Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
7c38007094 |
@@ -1,4 +1,4 @@
|
||||
"""Shared auxiliary client router for side tasks.
|
||||
from agent.telemetry_logger import log_token_usage\n"""Shared auxiliary client router for side tasks.
|
||||
|
||||
Provides a single resolution chain so every consumer (context compression,
|
||||
session search, web extraction, vision analysis, browser vision) picks up
|
||||
@@ -38,7 +38,6 @@ import json
|
||||
import logging
|
||||
import os
|
||||
import threading
|
||||
from agent.telemetry_logger import log_token_usage
|
||||
import time
|
||||
from pathlib import Path # noqa: F401 — used by test mocks
|
||||
from types import SimpleNamespace
|
||||
@@ -123,16 +122,6 @@ _OR_HEADERS = {
|
||||
"X-OpenRouter-Categories": "productivity,cli-agent",
|
||||
}
|
||||
|
||||
# Vercel AI Gateway app attribution headers. HTTP-Referer maps to
|
||||
# referrerUrl and X-Title maps to appName in the gateway analytics.
|
||||
from hermes_cli import __version__ as _HERMES_VERSION
|
||||
|
||||
_AI_GATEWAY_HEADERS = {
|
||||
"HTTP-Referer": "https://hermes-agent.nousresearch.com",
|
||||
"X-Title": "Hermes Agent",
|
||||
"User-Agent": f"HermesAgent/{_HERMES_VERSION}",
|
||||
}
|
||||
|
||||
# Nous Portal extra_body for product attribution.
|
||||
# Callers should pass this as extra_body in chat.completions.create()
|
||||
# when the auxiliary client is backed by Nous Portal.
|
||||
@@ -407,8 +396,7 @@ class _CodexCompletionsAdapter:
|
||||
prompt_tokens=getattr(resp_usage, "input_tokens", 0),
|
||||
completion_tokens=getattr(resp_usage, "output_tokens", 0),
|
||||
total_tokens=getattr(resp_usage, "total_tokens", 0),
|
||||
)
|
||||
log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
|
||||
)\n log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
|
||||
except Exception as exc:
|
||||
logger.debug("Codex auxiliary Responses API call failed: %s", exc)
|
||||
raise
|
||||
@@ -541,8 +529,7 @@ class _AnthropicCompletionsAdapter:
|
||||
prompt_tokens=prompt_tokens,
|
||||
completion_tokens=completion_tokens,
|
||||
total_tokens=total_tokens,
|
||||
)
|
||||
log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
|
||||
)\n log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
|
||||
|
||||
choice = SimpleNamespace(
|
||||
index=0,
|
||||
|
||||
@@ -168,7 +168,7 @@ import time as _time
|
||||
from datetime import datetime
|
||||
|
||||
from hermes_cli import __version__, __release_date__
|
||||
from hermes_constants import AI_GATEWAY_BASE_URL, OPENROUTER_BASE_URL
|
||||
from hermes_constants import OPENROUTER_BASE_URL
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -1112,8 +1112,6 @@ def select_provider_and_model(args=None):
|
||||
# Step 2: Provider-specific setup + model selection
|
||||
if selected_provider == "openrouter":
|
||||
_model_flow_openrouter(config, current_model)
|
||||
elif selected_provider == "ai-gateway":
|
||||
_model_flow_ai_gateway(config, current_model)
|
||||
elif selected_provider == "nous":
|
||||
_model_flow_nous(config, current_model, args=args)
|
||||
elif selected_provider == "openai-codex":
|
||||
@@ -1269,55 +1267,6 @@ def _model_flow_openrouter(config, current_model=""):
|
||||
print("No change.")
|
||||
|
||||
|
||||
def _model_flow_ai_gateway(config, current_model=""):
|
||||
"""Vercel AI Gateway provider: ensure API key, then pick model with pricing."""
|
||||
from hermes_cli.auth import _prompt_model_selection, _save_model_choice, deactivate_provider
|
||||
from hermes_cli.config import get_env_value, save_env_value
|
||||
from hermes_cli.models import ai_gateway_model_ids, get_pricing_for_provider
|
||||
|
||||
api_key = get_env_value("AI_GATEWAY_API_KEY")
|
||||
if not api_key:
|
||||
print("No Vercel AI Gateway API key configured.")
|
||||
print("Create API key here: https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway&title=AI+Gateway")
|
||||
print("Add a payment method to get $5 in free credits.")
|
||||
print()
|
||||
try:
|
||||
import getpass
|
||||
key = getpass.getpass("AI Gateway API key (or Enter to cancel): ").strip()
|
||||
except (KeyboardInterrupt, EOFError):
|
||||
print()
|
||||
return
|
||||
if not key:
|
||||
print("Cancelled.")
|
||||
return
|
||||
save_env_value("AI_GATEWAY_API_KEY", key)
|
||||
print("API key saved.")
|
||||
print()
|
||||
|
||||
models_list = ai_gateway_model_ids(force_refresh=True)
|
||||
pricing = get_pricing_for_provider("ai-gateway", force_refresh=True)
|
||||
|
||||
selected = _prompt_model_selection(models_list, current_model=current_model, pricing=pricing)
|
||||
if selected:
|
||||
_save_model_choice(selected)
|
||||
|
||||
from hermes_cli.config import load_config, save_config
|
||||
|
||||
cfg = load_config()
|
||||
model = cfg.get("model")
|
||||
if not isinstance(model, dict):
|
||||
model = {"default": model} if model else {}
|
||||
cfg["model"] = model
|
||||
model["provider"] = "ai-gateway"
|
||||
model["base_url"] = AI_GATEWAY_BASE_URL
|
||||
model["api_mode"] = "chat_completions"
|
||||
save_config(cfg)
|
||||
deactivate_provider()
|
||||
print(f"Default model set to: {selected} (via Vercel AI Gateway)")
|
||||
else:
|
||||
print("No change.")
|
||||
|
||||
|
||||
def _model_flow_nous(config, current_model="", args=None):
|
||||
"""Nous Portal provider: ensure logged in, then pick model."""
|
||||
from hermes_cli.auth import (
|
||||
|
||||
@@ -58,28 +58,6 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
|
||||
|
||||
_openrouter_catalog_cache: list[tuple[str, str]] | None = None
|
||||
|
||||
# Fallback Vercel AI Gateway snapshot used when the live catalog is unavailable.
|
||||
# OSS / open-weight models prioritized first, then closed-source by family.
|
||||
VERCEL_AI_GATEWAY_MODELS: list[tuple[str, str]] = [
|
||||
("moonshotai/kimi-k2.6", "recommended"),
|
||||
("alibaba/qwen3.6-plus", ""),
|
||||
("zai/glm-5.1", ""),
|
||||
("minimax/minimax-m2.7", ""),
|
||||
("anthropic/claude-sonnet-4.6", ""),
|
||||
("anthropic/claude-opus-4.7", ""),
|
||||
("anthropic/claude-opus-4.6", ""),
|
||||
("anthropic/claude-haiku-4.5", ""),
|
||||
("openai/gpt-5.4", ""),
|
||||
("openai/gpt-5.4-mini", ""),
|
||||
("openai/gpt-5.3-codex", ""),
|
||||
("google/gemini-3.1-pro-preview", ""),
|
||||
("google/gemini-3-flash", ""),
|
||||
("google/gemini-3.1-flash-lite-preview", ""),
|
||||
("xai/grok-4.20-reasoning", ""),
|
||||
]
|
||||
|
||||
_ai_gateway_catalog_cache: list[tuple[str, str]] | None = None
|
||||
|
||||
|
||||
def _codex_curated_models() -> list[str]:
|
||||
"""Derive the openai-codex curated list from codex_models.py.
