From 365d95bbbb5828cee0ace8f97bf305e9e2e31571 Mon Sep 17 00:00:00 2001 From: Jorge Calderon Date: Thu, 26 Dec 2024 13:55:15 -0500 Subject: [PATCH] fix: replaces /deepseek/deepseek-coder model with /deepseek/deepseek-chat --- aider/args.py | 2 +- aider/models.py | 8 +- aider/website/_data/code-in-json.yml | 60 +++--- aider/website/_data/edit_leaderboard.yml | 32 +-- aider/website/_data/refactor_leaderboard.yml | 4 +- aider/website/_posts/2024-07-25-new-models.md | 2 +- .../website/_posts/2024-08-14-code-in-json.md | 2 +- aider/website/assets/sample.aider.conf.yml | 2 +- aider/website/assets/sample.env | 2 +- .../website/docs/config/adv-model-settings.md | 6 +- aider/website/docs/config/aider_conf.md | 2 +- aider/website/docs/config/dotenv.md | 2 +- aider/website/docs/config/model-aliases.md | 2 +- aider/website/docs/config/options.md | 2 +- aider/website/docs/more/infinite-output.md | 2 +- .../chat-history-search-replace-gold.txt | 26 +-- tests/fixtures/chat-history.md | 204 +++++++++--------- 17 files changed, 180 insertions(+), 180 deletions(-) diff --git a/aider/args.py b/aider/args.py index 2ba98853dae..32f2a07bb6c 100644 --- a/aider/args.py +++ b/aider/args.py @@ -106,7 +106,7 @@ def get_parser(default_config_files, git_root): const=gpt_3_model_name, help=f"Use {gpt_3_model_name} model for the main chat", ) - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", diff --git a/aider/models.py b/aider/models.py index 885fef5f64b..191186a83f8 100644 --- a/aider/models.py +++ b/aider/models.py @@ -75,7 +75,7 @@ "35-turbo": "gpt-3.5-turbo", "3": "gpt-3.5-turbo", # Other models - "deepseek": "deepseek/deepseek-coder", + "deepseek": "deepseek/deepseek-chat", "flash": "gemini/gemini-2.0-flash-exp", } @@ -627,7 +627,7 @@ class ModelSettings: }, ), ModelSettings( - "deepseek/deepseek-coder", + "deepseek/deepseek-chat", "diff", use_repo_map=True, examples_as_sys_msg=True, @@ -648,7 +648,7 @@ class ModelSettings: }, ), ModelSettings( - "deepseek-coder", + "deepseek-chat", "diff", use_repo_map=True, examples_as_sys_msg=True, @@ -659,7 +659,7 @@ class ModelSettings: }, ), ModelSettings( - "openrouter/deepseek/deepseek-coder", + "openrouter/deepseek/deepseek-chat", "diff", use_repo_map=True, examples_as_sys_msg=True, diff --git a/aider/website/_data/code-in-json.yml b/aider/website/_data/code-in-json.yml index a0e6e571e63..35249ea3bf1 100644 --- a/aider/website/_data/code-in-json.yml +++ b/aider/website/_data/code-in-json.yml @@ -82,9 +82,9 @@ versions: 0.50.2-dev seconds_per_case: 10.5 total_cost: 1.6714 -- dirname: 2024-08-15-13-26-38--json-no-lint-deepseek-coder-whole +- dirname: 2024-08-15-13-26-38--json-no-lint-deepseek-chat-whole test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: Markdown commit_hash: bac04a2 pass_rate_1: 59.4 @@ -98,7 +98,7 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 0 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 27.9 @@ -187,9 +187,9 @@ versions: 0.50.2-dev seconds_per_case: 16.5 total_cost: 1.6556 -- dirname: 2024-08-15-14-06-12--json-no-lint-deepseek-coder-whole-2 +- dirname: 2024-08-15-14-06-12--json-no-lint-deepseek-chat-whole-2 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: Markdown commit_hash: bac04a2 pass_rate_1: 60.9 @@ -203,7 +203,7 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 0 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 25.8 @@ -292,9 +292,9 @@ versions: 0.50.2-dev seconds_per_case: 11.0 total_cost: 1.6555 -- dirname: 2024-08-15-14-21-06--json-no-lint-deepseek-coder-whole-3 +- dirname: 2024-08-15-14-21-06--json-no-lint-deepseek-chat-whole-3 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: Markdown commit_hash: bac04a2 pass_rate_1: 61.7 @@ -308,7 +308,7 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 3 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 24.4 @@ -397,9 +397,9 @@ versions: 0.50.2-dev seconds_per_case: 11.3 total_cost: 1.6635 -- dirname: 2024-08-15-14-38-35--json-no-lint-deepseek-coder-whole-4 +- dirname: 2024-08-15-14-38-35--json-no-lint-deepseek-chat-whole-4 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: Markdown commit_hash: bac04a2 pass_rate_1: 59.4 @@ -413,7 +413,7 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 0 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 24.5 @@ -502,9 +502,9 @@ versions: 0.50.2-dev seconds_per_case: 11.4 total_cost: 1.6685 -- dirname: 2024-08-15-14-54-41--json-no-lint-deepseek-coder-whole-5 +- dirname: 2024-08-15-14-54-41--json-no-lint-deepseek-chat-whole-5 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: Markdown commit_hash: bac04a2 pass_rate_1: 61.7 @@ -518,7 +518,7 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 0 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 24.5 @@ -713,9 +713,9 @@ seconds_per_case: 7.6 total_cost: 1.4948 -- dirname: 2024-08-15-19-35-32--json-no-lint-again-deepseek-coder-func-1 +- dirname: 2024-08-15-19-35-32--json-no-lint-again-deepseek-chat-func-1 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: JSON commit_hash: 3a2ac02-dirty pass_rate_1: 50.4 @@ -729,14 +729,14 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 1 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 17.8 total_cost: 0.0330 -- dirname: 2024-08-15-19-37-50--json-no-lint-again-deepseek-coder-func-2 +- dirname: 2024-08-15-19-37-50--json-no-lint-again-deepseek-chat-func-2 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: JSON commit_hash: 1a98c28 pass_rate_1: 49.6 @@ -750,14 +750,14 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 1 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 18.3 total_cost: 0.0336 -- dirname: 2024-08-15-19-40-20--json-no-lint-again-deepseek-coder-func-3 +- dirname: 2024-08-15-19-40-20--json-no-lint-again-deepseek-chat-func-3 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: JSON commit_hash: 1a98c28 pass_rate_1: 48.9 @@ -771,14 +771,14 @@ indentation_errors: 1 exhausted_context_windows: 1 test_timeouts: 2 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 18.4 total_cost: 0.0337 -- dirname: 2024-08-15-19-44-07--json-no-lint-again-deepseek-coder-func-4 +- dirname: 2024-08-15-19-44-07--json-no-lint-again-deepseek-chat-func-4 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: JSON commit_hash: 1a98c28 pass_rate_1: 53.4 @@ -792,14 +792,14 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 2 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 17.6 total_cost: 0.0330 -- dirname: 2024-08-15-19-46-48--json-no-lint-again-deepseek-coder-func-5 +- dirname: 2024-08-15-19-46-48--json-no-lint-again-deepseek-chat-func-5 test_cases: 133 - model: deepseek-coder V2 0724 + model: deepseek-chat V2 0724 edit_format: JSON commit_hash: 1a98c28-dirty pass_rate_1: 53.4 @@ -813,7 +813,7 @@ indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 2 - command: aider --model deepseek-coder + command: aider --model deepseek-chat date: 2024-08-15 versions: 0.50.2-dev seconds_per_case: 18.0 diff --git a/aider/website/_data/edit_leaderboard.yml b/aider/website/_data/edit_leaderboard.yml index 08e333889b9..01842cc4ab8 100644 --- a/aider/website/_data/edit_leaderboard.yml +++ b/aider/website/_data/edit_leaderboard.yml @@ -714,7 +714,7 @@ seconds_per_case: 18.1 total_cost: 0.0000 -- dirname: 2024-07-24-07-10-58--deepseek-coder2-0724-diff-direct +- dirname: 2024-07-24-07-10-58--deepseek-chat2-0724-diff-direct test_cases: 133 model: DeepSeek Coder V2 0724 edit_format: diff @@ -732,7 +732,7 @@ indentation_errors: 1 exhausted_context_windows: 0 test_timeouts: 2 - command: aider --model deepseek/deepseek-coder + command: aider --model deepseek/deepseek-chat date: 2024-07-24 versions: 0.45.2-dev seconds_per_case: 36.2 @@ -2006,20 +2006,20 @@ seconds_per_case: 35.8 total_cost: 0.0000 -- dirname: 2024-11-28-14-41-46--granite3-dense-8b-whole-1 - test_cases: 133 - model: ollama/granite3-dense:8b - edit_format: