBAL_CONFIG_PATH
 
 

pyproject.toml

@@ -63,6 +63,7 @@ homeassistant = ["aiohttp>=3.9.0,<4"]
 sms = ["aiohttp>=3.9.0,<4"]
 acp = ["agent-client-protocol>=0.9.0,<1.0"]
 mistral = ["mistralai>=2.3.0,<3"]
+bedrock = ["boto3>=1.35.0,<2"]
 termux = [
   # Tested Android / Termux path: keeps the core CLI feature-rich while
   # avoiding extras that currently depend on non-Android wheels (notably
@@ -108,6 +109,7 @@ all = [
   "hermes-agent[dingtalk]",
   "hermes-agent[feishu]",
   "hermes-agent[mistral]",
+  "hermes-agent[bedrock]",
   "hermes-agent[web]",
 ]
 

run_agent.py

@@ -685,7 +685,7 @@ class AIAgent:
         self.provider = provider_name or ""
         self.acp_command = acp_command or command
         self.acp_args = list(acp_args or args or [])
-        if api_mode in {"chat_completions", "codex_responses", "anthropic_messages"}:
+        if api_mode in {"chat_completions", "codex_responses", "anthropic_messages", "bedrock_converse"}:
             self.api_mode = api_mode
         elif self.provider == "openai-codex":
             self.api_mode = "codex_responses"
@@ -700,6 +700,9 @@ class AIAgent:
             # use a URL convention ending in /anthropic. Auto-detect these so the
             # Anthropic Messages API adapter is used instead of chat completions.
             self.api_mode = "anthropic_messages"
+        elif self.provider == "bedrock" or "bedrock-runtime" in self._base_url_lower:
+            # AWS Bedrock — auto-detect from provider name or base URL.
+            self.api_mode = "bedrock_converse"
         else:
             self.api_mode = "chat_completions"
 
@@ -721,8 +724,11 @@ class AIAgent:
         # Responses there. ACP runtimes are excluded: CopilotACPClient
         # handles its own routing and does not implement the Responses API
         # surface.
+        # When api_mode was explicitly provided, respect it — the user
+        # knows what their endpoint supports (#10473).
         if (
-            self.api_mode == "chat_completions"
+            api_mode is None
+            and self.api_mode == "chat_completions"
             and self.provider != "copilot-acp"
             and not str(self.base_url or "").lower().startswith("acp://copilot")
             and not str(self.base_url or "").lower().startswith("acp+tcp://")
@@ -889,24 +895,70 @@ class AIAgent:
 
         if self.api_mode == "anthropic_messages":
             from agent.anthropic_adapter import build_anthropic_client, resolve_anthropic_token
-            # Only fall back to ANTHROPIC_TOKEN when the provider is actually Anthropic.
+            # Bedrock + Claude → use AnthropicBedrock SDK for full feature parity
-            # Other anthropic_messages providers (MiniMax, Alibaba, etc.) must use their own API key.
+            # (prompt caching, thinking budgets, adaptive thinking).
-            # Falling back would send Anthropic credentials to third-party endpoints (Fixes #1739, #minimax-401).
+            _is_bedrock_anthropic = self.provider == "bedrock"
-            _is_native_anthropic = self.provider == "anthropic"
+            if _is_bedrock_anthropic:
-            effective_key = (api_key or resolve_anthropic_token() or "") if _is_native_anthropic else (api_key or "")
+                from agent.anthropic_adapter import build_anthropic_bedrock_client
-            self.api_key = effective_key
+                import re as _re
-            self._anthropic_api_key = effective_key
+                _region_match = _re.search(r"bedrock-runtime\.([a-z0-9-]+)\.", base_url or "")
-            self._anthropic_base_url = base_url
+                _br_region = _region_match.group(1) if _region_match else "us-east-1"
-            from agent.anthropic_adapter import _is_oauth_token as _is_oat
+                self._bedrock_region = _br_region
-            self._is_anthropic_oauth = _is_oat(effective_key)
+                self._anthropic_client = build_anthropic_bedrock_client(_br_region)
-            self._anthropic_client = build_anthropic_client(effective_key, base_url)
+                self._anthropic_api_key = "aws-sdk"
-            # No OpenAI client needed for Anthropic mode
+                self._anthropic_base_url = base_url
+                self._is_anthropic_oauth = False
+                self.api_key = "aws-sdk"
+                self.client = None
+                self._client_kwargs = {}
+                if not self.quiet_mode:
+                    print(f"🤖 AI Agent initialized with model: {self.model} (AWS Bedrock + AnthropicBedrock SDK, {_br_region})")
+            else:
+                # Only fall back to ANTHROPIC_TOKEN when the provider is actually Anthropic.
+                # Other anthropic_messages providers (MiniMax, Alibaba, etc.) must use their own API key.
+                # Falling back would send Anthropic credentials to third-party endpoints (Fixes #1739, #minimax-401).
+                _is_native_anthropic = self.provider == "anthropic"
+                effective_key = (api_key or resolve_anthropic_token() or "") if _is_native_anthropic else (api_key or "")
+                self.api_key = effective_key
+                self._anthropic_api_key = effective_key
+                self._anthropic_base_url = base_url
+                from agent.anthropic_adapter import _is_oauth_token as _is_oat
+                self._is_anthropic_oauth = _is_oat(effective_key)
+                self._anthropic_client = build_anthropic_client(effective_key, base_url)
+                # No OpenAI client needed for Anthropic mode
+                self.client = None
+                self._client_kwargs = {}
+                if not self.quiet_mode:
+                    print(f"🤖 AI Agent initialized with model: {self.model} (Anthropic native)")
+                    if effective_key and len(effective_key) > 12:
+                        print(f"🔑 Using token: {effective_key[:8]}...{effective_key[-4:]}")
+        elif self.api_mode == "bedrock_converse":
+            # AWS Bedrock — uses boto3 directly, no OpenAI client needed.
+            # Region is extracted from the base_url or defaults to us-east-1.
+            import re as _re
+            _region_match = _re.search(r"bedrock-runtime\.([a-z0-9-]+)\.", base_url or "")
+            self._bedrock_region = _region_match.group(1) if _region_match else "us-east-1"
+            # Guardrail config — read from config.yaml at init time.
+            self._bedrock_guardrail_config = None
+            try:
+                from hermes_cli.config import load_config as _load_br_cfg
+                _gr = _load_br_cfg().get("bedrock", {}).get("guardrail", {})
+                if _gr.get("guardrail_identifier") and _gr.get("guardrail_version"):
+                    self._bedrock_guardrail_config = {
+                        "guardrailIdentifier": _gr["guardrail_identifier"],
+                        "guardrailVersion": _gr["guardrail_version"],
+                    }
+                    if _gr.get("stream_processing_mode"):
+                        self._bedrock_guardrail_config["streamProcessingMode"] = _gr["stream_processing_mode"]
+                    if _gr.get("trace"):
+                        self._bedrock_guardrail_config["trace"] = _gr["trace"]
+            except Exception:
+                pass
             self.client = None
             self._client_kwargs = {}
             if not self.quiet_mode:
-                print(f"🤖 AI Agent initialized with model: {self.model} (Anthropic native)")
+                _gr_label = " + Guardrails" if self._bedrock_guardrail_config else ""
-                if effective_key and len(effective_key) > 12:
+                print(f"🤖 AI Agent initialized with model: {self.model} (AWS Bedrock, {self._bedrock_region}{_gr_label})")
-                    print(f"🔑 Using token: {effective_key[:8]}...{effective_key[-4:]}")
         else:
             if api_key and base_url:
                 # Explicit credentials from CLI/gateway — construct directly.
@@ -951,9 +1003,20 @@ class AIAgent:
                     # message instead of silently routing through OpenRouter.
                     _explicit = (self.provider or "").strip().lower()
                     if _explicit and _explicit not in ("auto", "openrouter", "custom"):
+                        # Look up the actual env var name from the provider
+                        # config — some providers use non-standard names
+                        # (e.g. alibaba → DASHSCOPE_API_KEY, not ALIBABA_API_KEY).
+                        _env_hint = f"{_explicit.upper()}_API_KEY"
+                        try:
+                            from hermes_cli.auth import PROVIDER_REGISTRY
+                            _pcfg = PROVIDER_REGISTRY.get(_explicit)
+                            if _pcfg and _pcfg.api_key_env_vars:
+                                _env_hint = _pcfg.api_key_env_vars[0]
+                        except Exception:
+                            pass
                         raise RuntimeError(
                             f"Provider '{_explicit}' is set in config.yaml but no API key "
-                            f"was found. Set the {_explicit.upper()}_API_KEY environment "
+                            f"was found. Set the {_env_hint} environment "
                             f"variable, or switch to a different provider with `hermes model`."
                         )
                     # Final fallback: try raw OpenRouter key
@@ -1217,6 +1280,15 @@ class AIAgent:
                             "hermes_home": str(_ghh()),
                             "agent_context": "primary",
                         }
+                        # Thread session title for memory provider scoping
+                        # (e.g. honcho uses this to derive chat-scoped session keys)
+                        if self._session_db:
+                            try:
+                                _st = self._session_db.get_session_title(self.session_id)
+                                if _st:
+                                    _init_kwargs["session_title"] = _st
+                            except Exception:
+                                pass
                         # Thread gateway user identity for per-user memory scoping
                         if self._user_id:
                             _init_kwargs["user_id"] = self._user_id
@@ -4206,6 +4278,9 @@ class AIAgent:
         return False
 
     def _create_openai_client(self, client_kwargs: dict, *, reason: str, shared: bool) -> Any:
+        from agent.auxiliary_client import _validate_base_url, _validate_proxy_env_urls
+        _validate_proxy_env_urls()
+        _validate_base_url(client_kwargs.get("base_url"))
         if self.provider == "copilot-acp" or str(client_kwargs.get("base_url", "")).startswith("acp://copilot"):
             from agent.copilot_acp_client import CopilotACPClient
 
@@ -4890,6 +4965,17 @@ class AIAgent:
                     )
                 elif self.api_mode == "anthropic_messages":
                     result["response"] = self._anthropic_messages_create(api_kwargs)
+                elif self.api_mode == "bedrock_converse":
+                    # Bedrock uses boto3 directly — no OpenAI client needed.
+                    from agent.bedrock_adapter import (
+                        _get_bedrock_runtime_client,
+                        normalize_converse_response,
+                    )
+                    region = api_kwargs.pop("__bedrock_region__", "us-east-1")
+                    api_kwargs.pop("__bedrock_converse__", None)
+                    client = _get_bedrock_runtime_client(region)
+                    raw_response = client.converse(**api_kwargs)
+                    result["response"] = normalize_converse_response(raw_response)
                 else:
                     request_client_holder["client"] = self._create_request_openai_client(reason="chat_completion_request")
                     result["response"] = request_client_holder["client"].chat.completions.create(**api_kwargs)
@@ -5129,6 +5215,65 @@ class AIAgent:
             finally:
                 self._codex_on_first_delta = None
 