|
||||
@@ -280,21 +258,18 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
|
||||
"minimax-m2.5",
|
||||
],
|
||||
"ai-gateway": [
|
||||
"moonshotai/kimi-k2.6",
|
||||
"alibaba/qwen3.6-plus",
|
||||
"zai/glm-5.1",
|
||||
"minimax/minimax-m2.7",
|
||||
"anthropic/claude-sonnet-4.6",
|
||||
"anthropic/claude-opus-4.7",
|
||||
"anthropic/claude-opus-4.6",
|
||||
"anthropic/claude-sonnet-4.6",
|
||||
"anthropic/claude-sonnet-4.5",
|
||||
"anthropic/claude-haiku-4.5",
|
||||
"openai/gpt-5.4",
|
||||
"openai/gpt-5.4-mini",
|
||||
"openai/gpt-5.3-codex",
|
||||
"google/gemini-3.1-pro-preview",
|
||||
"openai/gpt-5",
|
||||
"openai/gpt-4.1",
|
||||
"openai/gpt-4.1-mini",
|
||||
"google/gemini-3-pro-preview",
|
||||
"google/gemini-3-flash",
|
||||
"google/gemini-3.1-flash-lite-preview",
|
||||
"xai/grok-4.20-reasoning",
|
||||
"google/gemini-2.5-pro",
|
||||
"google/gemini-2.5-flash",
|
||||
"deepseek/deepseek-v3.2",
|
||||
],
|
||||
"kilocode": [
|
||||
"anthropic/claude-opus-4.6",
|
||||
@@ -541,7 +516,6 @@ class ProviderEntry(NamedTuple):
|
||||
CANONICAL_PROVIDERS: list[ProviderEntry] = [
|
||||
ProviderEntry("nous", "Nous Portal", "Nous Portal (Nous Research subscription)"),
|
||||
ProviderEntry("openrouter", "OpenRouter", "OpenRouter (100+ models, pay-per-use)"),
|
||||
ProviderEntry("ai-gateway", "Vercel AI Gateway", "Vercel AI Gateway (200+ models, $5 free credit, no markup)"),
|
||||
ProviderEntry("anthropic", "Anthropic", "Anthropic (Claude models — API key or Claude Code)"),
|
||||
ProviderEntry("openai-codex", "OpenAI Codex", "OpenAI Codex"),
|
||||
ProviderEntry("xiaomi", "Xiaomi MiMo", "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
|
||||
@@ -562,6 +536,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
|
||||
ProviderEntry("kilocode", "Kilo Code", "Kilo Code (Kilo Gateway API)"),
|
||||
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)"),
|
||||
]
|
||||
|
||||
# Derived dicts — used throughout the codebase
|
||||
@@ -704,90 +679,6 @@ def model_ids(*, force_refresh: bool = False) -> list[str]:
|
||||
|
||||
|
||||
|
||||
def _ai_gateway_model_is_free(pricing: Any) -> bool:
|
||||
"""Return True if an AI Gateway model has $0 input AND output pricing."""
|
||||
if not isinstance(pricing, dict):
|
||||
return False
|
||||
try:
|
||||
return float(pricing.get("input", "0")) == 0 and float(pricing.get("output", "0")) == 0
|
||||
except (TypeError, ValueError):
|
||||
return False
|
||||
|
||||
|
||||
def fetch_ai_gateway_models(
|
||||
timeout: float = 8.0,
|
||||
*,
|
||||
force_refresh: bool = False,
|
||||
) -> list[tuple[str, str]]:
|
||||
"""Return the curated AI Gateway picker list, refreshed from the live catalog when possible."""
|
||||
global _ai_gateway_catalog_cache
|
||||
|
||||
if _ai_gateway_catalog_cache is not None and not force_refresh:
|
||||
return list(_ai_gateway_catalog_cache)
|
||||
|
||||
from hermes_constants import AI_GATEWAY_BASE_URL
|
||||
|
||||
fallback = list(VERCEL_AI_GATEWAY_MODELS)
|
||||
preferred_ids = [mid for mid, _ in fallback]
|
||||
|
||||
try:
|
||||
req = urllib.request.Request(
|
||||
f"{AI_GATEWAY_BASE_URL.rstrip('/')}/models",
|
||||
headers={"Accept": "application/json"},
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=timeout) as resp:
|
||||
payload = json.loads(resp.read().decode())
|
||||
except Exception:
|
||||
return list(_ai_gateway_catalog_cache or fallback)
|
||||
|
||||
live_items = payload.get("data", [])
|
||||
if not isinstance(live_items, list):
|
||||
return list(_ai_gateway_catalog_cache or fallback)
|
||||
|
||||
live_by_id: dict[str, dict[str, Any]] = {}
|
||||
for item in live_items:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
mid = str(item.get("id") or "").strip()
|
||||
if not mid:
|
||||
continue
|
||||
live_by_id[mid] = item
|
||||
|
||||
curated: list[tuple[str, str]] = []
|
||||
for preferred_id in preferred_ids:
|
||||
live_item = live_by_id.get(preferred_id)
|
||||
if live_item is None:
|
||||
continue
|
||||
desc = "free" if _ai_gateway_model_is_free(live_item.get("pricing")) else ""
|
||||
curated.append((preferred_id, desc))
|
||||
|
||||
if not curated:
|
||||
return list(_ai_gateway_catalog_cache or fallback)
|
||||
|
||||
free_moonshot = next(
|
||||
(
|
||||
mid
|
||||
for mid, item in live_by_id.items()
|
||||
if mid.startswith("moonshotai/") and _ai_gateway_model_is_free(item.get("pricing"))
|
||||
),
|
||||
None,
|
||||
)
|
||||
if free_moonshot:
|
||||
curated = [(mid, desc) for mid, desc in curated if mid != free_moonshot]
|
||||
curated.insert(0, (free_moonshot, "recommended"))
|
||||
else:
|
||||
first_id, _ = curated[0]
|
||||
curated[0] = (first_id, "recommended")
|
||||
|
||||
_ai_gateway_catalog_cache = curated
|
||||
return list(curated)
|
||||
|
||||
|
||||
def ai_gateway_model_ids(*, force_refresh: bool = False) -> list[str]:
|
||||
"""Return just the AI Gateway model-id strings."""
|
||||
return [mid for mid, _ in fetch_ai_gateway_models(force_refresh=force_refresh)]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Pricing helpers — fetch live pricing from OpenRouter-compatible /v1/models
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -930,51 +821,6 @@ def fetch_models_with_pricing(
|
||||
return result
|
||||
|
||||
|
||||
def fetch_ai_gateway_pricing(
|
||||
timeout: float = 8.0,
|
||||
*,
|
||||
force_refresh: bool = False,
|
||||
) -> dict[str, dict[str, str]]:
|
||||
"""Fetch Vercel AI Gateway /v1/models and return Hermes-shaped pricing."""
|
||||
from hermes_constants import AI_GATEWAY_BASE_URL
|
||||
|
||||
cache_key = AI_GATEWAY_BASE_URL.rstrip("/")
|
||||
if not force_refresh and cache_key in _pricing_cache:
|
||||
return _pricing_cache[cache_key]
|
||||
|
||||
try:
|
||||
req = urllib.request.Request(
|
||||
f"{cache_key}/models",
|
||||
headers={"Accept": "application/json"},
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=timeout) as resp:
|
||||
payload = json.loads(resp.read().decode())
|
||||
except Exception:
|
||||
_pricing_cache[cache_key] = {}
|
||||
return {}
|
||||
|
||||
result: dict[str, dict[str, str]] = {}
|
||||
for item in payload.get("data", []):
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
mid = item.get("id")
|
||||
pricing = item.get("pricing")
|
||||
if not (mid and isinstance(pricing, dict)):
|
||||
continue
|
||||
entry: dict[str, str] = {
|
||||
"prompt": str(pricing.get("input", "")),
|
||||
"completion": str(pricing.get("output", "")),
|
||||
}
|
||||
if pricing.get("input_cache_read"):
|
||||
entry["input_cache_read"] = str(pricing["input_cache_read"])
|
||||
if pricing.get("input_cache_write"):
|
||||
entry["input_cache_write"] = str(pricing["input_cache_write"])
|
||||
result[mid] = entry
|
||||
|
||||
_pricing_cache[cache_key] = result
|
||||
return result
|
||||
|
||||
|
||||
def _resolve_openrouter_api_key() -> str:
|
||||
"""Best-effort OpenRouter API key for pricing fetch."""