whole - commit_hash: 200295e - pass_rate_1: 17.3 - pass_rate_2: 20.3 - percent_cases_well_formed: 78.9 - exhausted_context_windows: 0 - command: aider --model ollama/granite3-dense:8b - date: 2024-11-28 - versions: 0.65.2.dev - seconds_per_case: 38.1 - total_cost: 0.0000 +- dirname: 2024-11-28-14-41-46--granite3-dense-8b-whole-1 + test_cases: 133 + model: ollama/granite3-dense:8b + edit_format: whole + commit_hash: 200295e + pass_rate_1: 17.3 + pass_rate_2: 20.3 + percent_cases_well_formed: 78.9 + exhausted_context_windows: 0 + command: aider --model ollama/granite3-dense:8b + date: 2024-11-28 + versions: 0.65.2.dev + seconds_per_case: 38.1 + total_cost: 0.0000 - dirname: 2024-12-04-13-53-03--nova-whole test_cases: 133 diff --git a/aider/website/_data/refactor_leaderboard.yml b/aider/website/_data/refactor_leaderboard.yml index a39c5edd171..f0e34edf1e6 100644 --- a/aider/website/_data/refactor_leaderboard.yml +++ b/aider/website/_data/refactor_leaderboard.yml @@ -165,7 +165,7 @@ seconds_per_case: 42.8 total_cost: 11.5242 -- dirname: 2024-07-24-07-49-39--refac-deepseek-coder-v2-0724 +- dirname: 2024-07-24-07-49-39--refac-deepseek-chat-v2-0724 test_cases: 89 model: DeepSeek Coder V2 0724 (deprecated) edit_format: diff @@ -181,7 +181,7 @@ indentation_errors: 12 exhausted_context_windows: 3 test_timeouts: 0 - command: aider --model deepseek/deepseek-coder + command: aider --model deepseek/deepseek-chat date: 2024-07-24 versions: 0.45.2-dev seconds_per_case: 85.0 diff --git a/aider/website/_posts/2024-07-25-new-models.md b/aider/website/_posts/2024-07-25-new-models.md index 67ffa45c526..d406805552c 100644 --- a/aider/website/_posts/2024-07-25-new-models.md +++ b/aider/website/_posts/2024-07-25-new-models.md @@ -36,7 +36,7 @@ $ python -m pip install -U aider-chat $ cd /to/your/git/repo $ export DEEPSEEK_API_KEY=your-key-goes-here -$ aider --model deepseek/deepseek-coder +$ aider --model deepseek/deepseek-chat $ export MISTRAL_API_KEY=your-key-goes-here $ aider --model mistral/mistral-large-2407 diff --git a/aider/website/_posts/2024-08-14-code-in-json.md b/aider/website/_posts/2024-08-14-code-in-json.md index a6e4d495235..fdf70b5715f 100644 --- a/aider/website/_posts/2024-08-14-code-in-json.md +++ b/aider/website/_posts/2024-08-14-code-in-json.md @@ -147,7 +147,7 @@ Four of the strongest code editing models were benchmarked to assess the impact of JSON-wrapping code: - claude-3-5-sonnet-20240620 -- deepseek-coder (V2 0724) +- deepseek-chat (V2 0724) - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 diff --git a/aider/website/assets/sample.aider.conf.yml b/aider/website/assets/sample.aider.conf.yml index 2bd0419304a..b859b131723 100644 --- a/aider/website/assets/sample.aider.conf.yml +++ b/aider/website/assets/sample.aider.conf.yml @@ -44,7 +44,7 @@ ## Use gpt-3.5-turbo model for the main chat #35turbo: false -## Use deepseek/deepseek-coder model for the main chat +## Use deepseek/deepseek-chat model for the main chat #deepseek: false ## Use o1-mini model for the main chat diff --git a/aider/website/assets/sample.env b/aider/website/assets/sample.env index 56f449e4115..dfd065f41a1 100644 --- a/aider/website/assets/sample.env +++ b/aider/website/assets/sample.env @@ -48,7 +48,7 @@ ## Use gpt-3.5-turbo model for the main chat #AIDER_35TURBO= -## Use deepseek/deepseek-coder model for the main chat +## Use deepseek/deepseek-chat model for the main chat #AIDER_DEEPSEEK= ## Use o1-mini model for the main chat diff --git a/aider/website/docs/config/adv-model-settings.md b/aider/website/docs/config/adv-model-settings.md index 589a9d72a9a..55355b5a051 100644 --- a/aider/website/docs/config/adv-model-settings.md +++ b/aider/website/docs/config/adv-model-settings.md @@ -1105,7 +1105,7 @@ cog.out("```\n") extra_params: max_tokens: 8192 lazy: false - name: deepseek/deepseek-coder + name: deepseek/deepseek-chat reminder: sys send_undo_reply: false streaming: true @@ -1139,7 +1139,7 @@ cog.out("```\n") extra_params: max_tokens: 8192 lazy: false - name: deepseek-coder + name: deepseek-chat reminder: sys send_undo_reply: false streaming: true @@ -1155,7 +1155,7 @@ cog.out("```\n") examples_as_sys_msg: true extra_params: null lazy: false - name: openrouter/deepseek/deepseek-coder + name: openrouter/deepseek/deepseek-chat reminder: sys send_undo_reply: false streaming: true diff --git a/aider/website/docs/config/aider_conf.md b/aider/website/docs/config/aider_conf.md index cb42c1b2efa..e3a944e05aa 100644 --- a/aider/website/docs/config/aider_conf.md +++ b/aider/website/docs/config/aider_conf.md @@ -96,7 +96,7 @@ cog.outl("```") ## Use gpt-3.5-turbo model for the main chat #35turbo: false -## Use deepseek/deepseek-coder model for the main chat +## Use deepseek/deepseek-chat model for the main chat #deepseek: false ## Use o1-mini model for the main chat diff --git a/aider/website/docs/config/dotenv.md b/aider/website/docs/config/dotenv.md index 1005dd974eb..4583b7e8a57 100644 --- a/aider/website/docs/config/dotenv.md +++ b/aider/website/docs/config/dotenv.md @@ -88,7 +88,7 @@ cog.outl("```") ## Use gpt-3.5-turbo model for the main chat #AIDER_35TURBO= -## Use deepseek/deepseek-coder model for the main chat +## Use deepseek/deepseek-chat model for the main chat #AIDER_DEEPSEEK= ## Use o1-mini model for the main chat diff --git a/aider/website/docs/config/model-aliases.md b/aider/website/docs/config/model-aliases.md index 421df3e2104..b805dce5721 100644 --- a/aider/website/docs/config/model-aliases.md +++ b/aider/website/docs/config/model-aliases.md @@ -55,7 +55,7 @@ for alias, model in sorted(MODEL_ALIASES.items()): - `4`: gpt-4-0613 - `4-turbo`: gpt-4-1106-preview - `4o`: gpt-4o -- `deepseek`: deepseek/deepseek-coder +- `deepseek`: deepseek/deepseek-chat - `flash`: gemini/gemini-2.0-flash-exp - `haiku`: claude-3-5-haiku-20241022 - `opus`: claude-3-opus-20240229 diff --git a/aider/website/docs/config/options.md b/aider/website/docs/config/options.md index 459678a5f0d..920b2a3a87a 100644 --- a/aider/website/docs/config/options.md +++ b/aider/website/docs/config/options.md @@ -136,7 +136,7 @@ Aliases: - `-3` ### `--deepseek` -Use deepseek/deepseek-coder model for the main chat +Use deepseek/deepseek-chat model for the main chat Environment variable: `AIDER_DEEPSEEK` ### `--o1-mini` diff --git a/aider/website/docs/more/infinite-output.md b/aider/website/docs/more/infinite-output.md index 33e84188b74..9294416f010 100644 --- a/aider/website/docs/more/infinite-output.md +++ b/aider/website/docs/more/infinite-output.md @@ -66,7 +66,7 @@ cog.out(model_list) - codestral/codestral-2405 - codestral/codestral-latest - deepseek-chat -- deepseek-coder +- deepseek-chat - eu.anthropic.claude-3-5-sonnet-20241022-v2:0 - mistral/codestral-2405 - mistral/codestral-latest diff --git a/tests/fixtures/chat-history-search-replace-gold.txt b/tests/fixtures/chat-history-search-replace-gold.txt index de28f77fac2..5181e30ca49 100644 --- a/tests/fixtures/chat-history-search-replace-gold.txt +++ b/tests/fixtures/chat-history-search-replace-gold.txt @@ -11583,7 +11583,7 @@ from aider.llm import litellm @@@ REPLACE @@@@@@@@@@@@@@@@@@@@ -@@@ #### add --deepseek for model deepseek/deepseek-coder @@@@@@@@@@@@@@@@@@@@ +@@@ #### add --deepseek for model deepseek/deepseek-chat @@@@@@@@@@@@@@@@@@@@ @@@ SEARCH: aider/args.py @@@@@@@@@@@@@@@@@@@@ gpt_3_model_name = "gpt-3.5-turbo" group.add_argument( @@ -11608,7 +11608,7 @@ from aider.llm import litellm const=gpt_3_model_name, help=f"Use {gpt_3_model_name} model for the main chat", ) - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", @@ -11621,7 +11621,7 @@ from aider.llm import litellm @@@ #### add a --deepseek-beta bool arg. descibe as uses deepseek coder via the beta api endpoint @@@@@@@@@@@@@@@@@@@@ @@@ SEARCH: aider/args.py @@@@@@@@@@@@@@@@@@@@ - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", @@ -11630,7 +11630,7 @@ from aider.llm import litellm help=f"Use {deepseek_model} model for the main chat", ) @@@@@@@@@@@@@@@@@@@@ - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", @@ -11695,7 +11695,7 @@ from aider.llm import litellm args.model = "claude-3-5-sonnet-20240620" if args.deepseek_beta: - args.model = "deepseek-coder" + args.model = "deepseek-chat" os.environ["DEEPSEEK_API_BASE"] = "https://api.deepseek.com/beta" main_model = models.Model(args.model, weak_model=args.weak_model) @@ -11714,7 +11714,7 @@ from aider.llm import litellm args.model = "claude-3-5-sonnet-20240620" if args.deepseek_beta: - args.model = "deepseek-coder" + args.model = "deepseek-chat" os.environ["DEEPSEEK_API_BASE"] = "https://api.deepseek.com/beta" main_model = models.Model(args.model, weak_model=args.weak_model) @@ -13780,7 +13780,7 @@ HISTORY.md > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek HISTORY.md --dry-run --edit whole > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ whole edit format +> Model: deepseek/deepseek-chat with ♾️ whole edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Added HISTORY.md to the chat. @@ -19682,7 +19682,7 @@ document.addEventListener('DOMContentLoaded', function () { var ctx = document.getElementById('passRateChart').getContext('2d'); var data = { - labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-coder'], + labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-chat'], datasets: [ { label: 'Markdown', @@ -19753,7 +19753,7 @@ document.addEventListener('DOMContentLoaded', function () { var ctx = document.getElementById('passRateChart').getContext('2d'); var data = { - labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-coder'], + labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-chat'], datasets: [ { label: 'Markdown', @@ -20049,14 +20049,14 @@ MODELS=< /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder HISTORY.md --dry-run --msg translate it all to french --edit-format whole +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat HISTORY.md --dry-run --msg translate it all to french --edit-format whole > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with ♾️ whole edit format +> Model: openrouter/deepseek/deepseek-chat with ♾️ whole edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Added HISTORY.md to the chat. diff --git a/tests/fixtures/chat-history.md b/tests/fixtures/chat-history.md index fdf4fd8202f..4a7c217b04a 100644 --- a/tests/fixtures/chat-history.md +++ b/tests/fixtures/chat-history.md @@ -10315,9 +10315,9 @@ These changes should handle the case where files are in different git repositori # aider chat started at 2024-08-08 09:54:02 -> /Users/gauthier/Projects/aider/.venv/bin/aider aider/repomap.py --model deepseek/deepseek-coder +> /Users/gauthier/Projects/aider/.venv/bin/aider aider/repomap.py --model deepseek/deepseek-chat > Aider v0.48.2-dev -> Model: deepseek/deepseek-coder with diff edit format +> Model: deepseek/deepseek-chat with diff edit format > Git repo: .git with 300 files > Repo-map: using 1024 tokens > Added aider/repomap.py to the chat. @@ -45885,9 +45885,9 @@ This modification will allow the function to use the specified API base URL for #### /add aider/args.py > Added /Users/gauthier/Projects/aider/aider/args.py to the chat -#### add --deepseek for model deepseek/deepseek-coder +#### add --deepseek for model deepseek/deepseek-chat -Certainly! I'll add the `--deepseek` option for the "deepseek/deepseek-coder" model in the `aider/args.py` file. Here's the change: +Certainly! I'll add the `--deepseek` option for the "deepseek/deepseek-chat" model in the `aider/args.py` file. Here's the change: aider/args.py ```python @@ -45915,7 +45915,7 @@ aider/args.py const=gpt_3_model_name, help=f"Use {gpt_3_model_name} model for the main chat", ) - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", @@ -45926,11 +45926,11 @@ aider/args.py >>>>>>> REPLACE ``` -This change adds the `--deepseek` option to the argument parser, which will set the model to "deepseek/deepseek-coder" when used. The new option is placed right after the existing GPT-3.5 Turbo option for consistency. +This change adds the `--deepseek` option to the argument parser, which will set the model to "deepseek/deepseek-chat" when used. The new option is placed right after the existing GPT-3.5 Turbo option for consistency. > Tokens: 7,652 sent, 343 received. Cost: $0.03 request, $0.04 session. > Applied edit to aider/args.py -> Commit 5f8df31 feat: Add --deepseek option for deepseek/deepseek-coder model +> Commit 5f8df31 feat: Add --deepseek option for deepseek/deepseek-chat model > You can use /undo to undo and discard each aider commit. > > @@ -45943,7 +45943,7 @@ Certainly! I'll add the `--deepseek-beta` boolean argument to the `aider/args.py aider/args.py ```python <<<<<<< SEARCH - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", @@ -45952,7 +45952,7 @@ aider/args.py help=f"Use {deepseek_model} model for the main chat", ) ======= - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", @@ -46059,7 +46059,7 @@ aider/main.py args.model = "claude-3-5-sonnet-20240620" if args.deepseek_beta: - args.model = "deepseek-coder" + args.model = "deepseek-chat" os.environ["DEEPSEEK_API_BASE"] = "https://api.deepseek.com/beta" main_model = models.Model(args.model, weak_model=args.weak_model) @@ -46088,7 +46088,7 @@ These changes will add the `--deepseek-beta` flag to the argument parser and upd > args.model = "claude-3-5-sonnet-20240620" > > if args.deepseek_beta: -> args.model = "deepseek-coder" +> args.model = "deepseek-chat" > os.environ["DEEPSEEK_API_BASE"] = "https://api.deepseek.com/beta" > > main_model = models.Model(args.model, weak_model=args.weak_model) @@ -46139,7 +46139,7 @@ aider/main.py args.model = "claude-3-5-sonnet-20240620" if args.deepseek_beta: - args.model = "deepseek-coder" + args.model = "deepseek-chat" os.environ["DEEPSEEK_API_BASE"] = "https://api.deepseek.com/beta" main_model = models.Model(args.model, weak_model=args.weak_model) @@ -47244,9 +47244,9 @@ Option settings: # aider chat started at 2024-08-12 15:27:27 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model deepseek/deepseek-coder +> /Users/gauthier/Projects/aider/.venv/bin/aider --model deepseek/deepseek-chat > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with diff edit format +> Model: deepseek/deepseek-chat with diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -51213,7 +51213,7 @@ Hello! How can I assist you today? If you have any requests or need help with co > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -51279,7 +51279,7 @@ HISTORY.md > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek HISTORY.md --dry-run > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Added HISTORY.md to the chat. @@ -51338,7 +51338,7 @@ HISTORY.md > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek HISTORY.md --dry-run --edit whole > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ whole edit format +> Model: deepseek/deepseek-chat with ♾️ whole edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Added HISTORY.md to the chat. @@ -59107,7 +59107,7 @@ This *SEARCH/REPLACE block* correctly follows the format you specified. It will > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60267,11 +60267,11 @@ The changes will provide helpful information to Windows users about potentially # aider chat started at 2024-08-13 09:21:34 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek -> Model deepseek/deepseek-coder: Missing these environment variables: +> Model deepseek/deepseek-chat: Missing these environment variables: > - DEEPSEEK_API_KEY > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60285,12 +60285,12 @@ The changes will provide helpful information to Windows users about potentially # aider chat started