feat: add route-aware pricing estimates (#1695)
Salvaged from PR #1563 by @kshitijk4poor. Cherry-picked with authorship preserved. - Route-aware pricing architecture replacing static MODEL_PRICING + heuristics - Canonical usage normalization (Anthropic/OpenAI/Codex API shapes) - Cache-aware billing (separate cache_read/cache_write rates) - Cost status tracking (estimated/included/unknown/actual) - OpenRouter live pricing via models API - Schema migration v4→v5 with billing metadata columns - Removed speculative forward-looking entries - Removed cost display from CLI status bar - Threaded OpenRouter metadata pre-warm Co-authored-by: kshitij <82637225+kshitijk4poor@users.noreply.github.com>
This commit is contained in:
Teknium
95
cli.py
95
cli.py
@@ -58,7 +58,12 @@ except (ImportError, AttributeError):
|
||||
import threading
|
||||
import queue
|
||||
|
||||
from agent.usage_pricing import estimate_cost_usd, format_duration_compact, format_token_count_compact, has_known_pricing
|
||||
from agent.usage_pricing import (
|
||||
CanonicalUsage,
|
||||
estimate_usage_cost,
|
||||
format_duration_compact,
|
||||
format_token_count_compact,
|
||||
)
|
||||
from hermes_cli.banner import _format_context_length
|
||||
|
||||
_COMMAND_SPINNER_FRAMES = ("⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏")
|
||||
@@ -212,7 +217,7 @@ def load_cli_config() -> Dict[str, Any]:
|
||||
"resume_display": "full",
|
||||
"show_reasoning": False,
|
||||
"streaming": False,
|
||||
"show_cost": False,
|
||||
|
||||
"skin": "default",
|
||||
"theme_mode": "auto",
|
||||
},
|
||||
@@ -1034,8 +1039,7 @@ class HermesCLI:
|
||||
self.bell_on_complete = CLI_CONFIG["display"].get("bell_on_complete", False)
|
||||
# show_reasoning: display model thinking/reasoning before the response
|
||||
self.show_reasoning = CLI_CONFIG["display"].get("show_reasoning", False)
|
||||
# show_cost: display $ cost in the status bar (off by default)
|
||||
self.show_cost = CLI_CONFIG["display"].get("show_cost", False)
|
||||
|
||||
self.verbose = verbose if verbose is not None else (self.tool_progress_mode == "verbose")
|
||||
|
||||
# streaming: stream tokens to the terminal as they arrive (display.streaming in config.yaml)
|
||||
@@ -1260,12 +1264,14 @@ class HermesCLI:
|
||||
"context_tokens": 0,
|
||||
"context_length": None,
|
||||
"context_percent": None,
|
||||
"session_input_tokens": 0,
|
||||
"session_output_tokens": 0,
|
||||
"session_cache_read_tokens": 0,
|
||||
"session_cache_write_tokens": 0,
|
||||
"session_prompt_tokens": 0,
|
||||
"session_completion_tokens": 0,
|
||||
"session_total_tokens": 0,
|
||||
"session_api_calls": 0,
|
||||
"session_cost": 0.0,
|
||||
"pricing_known": has_known_pricing(model_name),
|
||||
"compressions": 0,
|
||||
}
|
||||
|
||||
@@ -1273,15 +1279,14 @@ class HermesCLI:
|
||||
if not agent:
|
||||
return snapshot
|
||||
|
||||
snapshot["session_input_tokens"] = getattr(agent, "session_input_tokens", 0) or 0
|
||||
snapshot["session_output_tokens"] = getattr(agent, "session_output_tokens", 0) or 0
|
||||
snapshot["session_cache_read_tokens"] = getattr(agent, "session_cache_read_tokens", 0) or 0