|
||||
return os.getenv("OPENROUTER_API_KEY", "").strip()
|
||||
@@ -993,7 +839,7 @@ def _resolve_nous_pricing_credentials() -> tuple[str, str]:
|
||||
|
||||
|
||||
def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> dict[str, dict[str, str]]:
|
||||
"""Return live pricing for providers that support it (openrouter, ai-gateway, nous)."""
|
||||
"""Return live pricing for providers that support it (openrouter, nous)."""
|
||||
normalized = normalize_provider(provider)
|
||||
if normalized == "openrouter":
|
||||
return fetch_models_with_pricing(
|
||||
@@ -1001,11 +847,11 @@ def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> d
|
||||
base_url="https://openrouter.ai/api",
|
||||
force_refresh=force_refresh,
|
||||
)
|
||||
if normalized == "ai-gateway":
|
||||
return fetch_ai_gateway_pricing(force_refresh=force_refresh)
|
||||
if normalized == "nous":
|
||||
api_key, base_url = _resolve_nous_pricing_credentials()
|
||||
if base_url:
|
||||
# Nous base_url typically looks like https://inference-api.nousresearch.com/v1
|
||||
# We need the part before /v1 for our fetch function
|
||||
stripped = base_url.rstrip("/")
|
||||
if stripped.endswith("/v1"):
|
||||
stripped = stripped[:-3]
|
||||
@@ -1407,7 +1253,9 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
|
||||
if live:
|
||||
return live
|
||||
if normalized == "ai-gateway":
|
||||
return ai_gateway_model_ids()
|
||||
live = _fetch_ai_gateway_models()
|
||||
if live:
|
||||
return live
|
||||
if normalized == "custom":
|
||||
base_url = _get_custom_base_url()
|
||||
if base_url:
|
||||
|
||||
@@ -26,6 +26,7 @@ from agent.memory_provider import MemoryProvider
|
||||
from tools.registry import tool_error
|
||||
from .store import MemoryStore
|
||||
from .retrieval import FactRetriever
|
||||
from .observations import ObservationSynthesizer
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -37,28 +38,29 @@ logger = logging.getLogger(__name__)
|
||||
FACT_STORE_SCHEMA = {
|
||||
"name": "fact_store",
|
||||
"description": (
|
||||
"Deep structured memory with algebraic reasoning. "
|
||||
"Deep structured memory with algebraic reasoning and grounded observation synthesis. "
|
||||
"Use alongside the memory tool — memory for always-on context, "
|
||||
"fact_store for deep recall and compositional queries.\n\n"
|
||||
"fact_store for deep recall, compositional queries, and higher-order observations.\n\n"
|
||||
"ACTIONS (simple → powerful):\n"
|
||||
"• add — Store a fact the user would expect you to remember.\n"
|
||||
"• search — Keyword lookup ('editor config', 'deploy process').\n"
|
||||
"• probe — Entity recall: ALL facts about a person/thing.\n"
|
||||
"• related — What connects to an entity? Structural adjacency.\n"
|
||||
"• reason — Compositional: facts connected to MULTIPLE entities simultaneously.\n"
|
||||
"• observe — Synthesized higher-order observations backed by supporting facts.\n"
|
||||
"• contradict — Memory hygiene: find facts making conflicting claims.\n"
|
||||
"• update/remove/list — CRUD operations.\n\n"
|
||||
"IMPORTANT: Before answering questions about the user, ALWAYS probe or reason first."
|
||||
"IMPORTANT: Before answering questions about the user, ALWAYS probe/reason/observe first."
|
||||
),
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"action": {
|
||||
"type": "string",
|
||||
"enum": ["add", "search", "probe", "related", "reason", "contradict", "update", "remove", "list"],
|
||||
"enum": ["add", "search", "probe", "related", "reason", "observe", "contradict", "update", "remove", "list"],
|
||||
},
|
||||
"content": {"type": "string", "description": "Fact content (required for 'add')."},
|
||||
"query": {"type": "string", "description": "Search query (required for 'search')."},
|
||||
"query": {"type": "string", "description": "Search query (required for 'search'/'observe')."},
|
||||
"entity": {"type": "string", "description": "Entity name for 'probe'/'related'."},
|
||||
"entities": {"type": "array", "items": {"type": "string"}, "description": "Entity names for 'reason'."},
|
||||
"fact_id": {"type": "integer", "description": "Fact ID for 'update'/'remove'."},
|
||||
@@ -66,6 +68,12 @@ FACT_STORE_SCHEMA = {
|
||||
"tags": {"type": "string", "description": "Comma-separated tags."},
|
||||
"trust_delta": {"type": "number", "description": "Trust adjustment for 'update'."},
|
||||
"min_trust": {"type": "number", "description": "Minimum trust filter (default: 0.3)."},
|
||||
"min_confidence": {"type": "number", "description": "Minimum observation confidence (default: 0.6)."},
|
||||
"observation_type": {
|
||||
"type": "string",
|
||||
"enum": ["recurring_preference", "stable_direction", "behavioral_pattern"],
|
||||
"description": "Optional observation type filter for 'observe'.",
|
||||
},
|
||||
"limit": {"type": "integer", "description": "Max results (default: 10)."},
|
||||
},
|
||||
"required": ["action"],
|
||||
@@ -118,7 +126,9 @@ class HolographicMemoryProvider(MemoryProvider):
|
||||
self._config = config or _load_plugin_config()
|
||||
self._store = None
|
||||
self._retriever = None
|
||||
self._observation_synth = None
|
||||
self._min_trust = float(self._config.get("min_trust_threshold", 0.3))
|
||||
self._observation_min_confidence = float(self._config.get("observation_min_confidence", 0.6))
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
@@ -177,6 +187,7 @@ class HolographicMemoryProvider(MemoryProvider):
|
||||
hrr_weight=hrr_weight,
|
||||
hrr_dim=hrr_dim,
|
||||
)
|
||||
self._observation_synth = ObservationSynthesizer(self._store)
|
||||
self._session_id = session_id
|
||||
|
||||
def system_prompt_block(self) -> str:
|
||||
@@ -193,30 +204,76 @@ class HolographicMemoryProvider(MemoryProvider):
|
||||
"# Holographic Memory\n"
|
||||
"Active. Empty fact store — proactively add facts the user would expect you to remember.\n"
|
||||
"Use fact_store(action='add') to store durable structured facts about people, projects, preferences, decisions.\n"
|
||||
"Use fact_store(action='observe') to synthesize higher-order observations with evidence.\n"
|
||||
"Use fact_feedback to rate facts after using them (trains trust scores)."
|
||||
)
|
||||
return (
|
||||
f"# Holographic Memory\n"
|
||||
f"Active. {total} facts stored with entity resolution and trust scoring.\n"
|
||||
f"Use fact_store to search, probe entities, reason across entities, or add facts.\n"
|
||||
f"Use fact_store to search, probe entities, reason across entities, or synthesize observations.\n"
|
||||
f"Use fact_feedback to rate facts after using them (trains trust scores)."