at 2024-08-13 09:21:47 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --exit -> Model deepseek/deepseek-coder: Missing these environment variables: +> Model deepseek/deepseek-chat: Missing these environment variables: > - DEEPSEEK_API_KEY > If you've just set these environment variables using 'setx'," you may need to restart your terminal or command prompt for the changes to take effect. > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60298,12 +60298,12 @@ The changes will provide helpful information to Windows users about potentially # aider chat started at 2024-08-13 09:22:22 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --exit -> Model deepseek/deepseek-coder: Missing these environment variables: +> Model deepseek/deepseek-chat: Missing these environment variables: > - DEEPSEEK_API_KEY > If you've just set these environment variables using 'setx'," you may need to restart your terminal or command prompt for the changes to take effect. > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60311,12 +60311,12 @@ The changes will provide helpful information to Windows users about potentially # aider chat started at 2024-08-13 09:22:50 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --exit -> Model deepseek/deepseek-coder: Missing these environment variables: +> Model deepseek/deepseek-chat: Missing these environment variables: > - DEEPSEEK_API_KEY > If you've just set these environment variables using 'setx' you may need to restart your terminal or command prompt for the changes to take effect. > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60324,12 +60324,12 @@ The changes will provide helpful information to Windows users about potentially # aider chat started at 2024-08-13 09:24:17 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --exit -> Model deepseek/deepseek-coder: Missing these environment variables: +> Model deepseek/deepseek-chat: Missing these environment variables: > - DEEPSEEK_API_KEY > If you've just set these environment variables using `setx` you may need to restart your terminal or command prompt for the changes to take effect. > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60337,12 +60337,12 @@ The changes will provide helpful information to Windows users about potentially # aider chat started at 2024-08-13 09:24:23 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --exit -> Model deepseek/deepseek-coder: Missing these environment variables: +> Model deepseek/deepseek-chat: Missing these environment variables: > - DEEPSEEK_API_KEY > If you just set these environment variables using `setx` you may need to restart your terminal or command prompt for the changes to take effect. > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.49.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 304 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60676,12 +60676,12 @@ This change adds the `edit_format=self.edit_format` parameter to the `event()` c # aider chat started at 2024-08-13 12:17:56 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --exit -> Model deepseek/deepseek-coder: Missing these environment variables: +> Model deepseek/deepseek-chat: Missing these environment variables: > - DEEPSEEK_API_KEY > If you just set these environment variables using `setx` you may need to restart your terminal or command prompt for the changes to take effect. > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.50.1-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 303 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -60690,7 +60690,7 @@ This change adds the `edit_format=self.edit_format` parameter to the `event()` c > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --exit > Aider v0.50.1-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 303 files > Repo-map: using 1024 tokens > Use /help for help, run "aider --help" to see cmd line args @@ -66075,7 +66075,7 @@ These changes will help us identify where the problem is occurring. After making #### /run python benchmark/over_time.py > Debug: Raw data from YAML file: -[{'dirname': '2024-05-01-20-05-59--direct-opus-filenames-outside-fence', 'test_cases': 133, 'model': 'claude-3-opus-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'diff', 'commit_hash': 'f4b1797-dirty, f4b1797', 'pass_rate_1': 53.4, 'pass_rate_2': 68.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 2, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --opus', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 32.4, 'total_cost': 13.8395}, {'dirname': '2024-03-06-16-42-00--claude3-sonnet-whole', 'test_cases': 133, 'model': 'claude-3-sonnet-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'whole', 'commit_hash': 'a5f8076-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 54.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --sonnet', 'date': datetime.date(2024, 3, 6), 'versions': '0.25.1-dev', 'seconds_per_case': 23.1, 'total_cost': 0.0}, {'dirname': '2024-05-03-20-47-24--gemini-1.5-pro-diff-fenced', 'test_cases': 133, 'model': 'gemini-1.5-pro-latest', 'edit_format': 'diff-fenced', 'commit_hash': '3a48dfb, 5d32dd7', 'pass_rate_1': 45.9, 'pass_rate_2': 57.1, 'percent_cases_well_formed': 87.2, 'error_outputs': 60, 'num_malformed_responses': 17, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 8, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-pro-latest', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 21.3, 'total_cost': 0.0}, {'dirname': '2024-05-08-20-59-15--may-gpt-3.5-turbo-whole', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0125', 'released': datetime.date(2024, 1, 25), 'edit_format': 'whole', 'commit_hash': '1d55f74', 'pass_rate_1': 41.4, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider -3', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.5032}, {'dirname': '2023-11-06-21-23-59--gpt-3.5-turbo-0301', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0301', 'released': datetime.date(2023, 3, 1), 'edit_format': 'whole', 'commit_hash': '44388db-dirty', 'pass_rate_1': 50.4, 'pass_rate_2': 57.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 8, 'command': 'aider --model gpt-3.5-turbo-0301', 'date': datetime.date(2023, 11, 6), 'versions': '0.16.4-dev', 'seconds_per_case': 6.5, 'total_cost': 0.4822}, {'dirname': '2023-11-07-02-41-07--gpt-3.5-turbo-0613', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'whole', 'commit_hash': '93aa497-dirty', 'pass_rate_1': 38.3, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'command': 'aider --model gpt-3.5-turbo-0613', 'date': datetime.date(2023, 11, 7), 'versions': '0.16.4-dev', 'seconds_per_case': 18.0, 'total_cost': 0.5366}, {'dirname': '2024-04-30-21-40-51--litellm-gpt-3.5-turbo-1106-again', 'test_cases': 132, 'model': 'gpt-3.5-turbo-1106', 'edit_format': 'whole', 'commit_hash': '7b14d77', 'pass_rate_1': 45.5, 'pass_rate_2': 56.