|
||||
snapshot["session_cache_write_tokens"] = getattr(agent, "session_cache_write_tokens", 0) or 0
|
||||
snapshot["session_prompt_tokens"] = getattr(agent, "session_prompt_tokens", 0) or 0
|
||||
snapshot["session_completion_tokens"] = getattr(agent, "session_completion_tokens", 0) or 0
|
||||
snapshot["session_total_tokens"] = getattr(agent, "session_total_tokens", 0) or 0
|
||||
snapshot["session_api_calls"] = getattr(agent, "session_api_calls", 0) or 0
|
||||
snapshot["session_cost"] = estimate_cost_usd(
|
||||
model_name,
|
||||
snapshot["session_prompt_tokens"],
|
||||
snapshot["session_completion_tokens"],
|
||||
)
|
||||
|
||||
compressor = getattr(agent, "context_compressor", None)
|
||||
if compressor:
|
||||
@@ -1302,19 +1307,11 @@ class HermesCLI:
|
||||
percent = snapshot["context_percent"]
|
||||
percent_label = f"{percent}%" if percent is not None else "--"
|
||||
duration_label = snapshot["duration"]
|
||||
show_cost = getattr(self, "show_cost", False)
|
||||
|
||||
if show_cost:
|
||||
cost_label = f"${snapshot['session_cost']:.2f}" if snapshot["pricing_known"] else "cost n/a"
|
||||
else:
|
||||
cost_label = None
|
||||
|
||||
if width < 52:
|
||||
return f"⚕ {snapshot['model_short']} · {duration_label}"
|
||||
if width < 76:
|
||||
parts = [f"⚕ {snapshot['model_short']}", percent_label]
|
||||
if cost_label:
|
||||
parts.append(cost_label)
|
||||
parts.append(duration_label)
|
||||
return " · ".join(parts)
|
||||
|
||||
@@ -1326,8 +1323,6 @@ class HermesCLI:
|
||||
context_label = "ctx --"
|
||||
|
||||
parts = [f"⚕ {snapshot['model_short']}", context_label, percent_label]
|
||||
if cost_label:
|
||||
parts.append(cost_label)
|
||||
parts.append(duration_label)
|
||||
return " │ ".join(parts)
|
||||
except Exception:
|
||||
@@ -1338,12 +1333,6 @@ class HermesCLI:
|
||||
snapshot = self._get_status_bar_snapshot()
|
||||
width = shutil.get_terminal_size((80, 24)).columns
|
||||
duration_label = snapshot["duration"]
|
||||
show_cost = getattr(self, "show_cost", False)
|
||||
|
||||
if show_cost:
|
||||
cost_label = f"${snapshot['session_cost']:.2f}" if snapshot["pricing_known"] else "cost n/a"
|
||||
else:
|
||||
cost_label = None
|
||||
|
||||
if width < 52:
|
||||
return [
|
||||
@@ -1363,11 +1352,6 @@ class HermesCLI:
|
||||
("class:status-bar-dim", " · "),
|
||||
(self._status_bar_context_style(percent), percent_label),
|
||||
]
|
||||
if cost_label:
|
||||
frags.extend([
|
||||
("class:status-bar-dim", " · "),
|
||||
("class:status-bar-dim", cost_label),
|
||||
])
|
||||
frags.extend([
|
||||
("class:status-bar-dim", " · "),
|
||||
("class:status-bar-dim", duration_label),
|
||||
@@ -1393,11 +1377,6 @@ class HermesCLI:
|
||||
("class:status-bar-dim", " "),
|
||||
(bar_style, percent_label),
|
||||
]
|
||||
if cost_label:
|
||||
frags.extend([
|
||||
("class:status-bar-dim", " │ "),
|
||||
("class:status-bar-dim", cost_label),
|
||||
])
|
||||
frags.extend([
|
||||
("class:status-bar-dim", " │ "),
|
||||
("class:status-bar-dim", duration_label),
|
||||
@@ -4250,6 +4229,10 @@ class HermesCLI:
|
||||
return
|
||||
|
||||
agent = self.agent
|