|
||||
)
|
||||
|
||||
def prefetch(self, query: str, *, session_id: str = "") -> str:
|
||||
if not self._retriever or not query:
|
||||
if not query:
|
||||
return ""
|
||||
|
||||
parts = []
|
||||
raw_results = []
|
||||
try:
|
||||
results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
|
||||
if not results:
|
||||
return ""
|
||||
if self._retriever:
|
||||
raw_results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
|
||||
except Exception as e:
|
||||
logger.debug("Holographic prefetch fact search failed: %s", e)
|
||||
raw_results = []
|
||||
|
||||
observations = []
|
||||
try:
|
||||
if self._observation_synth:
|
||||
observations = self._observation_synth.observe(
|
||||
query,
|
||||
min_confidence=self._observation_min_confidence,
|
||||
limit=3,
|
||||
refresh=True,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Holographic prefetch observation search failed: %s", e)
|
||||
observations = []
|
||||
|
||||
if not raw_results and observations:
|
||||
seen_fact_ids = set()
|
||||
evidence_backfill = []
|
||||
for observation in observations:
|
||||
for evidence in observation.get("evidence", []):
|
||||
fact_id = evidence.get("fact_id")
|
||||
if fact_id in seen_fact_ids:
|
||||
continue
|
||||
seen_fact_ids.add(fact_id)
|
||||
evidence_backfill.append(evidence)
|
||||
raw_results = evidence_backfill[:5]
|
||||
|
||||
if raw_results:
|
||||
lines = []
|
||||
for r in results:
|
||||
for r in raw_results:
|
||||
trust = r.get("trust_score", r.get("trust", 0))
|
||||
lines.append(f"- [{trust:.1f}] {r.get('content', '')}")
|
||||
return "## Holographic Memory\n" + "\n".join(lines)
|
||||
except Exception as e:
|
||||
logger.debug("Holographic prefetch failed: %s", e)
|
||||
return ""
|
||||
parts.append("## Holographic Memory\n" + "\n".join(lines))
|
||||
|
||||
if observations:
|
||||
lines = []
|
||||
for observation in observations:
|
||||
evidence_ids = ", ".join(
|
||||
f"#{item['fact_id']}" for item in observation.get("evidence", [])[:3]
|
||||
) or "none"
|
||||
lines.append(
|
||||
f"- [{observation.get('confidence', 0.0):.2f}] "
|
||||
f"{observation.get('observation_type', 'observation')}: "
|
||||
f"{observation.get('summary', '')} "
|
||||
f"(evidence: {evidence_ids})"
|
||||
)
|
||||
parts.append("## Holographic Observations\n" + "\n".join(lines))
|
||||
|
||||
return "\n\n".join(parts)
|
||||
|
||||
def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
|
||||
# Holographic memory stores explicit facts via tools, not auto-sync.
|
||||
@@ -252,6 +309,7 @@ class HolographicMemoryProvider(MemoryProvider):
|
||||
def shutdown(self) -> None:
|
||||
self._store = None
|
||||
self._retriever = None
|
||||
self._observation_synth = None
|
||||
|
||||
# -- Tool handlers -------------------------------------------------------
|
||||
|
||||
@@ -305,6 +363,19 @@ class HolographicMemoryProvider(MemoryProvider):
|
||||
)
|
||||
return json.dumps({"results": results, "count": len(results)})
|
||||
|
||||
elif action == "observe":
|
||||
synthesizer = self._observation_synth
|
||||
if not synthesizer:
|
||||
return tool_error("Observation synthesizer is not initialized")
|
||||
observations = synthesizer.observe(
|
||||
args.get("query", ""),
|
||||
observation_type=args.get("observation_type"),
|
||||
min_confidence=float(args.get("min_confidence", self._observation_min_confidence)),
|
||||
limit=int(args.get("limit", 10)),
|
||||
refresh=True,
|
||||
)
|
||||
return json.dumps({"observations": observations, "count": len(observations)})
|
||||
|
||||
elif action == "contradict":
|
||||
results = retriever.contradict(
|
||||
category=args.get("category"),
|
||||
|
||||
249
plugins/memory/holographic/observations.py
Normal file
249
plugins/memory/holographic/observations.py
Normal file
@@ -0,0 +1,249 @@
|
||||
"""Higher-order observation synthesis for holographic memory.
|
||||
|
||||
Builds grounded observations from accumulated facts and keeps them in a
|
||||
separate retrieval layer with explicit evidence links back to supporting facts.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
from .store import MemoryStore
|
||||
|
||||
_TOKEN_RE = re.compile(r"[a-z0-9_]+")
|
||||
_HIGHER_ORDER_CUES = {
|
||||
"prefer",
|
||||
"preference",
|
||||
"preferences",
|
||||
"style",
|
||||
"pattern",
|
||||
"patterns",
|
||||
"behavior",
|
||||
"behaviour",
|
||||
"habit",
|
||||
"habits",
|
||||
"workflow",
|
||||
"direction",
|
||||
"trajectory",
|
||||
"strategy",
|
||||
"tend",
|
||||
"usually",
|
||||
}
|
||||
|
||||
_OBSERVATION_PATTERNS = [
|
||||
{
|
||||
"observation_type": "recurring_preference",
|
||||
"subject": "communication_style",
|
||||
"categories": {"user_pref", "general"},
|
||||
"labels": {
|
||||
"concise": ["concise", "terse", "brief", "short", "no fluff"],
|
||||
"result_first": ["result-only", "result only", "outcome only", "quick", "quickly"],
|
||||
"silent_ops": ["silent", "no status", "no repetitive status", "no questions"],
|
||||
},
|
||||
"summary_prefix": "Recurring preference",
|
||||
},
|
||||
{
|
||||
"observation_type": "stable_direction",
|
||||
"subject": "project_direction",
|
||||
"categories": {"project", "general", "tool"},
|
||||
"labels": {
|
||||
"local_first": ["local-first", "local first", "local-only", "local only", "ollama", "own hardware"],
|
||||
"gitea_first": ["gitea-first", "gitea first", "forge", "pull request", "pr flow", "issue flow"],
|
||||
"ansible": ["ansible", "playbook", "role", "deploy via ansible"],
|
||||
},
|
||||
"summary_prefix": "Stable direction",
|
||||
},
|
||||
{
|
||||
"observation_type": "behavioral_pattern",
|
||||
"subject": "operator_workflow",
|
||||
"categories": {"general", "project", "tool", "user_pref"},
|
||||
"labels": {
|
||||
"commit_early": ["commit early", "commits early", "commit after", "wip commit"],
|
||||
"pr_first": ["open pr", "push a pr", "pull request", "pr immediately", "create pr"],
|
||||
"dedup_guard": ["no dupes", "no duplicates", "avoid duplicate", "existing pr"],
|
||||
},
|
||||
"summary_prefix": "Behavioral pattern",
|
||||
},
|
||||
]
|
||||
|
||||
_TYPE_QUERY_HINTS = {
|
||||
"recurring_preference": {"prefer", "preference", "style", "communication", "likes", "wants"},
|
||||
"stable_direction": {"direction", "trajectory", "strategy", "project", "roadmap", "moving"},
|
||||
"behavioral_pattern": {"pattern", "behavior", "workflow", "habit", "operator", "agent", "usually"},
|
||||
}
|
||||
|
||||
|
||||
class ObservationSynthesizer:
|
||||
"""Synthesizes grounded observations from facts and retrieves them by query."""