+        # Bedrock Converse uses boto3's converse_stream() with real-time delta
+        # callbacks — same UX as Anthropic and chat_completions streaming.
+        if self.api_mode == "bedrock_converse":
+            result = {"response": None, "error": None}
+            first_delta_fired = {"done": False}
+            deltas_were_sent = {"yes": False}
+
+            def _fire_first():
+                if not first_delta_fired["done"] and on_first_delta:
+                    first_delta_fired["done"] = True
+                    try:
+                        on_first_delta()
+                    except Exception:
+                        pass
+
+            def _bedrock_call():
+                try:
+                    from agent.bedrock_adapter import (
+                        _get_bedrock_runtime_client,
+                        stream_converse_with_callbacks,
+                    )
+                    region = api_kwargs.pop("__bedrock_region__", "us-east-1")
+                    api_kwargs.pop("__bedrock_converse__", None)
+                    client = _get_bedrock_runtime_client(region)
+                    raw_response = client.converse_stream(**api_kwargs)
+
+                    def _on_text(text):
+                        _fire_first()
+                        self._fire_stream_delta(text)
+                        deltas_were_sent["yes"] = True
+
+                    def _on_tool(name):
+                        _fire_first()
+                        self._fire_tool_gen_started(name)
+
+                    def _on_reasoning(text):
+                        _fire_first()
+                        self._fire_reasoning_delta(text)
+
+                    result["response"] = stream_converse_with_callbacks(
+                        raw_response,
+                        on_text_delta=_on_text if self._has_stream_consumers() else None,
+                        on_tool_start=_on_tool,
+                        on_reasoning_delta=_on_reasoning if self.reasoning_callback or self.stream_delta_callback else None,
+                        on_interrupt_check=lambda: self._interrupt_requested,
+                    )
+                except Exception as e:
+                    result["error"] = e
+
+            t = threading.Thread(target=_bedrock_call, daemon=True)
+            t.start()
+            while t.is_alive():
+                t.join(timeout=0.3)
+                if self._interrupt_requested:
+                    raise InterruptedError("Agent interrupted during Bedrock API call")
+            if result["error"] is not None:
+                raise result["error"]
+            return result["response"]
+
         result = {"response": None, "error": None}
         request_client_holder = {"client": None}
         first_delta_fired = {"done": False}
@@ -5760,6 +5905,8 @@ class AIAgent:
                 # provider-specific exceptions like Copilot gpt-5-mini on
                 # chat completions.
                 fb_api_mode = "codex_responses"
+            elif fb_provider == "bedrock" or "bedrock-runtime" in fb_base_url.lower():
+                fb_api_mode = "bedrock_converse"
 
             old_model = self.model
             self.model = fb_model
@@ -6239,6 +6386,25 @@ class AIAgent:
                 fast_mode=(self.request_overrides or {}).get("speed") == "fast",
             )
 
+        # AWS Bedrock native Converse API — bypasses the OpenAI client entirely.
+        # The adapter handles message/tool conversion and boto3 calls directly.
+        if self.api_mode == "bedrock_converse":
+            from agent.bedrock_adapter import build_converse_kwargs
+            region = getattr(self, "_bedrock_region", None) or "us-east-1"
+            guardrail = getattr(self, "_bedrock_guardrail_config", None)
+            return {
+                "__bedrock_converse__": True,
+                "__bedrock_region__": region,
+                **build_converse_kwargs(
+                    model=self.model,
+                    messages=api_messages,
+                    tools=self.tools,
+                    max_tokens=self.max_tokens or 4096,
+                    temperature=None,  # Let the model use its default
+                    guardrail_config=guardrail,
+                ),
+            }
+
         if self.api_mode == "codex_responses":
             instructions = ""
             payload_messages = api_messages
@@ -8504,6 +8670,53 @@ class AIAgent:
             api_kwargs = None  # Guard against UnboundLocalError in except handler
 
             while retry_count < max_retries:
+                # ── Nous Portal rate limit guard ──────────────────────
+                # If another session already recorded that Nous is rate-
+                # limited, skip the API call entirely.  Each attempt
+                # (including SDK-level retries) counts against RPH and
+                # deepens the rate limit hole.
+                if self.provider == "nous":
+                    try:
+                        from agent.nous_rate_guard import (
+                            nous_rate_limit_remaining,
+                            format_remaining as _fmt_nous_remaining,
+                        )
+                        _nous_remaining = nous_rate_limit_remaining()
+                        if _nous_remaining is not None and _nous_remaining > 0:
+                            _nous_msg = (
+                                f"Nous Portal rate limit active — "
+                                f"resets in {_fmt_nous_remaining(_nous_remaining)}."
+                            )
+                            self._vprint(
+                                f"{self.log_prefix}⏳ {_nous_msg} Trying fallback...",
+                                force=True,
+                            )
+                            self._emit_status(f"⏳ {_nous_msg}")
+                            if self._try_activate_fallback():
+                                retry_count = 0
+                                compression_attempts = 0
+                                primary_recovery_attempted = False
+                                continue
+                            # No fallback available — return with clear message
+                            self._persist_session(messages, conversation_history)
+                            return {
+                                "final_response": (
+                                    f"⏳ {_nous_msg}\n\n"
+                                    "No fallback provider available. "
+                                    "Try again after the reset, or add a "
+                                    "fallback provider in config.yaml."
+                                ),
+                                "messages": messages,
+                                "api_calls": api_call_count,
+                                "completed": False,
+                                "failed": True,
+                                "error": _nous_msg,
+                            }
+                    except ImportError:
+                        pass
+                    except Exception:
+                        pass  # Never let rate guard break the agent loop
+
                 try:
                     self._reset_stream_delivery_tracking()
                     api_kwargs = self._build_api_kwargs(api_messages)
@@ -8816,7 +9029,7 @@ class AIAgent:
                         # targeted error instead of wasting 3 API calls.
                         _trunc_content = None
                         _trunc_has_tool_calls = False
-                        if self.api_mode == "chat_completions":
+                        if self.api_mode in ("chat_completions", "bedrock_converse"):
                             _trunc_msg = response.choices[0].message if (hasattr(response, "choices") and response.choices) else None
                             _trunc_content = getattr(_trunc_msg, "content", None) if _trunc_msg else None
                             _trunc_has_tool_calls = bool(getattr(_trunc_msg, "tool_calls", None)) if _trunc_msg else False
@@ -8885,7 +9098,7 @@ class AIAgent:
                                 "error": _exhaust_error,
                             }
 
-                        if self.api_mode == "chat_completions":
+                        if self.api_mode in ("chat_completions", "bedrock_converse"):
                             assistant_message = response.choices[0].message
                             if not assistant_message.tool_calls:
                                 length_continue_retries += 1
@@ -8925,7 +9138,7 @@ class AIAgent:
                                     "error": "Response remained truncated after 3 continuation attempts",
                                 }
 
-                        if self.api_mode == "chat_completions":
+                        if self.api_mode in ("chat_completions", "bedrock_converse"):
                             assistant_message = response.choices[0].message
                             if assistant_message.tool_calls:
                                 if truncated_tool_call_retries < 1:
@@ -9092,6 +9305,15 @@ class AIAgent:
                                 self._vprint(f"{self.log_prefix}   💾 Cache: {cached:,}/{prompt:,} tokens ({hit_pct:.0f}% hit, {written:,} written)")
                     
                     has_retried_429 = False  # Reset on success
+                    # Clear Nous rate limit state on successful request —
+                    # proves the limit has reset and other sessions can
+                    # resume hitting Nous.
+                    if self.provider == "nous":
+                        try:
+                            from agent.nous_rate_guard import clear_nous_rate_limit
+                            clear_nous_rate_limit()
+                        except Exception:
+                            pass
                     self._touch_activity(f"API call #{api_call_count} completed")
                     break  # Success, exit retry loop
 
@@ -9503,6 +9725,38 @@ class AIAgent:
                                 primary_recovery_attempted = False
                                 continue
 
+                    # ── Nous Portal: record rate limit & skip retries ─────
+                    # When Nous returns a 429, record the reset time to a
+                    # shared file so ALL sessions (cron, gateway, auxiliary)
+                    # know not to pile on.  Then skip further retries —
+                    # each one burns another RPH request and deepens the
+                    # rate limit hole.  The retry loop's top-of-iteration
+                    # guard will catch this on the next pass and try
+                    # fallback or bail with a clear message.
+                    if (
+                        is_rate_limited
+                        and self.provider == "nous"
+                        and classified.reason == FailoverReason.rate_limit
+                        and not recovered_with_pool
+                    ):
+                        try:
+                            from agent.nous_rate_guard import record_nous_rate_limit
+                            _err_resp = getattr(api_error, "response", None)
+                            _err_hdrs = (
+                                getattr(_err_resp, "headers", None)
+                                if _err_resp else None
+                            )
+                            record_nous_rate_limit(
+                                headers=_err_hdrs,
+                                error_context=error_context,
+                            )
+                        except Exception:
+                            pass
+                        # Skip straight to max_retries — the top-of-loop
+                        # guard will handle fallback or bail cleanly.
+                        retry_count = max_retries
+                        continue
+
                     is_payload_too_large = (
                         classified.reason == FailoverReason.payload_too_large
                     )

scripts/install.sh

@@ -28,7 +28,7 @@ BOLD='\033[1m'
 # Configuration
 REPO_URL_SSH="git@github.com:NousResearch/hermes-agent.git"
 REPO_URL_HTTPS="https://github.com/NousResearch/hermes-agent.git"
-HERMES_HOME="$HOME/.hermes"
+HERMES_HOME="${HERMES_HOME:-$HOME/.hermes}"
 INSTALL_DIR="${HERMES_INSTALL_DIR:-$HERMES_HOME/hermes-agent}"
 PYTHON_VERSION="3.11"
 NODE_VERSION="22"
@@ -66,6 +66,10 @@ while [[ $# -gt 0 ]]; do
             INSTALL_DIR="$2"
             shift 2
             ;;
+        --hermes-home)
+            HERMES_HOME="$2"
+            shift 2
+            ;;
         -h|--help)
             echo "Hermes Agent Installer"
             echo ""
@@ -76,6 +80,7 @@ while [[ $# -gt 0 ]]; do
             echo "  --skip-setup   Skip interactive setup wizard"
             echo "  --branch NAME  Git branch to install (default: main)"
             echo "  --dir PATH     Installation directory (default: ~/.hermes/hermes-agent)"
+            echo "  --hermes-home PATH  Data directory (default: ~/.hermes, or \$HERMES_HOME)"
             echo "  -h, --help     Show this help"
             exit 0
             ;;