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 19, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-3.5-turbo-1106', 'date': datetime.date(2024, 4, 30), 'versions': '0.30.2-dev', 'seconds_per_case': 5.3, 'total_cost': 0.3261}, {'dirname': '2024-01-25-23-37-15--jan-exercism-gpt-4-0125-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-0125-preview', 'released': datetime.date(2024, 1, 25), 'edit_format': 'udiff', 'commit_hash': 'edcf9b1', 'pass_rate_1': 55.6, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 6, 'num_malformed_responses': 3, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model gpt-4-0125-preview', 'date': datetime.date(2024, 1, 25), 'versions': '0.22.1-dev', 'seconds_per_case': 44.8, 'total_cost': 14.6428}, {'dirname': '2024-05-04-15-07-30--redo-gpt-4-0314-diff-reminder-rules', 'test_cases': 133, 'model': 'gpt-4-0314', 'released': datetime.date(2023, 3, 14), 'edit_format': 'diff', 'commit_hash': '0d43468', 'pass_rate_1': 50.4, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 93.2, 'error_outputs': 28, 'num_malformed_responses': 9, 'user_asks': 1, 'lazy_comments': 3, 'syntax_errors': 9, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gpt-4-0314', 'date': datetime.date(2024, 5, 4), 'versions': '0.31.2-dev', 'seconds_per_case': 19.8, 'total_cost': 16.2689}, {'dirname': '2023-12-16-21-24-28--editblock-gpt-4-0613-actual-main', 'test_cases': 133, 'model': 'gpt-4-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'diff', 'commit_hash': '3aa17c4', 'pass_rate_1': 46.6, 'pass_rate_2': 67.7, 'percent_cases_well_formed': 100.0, 'error_outputs': 14, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider -4', 'date': datetime.date(2023, 12, 16), 'versions': '0.18.2-dev', 'seconds_per_case': 33.6, 'total_cost': 17.4657}, {'dirname': '2024-05-08-21-16-03--may-gpt-4-1106-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-1106-preview', 'released': datetime.date(2023, 11, 6), 'edit_format': 'udiff', 'commit_hash': '87664dc', 'pass_rate_1': 51.9, 'pass_rate_2': 65.4, 'percent_cases_well_formed': 92.5, 'error_outputs': 30, 'num_malformed_responses': 10, 'user_asks': 0, 'lazy_comments': 3, 'syntax_errors': 11, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model gpt-4-1106-preview', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 20.4, 'total_cost': 6.6061}, {'dirname': '2024-05-01-02-09-20--gpt-4-turbo-examples', 'test_cases': 133, 'model': 'gpt-4-turbo-2024-04-09 (udiff)', 'released': datetime.date(2024, 4, 9), 'edit_format': 'udiff', 'commit_hash': 'e610e5b-dirty', 'pass_rate_1': 48.1, 'pass_rate_2': 63.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 12, 'num_malformed_responses': 4, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 4, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --gpt-4-turbo', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 22.8, 'total_cost': 6.3337}, {'dirname': '2024-05-03-22-24-48--openrouter--llama3-diff-examples-sys-msg', 'test_cases': 132, 'model': 'llama3-70b-8192', 'released': datetime.date(2024, 4, 18), 'edit_format': 'diff', 'commit_hash': 'b5bb453', 'pass_rate_1': 38.6, 'pass_rate_2': 49.2, 'percent_cases_well_formed': 73.5, 'error_outputs': 105, 'num_malformed_responses': 35, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model groq/llama3-70b-8192', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 14.5, 'total_cost': 0.4311}, {'dirname': '2024-05-06-18-31-08--command-r-plus-whole-final', 'test_cases': 133, 'model': 'command-r-plus', 'released': datetime.date(2024, 4, 4), 'edit_format': 'whole', 'commit_hash': 'fc3a43e-dirty', 'pass_rate_1': 21.8, 'pass_rate_2': 31.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --model command-r-plus', 'date': datetime.date(2024, 5, 6), 'versions': '0.31.2-dev', 'seconds_per_case': 22.9, 'total_cost': 2.7494}, {'dirname': '2024-05-09-18-57-52--deepseek-chat-v2-diff-reverted-and-helpful-assistant2', 'test_cases': 133, 'model': 'DeepSeek Chat V2 (original)', 'released': datetime.date(2024, 5, 6), 'edit_format': 'diff', 'commit_hash': '80a3f6d', 'pass_rate_1': 44.4, 'pass_rate_2': 60.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 14, 'num_malformed_responses': 4, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 13, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 5, 9), 'versions': '0.33.1-dev', 'seconds_per_case': 86.8, 'total_cost': 0.0941}, {'dirname': '2024-05-07-20-32-37--qwen1.5-110b-chat-whole', 'test_cases': 133, 'model': 'qwen1.5-110b-chat', 'released': datetime.date(2024, 2, 4), 'edit_format': 'whole', 'commit_hash': '70b1c0c', 'pass_rate_1': 30.8, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 20, 'syntax_errors': 0, 'indentation_errors': 6, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model together_ai/qwen/qwen1.5-110b-chat', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 46.9, 'total_cost': 0.0}, {'dirname': '2024-05-07-20-57-04--wizardlm-2-8x22b-whole', 'test_cases': 133, 'model': 'WizardLM-2 8x22B', 'edit_format': 'whole', 'commit_hash': '8e272bf, bbe8639', 'pass_rate_1': 27.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openrouter/microsoft/wizardlm-2-8x22b', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 36.6, 'total_cost': 0.0}, {'dirname': '2024-05-13-17-39-05--gpt-4o-diff', 'test_cases': 133, 'model': 'gpt-4o', 'released': datetime.date(2024, 5, 13), 'edit_format': 'diff', 'commit_hash': 'b6cd852', 'pass_rate_1': 60.2, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 96.2, 'error_outputs': 103, 'num_malformed_responses': 5, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider', 'date': datetime.date(2024, 5, 13), 'versions': '0.34.1-dev', 'seconds_per_case': 6.0, 'total_cost': 0.0}, {'dirname': '2024-04-12-22-18-20--gpt-4-turbo-2024-04-09-plain-diff', 'test_cases': 33, 'model': 'gpt-4-turbo-2024-04-09 (diff)', 'edit_format': 'diff', 'commit_hash': '9b2e697-dirty', 'pass_rate_1': 48.5, 'pass_rate_2': 57.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 15, 'num_malformed_responses': 0, 'user_asks': 15, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-4-turbo-2024-04-09', 'date': datetime.date(2024, 4, 12), 'versions': '0.28.1-dev', 'seconds_per_case': 17.6, 'total_cost': 1.6205}, {'dirname': '2024-06-08-22-37-55--qwen2-72b-instruct-whole', 'test_cases': 133, 'model': 'Qwen2 72B Instruct', 'edit_format': 'whole', 'commit_hash': '02c7335-dirty, 1a97498-dirty', 'pass_rate_1': 44.4, 'pass_rate_2': 55.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model together_ai/qwen/Qwen2-72B-Instruct', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 14.3, 'total_cost': 0.0}, {'dirname': '2024-06-08-23-45-41--gemini-1.5-flash-latest-whole', 'test_cases': 133, 'model': 'gemini-1.5-flash-latest', 'edit_format': 'whole', 'commit_hash': '86ea47f-dirty', 'pass_rate_1': 33.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 16, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 12, 'lazy_comments': 0, 'syntax_errors': 9, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-flash-latest', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 7.2, 'total_cost': 0.0}, {'dirname': '2024-06-09-03-28-21--codestral-whole', 'test_cases': 133, 'model': 'codestral-2405', 'edit_format': 'whole', 'commit_hash': 'effc88a', 'pass_rate_1': 35.3, 'pass_rate_2': 51.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 4, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 4, 'lazy_comments': 1, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model mistral/codestral-2405', 'date': datetime.date(2024, 6, 9), 'versions': '0.37.1-dev', 'seconds_per_case': 7.5, 'total_cost': 0.6805}, {'dirname': '2024-06-08-19-25-26--codeqwen:7b-chat-v1.5-q8_0-whole', 'test_cases': 133, 'model': 'codeqwen:7b-chat-v1.5-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 32.3, 'pass_rate_2': 34.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model ollama/codeqwen:7b-chat-v1.5-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 15.6, 'total_cost': 0.0}, {'dirname': '2024-06-08-16-12-31--codestral:22b-v0.1-q8_0-whole', 'test_cases': 133, 'model': 'codestral:22b-v0.1-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 35.3, 'pass_rate_2': 48.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/codestral:22b-v0.1-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 46.4, 'total_cost': 0.0}, {'dirname': '2024-06-08-17-54-04--qwen2:72b-instruct-q8_0-whole', 'test_cases': 133, 'model': 'qwen2:72b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': '74e51d5-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 49.