|
||||
|
||||
def __init__(self, store: MemoryStore):
|
||||
self.store = store
|
||||
|
||||
def synthesize(
|
||||
self,
|
||||
*,
|
||||
persist: bool = True,
|
||||
min_confidence: float = 0.6,
|
||||
limit: int = 10,
|
||||
) -> list[dict[str, Any]]:
|
||||
facts = self.store.list_facts(min_trust=0.0, limit=1000)
|
||||
observations: list[dict[str, Any]] = []
|
||||
|
||||
for pattern in _OBSERVATION_PATTERNS:
|
||||
candidate = self._build_candidate(pattern, facts, min_confidence=min_confidence)
|
||||
if not candidate:
|
||||
continue
|
||||
|
||||
if persist:
|
||||
candidate["observation_id"] = self.store.upsert_observation(
|
||||
candidate["observation_type"],
|
||||
candidate["subject"],
|
||||
candidate["summary"],
|
||||
candidate["confidence"],
|
||||
candidate["evidence_fact_ids"],
|
||||
metadata=candidate["metadata"],
|
||||
)
|
||||
|
||||
candidate["evidence"] = self._expand_evidence(candidate["evidence_fact_ids"])
|
||||
candidate["evidence_count"] = len(candidate["evidence"])
|
||||
candidate.pop("evidence_fact_ids", None)
|
||||
observations.append(candidate)
|
||||
|
||||
observations.sort(
|
||||
key=lambda item: (item["confidence"], item.get("evidence_count", 0)),
|
||||
reverse=True,
|
||||
)
|
||||
return observations[:limit]
|
||||
|
||||
def observe(
|
||||
self,
|
||||
query: str = "",
|
||||
*,
|
||||
observation_type: str | None = None,
|
||||
min_confidence: float = 0.6,
|
||||
limit: int = 10,
|
||||
refresh: bool = True,
|
||||
) -> list[dict[str, Any]]:
|
||||
if refresh:
|
||||
self.synthesize(persist=True, min_confidence=min_confidence, limit=limit)
|
||||
|
||||
observations = self.store.list_observations(
|
||||
observation_type=observation_type,
|
||||
min_confidence=min_confidence,
|
||||
limit=max(limit * 4, 20),
|
||||
)
|
||||
if not observations:
|
||||
return []
|
||||
|
||||
if not query:
|
||||
return observations[:limit]
|
||||
|
||||
query_tokens = self._tokenize(query)
|
||||
is_higher_order = bool(query_tokens & _HIGHER_ORDER_CUES)
|
||||
ranked: list[dict[str, Any]] = []
|
||||
|
||||
for item in observations:
|
||||
searchable = " ".join(
|
||||
[
|
||||
item.get("summary", ""),
|
||||
item.get("subject", ""),
|
||||
item.get("observation_type", ""),
|
||||
" ".join(item.get("metadata", {}).get("labels", [])),
|
||||
]
|
||||
)
|
||||
overlap = self._overlap_score(query_tokens, self._tokenize(searchable))
|
||||
type_bonus = self._type_bonus(query_tokens, item.get("observation_type", ""))
|
||||
if overlap <= 0 and type_bonus <= 0 and not is_higher_order:
|
||||
continue
|
||||
ranked_item = dict(item)
|
||||
ranked_item["score"] = round(item.get("confidence", 0.0) + overlap + type_bonus, 3)
|
||||
ranked.append(ranked_item)
|
||||
|
||||
if not ranked and is_higher_order:
|
||||
ranked = [
|
||||
{**item, "score": round(float(item.get("confidence", 0.0)), 3)}
|
||||
for item in observations
|
||||
]
|
||||
|
||||
ranked.sort(
|
||||
key=lambda item: (item.get("score", 0.0), item.get("confidence", 0.0), item.get("evidence_count", 0)),
|
||||
reverse=True,
|
||||
)
|
||||
return ranked[:limit]
|
||||
|
||||
def _build_candidate(
|
||||
self,
|
||||
pattern: dict[str, Any],
|
||||
facts: list[dict[str, Any]],
|
||||
*,
|
||||
min_confidence: float,
|
||||
) -> dict[str, Any] | None:
|
||||
matched_fact_ids: set[int] = set()
|
||||
matched_labels: dict[str, set[int]] = {label: set() for label in pattern["labels"]}
|
||||
|
||||
for fact in facts:
|
||||
if fact.get("category") not in pattern["categories"]:
|
||||
continue
|
||||
haystack = f"{fact.get('content', '')} {fact.get('tags', '')}".lower()
|
||||
local_match = False
|
||||
for label, keywords in pattern["labels"].items():
|
||||
if any(keyword in haystack for keyword in keywords):
|
||||
matched_labels[label].add(int(fact["fact_id"]))
|
||||
local_match = True
|
||||
if local_match:
|
||||
matched_fact_ids.add(int(fact["fact_id"]))
|
||||
|
||||
if len(matched_fact_ids) < 2:
|
||||
return None
|
||||
|
||||
active_labels = sorted(label for label, ids in matched_labels.items() if ids)
|
||||
confidence = min(0.95, 0.35 + 0.12 * len(matched_fact_ids) + 0.08 * len(active_labels))
|
||||
confidence = round(confidence, 3)
|
||||
if confidence < min_confidence:
|
||||
return None
|
||||
|
||||
label_summary = ", ".join(label.replace("_", "-") for label in active_labels)
|
||||
subject_text = pattern["subject"].replace("_", " ")
|
||||
summary = (
|
||||
f"{pattern['summary_prefix']}: {subject_text} trends toward {label_summary} "
|
||||
f"based on {len(matched_fact_ids)} supporting facts."
|
||||
)
|
||||
return {
|
||||
"observation_type": pattern["observation_type"],
|
||||
"subject": pattern["subject"],
|
||||
"summary": summary,
|
||||
"confidence": confidence,
|
||||
"metadata": {
|
||||
"labels": active_labels,
|
||||
"evidence_count": len(matched_fact_ids),
|
||||
},
|
||||
"evidence_fact_ids": sorted(matched_fact_ids),
|
||||
}
|
||||
|
||||
def _expand_evidence(self, fact_ids: list[int]) -> list[dict[str, Any]]:
|
||||
facts_by_id = {
|
||||
fact["fact_id"]: fact
|
||||
for fact in self.store.list_facts(min_trust=0.0, limit=1000)
|
||||
}
|
||||
return [facts_by_id[fact_id] for fact_id in fact_ids if fact_id in facts_by_id]
|
||||
|
||||
@staticmethod
|
||||
def _tokenize(text: str) -> set[str]:
|
||||
return set(_TOKEN_RE.findall(text.lower()))
|
||||
|
||||
@staticmethod
|
||||
def _overlap_score(query_tokens: set[str], text_tokens: set[str]) -> float:
|
||||
if not query_tokens or not text_tokens:
|
||||
return 0.0
|
||||
overlap = query_tokens & text_tokens
|
||||
if not overlap:
|
||||
return 0.0
|
||||
return round(len(overlap) / max(len(query_tokens), 1), 3)
|
||||
|
||||
@staticmethod
|
||||
def _type_bonus(query_tokens: set[str], observation_type: str) -> float:
|
||||
hints = _TYPE_QUERY_HINTS.get(observation_type, set())
|
||||
if not hints:
|
||||
return 0.0
|
||||
return 0.25 if query_tokens & hints else 0.0
|
||||
@@ -3,6 +3,7 @@ SQLite-backed fact store with entity resolution and trust scoring.
|
||||
Single-user Hermes memory store plugin.
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
import sqlite3
|
||||
import threading
|
||||
@@ -73,6 +74,28 @@ CREATE TABLE IF NOT EXISTS memory_banks (
|
||||
fact_count INTEGER DEFAULT 0,
|
||||
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
);
|
||||
|
||||
CREATE TABLE IF NOT EXISTS observations (
|
||||
observation_id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
observation_type TEXT NOT NULL,
|
||||
subject TEXT NOT NULL,
|
||||
summary TEXT NOT NULL,
|
||||
confidence REAL DEFAULT 0.0,
|
||||
metadata_json TEXT DEFAULT '{}',
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
UNIQUE(observation_type, subject)
|
||||
);
|
||||
|
||||
CREATE TABLE IF NOT EXISTS observation_evidence (
|
||||
observation_id INTEGER REFERENCES observations(observation_id) ON DELETE CASCADE,
|
||||
fact_id INTEGER REFERENCES facts(fact_id) ON DELETE CASCADE,
|
||||
evidence_weight REAL DEFAULT 1.0,
|
||||
PRIMARY KEY (observation_id, fact_id)
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_observations_type ON observations(observation_type);
|
||||
CREATE INDEX IF NOT EXISTS idx_observations_confidence ON observations(confidence DESC);
|
||||
"""
|
||||
|
||||
# Trust adjustment constants
|
||||
@@ -128,6 +151,7 @@ class MemoryStore:
|
||||
def _init_db(self) -> None:
|
||||
"""Create tables, indexes, and triggers if they do not exist. Enable WAL mode."""