scripts/release.py

@@ -62,6 +62,7 @@ AUTHOR_MAP = {
     "258577966+voidborne-d@users.noreply.github.com": "voidborne-d",
     "70424851+insecurejezza@users.noreply.github.com": "insecurejezza",
     "259807879+Bartok9@users.noreply.github.com": "Bartok9",
+    "241404605+MestreY0d4-Uninter@users.noreply.github.com": "MestreY0d4-Uninter",
     "268667990+Roy-oss1@users.noreply.github.com": "Roy-oss1",
     "241404605+MestreY0d4-Uninter@users.noreply.github.com": "MestreY0d4-Uninter",
     # contributors (manual mapping from git names)
@@ -81,6 +82,7 @@ AUTHOR_MAP = {
     "brooklyn.bb.nicholson@gmail.com": "brooklynnicholson",
     "4317663+helix4u@users.noreply.github.com": "helix4u",
     "331214+counterposition@users.noreply.github.com": "counterposition",
+    "blspear@gmail.com": "BrennerSpear",
     "gpickett00@gmail.com": "gpickett00",
     "mcosma@gmail.com": "wakamex",
     "clawdia.nash@proton.me": "clawdia-nash",

skills/autonomous-ai-agents/hermes-agent/SKILL.md

@@ -313,7 +313,7 @@ Type these during an interactive chat session.
 ```
 ~/.hermes/config.yaml       Main configuration
 ~/.hermes/.env              API keys and secrets
-~/.hermes/skills/           Installed skills
+$HERMES_HOME/skills/        Installed skills
 ~/.hermes/sessions/         Session transcripts
 ~/.hermes/logs/             Gateway and error logs
 ~/.hermes/auth.json         OAuth tokens and credential pools

skills/github/github-code-review/SKILL.md

@@ -334,7 +334,7 @@ When the user asks you to "review PR #N", "look at this PR", or gives you a PR U
 ### Step 1: Set up environment
 
 ```bash
-source ~/.hermes/skills/github/github-auth/scripts/gh-env.sh
+source "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/gh-env.sh"
 # Or run the inline setup block from the top of this skill
 ```
 

skills/github/github-repo-management/references/github-api-cheatsheet.md

@@ -6,7 +6,7 @@ All requests need: `-H "Authorization: token $GITHUB_TOKEN"`
 
 Use the `gh-env.sh` helper to set `$GITHUB_TOKEN`, `$GH_OWNER`, `$GH_REPO` automatically:
 ```bash
-source ~/.hermes/skills/github/github-auth/scripts/gh-env.sh
+source "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/gh-env.sh"
 ```
 
 ## Repositories

skills/productivity/google-workspace/SKILL.md

@@ -32,7 +32,7 @@ on CLI, Telegram, Discord, or any platform.
 Define a shorthand first:
 
 ```bash
-GSETUP="python ~/.hermes/skills/productivity/google-workspace/scripts/setup.py"
+GSETUP="python ${HERMES_HOME:-$HOME/.hermes}/skills/productivity/google-workspace/scripts/setup.py"
 ```
 
 ### Step 0: Check if already set up
@@ -163,7 +163,7 @@ Should print `AUTHENTICATED`. Setup is complete — token refreshes automaticall
 All commands go through the API script. Set `GAPI` as a shorthand:
 
 ```bash
-GAPI="python ~/.hermes/skills/productivity/google-workspace/scripts/google_api.py"
+GAPI="python ${HERMES_HOME:-$HOME/.hermes}/skills/productivity/google-workspace/scripts/google_api.py"
 ```
 
 ### Gmail

skills/red-teaming/godmode/SKILL.md

@@ -60,7 +60,7 @@ The fastest path — auto-detect the model, test strategies, and lock in the win
 # In execute_code — use the loader to avoid exec-scoping issues:
 import os
 exec(open(os.path.expanduser(
-    "~/.hermes/skills/red-teaming/godmode/scripts/load_godmode.py"
+    os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/load_godmode.py")
 )).read())
 
 # Auto-detect model from config and jailbreak it
@@ -192,7 +192,7 @@ python3 scripts/parseltongue.py "How do I hack into a WiFi network?" --tier stan
 Or use `execute_code` inline:
 ```python
 # Load the parseltongue module
-exec(open(os.path.expanduser("~/.hermes/skills/red-teaming/godmode/scripts/parseltongue.py")).read())
+exec(open(os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/parseltongue.py")).read())
 
 query = "How do I hack into a WiFi network?"
 variants = generate_variants(query, tier="standard")
@@ -229,7 +229,7 @@ Race multiple models against the same query, score responses, pick the winner:
 
 ```python
 # Via execute_code
-exec(open(os.path.expanduser("~/.hermes/skills/red-teaming/godmode/scripts/godmode_race.py")).read())
+exec(open(os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/godmode_race.py")).read())
 
 result = race_models(
     query="Explain how SQL injection works with a practical example",

skills/red-teaming/godmode/references/jailbreak-templates.md

@@ -114,7 +114,7 @@ hermes
 ### Via the GODMODE CLASSIC racer script
 
 ```python
-exec(open(os.path.expanduser("~/.hermes/skills/red-teaming/godmode/scripts/godmode_race.py")).read())
+exec(open(os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/godmode_race.py")).read())
 result = race_godmode_classic("Your query here")
 print(f"Winner: {result['codename']} — Score: {result['score']}")
 print(result['content'])

