Skip to content

feat: support 1M-token context for Claude Sonnet 4; raise defaults to 1,000,000 #21

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jacsamell merged 1 commit into from
Aug 13, 2025
Merged

feat: support 1M-token context for Claude Sonnet 4; raise defaults to 1,000,000 #21

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ jobs:
auto_improve: true
enable_auto_approval: true
model: 'anthropic/claude-sonnet-4-20250514'
max_model_tokens: '100000'
max_model_tokens: '1000000'
require_trigger: false
```

Expand Down Expand Up @@ -101,7 +101,7 @@ jobs:
| `auto_improve` | Enable code improvement suggestions | ❌ No | `true` |
| `enable_auto_approval` | Enable automatic approval of safe changes | ❌ No | `false` |
| `model` | AI model to use | ❌ No | `anthropic/claude-sonnet-4-20250514` |
| `max_model_tokens` | Maximum tokens for AI model | ❌ No | `100000` |
| `max_model_tokens` | Maximum tokens for AI model | ❌ No | `1000000` |
| `require_trigger` | Require ##prbot trigger in PR description | ❌ No | `false` |

## 📤 Outputs
Expand All @@ -121,7 +121,7 @@ Create `.pr_bot.toml`:
[config]
model = "anthropic/claude-sonnet-4-20250514"
enable_auto_approval = true
max_model_tokens = 100000
max_model_tokens = 1000000
use_cursor_rules = true # Enable Cursor rules (default: true)

[github_action_config]
Expand Down
2 changes: 1 addition & 1 deletion action.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ inputs:
max_model_tokens:
description: 'Maximum tokens for AI model'
required: false
default: '100000'
default: '1000000'
require_trigger:
description: 'Require ##prbot trigger in PR description'
required: false
Expand Down
2 changes: 1 addition & 1 deletion pr_agent/algo/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@
'anthropic.claude-v2': 100000,
'anthropic/claude-3-opus-20240229': 100000,
'anthropic/claude-opus-4-20250514': 200000, # Claude Opus 4
'anthropic/claude-sonnet-4-20250514': 200000, # Claude Sonnet 4
'anthropic/claude-sonnet-4-20250514': 1000000, # Claude Sonnet 4 — 1M context (Anthropic API)
'anthropic/claude-3-5-sonnet-20240620': 100000,
'anthropic/claude-3-5-sonnet-20241022': 100000,
'anthropic/claude-3-7-sonnet-20250219': 200000,
Expand Down
2 changes: 1 addition & 1 deletion pr_agent/settings/configuration.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ response_language="en-US" # Language locales code for PR responses in ISO 3166 a
# token limits
max_description_tokens = 500
max_commits_tokens = 500
max_model_tokens = 175000 # Global cap to align with desired headroom under 200K models
max_model_tokens = 1000000 # Global cap to enable Claude Sonnet 4 long context (1M)
custom_model_max_tokens=-1 # for models not in the default list
model_token_count_estimate_factor=0.3 # factor to increase the token count estimate, in order to reduce likelihood of model failure due to too many tokens - applicable only when requesting an accurate estimate.
# patch extension logic
Expand Down