|
||||
self._conn.execute("PRAGMA journal_mode=WAL")
|
||||
self._conn.execute("PRAGMA foreign_keys=ON")
|
||||
self._conn.executescript(_SCHEMA)
|
||||
# Migrate: add hrr_vector column if missing (safe for existing databases)
|
||||
columns = {row[1] for row in self._conn.execute("PRAGMA table_info(facts)").fetchall()}
|
||||
@@ -346,6 +370,115 @@ class MemoryStore:
|
||||
rows = self._conn.execute(sql, params).fetchall()
|
||||
return [self._row_to_dict(r) for r in rows]
|
||||
|
||||
def upsert_observation(
|
||||
self,
|
||||
observation_type: str,
|
||||
subject: str,
|
||||
summary: str,
|
||||
confidence: float,
|
||||
evidence_fact_ids: list[int],
|
||||
metadata: dict | None = None,
|
||||
) -> int:
|
||||
"""Create or update a synthesized observation and its evidence links."""
|
||||
with self._lock:
|
||||
metadata_json = json.dumps(metadata or {}, sort_keys=True)
|
||||
self._conn.execute(
|
||||
"""
|
||||
INSERT INTO observations (
|
||||
observation_type, subject, summary, confidence, metadata_json
|
||||
)
|
||||
VALUES (?, ?, ?, ?, ?)
|
||||
ON CONFLICT(observation_type, subject) DO UPDATE SET
|
||||
summary = excluded.summary,
|
||||
confidence = excluded.confidence,
|
||||
metadata_json = excluded.metadata_json,
|
||||
updated_at = CURRENT_TIMESTAMP
|
||||
""",
|
||||
(observation_type, subject, summary, confidence, metadata_json),
|
||||
)
|
||||
row = self._conn.execute(
|
||||
"""
|
||||
SELECT observation_id
|
||||
FROM observations
|
||||
WHERE observation_type = ? AND subject = ?
|
||||
""",
|
||||
(observation_type, subject),
|
||||
).fetchone()
|
||||
observation_id = int(row["observation_id"])
|
||||
|
||||
self._conn.execute(
|
||||
"DELETE FROM observation_evidence WHERE observation_id = ?",
|
||||
(observation_id,),
|
||||
)
|
||||
unique_fact_ids = sorted({int(fid) for fid in evidence_fact_ids})
|
||||
if unique_fact_ids:
|
||||
self._conn.executemany(
|
||||
"""
|
||||
INSERT OR IGNORE INTO observation_evidence (observation_id, fact_id)
|
||||
VALUES (?, ?)
|
||||
""",
|
||||
[(observation_id, fact_id) for fact_id in unique_fact_ids],
|
||||
)
|
||||
self._conn.commit()
|
||||
return observation_id
|
||||
|
||||
def list_observations(
|
||||
self,
|
||||
observation_type: str | None = None,
|
||||
min_confidence: float = 0.0,
|
||||
limit: int = 50,
|
||||
) -> list[dict]:
|
||||
"""List synthesized observations with expanded supporting evidence."""
|
||||
with self._lock:
|
||||
params: list = [min_confidence]
|
||||
observation_clause = ""
|
||||
if observation_type is not None:
|
||||
observation_clause = "AND observation_type = ?"
|
||||
params.append(observation_type)
|
||||
params.append(limit)
|
||||
rows = self._conn.execute(
|
||||
f"""
|
||||
SELECT observation_id, observation_type, subject, summary, confidence,
|
||||
metadata_json, created_at, updated_at,
|
||||
(
|
||||
SELECT COUNT(*)
|
||||
FROM observation_evidence oe
|
||||
WHERE oe.observation_id = observations.observation_id
|
||||
) AS evidence_count
|
||||
FROM observations
|
||||
WHERE confidence >= ?
|
||||
{observation_clause}
|
||||
ORDER BY confidence DESC, updated_at DESC
|
||||
LIMIT ?
|
||||
""",
|
||||
params,
|
||||
).fetchall()
|
||||
|
||||
results = []
|
||||
for row in rows:
|
||||
item = dict(row)
|
||||
try:
|
||||
item["metadata"] = json.loads(item.pop("metadata_json") or "{}")
|
||||
except json.JSONDecodeError:
|
||||
item["metadata"] = {}
|
||||
item["evidence"] = self._get_observation_evidence(int(item["observation_id"]))
|
||||
results.append(item)
|
||||
return results
|
||||
|
||||
def _get_observation_evidence(self, observation_id: int) -> list[dict]:
|
||||
rows = self._conn.execute(
|
||||
"""
|
||||
SELECT f.fact_id, f.content, f.category, f.tags, f.trust_score,
|
||||
f.retrieval_count, f.helpful_count, f.created_at, f.updated_at
|
||||
FROM observation_evidence oe
|
||||
JOIN facts f ON f.fact_id = oe.fact_id
|
||||
WHERE oe.observation_id = ?
|
||||
ORDER BY f.trust_score DESC, f.updated_at DESC
|
||||
""",
|
||||
(observation_id,),
|
||||
).fetchall()
|
||||
return [self._row_to_dict(row) for row in rows]
|
||||
|
||||
def record_feedback(self, fact_id: int, helpful: bool) -> dict:
|
||||
"""Record user feedback and adjust trust asymmetrically.
|
||||
|
||||
|
||||
@@ -908,10 +908,6 @@ class AIAgent:
|
||||
"X-OpenRouter-Title": "Hermes Agent",
|
||||
"X-OpenRouter-Categories": "productivity,cli-agent",
|
||||
}
|
||||
elif "ai-gateway.vercel.sh" in effective_base.lower():
|
||||
from agent.auxiliary_client import _AI_GATEWAY_HEADERS
|
||||
|
||||
client_kwargs["default_headers"] = dict(_AI_GATEWAY_HEADERS)
|
||||
elif "api.githubcopilot.com" in effective_base.lower():
|
||||
from hermes_cli.models import copilot_default_headers
|
||||
|
||||
@@ -4671,13 +4667,11 @@ class AIAgent:
|
||||
return True
|
||||
|
||||
def _apply_client_headers_for_base_url(self, base_url: str) -> None:
|
||||
from agent.auxiliary_client import _AI_GATEWAY_HEADERS, _OR_HEADERS
|
||||
from agent.auxiliary_client import _OR_HEADERS
|
||||
|
||||
normalized = (base_url or "").lower()
|
||||
if "openrouter" in normalized:
|
||||
self._client_kwargs["default_headers"] = dict(_OR_HEADERS)
|
||||
elif "ai-gateway.vercel.sh" in normalized:
|
||||
self._client_kwargs["default_headers"] = dict(_AI_GATEWAY_HEADERS)
|
||||
elif "api.githubcopilot.com" in normalized:
|
||||
from hermes_cli.models import copilot_default_headers
|
||||
|
||||
|
||||
@@ -1,222 +0,0 @@
|
||||
"""AI Gateway provider UX, live pricing, and model promotion tests."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from hermes_cli import models as models_module
|
||||
from hermes_cli.models import (
|
||||
CANONICAL_PROVIDERS,
|
||||
VERCEL_AI_GATEWAY_MODELS,
|
||||
_ai_gateway_model_is_free,
|
||||
ai_gateway_model_ids,
|
||||
fetch_ai_gateway_models,
|
||||
fetch_ai_gateway_pricing,
|
||||
get_pricing_for_provider,
|
||||
)
|
||||
|
||||
|
||||
def _mock_urlopen(payload):
|
||||
resp = MagicMock()
|
||||
resp.read.return_value = json.dumps(payload).encode()
|
||||
ctx = MagicMock()
|
||||
ctx.__enter__.return_value = resp
|
||||
ctx.__exit__.return_value = False
|
||||
return ctx
|
||||
|
||||
|
||||
def _reset_caches():
|
||||
models_module._ai_gateway_catalog_cache = None
|
||||
models_module._pricing_cache.clear()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def config_home(tmp_path, monkeypatch):
|
||||
home = tmp_path / "hermes"
|
||||
home.mkdir()
|
||||
(home / "config.yaml").write_text("model: some-old-model\n")
|
||||
(home / ".env").write_text("")
|
||||
monkeypatch.setenv("HERMES_HOME", str(home))
|
||||
monkeypatch.delenv("AI_GATEWAY_API_KEY", raising=False)