skills/red-teaming/godmode/references/refusal-detection.md

@@ -129,7 +129,7 @@ These don't auto-reject but reduce the response score:
 ## Using in Python
 
 ```python
-exec(open(os.path.expanduser("~/.hermes/skills/red-teaming/godmode/scripts/godmode_race.py")).read())
+exec(open(os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/godmode_race.py")).read())
 
 # Check if a response is a refusal
 text = "I'm sorry, but I can't assist with that request."

skills/red-teaming/godmode/scripts/auto_jailbreak.py

@@ -7,7 +7,7 @@ finds what works, and locks it in by writing config.yaml + prefill.json.
 
 Usage in execute_code:
     exec(open(os.path.expanduser(
-        "~/.hermes/skills/red-teaming/godmode/scripts/auto_jailbreak.py"
+        os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/auto_jailbreak.py")
     )).read())
     
     result = auto_jailbreak()  # Uses current model from config

skills/red-teaming/godmode/scripts/godmode_race.py

@@ -7,7 +7,7 @@ Queries multiple models in parallel via OpenRouter, scores responses
 on quality/filteredness/speed, returns the best unfiltered answer.
 
 Usage in execute_code:
-    exec(open(os.path.expanduser("~/.hermes/skills/red-teaming/godmode/scripts/godmode_race.py")).read())
+    exec(open(os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/godmode_race.py")).read())
     
     result = race_models(
         query="Your query here",

skills/red-teaming/godmode/scripts/load_godmode.py

@@ -3,7 +3,7 @@ Loader for G0DM0D3 scripts. Handles the exec-scoping issues.
 
 Usage in execute_code:
     exec(open(os.path.expanduser(
-        "~/.hermes/skills/red-teaming/godmode/scripts/load_godmode.py"
+        os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/load_godmode.py")
     )).read())
     
     # Now all functions are available:

skills/red-teaming/godmode/scripts/parseltongue.py

@@ -11,7 +11,7 @@ Usage:
     python parseltongue.py "How do I hack a WiFi network?" --tier standard
 
     # As a module in execute_code
-    exec(open("~/.hermes/skills/red-teaming/godmode/scripts/parseltongue.py").read())
+    exec(open(os.path.join(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")), "skills/red-teaming/godmode/scripts/parseltongue.py")).read())
     variants = generate_variants("How do I hack a WiFi network?", tier="standard")
 """
 

tests/agent/test_bedrock_integration.py

@@ -0,0 +1,269 @@
+"""Integration tests for the AWS Bedrock provider wiring.
+
+Verifies that the Bedrock provider is correctly registered in the
+provider registry, model catalog, and runtime resolution pipeline.
+These tests do NOT require AWS credentials or boto3 — all AWS calls
+are mocked.
+
+Note: Tests that import ``hermes_cli.auth`` or ``hermes_cli.runtime_provider``
+require Python 3.10+ due to ``str | None`` type syntax in the import chain.
+"""
+
+import os
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+
+class TestProviderRegistry:
+    """Verify Bedrock is registered in PROVIDER_REGISTRY."""
+
+    def test_bedrock_in_registry(self):
+        from hermes_cli.auth import PROVIDER_REGISTRY
+        assert "bedrock" in PROVIDER_REGISTRY
+
+    def test_bedrock_auth_type_is_aws_sdk(self):
+        from hermes_cli.auth import PROVIDER_REGISTRY
+        pconfig = PROVIDER_REGISTRY["bedrock"]
+        assert pconfig.auth_type == "aws_sdk"
+
+    def test_bedrock_has_no_api_key_env_vars(self):
+        """Bedrock uses the AWS SDK credential chain, not API keys."""
+        from hermes_cli.auth import PROVIDER_REGISTRY
+        pconfig = PROVIDER_REGISTRY["bedrock"]
+        assert pconfig.api_key_env_vars == ()
+
+    def test_bedrock_base_url_env_var(self):
+        from hermes_cli.auth import PROVIDER_REGISTRY
+        pconfig = PROVIDER_REGISTRY["bedrock"]
+        assert pconfig.base_url_env_var == "BEDROCK_BASE_URL"
+
+
+class TestProviderAliases:
+    """Verify Bedrock aliases resolve correctly."""
+
+    def test_aws_alias(self):
+        from hermes_cli.models import _PROVIDER_ALIASES
+        assert _PROVIDER_ALIASES.get("aws") == "bedrock"
+
+    def test_aws_bedrock_alias(self):
+        from hermes_cli.models import _PROVIDER_ALIASES
+        assert _PROVIDER_ALIASES.get("aws-bedrock") == "bedrock"
+
+    def test_amazon_bedrock_alias(self):
+        from hermes_cli.models import _PROVIDER_ALIASES
+        assert _PROVIDER_ALIASES.get("amazon-bedrock") == "bedrock"
+
+    def test_amazon_alias(self):
+        from hermes_cli.models import _PROVIDER_ALIASES
+        assert _PROVIDER_ALIASES.get("amazon") == "bedrock"
+
+
+class TestProviderLabels:
+    """Verify Bedrock appears in provider labels."""
+
+    def test_bedrock_label(self):
+        from hermes_cli.models import _PROVIDER_LABELS
+        assert _PROVIDER_LABELS.get("bedrock") == "AWS Bedrock"
+
+
+class TestModelCatalog:
+    """Verify Bedrock has a static model fallback list."""
+
+    def test_bedrock_has_curated_models(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        models = _PROVIDER_MODELS.get("bedrock", [])
+        assert len(models) > 0
+
+    def test_bedrock_models_include_claude(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        models = _PROVIDER_MODELS.get("bedrock", [])
+        claude_models = [m for m in models if "anthropic.claude" in m]
+        assert len(claude_models) > 0
+
+    def test_bedrock_models_include_nova(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        models = _PROVIDER_MODELS.get("bedrock", [])
+        nova_models = [m for m in models if "amazon.nova" in m]
+        assert len(nova_models) > 0
+
+
+class TestResolveProvider:
+    """Verify resolve_provider() handles bedrock correctly."""
+
+    def test_explicit_bedrock_resolves(self, monkeypatch):
+        """When user explicitly requests 'bedrock', it should resolve."""
+        from hermes_cli.auth import PROVIDER_REGISTRY
+        # bedrock is in the registry, so resolve_provider should return it
+        from hermes_cli.auth import resolve_provider
+        result = resolve_provider("bedrock")
+        assert result == "bedrock"
+
+    def test_aws_alias_resolves_to_bedrock(self):
+        from hermes_cli.auth import resolve_provider
+        result = resolve_provider("aws")
+        assert result == "bedrock"
+
+    def test_amazon_bedrock_alias_resolves(self):
+        from hermes_cli.auth import resolve_provider
+        result = resolve_provider("amazon-bedrock")
+        assert result == "bedrock"
+
+    def test_auto_detect_with_aws_credentials(self, monkeypatch):
+        """When AWS credentials are present and no other provider is configured,
+        auto-detect should find bedrock."""
+        from hermes_cli.auth import resolve_provider
+
+        # Clear all other provider env vars
+        for var in ["OPENAI_API_KEY", "OPENROUTER_API_KEY", "ANTHROPIC_API_KEY",
+                     "ANTHROPIC_TOKEN", "GOOGLE_API_KEY", "DEEPSEEK_API_KEY"]:
+            monkeypatch.delenv(var, raising=False)
+
+        # Set AWS credentials
+        monkeypatch.setenv("AWS_ACCESS_KEY_ID", "AKIAIOSFODNN7EXAMPLE")
+        monkeypatch.setenv("AWS_SECRET_ACCESS_KEY", "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY")
+
+        # Mock the auth store to have no active provider
+        with patch("hermes_cli.auth._load_auth_store", return_value={}):
+            result = resolve_provider("auto")
+        assert result == "bedrock"
+
+
+class TestRuntimeProvider:
+    """Verify resolve_runtime_provider() handles bedrock correctly."""
+
+    def test_bedrock_runtime_resolution(self, monkeypatch):
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+
+        monkeypatch.setenv("AWS_ACCESS_KEY_ID", "AKIAIOSFODNN7EXAMPLE")
+        monkeypatch.setenv("AWS_SECRET_ACCESS_KEY", "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY")
+        monkeypatch.setenv("AWS_REGION", "eu-west-1")
+
+        # Mock resolve_provider to return bedrock
+        with patch("hermes_cli.runtime_provider.resolve_provider", return_value="bedrock"), \
+             patch("hermes_cli.runtime_provider._get_model_config", return_value={"provider": "bedrock"}):
+            result = resolve_runtime_provider(requested="bedrock")
+
+        assert result["provider"] == "bedrock"
+        assert result["api_mode"] == "bedrock_converse"
+        assert result["region"] == "eu-west-1"
+        assert "bedrock-runtime.eu-west-1.amazonaws.com" in result["base_url"]
+        assert result["api_key"] == "aws-sdk"
+
+    def test_bedrock_runtime_default_region(self, monkeypatch):
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+
+        monkeypatch.setenv("AWS_PROFILE", "default")
+        monkeypatch.delenv("AWS_REGION", raising=False)
+        monkeypatch.delenv("AWS_DEFAULT_REGION", raising=False)
+
+        with patch("hermes_cli.runtime_provider.resolve_provider", return_value="bedrock"), \
+             patch("hermes_cli.runtime_provider._get_model_config", return_value={"provider": "bedrock"}):
+            result = resolve_runtime_provider(requested="bedrock")
+
+        assert result["region"] == "us-east-1"
+
+    def test_bedrock_runtime_no_credentials_raises_on_auto_detect(self, monkeypatch):
+        """When bedrock is auto-detected (not explicitly requested) and no
+        credentials are found, runtime resolution should raise AuthError."""
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+        from hermes_cli.auth import AuthError
+
+        # Clear all AWS env vars
+        for var in ["AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY", "AWS_PROFILE",
+                     "AWS_BEARER_TOKEN_BEDROCK", "AWS_CONTAINER_CREDENTIALS_RELATIVE_URI",
+                     "AWS_WEB_IDENTITY_TOKEN_FILE"]:
+            monkeypatch.delenv(var, raising=False)
+
+        # Mock both the provider resolution and boto3's credential chain
+        mock_session = MagicMock()
+        mock_session.get_credentials.return_value = None
+        with patch("hermes_cli.runtime_provider.resolve_provider", return_value="bedrock"), \
+             patch("hermes_cli.runtime_provider._get_model_config", return_value={"provider": "bedrock"}), \
+             patch("hermes_cli.runtime_provider.resolve_requested_provider", return_value="auto"), \
+             patch.dict("sys.modules", {"botocore": MagicMock(), "botocore.session": MagicMock()}):
+            import botocore.session as _bs
+            _bs.get_session = MagicMock(return_value=mock_session)
+            with pytest.raises(AuthError, match="No AWS credentials"):
+                resolve_runtime_provider(requested="auto")
+
+    def test_bedrock_runtime_explicit_skips_credential_check(self, monkeypatch):
+        """When user explicitly requests bedrock, trust boto3's credential chain
+        even if env-var detection finds nothing (covers IMDS, SSO, etc.)."""
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+
+        # No AWS env vars set — but explicit bedrock request should not raise
+        for var in ["AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY", "AWS_PROFILE",
+                     "AWS_BEARER_TOKEN_BEDROCK"]:
+            monkeypatch.delenv(var, raising=False)
+
+        with patch("hermes_cli.runtime_provider.resolve_provider", return_value="bedrock"), \
+             patch("hermes_cli.runtime_provider._get_model_config", return_value={"provider": "bedrock"}):
+            result = resolve_runtime_provider(requested="bedrock")