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 27, 'lazy_comments': 0, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model ollama/qwen2:72b-instruct-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 280.6, 'total_cost': 0.0}, {'dirname': '2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue', 'test_cases': 133, 'model': 'claude-3.5-sonnet', 'edit_format': 'diff', 'commit_hash': '35f21b5', 'pass_rate_1': 57.1, 'pass_rate_2': 77.4, 'percent_cases_well_formed': 99.2, 'error_outputs': 23, 'released': datetime.date(2024, 6, 20), 'num_malformed_responses': 4, 'num_with_malformed_responses': 1, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --sonnet', 'date': datetime.date(2024, 7, 4), 'versions': '0.42.1-dev', 'seconds_per_case': 17.6, 'total_cost': 3.6346}, {'dirname': '2024-07-01-21-41-48--haiku-whole', 'test_cases': 133, 'model': 'claude-3-haiku-20240307', 'edit_format': 'whole', 'commit_hash': '75f506d', 'pass_rate_1': 40.6, 'pass_rate_2': 47.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 6, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 3, 13), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model claude-3-haiku-20240307', 'date': datetime.date(2024, 7, 1), 'versions': '0.41.1-dev', 'seconds_per_case': 7.1, 'total_cost': 0.1946}, {'dirname': '2024-07-09-10-12-27--gemma2:27b-instruct-q8_0', 'test_cases': 133, 'model': 'gemma2:27b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': 'f9d96ac-dirty', 'pass_rate_1': 31.6, 'pass_rate_2': 36.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 35, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 35, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/gemma2:27b-instruct-q8_0', 'date': datetime.date(2024, 7, 9), 'versions': '0.43.0', 'seconds_per_case': 101.3, 'total_cost': 0.0}, {'dirname': '2024-07-18-18-57-46--gpt-4o-mini-whole', 'test_cases': 133, 'model': 'gpt-4o-mini', 'edit_format': 'whole', 'commit_hash': 'd31eef3-dirty', 'pass_rate_1': 40.6, 'pass_rate_2': 55.6, 'released': datetime.date(2024, 7, 18), 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model gpt-4o-mini', 'date': datetime.date(2024, 7, 18), 'versions': '0.44.1-dev', 'seconds_per_case': 7.8, 'total_cost': 0.0916}, {'dirname': '2024-07-19-08-57-13--openrouter-deepseek-chat-v2-0628', 'test_cases': 133, 'model': 'DeepSeek Chat V2 0628', 'edit_format': 'diff', 'commit_hash': '96ff06e-dirty', 'pass_rate_1': 60.9, 'pass_rate_2': 69.9, 'percent_cases_well_formed': 97.7, 'released': datetime.date(2024, 6, 28), 'error_outputs': 58, 'num_malformed_responses': 13, 'num_with_malformed_responses': 3, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 7, 19), 'versions': '0.45.2-dev', 'seconds_per_case': 37.1, 'total_cost': 0.0}, {'dirname': '2024-07-23-22-07-08--llama-205b-diff', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (diff)', 'edit_format': 'diff', 'commit_hash': 'f7ce78b-dirty', 'pass_rate_1': 46.6, 'pass_rate_2': 63.9, 'released': datetime.date(2024, 7, 23), 'percent_cases_well_formed': 92.5, 'error_outputs': 84, 'num_malformed_responses': 19, 'num_with_malformed_responses': 10, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 23), 'versions': '0.45.2-dev', 'seconds_per_case': 56.8, 'total_cost': 0.0}, {'dirname': '2024-07-24-06-30-29--llama-405b-whole', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (whole)', 'edit_format': 'whole', 'commit_hash': 'a362dea-dirty', 'pass_rate_1': 48.9, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 18.1, 'total_cost': 0.0}, {'dirname': '2024-07-24-07-10-58--deepseek-coder2-0724-diff-direct', 'test_cases': 133, 'model': 'DeepSeek Coder V2 0724', 'edit_format': 'diff', 'commit_hash': '89965bf', 'pass_rate_1': 57.9, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 97.7, 'error_outputs': 13, 'released': datetime.date(2024, 7, 24), 'num_malformed_responses': 3, 'num_with_malformed_responses': 3, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-coder', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 36.2, 'total_cost': 0.0981}, {'dirname': '2024-07-24-19-08-47--mistral-large-2407-whole', 'test_cases': 133, 'model': 'Mistral Large 2 (2407)', 'edit_format': 'whole', 'commit_hash': '859a13e', 'pass_rate_1': 39.8, 'pass_rate_2': 60.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'released': datetime.date(2024, 7, 24), 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model mistral/mistral-large-2407', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 26.6, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-12-27--fireworks-llama-8b-whole', 'test_cases': 133, 'model': 'llama-3.1-8b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 26.3, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 23, 'lazy_comments': 8, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 4, 'test_timeouts': 7, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 3.8, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-07-45--fireworks-llama-70b-whole', 'test_cases': 133, 'model': 'llama-3.1-70b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 43.6, 'pass_rate_2': 58.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 7, 23), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 6, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 7.3, 'total_cost': 0.0}, {'dirname': '2024-08-06-18-28-39--gpt-4o-2024-08-06-diff-again', 'test_cases': 133, 'model': 'gpt-4o-2024-08-06', 'edit_format': 'diff', 'commit_hash': 'ed9ed89', 'pass_rate_1': 57.1, 'pass_rate_2': 71.4, 'percent_cases_well_formed': 98.5, 'error_outputs': 18, 'num_malformed_responses': 2, 'num_with_malformed_responses': 2, 'user_asks': 10, 'lazy_comments': 0, 'syntax_errors': 6, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'released': datetime.date(2024, 8, 6), 'command': 'aider --model openai/gpt-4o-2024-08-06', 'date': datetime.date(2024, 8, 6), 'versions': '0.48.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.0}, {'dirname': '2024-08-14-13-07-12--chatgpt-4o-latest-diff', 'test_cases': 133, 'model': 'chatgpt-4o-latest', 'edit_format': 'diff', 'commit_hash': 'b1c3769', 'pass_rate_1': 53.4, 'pass_rate_2': 69.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 27, 'num_malformed_responses': 5, 'num_with_malformed_responses': 3, 'user_asks': 7, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openai/chatgpt-4o-latest', 'date': datetime.date(2024, 8, 14), 'released': datetime.date(2024, 8, 8), 'versions': '0.50.2-dev', 'seconds_per_case': 26.3, 'total_cost': 3.6113}]2024-08-14 06:20:48.437 Python[6129:11424500] ApplePersistenceIgnoreState: Existing state will not be touched. New state will be written to /var/folders/49/kxrdwwbx0h9bchx99397477c0000gn/T/org.python.python.savedState +[{'dirname': '2024-05-01-20-05-59--direct-opus-filenames-outside-fence', 'test_cases': 133, 'model': 'claude-3-opus-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'diff', 'commit_hash': 'f4b1797-dirty, f4b1797', 'pass_rate_1': 53.4, 'pass_rate_2': 68.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 2, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --opus', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 32.4, 'total_cost': 13.8395}, {'dirname': '2024-03-06-16-42-00--claude3-sonnet-whole', 'test_cases': 133, 'model': 'claude-3-sonnet-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'whole', 'commit_hash': 'a5f8076-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 54.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --sonnet', 'date': datetime.date(2024, 3, 6), 'versions': '0.25.1-dev', 'seconds_per_case': 23.1, 'total_cost': 0.0}, {'dirname': '2024-05-03-20-47-24--gemini-1.5-pro-diff-fenced', 'test_cases': 133, 'model': 'gemini-1.5-pro-latest', 'edit_format': 'diff-fenced', 'commit_hash': '3a48dfb, 5d32dd7', 'pass_rate_1': 45.9, 'pass_rate_2': 57.1, 'percent_cases_well_formed': 87.2, 'error_outputs': 60, 'num_malformed_responses': 17, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 8, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-pro-latest', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 21.3, 'total_cost': 0.0}, {'dirname': '2024-05-08-20-59-15--may-gpt-3.5-turbo-whole', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0125', 'released': datetime.date(2024, 1, 25), 'edit_format': 'whole', 'commit_hash': '1d55f74', 'pass_rate_1': 41.4, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider -3', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.5032}, {'dirname': '2023-11-06-21-23-59--gpt-3.5-turbo-0301', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0301', 'released': datetime.date(2023, 3, 1), 'edit_format': 'whole', 'commit_hash': '44388db-dirty', 'pass_rate_1': 50.4, 'pass_rate_2': 57.