|
||||
monkeypatch.delenv("AI_GATEWAY_BASE_URL", raising=False)
|
||||
return home
|
||||
|
||||
|
||||
def test_ai_gateway_provider_is_promoted_near_top_of_picker():
|
||||
slugs = [entry.slug for entry in CANONICAL_PROVIDERS]
|
||||
assert "ai-gateway" in slugs[:3]
|
||||
|
||||
|
||||
def test_ai_gateway_pricing_translates_input_output_to_prompt_completion():
|
||||
_reset_caches()
|
||||
payload = {
|
||||
"data": [
|
||||
{
|
||||
"id": "moonshotai/kimi-k2.5",
|
||||
"type": "language",
|
||||
"pricing": {
|
||||
"input": "0.0000006",
|
||||
"output": "0.0000025",
|
||||
"input_cache_read": "0.00000015",
|
||||
"input_cache_write": "0.0000006",
|
||||
},
|
||||
}
|
||||
]
|
||||
}
|
||||
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
|
||||
result = fetch_ai_gateway_pricing(force_refresh=True)
|
||||
|
||||
entry = result["moonshotai/kimi-k2.5"]
|
||||
assert entry["prompt"] == "0.0000006"
|
||||
assert entry["completion"] == "0.0000025"
|
||||
assert entry["input_cache_read"] == "0.00000015"
|
||||
assert entry["input_cache_write"] == "0.0000006"
|
||||
|
||||
|
||||
def test_get_pricing_for_provider_supports_ai_gateway():
|
||||
_reset_caches()
|
||||
payload = {
|
||||
"data": [
|
||||
{
|
||||
"id": "moonshotai/kimi-k2.5",
|
||||
"type": "language",
|
||||
"pricing": {"input": "0.0001", "output": "0.0002"},
|
||||
}
|
||||
]
|
||||
}
|
||||
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
|
||||
result = get_pricing_for_provider("ai-gateway", force_refresh=True)
|
||||
assert result["moonshotai/kimi-k2.5"] == {"prompt": "0.0001", "completion": "0.0002"}
|
||||
|
||||
|
||||
def test_ai_gateway_pricing_returns_empty_on_fetch_failure():
|
||||
_reset_caches()
|
||||
with patch("urllib.request.urlopen", side_effect=OSError("network down")):
|
||||
result = fetch_ai_gateway_pricing(force_refresh=True)
|
||||
assert result == {}
|
||||
|
||||
|
||||
def test_ai_gateway_pricing_skips_entries_without_pricing_dict():
|
||||
_reset_caches()
|
||||
payload = {
|
||||
"data": [
|
||||
{"id": "x/y", "pricing": None},
|
||||
{"id": "a/b", "pricing": {"input": "0", "output": "0"}},
|
||||
]
|
||||
}
|
||||
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
|
||||
result = fetch_ai_gateway_pricing(force_refresh=True)
|
||||
assert "x/y" not in result
|
||||
assert result["a/b"] == {"prompt": "0", "completion": "0"}
|
||||
|
||||
|
||||
def test_ai_gateway_free_detector():
|
||||
assert _ai_gateway_model_is_free({"input": "0", "output": "0"}) is True
|
||||
assert _ai_gateway_model_is_free({"input": "0", "output": "0.01"}) is False
|
||||
assert _ai_gateway_model_is_free({"input": "0.01", "output": "0"}) is False
|
||||
assert _ai_gateway_model_is_free(None) is False
|
||||
assert _ai_gateway_model_is_free({"input": "not a number"}) is False
|
||||
|
||||
|
||||
def test_fetch_ai_gateway_models_filters_against_live_catalog():
|
||||
_reset_caches()
|
||||
preferred = [mid for mid, _ in VERCEL_AI_GATEWAY_MODELS]
|
||||
live_ids = preferred[:3]
|
||||
payload = {
|
||||
"data": [
|
||||
{"id": mid, "pricing": {"input": "0.001", "output": "0.002"}}
|
||||
for mid in live_ids
|
||||
]
|
||||
}
|
||||
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
|
||||
result = fetch_ai_gateway_models(force_refresh=True)
|
||||
|
||||
assert [mid for mid, _ in result] == live_ids
|
||||
assert result[0][1] == "recommended"
|
||||
assert ai_gateway_model_ids(force_refresh=False) == live_ids
|
||||
|
||||
|
||||
def test_fetch_ai_gateway_models_tags_free_models():
|
||||
_reset_caches()
|
||||
first_id = VERCEL_AI_GATEWAY_MODELS[0][0]
|
||||
second_id = VERCEL_AI_GATEWAY_MODELS[1][0]
|
||||
payload = {
|
||||
"data": [
|
||||
{"id": first_id, "pricing": {"input": "0.001", "output": "0.002"}},
|
||||
{"id": second_id, "pricing": {"input": "0", "output": "0"}},
|
||||
]
|
||||
}
|
||||
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
|
||||
result = fetch_ai_gateway_models(force_refresh=True)
|
||||
|
||||
by_id = dict(result)
|
||||
assert by_id[first_id] == "recommended"
|
||||
assert by_id[second_id] == "free"
|
||||
|
||||
|
||||
def test_free_moonshot_model_auto_promoted_to_top_even_if_not_curated():
|
||||
_reset_caches()
|
||||
first_curated = VERCEL_AI_GATEWAY_MODELS[0][0]
|
||||
unlisted_free_moonshot = "moonshotai/kimi-coder-free-preview"
|
||||
payload = {
|
||||
"data": [
|
||||
{"id": first_curated, "pricing": {"input": "0.001", "output": "0.002"}},
|
||||
{"id": unlisted_free_moonshot, "pricing": {"input": "0", "output": "0"}},
|
||||
]
|
||||
}
|
||||
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
|
||||
result = fetch_ai_gateway_models(force_refresh=True)
|
||||
|
||||
assert result[0] == (unlisted_free_moonshot, "recommended")
|
||||
assert any(mid == first_curated for mid, _ in result)
|
||||
|
||||
|
||||
def test_paid_moonshot_does_not_get_auto_promoted():
|
||||
_reset_caches()
|
||||
first_curated = VERCEL_AI_GATEWAY_MODELS[0][0]
|
||||
payload = {
|
||||
"data": [
|
||||
{"id": first_curated, "pricing": {"input": "0.001", "output": "0.002"}},
|
||||
{"id": "moonshotai/some-paid-variant", "pricing": {"input": "0.001", "output": "0.002"}},
|
||||
]
|
||||
}
|
||||
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
|
||||
result = fetch_ai_gateway_models(force_refresh=True)
|
||||
|
||||
assert result[0][0] == first_curated
|
||||
|
||||
|
||||
def test_fetch_ai_gateway_models_falls_back_on_error():
|
||||
_reset_caches()
|
||||
with patch("urllib.request.urlopen", side_effect=OSError("network")):
|
||||
result = fetch_ai_gateway_models(force_refresh=True)
|
||||
assert result == list(VERCEL_AI_GATEWAY_MODELS)
|
||||
|
||||
|
||||
def test_ai_gateway_setup_flow_shows_deeplink_and_passes_pricing(config_home, monkeypatch, capsys):
|
||||
from hermes_cli.main import _model_flow_ai_gateway
|
||||
from hermes_cli.config import load_config
|
||||
|
||||
pricing = {"moonshotai/kimi-k2.6": {"prompt": "0", "completion": "0"}}
|
||||
monkeypatch.setenv("HERMES_HOME", str(config_home))
|
||||
|
||||
with patch("getpass.getpass", return_value="vercel-key"), \
|
||||
patch("hermes_cli.models.ai_gateway_model_ids", return_value=["moonshotai/kimi-k2.6"]), \
|
||||
patch("hermes_cli.models.get_pricing_for_provider", return_value=pricing), \
|
||||
patch("hermes_cli.auth._prompt_model_selection", return_value="moonshotai/kimi-k2.6") as prompt_selection, \
|
||||
patch("hermes_cli.auth.deactivate_provider"):
|
||||
_model_flow_ai_gateway(load_config(), "")
|
||||
|
||||
out = capsys.readouterr().out
|
||||
assert "vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway&title=AI+Gateway" in out
|
||||
assert "free credits" in out.lower()