+        assert result["provider"] == "bedrock"
+        assert result["api_mode"] == "bedrock_converse"
+
+
+# ---------------------------------------------------------------------------
+# providers.py integration
+# ---------------------------------------------------------------------------
+
+class TestProvidersModule:
+    """Verify bedrock is wired into hermes_cli/providers.py."""
+
+    def test_bedrock_alias_in_providers(self):
+        from hermes_cli.providers import ALIASES
+        assert ALIASES.get("bedrock") is None  # "bedrock" IS the canonical name, not an alias
+        assert ALIASES.get("aws") == "bedrock"
+        assert ALIASES.get("aws-bedrock") == "bedrock"
+
+    def test_bedrock_transport_mapping(self):
+        from hermes_cli.providers import TRANSPORT_TO_API_MODE
+        assert TRANSPORT_TO_API_MODE.get("bedrock_converse") == "bedrock_converse"
+
+    def test_determine_api_mode_from_bedrock_url(self):
+        from hermes_cli.providers import determine_api_mode
+        assert determine_api_mode(
+            "unknown", "https://bedrock-runtime.us-east-1.amazonaws.com"
+        ) == "bedrock_converse"
+
+    def test_label_override(self):
+        from hermes_cli.providers import _LABEL_OVERRIDES
+        assert _LABEL_OVERRIDES.get("bedrock") == "AWS Bedrock"
+
+
+# ---------------------------------------------------------------------------
+# Error classifier integration
+# ---------------------------------------------------------------------------
+
+class TestErrorClassifierBedrock:
+    """Verify Bedrock error patterns are in the global error classifier."""
+
+    def test_throttling_in_rate_limit_patterns(self):
+        from agent.error_classifier import _RATE_LIMIT_PATTERNS
+        assert "throttlingexception" in _RATE_LIMIT_PATTERNS
+
+    def test_context_overflow_patterns(self):
+        from agent.error_classifier import _CONTEXT_OVERFLOW_PATTERNS
+        assert "input is too long" in _CONTEXT_OVERFLOW_PATTERNS
+
+
+# ---------------------------------------------------------------------------
+# pyproject.toml bedrock extra
+# ---------------------------------------------------------------------------
+
+class TestPackaging:
+    """Verify bedrock optional dependency is declared."""
+
+    def test_bedrock_extra_exists(self):
+        import configparser
+        from pathlib import Path
+        # Read pyproject.toml to verify [bedrock] extra
+        toml_path = Path(__file__).parent.parent.parent / "pyproject.toml"
+        content = toml_path.read_text()
+        assert 'bedrock = ["boto3' in content
+
+    def test_bedrock_in_all_extra(self):
+        from pathlib import Path
+        content = (Path(__file__).parent.parent.parent / "pyproject.toml").read_text()
+        assert '"hermes-agent[bedrock]"' in content

tests/agent/test_nous_rate_guard.py

@@ -0,0 +1,253 @@
+"""Tests for agent/nous_rate_guard.py — cross-session Nous Portal rate limit guard."""
+
+import json
+import os
+import time
+
+import pytest
+
+
+@pytest.fixture
+def rate_guard_env(tmp_path, monkeypatch):
+    """Isolate rate guard state to a temp directory."""
+    hermes_home = str(tmp_path / ".hermes")
+    os.makedirs(hermes_home, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", hermes_home)
+    # Clear any cached module-level imports
+    return hermes_home
+
+
+class TestRecordNousRateLimit:
+    """Test recording rate limit state."""
+
+    def test_records_with_header_reset(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        headers = {"x-ratelimit-reset-requests-1h": "1800"}
+        record_nous_rate_limit(headers=headers)
+
+        path = _state_path()
+        assert os.path.exists(path)
+        with open(path) as f:
+            state = json.load(f)
+        assert state["reset_seconds"] == pytest.approx(1800, abs=2)
+        assert state["reset_at"] > time.time()
+
+    def test_records_with_per_minute_header(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        headers = {"x-ratelimit-reset-requests": "45"}
+        record_nous_rate_limit(headers=headers)
+
+        with open(_state_path()) as f:
+            state = json.load(f)
+        assert state["reset_seconds"] == pytest.approx(45, abs=2)
+
+    def test_records_with_retry_after_header(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        headers = {"retry-after": "60"}
+        record_nous_rate_limit(headers=headers)
+
+        with open(_state_path()) as f:
+            state = json.load(f)
+        assert state["reset_seconds"] == pytest.approx(60, abs=2)
+
+    def test_prefers_hourly_over_per_minute(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        headers = {
+            "x-ratelimit-reset-requests-1h": "1800",
+            "x-ratelimit-reset-requests": "45",
+        }
+        record_nous_rate_limit(headers=headers)
+
+        with open(_state_path()) as f:
+            state = json.load(f)
+        # Should use the hourly value, not the per-minute one
+        assert state["reset_seconds"] == pytest.approx(1800, abs=2)
+
+    def test_falls_back_to_error_context_reset_at(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        future_reset = time.time() + 900
+        record_nous_rate_limit(
+            headers=None,
+            error_context={"reset_at": future_reset},
+        )
+
+        with open(_state_path()) as f:
+            state = json.load(f)
+        assert state["reset_at"] == pytest.approx(future_reset, abs=1)
+
+    def test_falls_back_to_default_cooldown(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        record_nous_rate_limit(headers=None)
+
+        with open(_state_path()) as f:
+            state = json.load(f)
+        # Default is 300 seconds (5 minutes)
+        assert state["reset_seconds"] == pytest.approx(300, abs=2)
+
+    def test_custom_default_cooldown(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        record_nous_rate_limit(headers=None, default_cooldown=120.0)
+
+        with open(_state_path()) as f:
+            state = json.load(f)
+        assert state["reset_seconds"] == pytest.approx(120, abs=2)
+
+    def test_creates_directory_if_missing(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, _state_path
+
+        record_nous_rate_limit(headers={"retry-after": "10"})
+        assert os.path.exists(_state_path())
+
+
+class TestNousRateLimitRemaining:
+    """Test checking remaining rate limit time."""
+
+    def test_returns_none_when_no_file(self, rate_guard_env):
+        from agent.nous_rate_guard import nous_rate_limit_remaining
+
+        assert nous_rate_limit_remaining() is None
+
+    def test_returns_remaining_seconds_when_active(self, rate_guard_env):
+        from agent.nous_rate_guard import record_nous_rate_limit, nous_rate_limit_remaining
+
+        record_nous_rate_limit(headers={"x-ratelimit-reset-requests-1h": "600"})
+        remaining = nous_rate_limit_remaining()
+        assert remaining is not None
+        assert 595 < remaining <= 605  # ~600 seconds, allowing for test execution time
+
+    def test_returns_none_when_expired(self, rate_guard_env):
+        from agent.nous_rate_guard import nous_rate_limit_remaining, _state_path
+
+        # Write an already-expired state
+        state_dir = os.path.dirname(_state_path())
+        os.makedirs(state_dir, exist_ok=True)
+        with open(_state_path(), "w") as f:
+            json.dump({"reset_at": time.time() - 10, "recorded_at": time.time() - 100}, f)
+
+        assert nous_rate_limit_remaining() is None
+        # File should be cleaned up
+        assert not os.path.exists(_state_path())
+
+    def test_handles_corrupt_file(self, rate_guard_env):
+        from agent.nous_rate_guard import nous_rate_limit_remaining, _state_path
+
+        state_dir = os.path.dirname(_state_path())
+        os.makedirs(state_dir, exist_ok=True)
+        with open(_state_path(), "w") as f:
+            f.write("not valid json{{{")
+
+        assert nous_rate_limit_remaining() is None
+
+
+class TestClearNousRateLimit:
+    """Test clearing rate limit state."""
+
+    def test_clears_existing_file(self, rate_guard_env):
+        from agent.nous_rate_guard import (
+            record_nous_rate_limit,
+            clear_nous_rate_limit,
+            nous_rate_limit_remaining,
+            _state_path,
+        )
+
+        record_nous_rate_limit(headers={"retry-after": "600"})
+        assert nous_rate_limit_remaining() is not None
+
+        clear_nous_rate_limit()
+        assert nous_rate_limit_remaining() is None
+        assert not os.path.exists(_state_path())
+
+    def test_clear_when_no_file(self, rate_guard_env):
+        from agent.nous_rate_guard import clear_nous_rate_limit
+
+        # Should not raise
+        clear_nous_rate_limit()
+
+
+class TestFormatRemaining:
+    """Test human-readable duration formatting."""
+
+    def test_seconds(self):
+        from agent.nous_rate_guard import format_remaining
+
+        assert format_remaining(30) == "30s"
+
+    def test_minutes(self):
+        from agent.nous_rate_guard import format_remaining
+
+        assert format_remaining(125) == "2m 5s"
+
+    def test_exact_minutes(self):
+        from agent.nous_rate_guard import format_remaining
+
+        assert format_remaining(120) == "2m"
+
+    def test_hours(self):
+        from agent.nous_rate_guard import format_remaining
+
+        assert format_remaining(3720) == "1h 2m"
+
+
+class TestParseResetSeconds:
+    """Test header parsing for reset times."""
+
+    def test_case_insensitive_headers(self, rate_guard_env):
+        from agent.nous_rate_guard import _parse_reset_seconds
+
+        headers = {"X-Ratelimit-Reset-Requests-1h": "1200"}
+        assert _parse_reset_seconds(headers) == 1200.0
+
+    def test_returns_none_for_empty_headers(self):
+        from agent.nous_rate_guard import _parse_reset_seconds
+
+        assert _parse_reset_seconds(None) is None
+        assert _parse_reset_seconds({}) is None
+
+    def test_ignores_zero_values(self):
+        from agent.nous_rate_guard import _parse_reset_seconds
+
+        headers = {"x-ratelimit-reset-requests-1h": "0"}
+        assert _parse_reset_seconds(headers) is None
+
+    def test_ignores_invalid_values(self):
+        from agent.nous_rate_guard import _parse_reset_seconds
+
+        headers = {"x-ratelimit-reset-requests-1h": "not-a-number"}
+        assert _parse_reset_seconds(headers) is None
+
+
+class TestAuxiliaryClientIntegration:
+    """Test that the auxiliary client respects the rate guard."""
+
+    def test_try_nous_skips_when_rate_limited(self, rate_guard_env, monkeypatch):
+        from agent.nous_rate_guard import record_nous_rate_limit
+
+        # Record a rate limit
+        record_nous_rate_limit(headers={"retry-after": "600"})
+
+        # Mock _read_nous_auth to return valid creds (would normally succeed)
+        import agent.auxiliary_client as aux
+        monkeypatch.setattr(aux, "_read_nous_auth", lambda: {
+            "access_token": "test-token",
+            "inference_base_url": "https://api.nous.test/v1",
+        })
+
+        result = aux._try_nous()
+        assert result == (None, None)
+
+    def test_try_nous_works_when_not_rate_limited(self, rate_guard_env, monkeypatch):
+        import agent.auxiliary_client as aux
+
+        # No rate limit recorded — _try_nous should proceed normally