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 8, 'command': 'aider --model gpt-3.5-turbo-0301', 'date': datetime.date(2023, 11, 6), 'versions': '0.16.4-dev', 'seconds_per_case': 6.5, 'total_cost': 0.4822}, {'dirname': '2023-11-07-02-41-07--gpt-3.5-turbo-0613', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'whole', 'commit_hash': '93aa497-dirty', 'pass_rate_1': 38.3, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'command': 'aider --model gpt-3.5-turbo-0613', 'date': datetime.date(2023, 11, 7), 'versions': '0.16.4-dev', 'seconds_per_case': 18.0, 'total_cost': 0.5366}, {'dirname': '2024-04-30-21-40-51--litellm-gpt-3.5-turbo-1106-again', 'test_cases': 132, 'model': 'gpt-3.5-turbo-1106', 'edit_format': 'whole', 'commit_hash': '7b14d77', 'pass_rate_1': 45.5, 'pass_rate_2': 56.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 19, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-3.5-turbo-1106', 'date': datetime.date(2024, 4, 30), 'versions': '0.30.2-dev', 'seconds_per_case': 5.3, 'total_cost': 0.3261}, {'dirname': '2024-01-25-23-37-15--jan-exercism-gpt-4-0125-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-0125-preview', 'released': datetime.date(2024, 1, 25), 'edit_format': 'udiff', 'commit_hash': 'edcf9b1', 'pass_rate_1': 55.6, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 6, 'num_malformed_responses': 3, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model gpt-4-0125-preview', 'date': datetime.date(2024, 1, 25), 'versions': '0.22.1-dev', 'seconds_per_case': 44.8, 'total_cost': 14.6428}, {'dirname': '2024-05-04-15-07-30--redo-gpt-4-0314-diff-reminder-rules', 'test_cases': 133, 'model': 'gpt-4-0314', 'released': datetime.date(2023, 3, 14), 'edit_format': 'diff', 'commit_hash': '0d43468', 'pass_rate_1': 50.4, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 93.2, 'error_outputs': 28, 'num_malformed_responses': 9, 'user_asks': 1, 'lazy_comments': 3, 'syntax_errors': 9, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gpt-4-0314', 'date': datetime.date(2024, 5, 4), 'versions': '0.31.2-dev', 'seconds_per_case': 19.8, 'total_cost': 16.2689}, {'dirname': '2023-12-16-21-24-28--editblock-gpt-4-0613-actual-main', 'test_cases': 133, 'model': 'gpt-4-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'diff', 'commit_hash': '3aa17c4', 'pass_rate_1': 46.6, 'pass_rate_2': 67.7, 'percent_cases_well_formed': 100.0, 'error_outputs': 14, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider -4', 'date': datetime.date(2023, 12, 16), 'versions': '0.18.2-dev', 'seconds_per_case': 33.6, 'total_cost': 17.4657}, {'dirname': '2024-05-08-21-16-03--may-gpt-4-1106-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-1106-preview', 'released': datetime.date(2023, 11, 6), 'edit_format': 'udiff', 'commit_hash': '87664dc', 'pass_rate_1': 51.9, 'pass_rate_2': 65.4, 'percent_cases_well_formed': 92.5, 'error_outputs': 30, 'num_malformed_responses': 10, 'user_asks': 0, 'lazy_comments': 3, 'syntax_errors': 11, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model gpt-4-1106-preview', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 20.4, 'total_cost': 6.6061}, {'dirname': '2024-05-01-02-09-20--gpt-4-turbo-examples', 'test_cases': 133, 'model': 'gpt-4-turbo-2024-04-09 (udiff)', 'released': datetime.date(2024, 4, 9), 'edit_format': 'udiff', 'commit_hash': 'e610e5b-dirty', 'pass_rate_1': 48.1, 'pass_rate_2': 63.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 12, 'num_malformed_responses': 4, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 4, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --gpt-4-turbo', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 22.8, 'total_cost': 6.3337}, {'dirname': '2024-05-03-22-24-48--openrouter--llama3-diff-examples-sys-msg', 'test_cases': 132, 'model': 'llama3-70b-8192', 'released': datetime.date(2024, 4, 18), 'edit_format': 'diff', 'commit_hash': 'b5bb453', 'pass_rate_1': 38.6, 'pass_rate_2': 49.2, 'percent_cases_well_formed': 73.5, 'error_outputs': 105, 'num_malformed_responses': 35, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model groq/llama3-70b-8192', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 14.5, 'total_cost': 0.4311}, {'dirname': '2024-05-06-18-31-08--command-r-plus-whole-final', 'test_cases': 133, 'model': 'command-r-plus', 'released': datetime.date(2024, 4, 4), 'edit_format': 'whole', 'commit_hash': 'fc3a43e-dirty', 'pass_rate_1': 21.8, 'pass_rate_2': 31.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --model command-r-plus', 'date': datetime.date(2024, 5, 6), 'versions': '0.31.2-dev', 'seconds_per_case': 22.9, 'total_cost': 2.7494}, {'dirname': '2024-05-09-18-57-52--deepseek-chat-v2-diff-reverted-and-helpful-assistant2', 'test_cases': 133, 'model': 'DeepSeek Chat V2 (original)', 'released': datetime.date(2024, 5, 6), 'edit_format': 'diff', 'commit_hash': '80a3f6d', 'pass_rate_1': 44.4, 'pass_rate_2': 60.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 14, 'num_malformed_responses': 4, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 13, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 5, 9), 'versions': '0.33.1-dev', 'seconds_per_case': 86.8, 'total_cost': 0.0941}, {'dirname': '2024-05-07-20-32-37--qwen1.5-110b-chat-whole', 'test_cases': 133, 'model': 'qwen1.5-110b-chat', 'released': datetime.date(2024, 2, 4), 'edit_format': 'whole', 'commit_hash': '70b1c0c', 'pass_rate_1': 30.8, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 20, 'syntax_errors': 0, 'indentation_errors': 6, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model together_ai/qwen/qwen1.5-110b-chat', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 46.9, 'total_cost': 0.0}, {'dirname': '2024-05-07-20-57-04--wizardlm-2-8x22b-whole', 'test_cases': 133, 'model': 'WizardLM-2 8x22B', 'edit_format': 'whole', 'commit_hash': '8e272bf, bbe8639', 'pass_rate_1': 27.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openrouter/microsoft/wizardlm-2-8x22b', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 36.6, 'total_cost': 0.0}, {'dirname': '2024-05-13-17-39-05--gpt-4o-diff', 'test_cases': 133, 'model': 'gpt-4o', 'released': datetime.date(2024, 5, 13), 'edit_format': 'diff', 'commit_hash': 'b6cd852', 'pass_rate_1': 60.2, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 96.2, 'error_outputs': 103, 'num_malformed_responses': 5, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider', 'date': datetime.date(2024, 5, 13), 'versions': '0.34.1-dev', 'seconds_per_case': 6.0, 'total_cost': 0.0}, {'dirname': '2024-04-12-22-18-20--gpt-4-turbo-2024-04-09-plain-diff', 'test_cases': 33, 'model': 'gpt-4-turbo-2024-04-09 (diff)', 'edit_format': 'diff', 'commit_hash': '9b2e697-dirty', 'pass_rate_1': 48.5, 'pass_rate_2': 57.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 15, 'num_malformed_responses': 0, 'user_asks': 15, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-4-turbo-2024-04-09', 'date': datetime.date(2024, 4, 12), 'versions': '0.28.1-dev', 'seconds_per_case': 17.6, 'total_cost': 1.6205}, {'dirname': '2024-06-08-22-37-55--qwen2-72b-instruct-whole', 'test_cases': 133, 'model': 'Qwen2 72B Instruct', 'edit_format': 'whole', 'commit_hash': '02c7335-dirty, 1a97498-dirty', 'pass_rate_1': 44.4, 'pass_rate_2': 55.