|
||||
assert prompt_selection.call_args.kwargs["pricing"] == pricing
|
||||
|
||||
import yaml
|
||||
config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
|
||||
model = config["model"]
|
||||
assert model["provider"] == "ai-gateway"
|
||||
assert model["api_mode"] == "chat_completions"
|
||||
96
tests/plugins/memory/test_holographic_observations.py
Normal file
96
tests/plugins/memory/test_holographic_observations.py
Normal file
@@ -0,0 +1,96 @@
|
||||
import json
|
||||
|
||||
import pytest
|
||||
|
||||
from plugins.memory.holographic import HolographicMemoryProvider
|
||||
from plugins.memory.holographic.store import MemoryStore
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def store(tmp_path):
|
||||
db_path = tmp_path / "memory.db"
|
||||
s = MemoryStore(db_path=str(db_path), default_trust=0.5)
|
||||
yield s
|
||||
s.close()
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def provider(tmp_path):
|
||||
p = HolographicMemoryProvider(
|
||||
config={
|
||||
"db_path": str(tmp_path / "memory.db"),
|
||||
"default_trust": 0.5,
|
||||
}
|
||||
)
|
||||
p.initialize(session_id="test-session")
|
||||
yield p
|
||||
if p._store:
|
||||
p._store.close()
|
||||
|
||||
|
||||
class TestObservationSynthesis:
|
||||
def test_observe_action_persists_observation_with_evidence_links(self, provider):
|
||||
fact_ids = [
|
||||
provider._store.add_fact('User prefers concise status updates', category='user_pref'),
|
||||
provider._store.add_fact('User wants result-only replies with no fluff', category='user_pref'),
|
||||
]
|
||||
|
||||
result = json.loads(
|
||||
provider.handle_tool_call(
|
||||
'fact_store',
|
||||
{
|
||||
'action': 'observe',
|
||||
'query': 'What communication style does the user prefer?',
|
||||
'limit': 5,
|
||||
},
|
||||
)
|
||||
)
|
||||
|
||||
assert result['count'] == 1
|
||||
observation = result['observations'][0]
|
||||
assert observation['observation_type'] == 'recurring_preference'
|
||||
assert observation['confidence'] >= 0.6
|
||||
assert sorted(item['fact_id'] for item in observation['evidence']) == sorted(fact_ids)
|
||||
|
||||
stored = provider._store.list_observations(limit=10)
|
||||
assert len(stored) == 1
|
||||
assert stored[0]['observation_type'] == 'recurring_preference'
|
||||
assert stored[0]['evidence_count'] == 2
|
||||
assert len(provider._store.list_facts(limit=10)) == 2
|
||||
|
||||
def test_observe_action_synthesizes_three_observation_types(self, provider):
|
||||
provider._store.add_fact('User prefers concise updates', category='user_pref')
|
||||
provider._store.add_fact('User wants result-only communication', category='user_pref')
|
||||
provider._store.add_fact('Project is moving to a local-first deployment model', category='project')
|
||||
provider._store.add_fact('Project direction stays Gitea-first for issue and PR flow', category='project')
|
||||
provider._store.add_fact('Operator always commits early before moving on', category='general')
|
||||
provider._store.add_fact('Operator pushes a PR immediately after each meaningful fix', category='general')
|
||||
|
||||
result = json.loads(provider.handle_tool_call('fact_store', {'action': 'observe', 'limit': 10}))
|
||||
types = {item['observation_type'] for item in result['observations']}
|
||||
|
||||
assert {'recurring_preference', 'stable_direction', 'behavioral_pattern'} <= types
|
||||
|
||||
def test_single_fact_does_not_create_overconfident_observation(self, provider):
|
||||
provider._store.add_fact('User prefers concise updates', category='user_pref')
|
||||
|
||||
result = json.loads(
|
||||
provider.handle_tool_call(
|
||||
'fact_store',
|
||||
{'action': 'observe', 'query': 'What does the user prefer?', 'limit': 5},
|
||||
)
|
||||
)
|
||||
|
||||
assert result['count'] == 0
|
||||
assert provider._store.list_observations(limit=10) == []
|
||||
|
||||
def test_prefetch_surfaces_observations_as_separate_layer(self, provider):
|
||||
provider._store.add_fact('User prefers concise updates', category='user_pref')
|
||||
provider._store.add_fact('User wants result-only communication', category='user_pref')
|
||||
|
||||
prefetch = provider.prefetch('What communication style does the user prefer?')
|
||||
|
||||
assert '## Holographic Observations' in prefetch
|
||||
assert '## Holographic Memory' in prefetch
|
||||
assert 'recurring_preference' in prefetch
|
||||
assert 'evidence' in prefetch.lower()
|
||||
@@ -1,62 +0,0 @@
|
||||
"""Attribution default_headers applied per provider via base-URL detection."""
|
||||
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from run_agent import AIAgent
|
||||
|
||||
|
||||
@patch("run_agent.OpenAI")
|
||||
def test_openrouter_base_url_applies_or_headers(mock_openai):
|
||||
mock_openai.return_value = MagicMock()
|
||||
agent = AIAgent(
|
||||
api_key="test-key",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
model="test/model",
|
||||
quiet_mode=True,
|
||||
skip_context_files=True,
|
||||
skip_memory=True,
|
||||
)
|
||||
|
||||
agent._apply_client_headers_for_base_url("https://openrouter.ai/api/v1")
|
||||
|
||||
headers = agent._client_kwargs["default_headers"]
|
||||
assert headers["HTTP-Referer"] == "https://hermes-agent.nousresearch.com"
|
||||
assert headers["X-OpenRouter-Title"] == "Hermes Agent"
|
||||
|
||||
|
||||
@patch("run_agent.OpenAI")
|
||||
def test_ai_gateway_base_url_applies_attribution_headers(mock_openai):
|
||||
mock_openai.return_value = MagicMock()
|
||||
agent = AIAgent(
|
||||
api_key="test-key",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
model="test/model",
|
||||
quiet_mode=True,
|
||||
skip_context_files=True,
|
||||
skip_memory=True,
|
||||
)
|
||||
|
||||
agent._apply_client_headers_for_base_url("https://ai-gateway.vercel.sh/v1")
|
||||
|
||||
headers = agent._client_kwargs["default_headers"]
|
||||
assert headers["HTTP-Referer"] == "https://hermes-agent.nousresearch.com"
|
||||
assert headers["X-Title"] == "Hermes Agent"
|
||||
assert headers["User-Agent"].startswith("HermesAgent/")
|
||||
|
||||
|
||||
@patch("run_agent.OpenAI")
|
||||
def test_unknown_base_url_clears_default_headers(mock_openai):
|
||||
mock_openai.return_value = MagicMock()
|
||||
agent = AIAgent(
|
||||
api_key="test-key",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
model="test/model",
|
||||
quiet_mode=True,
|
||||
skip_context_files=True,
|
||||
skip_memory=True,
|
||||
)
|
||||
agent._client_kwargs["default_headers"] = {"X-Stale": "yes"}
|
||||
|
||||
agent._apply_client_headers_for_base_url("https://api.example.com/v1")
|
||||
|
||||
assert "default_headers" not in agent._client_kwargs
|
||||
Reference in New Issue
Block a user