+        # (will return None because no real creds, but won't be blocked
+        # by the rate guard)
+        monkeypatch.setattr(aux, "_read_nous_auth", lambda: None)
+        result = aux._try_nous()
+        assert result == (None, None)

tests/agent/test_proxy_and_url_validation.py

@@ -0,0 +1,60 @@
+"""Tests for malformed proxy env var and base URL validation.
+
+Salvaged from PR #6403 by MestreY0d4-Uninter — validates that the agent
+surfaces clear errors instead of cryptic httpx ``Invalid port`` exceptions
+when proxy env vars or custom endpoint URLs are malformed.
+"""
+from __future__ import annotations
+
+import pytest
+
+from agent.auxiliary_client import _validate_base_url, _validate_proxy_env_urls
+
+
+# -- proxy env validation ------------------------------------------------
+
+
+def test_proxy_env_accepts_normal_values(monkeypatch):
+    monkeypatch.setenv("HTTP_PROXY", "http://127.0.0.1:6153")
+    monkeypatch.setenv("HTTPS_PROXY", "https://proxy.example.com:8443")
+    monkeypatch.setenv("ALL_PROXY", "socks5://127.0.0.1:1080")
+    _validate_proxy_env_urls()  # should not raise
+
+
+def test_proxy_env_accepts_empty(monkeypatch):
+    monkeypatch.delenv("HTTP_PROXY", raising=False)
+    monkeypatch.delenv("HTTPS_PROXY", raising=False)
+    monkeypatch.delenv("ALL_PROXY", raising=False)
+    monkeypatch.delenv("http_proxy", raising=False)
+    monkeypatch.delenv("https_proxy", raising=False)
+    monkeypatch.delenv("all_proxy", raising=False)
+    _validate_proxy_env_urls()  # should not raise
+
+
+@pytest.mark.parametrize("key", [
+    "HTTP_PROXY", "HTTPS_PROXY", "ALL_PROXY",
+    "http_proxy", "https_proxy", "all_proxy",
+])
+def test_proxy_env_rejects_malformed_port(monkeypatch, key):
+    monkeypatch.setenv(key, "http://127.0.0.1:6153export")
+    with pytest.raises(RuntimeError, match=rf"Malformed proxy environment variable {key}=.*6153export"):
+        _validate_proxy_env_urls()
+
+
+# -- base URL validation -------------------------------------------------
+
+
+@pytest.mark.parametrize("url", [
+    "https://api.example.com/v1",
+    "http://127.0.0.1:6153/v1",
+    "acp://copilot",
+    "",
+    None,
+])
+def test_base_url_accepts_valid(url):
+    _validate_base_url(url)  # should not raise
+
+
+def test_base_url_rejects_malformed_port():
+    with pytest.raises(RuntimeError, match="Malformed custom endpoint URL"):
+        _validate_base_url("http://127.0.0.1:6153export")

tests/agent/test_redact.py

@@ -284,3 +284,95 @@ class TestElevenLabsTavilyExaKeys:
         assert "XYZ789abcdef" not in result
         assert "HOME=/home/user" in result
         assert "SHELL=/bin/bash" in result
+
+
+class TestJWTTokens:
+    """JWT tokens start with eyJ (base64 for '{') and have dot-separated parts."""
+
+    def test_full_3part_jwt(self):
+        text = (
+            "Token: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9"
+            ".eyJpc3MiOiI0MjNiZDJkYjg4MjI0MDAwIn0"
+            ".Gxgv0rru-_kS-I_60EJ7CENTnBh9UeuL3QhkMoQ-VnM"
+        )
+        result = redact_sensitive_text(text)
+        assert "Token:" in result
+        # Payload and signature must not survive
+        assert "eyJpc3Mi" not in result
+        assert "Gxgv0rru" not in result
+
+    def test_2part_jwt(self):
+        text = "eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxMjM0NTY3ODkwIn0"
+        result = redact_sensitive_text(text)
+        assert "eyJzdWIi" not in result
+
+    def test_standalone_jwt_header(self):
+        text = "leaked header: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9 here"
+        result = redact_sensitive_text(text)
+        assert "IkpXVCJ9" not in result
+        assert "leaked header:" in result
+
+    def test_jwt_with_base64_padding(self):
+        text = "eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxMjM0NTY3ODkwIn0=.abc123def456ghij"
+        result = redact_sensitive_text(text)
+        assert "abc123def456" not in result
+
+    def test_short_eyj_not_matched(self):
+        """eyJ followed by fewer than 10 base64 chars should not match."""
+        text = "eyJust a normal word"
+        assert redact_sensitive_text(text) == text
+
+    def test_jwt_preserves_surrounding_text(self):
+        text = "before eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxMjM0NTY3ODkwIn0 after"
+        result = redact_sensitive_text(text)
+        assert result.startswith("before ")
+        assert result.endswith(" after")
+
+    def test_home_assistant_jwt_in_memory(self):
+        """Real-world pattern: HA token stored in agent memory block."""
+        text = (
+            "Home Assistant API Token: "
+            "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9"
+            ".eyJpc3MiOiJhYmNkZWYiLCJleHAiOjE3NzQ5NTcxMDN9"
+            ".Gxgv0rru-_kS-I_60EJ7CENTnBh9UeuL3QhkMoQ-VnM"
+        )
+        result = redact_sensitive_text(text)
+        assert "Home Assistant API Token:" in result
+        assert "Gxgv0rru" not in result
+        assert "..." in result
+
+
+class TestDiscordMentions:
+    """Discord snowflake IDs in <@ID> or <@!ID> format."""
+
+    def test_normal_mention(self):
+        result = redact_sensitive_text("Hello <@222589316709220353>")
+        assert "222589316709220353" not in result
+        assert "<@***>" in result
+
+    def test_nickname_mention(self):
+        result = redact_sensitive_text("Ping <@!1331549159177846844>")
+        assert "1331549159177846844" not in result
+        assert "<@!***>" in result
+
+    def test_multiple_mentions(self):
+        text = "<@111111111111111111> and <@222222222222222222>"
+        result = redact_sensitive_text(text)
+        assert "111111111111111111" not in result
+        assert "222222222222222222" not in result
+
+    def test_short_id_not_matched(self):
+        """IDs shorter than 17 digits are not Discord snowflakes."""
+        text = "<@12345>"
+        assert redact_sensitive_text(text) == text
+
+    def test_slack_mention_not_matched(self):
+        """Slack mentions use letters, not pure digits."""
+        text = "<@U024BE7LH>"
+        assert redact_sensitive_text(text) == text
+
+    def test_preserves_surrounding_text(self):
+        text = "User <@222589316709220353> said hello"
+        result = redact_sensitive_text(text)
+        assert result.startswith("User ")
+        assert result.endswith(" said hello")

tests/gateway/test_config.py

@@ -193,6 +193,67 @@ class TestLoadGatewayConfig:
 
         assert config.thread_sessions_per_user is False
 
+    def test_bridges_discord_channel_prompts_from_config_yaml(self, tmp_path, monkeypatch):
+        hermes_home = tmp_path / ".hermes"
+        hermes_home.mkdir()
+        config_path = hermes_home / "config.yaml"
+        config_path.write_text(
+            "discord:\n"
+            "  channel_prompts:\n"
+            "    \"123\": Research mode\n"
+            "    456: Therapist mode\n",
+            encoding="utf-8",
+        )
+
+        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+        config = load_gateway_config()
+
+        assert config.platforms[Platform.DISCORD].extra["channel_prompts"] == {
+            "123": "Research mode",
+            "456": "Therapist mode",
+        }
+
+    def test_bridges_telegram_channel_prompts_from_config_yaml(self, tmp_path, monkeypatch):
+        hermes_home = tmp_path / ".hermes"
+        hermes_home.mkdir()
+        config_path = hermes_home / "config.yaml"
+        config_path.write_text(
+            "telegram:\n"
+            "  channel_prompts:\n"
+            '    "-1001234567": Research assistant\n'
+            "    789: Creative writing\n",
+            encoding="utf-8",
+        )
+
+        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+        config = load_gateway_config()
+
+        assert config.platforms[Platform.TELEGRAM].extra["channel_prompts"] == {
+            "-1001234567": "Research assistant",
+            "789": "Creative writing",
+        }
+
+    def test_bridges_slack_channel_prompts_from_config_yaml(self, tmp_path, monkeypatch):
+        hermes_home = tmp_path / ".hermes"
+        hermes_home.mkdir()
+        config_path = hermes_home / "config.yaml"
+        config_path.write_text(
+            "slack:\n"
+            "  channel_prompts:\n"
+            '    "C01ABC": Code review mode\n',
+            encoding="utf-8",
+        )
+
+        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+        config = load_gateway_config()
+
+        assert config.platforms[Platform.SLACK].extra["channel_prompts"] == {
+            "C01ABC": "Code review mode",
+        }
+
     def test_invalid_quick_commands_in_config_yaml_are_ignored(self, tmp_path, monkeypatch):
         hermes_home = tmp_path / ".hermes"
         hermes_home.mkdir()

tests/gateway/test_discord_channel_prompts.py

@@ -0,0 +1,259 @@
+"""Tests for Discord channel_prompts resolution and injection."""
+
+import sys
+import threading
+import types
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+
+def _ensure_discord_mock():
+    if "discord" in sys.modules and hasattr(sys.modules["discord"], "__file__"):
+        return
+    discord_mod = types.ModuleType("discord")
+    discord_mod.Intents = MagicMock()
+    discord_mod.Intents.default.return_value = MagicMock()
+    discord_mod.DMChannel = type("DMChannel", (), {})
+    discord_mod.Thread = type("Thread", (), {})
+    discord_mod.ForumChannel = type("ForumChannel", (), {})
+    discord_mod.Interaction = object
+    ext_mod = MagicMock()
+    commands_mod = MagicMock()
+    commands_mod.Bot = MagicMock
+    ext_mod.commands = commands_mod
+    sys.modules.setdefault("discord", discord_mod)
+    sys.modules.setdefault("discord.ext", ext_mod)
+    sys.modules.setdefault("discord.ext.commands", commands_mod)
+
+
+import gateway.run as gateway_run
+from gateway.config import Platform
+from gateway.platforms.base import MessageEvent
+from gateway.session import SessionSource
+
+
+class _CapturingAgent:
+    last_init = None
+
+    def __init__(self, *args, **kwargs):
+        type(self).last_init = dict(kwargs)
+        self.tools = []
+
+    def run_conversation(self, user_message, conversation_history=None, task_id=None, persist_user_message=None):
+        return {
+            "final_response": "ok",
+            "messages": [],
+            "api_calls": 1,
+            "completed": True,
+        }
+
+
+def _install_fake_agent(monkeypatch):
+    fake_run_agent = types.ModuleType("run_agent")
+    fake_run_agent.AIAgent = _CapturingAgent
+    monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
+
+
+def _make_adapter():
+    _ensure_discord_mock()
+    from gateway.platforms.discord import DiscordAdapter
+
+    adapter = object.__new__(DiscordAdapter)
+    adapter.config = MagicMock()
+    adapter.config.extra = {}
+    return adapter
+
+
+def _make_runner():
+    runner = object.__new__(gateway_run.GatewayRunner)
+    runner.adapters = {}
+    runner._ephemeral_system_prompt = "Global prompt"
+    runner._prefill_messages = []
+    runner._reasoning_config = None
+    runner._service_tier = None
+    runner._provider_routing = {}
+    runner._fallback_model = None
+    runner._smart_model_routing = {}
+    runner._running_agents = {}
+    runner._pending_model_notes = {}
+    runner._session_db = None
+    runner._agent_cache = {}
+    runner._agent_cache_lock = threading.Lock()
