mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(/model): show provider-enforced context length, not raw models.dev (#15438)

Browse source 
/model gpt-5.5 on openai-codex showed 'Context: 1,050,000 tokens' because
the display block used ModelInfo.context_window directly from models.dev.
Codex OAuth actually enforces 272K for the same slug, and the agent's
compressor already runs at 272K via get_model_context_length() — so the
banner + real context budget said 272K while /model lied with 1M.

Route the display context through a new resolve_display_context_length()
helper that always prefers agent.model_metadata.get_model_context_length
(which knows about Codex OAuth, Copilot, Nous caps) and only falls back
to models.dev when that returns nothing.

Fix applied to all 3 /model display sites:
  cli.py _handle_model_switch
  gateway/run.py picker on_model_selected callback
  gateway/run.py text-fallback confirmation

Reported by @emilstridell (Telegram, April 2026).
This commit is contained in:
Teknium 2026-04-24 17:21:38 -07:00 • committed by GitHub
parent 13038dc747
commit 05d8f11085
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 161 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

39
gateway/run.py
View file

@ -5659,9 +5659,17 @@ class GatewayRunner:
lines = [f"Model switched to `{result.new_model}`"]
lines.append(f"Provider: {plabel}")
mi = result.model_info
from hermes_cli.model_switch import resolve_display_context_length
ctx = resolve_display_context_length(
result.new_model,
result.target_provider,
base_url=result.base_url or current_base_url or "",
api_key=result.api_key or current_api_key or "",
model_info=mi,
)
if ctx:
lines.append(f"Context: {ctx:,} tokens")
if mi:
if mi.context_window:
lines.append(f"Context: {mi.context_window:,} tokens")
if mi.max_output:
lines.append(f"Max output: {mi.max_output:,} tokens")
if mi.has_cost_data():
@ -5795,28 +5803,25 @@ class GatewayRunner:
lines = [f"Model switched to `{result.new_model}`"]
lines.append(f"Provider: {provider_label}")
# Rich metadata from models.dev
# Context: always resolve via the provider-aware chain so Codex OAuth,
# Copilot, and Nous-enforced caps win over the raw models.dev entry.
mi = result.model_info
from hermes_cli.model_switch import resolve_display_context_length
ctx = resolve_display_context_length(
result.new_model,
result.target_provider,
base_url=result.base_url or current_base_url or "",
api_key=result.api_key or current_api_key or "",
model_info=mi,
)
if ctx:
lines.append(f"Context: {ctx:,} tokens")
if mi:
if mi.context_window:
lines.append(f"Context: {mi.context_window:,} tokens")
if mi.max_output:
lines.append(f"Max output: {mi.max_output:,} tokens")
if mi.has_cost_data():
lines.append(f"Cost: {mi.format_cost()}")
lines.append(f"Capabilities: {mi.format_capabilities()}")
else:
try:
from agent.model_metadata import get_model_context_length
ctx = get_model_context_length(
result.new_model,
base_url=result.base_url or current_base_url,
api_key=result.api_key or current_api_key,
provider=result.target_provider,
)
lines.append(f"Context: {ctx:,} tokens")
except Exception:
pass
# Cache notice
cache_enabled = (