||||
input_tokens = getattr(agent, "session_input_tokens", 0) or 0
|
||||
output_tokens = getattr(agent, "session_output_tokens", 0) or 0
|
||||
cache_read_tokens = getattr(agent, "session_cache_read_tokens", 0) or 0
|
||||
cache_write_tokens = getattr(agent, "session_cache_write_tokens", 0) or 0
|
||||
prompt = agent.session_prompt_tokens
|
||||
completion = agent.session_completion_tokens
|
||||
total = agent.session_total_tokens
|
||||
@@ -4267,33 +4250,45 @@ class HermesCLI:
|
||||
compressions = compressor.compression_count
|
||||
|
||||
msg_count = len(self.conversation_history)
|
||||
cost = estimate_cost_usd(agent.model, prompt, completion)
|
||||
prompt_cost = estimate_cost_usd(agent.model, prompt, 0)
|
||||
completion_cost = estimate_cost_usd(agent.model, 0, completion)
|
||||
pricing_known = has_known_pricing(agent.model)
|
||||
cost_result = estimate_usage_cost(
|
||||
agent.model,
|
||||
CanonicalUsage(
|
||||
input_tokens=input_tokens,
|
||||
output_tokens=output_tokens,
|
||||
cache_read_tokens=cache_read_tokens,
|
||||
cache_write_tokens=cache_write_tokens,
|
||||
),
|
||||
provider=getattr(agent, "provider", None),
|
||||
base_url=getattr(agent, "base_url", None),
|
||||
)
|
||||
elapsed = format_duration_compact((datetime.now() - self.session_start).total_seconds())
|
||||
|
||||
print(f" 📊 Session Token Usage")
|
||||
print(f" {'─' * 40}")
|
||||
print(f" Model: {agent.model}")
|
||||
print(f" Prompt tokens (input): {prompt:>10,}")
|
||||
print(f" Completion tokens (output): {completion:>9,}")
|
||||
print(f" Input tokens: {input_tokens:>10,}")
|
||||
print(f" Cache read tokens: {cache_read_tokens:>10,}")
|
||||
print(f" Cache write tokens: {cache_write_tokens:>10,}")
|
||||
print(f" Output tokens: {output_tokens:>10,}")
|
||||
print(f" Prompt tokens (total): {prompt:>10,}")
|
||||
print(f" Completion tokens: {completion:>10,}")
|
||||
print(f" Total tokens: {total:>10,}")
|
||||
print(f" API calls: {calls:>10,}")
|
||||
print(f" Session duration: {elapsed:>10}")
|
||||
if pricing_known:
|
||||
print(f" Input cost: ${prompt_cost:>10.4f}")
|
||||
print(f" Output cost: ${completion_cost:>10.4f}")
|
||||
print(f" Total cost: ${cost:>10.4f}")
|
||||
print(f" Cost status: {cost_result.status:>10}")
|
||||
print(f" Cost source: {cost_result.source:>10}")
|
||||
if cost_result.amount_usd is not None:
|
||||
prefix = "~" if cost_result.status == "estimated" else ""
|
||||
print(f" Total cost: {prefix}${float(cost_result.amount_usd):>10.4f}")
|
||||
elif cost_result.status == "included":
|
||||
print(f" Total cost: {'included':>10}")
|
||||
else:
|
||||
print(f" Input cost: {'n/a':>10}")
|
||||
print(f" Output cost: {'n/a':>10}")
|
||||
print(f" Total cost: {'n/a':>10}")
|
||||
print(f" {'─' * 40}")
|
||||
print(f" Current context: {last_prompt:,} / {ctx_len:,} ({pct:.0f}%)")
|
||||
print(f" Messages: {msg_count}")
|
||||
print(f" Compressions: {compressions}")
|
||||
if not pricing_known:
|
||||
if cost_result.status == "unknown":
|
||||
print(f" Note: Pricing unknown for {agent.model}")
|
||||
|
||||
if self.verbose:
|
||||
|
||||
Reference in New Issue
Block a user