+    runner._session_model_overrides = {}
+    runner.hooks = SimpleNamespace(loaded_hooks=False)
+    runner.config = SimpleNamespace(streaming=None)
+    runner.session_store = SimpleNamespace(
+        get_or_create_session=lambda source: SimpleNamespace(session_id="session-1"),
+        load_transcript=lambda session_id: [],
+    )
+    runner._get_or_create_gateway_honcho = lambda session_key: (None, None)
+    runner._enrich_message_with_vision = AsyncMock(return_value="ENRICHED")
+    return runner
+
+
+def _make_source() -> SessionSource:
+    return SessionSource(
+        platform=Platform.DISCORD,
+        chat_id="12345",
+        chat_type="thread",
+        user_id="user-1",
+    )
+
+
+class TestResolveChannelPrompts:
+    def test_no_prompt_returns_none(self):
+        adapter = _make_adapter()
+        assert adapter._resolve_channel_prompt("123") is None
+
+    def test_match_by_channel_id(self):
+        adapter = _make_adapter()
+        adapter.config.extra = {"channel_prompts": {"100": "Research mode"}}
+        assert adapter._resolve_channel_prompt("100") == "Research mode"
+
+    def test_numeric_yaml_keys_normalized_at_config_load(self):
+        """Numeric YAML keys are normalized to strings by config bridging.
+
+        The resolver itself expects string keys (config.py handles normalization),
+        so raw numeric keys will not match — this is intentional.
+        """
+        adapter = _make_adapter()
+        # Simulates post-bridging state: keys are already strings
+        adapter.config.extra = {"channel_prompts": {"100": "Research mode"}}
+        assert adapter._resolve_channel_prompt("100") == "Research mode"
+        # Pre-bridging numeric key would not match (bridging is responsible)
+        adapter.config.extra = {"channel_prompts": {100: "Research mode"}}
+        assert adapter._resolve_channel_prompt("100") is None
+
+    def test_match_by_parent_id(self):
+        adapter = _make_adapter()
+        adapter.config.extra = {"channel_prompts": {"200": "Forum prompt"}}
+        assert adapter._resolve_channel_prompt("999", parent_id="200") == "Forum prompt"
+
+    def test_exact_channel_overrides_parent(self):
+        adapter = _make_adapter()
+        adapter.config.extra = {
+            "channel_prompts": {
+                "999": "Thread override",
+                "200": "Forum prompt",
+            }
+        }
+        assert adapter._resolve_channel_prompt("999", parent_id="200") == "Thread override"
+
+    def test_build_message_event_sets_channel_prompt(self):
+        adapter = _make_adapter()
+        adapter.config.extra = {"channel_prompts": {"321": "Command prompt"}}
+        adapter.build_source = MagicMock(return_value=SimpleNamespace())
+
+        interaction = SimpleNamespace(
+            channel_id=321,
+            channel=SimpleNamespace(name="general", guild=None, parent_id=None),
+            user=SimpleNamespace(id=1, display_name="Brenner"),
+        )
+        adapter._get_effective_topic = MagicMock(return_value=None)
+
+        event = adapter._build_slash_event(interaction, "/retry")
+
+        assert event.channel_prompt == "Command prompt"
+
+    @pytest.mark.asyncio
+    async def test_dispatch_thread_session_inherits_parent_channel_prompt(self):
+        adapter = _make_adapter()
+        adapter.config.extra = {"channel_prompts": {"200": "Parent prompt"}}
+        adapter.build_source = MagicMock(return_value=SimpleNamespace())
+        adapter._get_effective_topic = MagicMock(return_value=None)
+        adapter.handle_message = AsyncMock()
+
+        interaction = SimpleNamespace(
+            guild=SimpleNamespace(name="Wetlands"),
+            channel=SimpleNamespace(id=200, parent=None),
+            user=SimpleNamespace(id=1, display_name="Brenner"),
+        )
+
+        await adapter._dispatch_thread_session(interaction, "999", "new-thread", "hello")
+
+        dispatched_event = adapter.handle_message.await_args.args[0]
+        assert dispatched_event.channel_prompt == "Parent prompt"
+
+    def test_blank_prompts_are_ignored(self):
+        adapter = _make_adapter()
+        adapter.config.extra = {"channel_prompts": {"100": "   "}}
+        assert adapter._resolve_channel_prompt("100") is None
+
+
+@pytest.mark.asyncio
+async def test_retry_preserves_channel_prompt(monkeypatch):
+    runner = _make_runner()
+    runner.session_store = SimpleNamespace(
+        get_or_create_session=lambda source: SimpleNamespace(session_id="session-1", last_prompt_tokens=10),
+        load_transcript=lambda session_id: [
+            {"role": "user", "content": "original message"},
+            {"role": "assistant", "content": "old reply"},
+        ],
+        rewrite_transcript=MagicMock(),
+    )
+    runner._handle_message = AsyncMock(return_value="ok")
+
+    event = MessageEvent(
+        text="/retry",
+        message_type=gateway_run.MessageType.COMMAND,
+        source=_make_source(),
+        raw_message=SimpleNamespace(),
+        channel_prompt="Channel prompt",
+    )
+
+    result = await runner._handle_retry_command(event)
+
+    assert result == "ok"
+    retried_event = runner._handle_message.await_args.args[0]
+    assert retried_event.channel_prompt == "Channel prompt"
+
+
+@pytest.mark.asyncio
+async def test_run_agent_appends_channel_prompt_to_ephemeral_system_prompt(monkeypatch, tmp_path):
+    _install_fake_agent(monkeypatch)
+    runner = _make_runner()
+
+    (tmp_path / "config.yaml").write_text("agent:\n  system_prompt: Global prompt\n", encoding="utf-8")
+    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
+    monkeypatch.setattr(gateway_run, "_env_path", tmp_path / ".env")
+    monkeypatch.setattr(gateway_run, "load_dotenv", lambda *args, **kwargs: None)
+    monkeypatch.setattr(gateway_run, "_load_gateway_config", lambda: {})
+    monkeypatch.setattr(gateway_run, "_resolve_gateway_model", lambda config=None: "gpt-5.4")
+    monkeypatch.setattr(
+        gateway_run,
+        "_resolve_runtime_agent_kwargs",
+        lambda: {
+            "provider": "openrouter",
+            "api_mode": "chat_completions",
+            "base_url": "https://openrouter.ai/api/v1",
+            "api_key": "***",
+        },
+    )
+
+    import hermes_cli.tools_config as tools_config
+
+    monkeypatch.setattr(tools_config, "_get_platform_tools", lambda user_config, platform_key: {"core"})
+
+    _CapturingAgent.last_init = None
+    event = MessageEvent(
+        text="hi",
+        source=_make_source(),
+        message_id="m1",
+        channel_prompt="Channel prompt",
+    )
+    result = await runner._run_agent(
+        message="hi",
+        context_prompt="Context prompt",
+        history=[],
+        source=_make_source(),
+        session_id="session-1",
+        session_key="agent:main:discord:thread:12345",
+        channel_prompt=event.channel_prompt,
+    )
+
+    assert result["final_response"] == "ok"
+    assert _CapturingAgent.last_init["ephemeral_system_prompt"] == (
+        "Context prompt\n\nChannel prompt\n\nGlobal prompt"
+    )

tests/hermes_cli/test_config.py

@@ -459,7 +459,7 @@ class TestCustomProviderCompatibility:
             migrate_config(interactive=False, quiet=True)
             raw = yaml.safe_load(config_path.read_text(encoding="utf-8"))
 
-        assert raw["_config_version"] == 17
+        assert raw["_config_version"] == 18
         assert raw["providers"]["openai-direct"] == {
             "api": "https://api.openai.com/v1",
             "api_key": "test-key",
@@ -606,6 +606,26 @@ class TestInterimAssistantMessageConfig:
             migrate_config(interactive=False, quiet=True)
             raw = yaml.safe_load(config_path.read_text(encoding="utf-8"))
 
-        assert raw["_config_version"] == 17
+        assert raw["_config_version"] == 18
         assert raw["display"]["tool_progress"] == "off"
         assert raw["display"]["interim_assistant_messages"] is True
+
+
+class TestDiscordChannelPromptsConfig:
+    def test_default_config_includes_discord_channel_prompts(self):
+        assert DEFAULT_CONFIG["discord"]["channel_prompts"] == {}
+
+    def test_migrate_adds_discord_channel_prompts_default(self, tmp_path):
+        config_path = tmp_path / "config.yaml"
+        config_path.write_text(
+            yaml.safe_dump({"_config_version": 17, "discord": {"auto_thread": True}}),
+            encoding="utf-8",
+        )
+
+        with patch.dict(os.environ, {"HERMES_HOME": str(tmp_path)}):
+            migrate_config(interactive=False, quiet=True)
+            raw = yaml.safe_load(config_path.read_text(encoding="utf-8"))
+
+        assert raw["_config_version"] == 18
+        assert raw["discord"]["auto_thread"] is True
+        assert raw["discord"]["channel_prompts"] == {}

tests/tools/test_browser_camofox_state.py

@@ -64,4 +64,4 @@ class TestCamofoxConfigDefaults:
 
         # The current schema version is tracked globally; unrelated default
         # options may bump it after browser defaults are added.
-        assert DEFAULT_CONFIG["_config_version"] == 17
+        assert DEFAULT_CONFIG["_config_version"] == 18

tools/skill_manager_tool.py

@@ -82,6 +82,18 @@ SKILLS_DIR = HERMES_HOME / "skills"
 
 MAX_NAME_LENGTH = 64
 MAX_DESCRIPTION_LENGTH = 1024
+
+
+def _is_local_skill(skill_path: Path) -> bool:
+    """Check if a skill path is within the local SKILLS_DIR.
+
+    Skills found in external_dirs are read-only from the agent's perspective.
+    """
+    try:
+        skill_path.resolve().relative_to(SKILLS_DIR.resolve())
+        return True
+    except ValueError:
+        return False
 MAX_SKILL_CONTENT_CHARS = 100_000   # ~36k tokens at 2.75 chars/token
 MAX_SKILL_FILE_BYTES = 1_048_576    # 1 MiB per supporting file
 
@@ -360,6 +372,9 @@ def _edit_skill(name: str, content: str) -> Dict[str, Any]:
     if not existing:
         return {"success": False, "error": f"Skill '{name}' not found. Use skills_list() to see available skills."}
 
+    if not _is_local_skill(existing["path"]):
+        return {"success": False, "error": f"Skill '{name}' is in an external directory and cannot be modified. Copy it to your local skills directory first."}
+
     skill_md = existing["path"] / "SKILL.md"
     # Back up original content for rollback
     original_content = skill_md.read_text(encoding="utf-8") if skill_md.exists() else None
@@ -400,6 +415,9 @@ def _patch_skill(
     if not existing:
         return {"success": False, "error": f"Skill '{name}' not found."}
 
+    if not _is_local_skill(existing["path"]):
+        return {"success": False, "error": f"Skill '{name}' is in an external directory and cannot be modified. Copy it to your local skills directory first."}
+
     skill_dir = existing["path"]
 
     if file_path:
@@ -473,6 +491,9 @@ def _delete_skill(name: str) -> Dict[str, Any]:
     if not existing:
         return {"success": False, "error": f"Skill '{name}' not found."}
 
+    if not _is_local_skill(existing["path"]):
+        return {"success": False, "error": f"Skill '{name}' is in an external directory and cannot be deleted."}
+
     skill_dir = existing["path"]
     shutil.rmtree(skill_dir)
 
@@ -515,6 +536,9 @@ def _write_file(name: str, file_path: str, file_content: str) -> Dict[str, Any]:
     if not existing:
         return {"success": False, "error": f"Skill '{name}' not found. Create it first with action='create'."}
 
+    if not _is_local_skill(existing["path"]):
+        return {"success": False, "error": f"Skill '{name}' is in an external directory and cannot be modified. Copy it to your local skills directory first."}
+
     target, err = _resolve_skill_target(existing["path"], file_path)
     if err:
         return {"success": False, "error": err}
@@ -548,6 +572,10 @@ def _remove_file(name: str, file_path: str) -> Dict[str, Any]:
     existing = _find_skill(name)
     if not existing:
         return {"success": False, "error": f"Skill '{name}' not found."}
+
+    if not _is_local_skill(existing["path"]):
+        return {"success": False, "error": f"Skill '{name}' is in an external directory and cannot be modified."}
+
     skill_dir = existing["path"]
 
     target, err = _resolve_skill_target(skill_dir, file_path)

website/docs/guides/aws-bedrock.md

@@ -0,0 +1,164 @@
+---
+sidebar_position: 14
+title: "AWS Bedrock"
+description: "Use Hermes Agent with Amazon Bedrock — native Converse API, IAM authentication, Guardrails, and cross-region inference"
+---
+
+# AWS Bedrock
+
+Hermes Agent supports Amazon Bedrock as a native provider using the **Converse API** — not the OpenAI-compatible endpoint. This gives you full access to the Bedrock ecosystem: IAM authentication, Guardrails, cross-region inference profiles, and all foundation models.
+
+## Prerequisites
+
+- **AWS credentials** — any source supported by the [boto3 credential chain](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html):
+  - IAM instance role (EC2, ECS, Lambda — zero config)
+  - `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` environment variables
+  - `AWS_PROFILE` for SSO or named profiles
+  - `aws configure` for local development
+- **boto3** — install with `pip install hermes-agent[bedrock]`
+- **IAM permissions** — at minimum:
+  - `bedrock:InvokeModel` and `bedrock:InvokeModelWithResponseStream` (for inference)
+  - `bedrock:ListFoundationModels` and `bedrock:ListInferenceProfiles` (for model discovery)
+
+:::tip EC2 / ECS / Lambda
+On AWS compute, attach an IAM role with `AmazonBedrockFullAccess` and you're done. No API keys, no `.env` configuration — Hermes detects the instance role automatically.
+:::
+
+## Quick Start
+
+```bash
+# Install with Bedrock support
+pip install hermes-agent[bedrock]
+
+# Select Bedrock as your provider
+hermes model
+# → Choose "More providers..." → "AWS Bedrock"
+# → Select your region and model
+
+# Start chatting
+hermes chat
+```
+
+## Configuration
+
+After running `hermes model`, your `~/.hermes/config.yaml` will contain:
+
+```yaml
+model:
+  default: us.anthropic.claude-sonnet-4-6
+  provider: bedrock
+  base_url: https://bedrock-runtime.us-east-2.amazonaws.com
+
+bedrock:
+  region: us-east-2
+```
+
+### Region
+
+Set the AWS region in any of these ways (highest priority first):
+
+1. `bedrock.region` in `config.yaml`
+2. `AWS_REGION` environment variable
+3. `AWS_DEFAULT_REGION` environment variable
+4. Default: `us-east-1`
+
+### Guardrails
+
+To apply [Amazon Bedrock Guardrails](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html) to all model invocations:
+
+```yaml
+bedrock:
+  region: us-east-2
+  guardrail:
+    guardrail_identifier: "abc123def456"  # From the Bedrock console
+    guardrail_version: "1"                # Version number or "DRAFT"
+    stream_processing_mode: "async"       # "sync" or "async"
+    trace: "disabled"                     # "enabled", "disabled", or "enabled_full"
+```
+
+### Model Discovery
+
+Hermes auto-discovers available models via the Bedrock control plane. You can customize discovery:
+
+```yaml
+bedrock:
+  discovery:
+    enabled: true
+    provider_filter: ["anthropic", "amazon"]  # Only show these providers
+    refresh_interval: 3600                     # Cache for 1 hour
+```
+
+## Available Models
+
+Bedrock models use **inference profile IDs** for on-demand invocation. The `hermes model` picker shows these automatically, with recommended models at the top:
+
+| Model | ID | Notes |
+|-------|-----|-------|
+| Claude Sonnet 4.6 | `us.anthropic.claude-sonnet-4-6` | Recommended — best balance of speed and capability |
+| Claude Opus 4.6 | `us.anthropic.claude-opus-4-6-v1` | Most capable |
+| Claude Haiku 4.5 | `us.anthropic.claude-haiku-4-5-20251001-v1:0` | Fastest Claude |
+| Amazon Nova Pro | `us.amazon.nova-pro-v1:0` | Amazon's flagship |
+| Amazon Nova Micro | `us.amazon.nova-micro-v1:0` | Fastest, cheapest |
+| DeepSeek V3.2 | `deepseek.v3.2` | Strong open model |
+| Llama 4 Scout 17B | `us.meta.llama4-scout-17b-instruct-v1:0` | Meta's latest |
+
+:::info Cross-Region Inference
+Models prefixed with `us.` use cross-region inference profiles, which provide better capacity and automatic failover across AWS regions. Models prefixed with `global.` route across all available regions worldwide.
+:::
+
+## Switching Models Mid-Session
+
+Use the `/model` command during a conversation:
+
+```
+/model us.amazon.nova-pro-v1:0
+/model deepseek.v3.2
+/model us.anthropic.claude-opus-4-6-v1
+```
+
+## Diagnostics
+
+```bash
+hermes doctor
+```
+
+The doctor checks:
+- Whether AWS credentials are available (env vars, IAM role, SSO)
+- Whether `boto3` is installed
+- Whether the Bedrock API is reachable (ListFoundationModels)
+- Number of available models in your region
+
+## Gateway (Messaging Platforms)
+
+Bedrock works with all Hermes gateway platforms (Telegram, Discord, Slack, Feishu, etc.). Configure Bedrock as your provider, then start the gateway normally:
+
+```bash
+hermes gateway setup
+hermes gateway start
+```
+
+The gateway reads `config.yaml` and uses the same Bedrock provider configuration.
+
+## Troubleshooting
+
+### "No API key found" / "No AWS credentials"
+
+Hermes checks for credentials in this order:
+1. `AWS_BEARER_TOKEN_BEDROCK`
+2. `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`
+3. `AWS_PROFILE`
+4. EC2 instance metadata (IMDS)
+5. ECS container credentials
+6. Lambda execution role
+
+If none are found, run `aws configure` or attach an IAM role to your compute instance.
+
+### "Invocation of model ID ... with on-demand throughput isn't supported"
+
+Use an **inference profile ID** (prefixed with `us.` or `global.`) instead of the bare foundation model ID. For example:
+- ❌ `anthropic.claude-sonnet-4-6`
+- ✅ `us.anthropic.claude-sonnet-4-6`
+
+### "ThrottlingException"
+
+You've hit the Bedrock per-model rate limit. Hermes automatically retries with backoff. To increase limits, request a quota increase in the [AWS Service Quotas console](https://console.aws.amazon.com/servicequotas/).

website/docs/user-guide/messaging/discord.md

@@ -297,6 +297,7 @@ discord:
   reactions: true                 # Add emoji reactions during processing
   ignored_channels: []            # Channel IDs where bot never responds
   no_thread_channels: []          # Channel IDs where bot responds without threading
+  channel_prompts: {}             # Per-channel ephemeral system prompts
 
 # Session isolation (applies to all gateway platforms, not just Discord)
 group_sessions_per_user: true     # Isolate sessions per user in shared channels
@@ -381,6 +382,28 @@ discord:
 
 Useful for channels dedicated to bot interaction where threads would add unnecessary noise.
 
+#### `discord.channel_prompts`
+
+**Type:** mapping — **Default:** `{}`
+
+Per-channel ephemeral system prompts that are injected on every turn in the matching Discord channel or thread without being persisted to transcript history.
+
+```yaml
+discord:
+  channel_prompts:
+    "1234567890": |
+      This channel is for research tasks. Prefer deep comparisons,
+      citations, and concise synthesis.
+    "9876543210": |
+      This forum is for therapy-style support. Be warm, grounded,
+      and non-judgmental.
+```
+
+Behavior:
+- Exact thread/channel ID matches win.
+- If a message arrives inside a thread or forum post and that thread has no explicit entry, Hermes falls back to the parent channel/forum ID.
+- Prompts are applied ephemerally at runtime, so changing them affects future turns immediately without rewriting past session history.
+
 #### `group_sessions_per_user`
 
 **Type:** boolean — **Default:** `true`

website/docs/user-guide/messaging/mattermost.md

@@ -281,6 +281,23 @@ If this returns your bot's user info, the token is valid. If it returns an error
 
 **Fix**: Add your User ID to `MATTERMOST_ALLOWED_USERS` in `~/.hermes/.env` and restart the gateway. Remember: the User ID is a 26-character alphanumeric string, not your `@username`.
 
+## Per-Channel Prompts
+
+Assign ephemeral system prompts to specific Mattermost channels. The prompt is injected at runtime on every turn — never persisted to transcript history — so changes take effect immediately.
+
+```yaml
+mattermost:
+  channel_prompts:
+    "channel_id_abc123": |
+      You are a research assistant. Focus on academic sources,
+      citations, and concise synthesis.
+    "channel_id_def456": |
+      Code review mode. Be precise about edge cases and
+      performance implications.
+```
+
+Keys are Mattermost channel IDs (find them in the channel URL or via the API). All messages in the matching channel get the prompt injected as an ephemeral system instruction.
+
 ## Security
 
 :::warning

website/docs/user-guide/messaging/slack.md

@@ -418,6 +418,23 @@ Hermes supports voice on Slack:
 
 ---
 
+## Per-Channel Prompts
+
+Assign ephemeral system prompts to specific Slack channels. The prompt is injected at runtime on every turn — never persisted to transcript history — so changes take effect immediately.
+
+```yaml
+slack:
+  channel_prompts:
+    "C01RESEARCH": |
+      You are a research assistant. Focus on academic sources,
+      citations, and concise synthesis.
+    "C02ENGINEERING": |
+      Code review mode. Be precise about edge cases and
+      performance implications.
+```
+
+Keys are Slack channel IDs (find them via channel details → "About" → scroll to bottom). All messages in the matching channel get the prompt injected as an ephemeral system instruction.
+
 ## Troubleshooting
 
 | Problem | Solution |

website/docs/user-guide/messaging/telegram.md

@@ -526,6 +526,29 @@ Unlike Discord (where reactions are additive), Telegram's Bot API replaces all b
 If the bot doesn't have permission to add reactions in a group, the reaction calls fail silently and message processing continues normally.
 :::
 
+## Per-Channel Prompts
+
+Assign ephemeral system prompts to specific Telegram groups or forum topics. The prompt is injected at runtime on every turn — never persisted to transcript history — so changes take effect immediately.
+
+```yaml
+telegram:
+  channel_prompts:
+    "-1001234567890": |
+      You are a research assistant. Focus on academic sources,
+      citations, and concise synthesis.
+    "42":  |
+      This topic is for creative writing feedback. Be warm and
+      constructive.
+```
+
+Keys are chat IDs (groups/supergroups) or forum topic IDs. For forum groups, topic-level prompts override the group-level prompt:
+
+- Message in topic `42` inside group `-1001234567890` → uses topic `42`'s prompt
+- Message in topic `99` (no explicit entry) → falls back to group `-1001234567890`'s prompt
+- Message in a group with no entry → no channel prompt applied
+
+Numeric YAML keys are automatically normalized to strings.
+
 ## Troubleshooting
 
 | Problem | Solution |