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model together_ai/qwen/Qwen2-72B-Instruct', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 14.3, 'total_cost': 0.0}, {'dirname': '2024-06-08-23-45-41--gemini-1.5-flash-latest-whole', 'test_cases': 133, 'model': 'gemini-1.5-flash-latest', 'edit_format': 'whole', 'commit_hash': '86ea47f-dirty', 'pass_rate_1': 33.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 16, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 12, 'lazy_comments': 0, 'syntax_errors': 9, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-flash-latest', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 7.2, 'total_cost': 0.0}, {'dirname': '2024-06-09-03-28-21--codestral-whole', 'test_cases': 133, 'model': 'codestral-2405', 'edit_format': 'whole', 'commit_hash': 'effc88a', 'pass_rate_1': 35.3, 'pass_rate_2': 51.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 4, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 4, 'lazy_comments': 1, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model mistral/codestral-2405', 'date': datetime.date(2024, 6, 9), 'versions': '0.37.1-dev', 'seconds_per_case': 7.5, 'total_cost': 0.6805}, {'dirname': '2024-06-08-19-25-26--codeqwen:7b-chat-v1.5-q8_0-whole', 'test_cases': 133, 'model': 'codeqwen:7b-chat-v1.5-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 32.3, 'pass_rate_2': 34.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model ollama/codeqwen:7b-chat-v1.5-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 15.6, 'total_cost': 0.0}, {'dirname': '2024-06-08-16-12-31--codestral:22b-v0.1-q8_0-whole', 'test_cases': 133, 'model': 'codestral:22b-v0.1-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 35.3, 'pass_rate_2': 48.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/codestral:22b-v0.1-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 46.4, 'total_cost': 0.0}, {'dirname': '2024-06-08-17-54-04--qwen2:72b-instruct-q8_0-whole', 'test_cases': 133, 'model': 'qwen2:72b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': '74e51d5-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 49.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 27, 'lazy_comments': 0, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model ollama/qwen2:72b-instruct-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 280.6, 'total_cost': 0.0}, {'dirname': '2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue', 'test_cases': 133, 'model': 'claude-3.5-sonnet', 'edit_format': 'diff', 'commit_hash': '35f21b5', 'pass_rate_1': 57.1, 'pass_rate_2': 77.4, 'percent_cases_well_formed': 99.2, 'error_outputs': 23, 'released': datetime.date(2024, 6, 20), 'num_malformed_responses': 4, 'num_with_malformed_responses': 1, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --sonnet', 'date': datetime.date(2024, 7, 4), 'versions': '0.42.1-dev', 'seconds_per_case': 17.6, 'total_cost': 3.6346}, {'dirname': '2024-07-01-21-41-48--haiku-whole', 'test_cases': 133, 'model': 'claude-3-haiku-20240307', 'edit_format': 'whole', 'commit_hash': '75f506d', 'pass_rate_1': 40.6, 'pass_rate_2': 47.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 6, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 3, 13), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model claude-3-haiku-20240307', 'date': datetime.date(2024, 7, 1), 'versions': '0.41.1-dev', 'seconds_per_case': 7.1, 'total_cost': 0.1946}, {'dirname': '2024-07-09-10-12-27--gemma2:27b-instruct-q8_0', 'test_cases': 133, 'model': 'gemma2:27b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': 'f9d96ac-dirty', 'pass_rate_1': 31.6, 'pass_rate_2': 36.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 35, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 35, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/gemma2:27b-instruct-q8_0', 'date': datetime.date(2024, 7, 9), 'versions': '0.43.0', 'seconds_per_case': 101.3, 'total_cost': 0.0}, {'dirname': '2024-07-18-18-57-46--gpt-4o-mini-whole', 'test_cases': 133, 'model': 'gpt-4o-mini', 'edit_format': 'whole', 'commit_hash': 'd31eef3-dirty', 'pass_rate_1': 40.6, 'pass_rate_2': 55.6, 'released': datetime.date(2024, 7, 18), 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model gpt-4o-mini', 'date': datetime.date(2024, 7, 18), 'versions': '0.44.1-dev', 'seconds_per_case': 7.8, 'total_cost': 0.0916}, {'dirname': '2024-07-19-08-57-13--openrouter-deepseek-chat-v2-0628', 'test_cases': 133, 'model': 'DeepSeek Chat V2 0628', 'edit_format': 'diff', 'commit_hash': '96ff06e-dirty', 'pass_rate_1': 60.9, 'pass_rate_2': 69.9, 'percent_cases_well_formed': 97.7, 'released': datetime.date(2024, 6, 28), 'error_outputs': 58, 'num_malformed_responses': 13, 'num_with_malformed_responses': 3, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 7, 19), 'versions': '0.45.2-dev', 'seconds_per_case': 37.1, 'total_cost': 0.0}, {'dirname': '2024-07-23-22-07-08--llama-205b-diff', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (diff)', 'edit_format': 'diff', 'commit_hash': 'f7ce78b-dirty', 'pass_rate_1': 46.6, 'pass_rate_2': 63.9, 'released': datetime.date(2024, 7, 23), 'percent_cases_well_formed': 92.5, 'error_outputs': 84, 'num_malformed_responses': 19, 'num_with_malformed_responses': 10, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 23), 'versions': '0.45.2-dev', 'seconds_per_case': 56.8, 'total_cost': 0.0}, {'dirname': '2024-07-24-06-30-29--llama-405b-whole', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (whole)', 'edit_format': 'whole', 'commit_hash': 'a362dea-dirty', 'pass_rate_1': 48.9, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 18.1, 'total_cost': 0.0}, {'dirname': '2024-07-24-07-10-58--deepseek-chat2-0724-diff-direct', 'test_cases': 133, 'model': 'DeepSeek Coder V2 0724', 'edit_format': 'diff', 'commit_hash': '89965bf', 'pass_rate_1': 57.9, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 97.7, 'error_outputs': 13, 'released': datetime.date(2024, 7, 24), 'num_malformed_responses': 3, 'num_with_malformed_responses': 3, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 36.2, 'total_cost': 0.0981}, {'dirname': '2024-07-24-19-08-47--mistral-large-2407-whole', 'test_cases': 133, 'model': 'Mistral Large 2 (2407)', 'edit_format': 'whole', 'commit_hash': '859a13e', 'pass_rate_1': 39.8, 'pass_rate_2': 60.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'released': datetime.date(2024, 7, 24), 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model mistral/mistral-large-2407', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 26.6, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-12-27--fireworks-llama-8b-whole', 'test_cases': 133, 'model': 'llama-3.1-8b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 26.3, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 23, 'lazy_comments': 8, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 4, 'test_timeouts': 7, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 3.8, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-07-45--fireworks-llama-70b-whole', 'test_cases': 133, 'model': 'llama-3.1-70b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 43.6, 'pass_rate_2': 58.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 7, 23), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 6, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 7.3, 'total_cost': 0.0}, {'dirname': '2024-08-06-18-28-39--gpt-4o-2024-08-06-diff-again', 'test_cases': 133, 'model': 'gpt-4o-2024-08-06', 'edit_format': 'diff', 'commit_hash': 'ed9ed89', 'pass_rate_1': 57.1, 'pass_rate_2': 71.4, 'percent_cases_well_formed': 98.5, 'error_outputs': 18, 'num_malformed_responses': 2, 'num_with_malformed_responses': 2, 'user_asks': 10, 'lazy_comments': 0, 'syntax_errors': 6, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'released': datetime.date(2024, 8, 6), 'command': 'aider --model openai/gpt-4o-2024-08-06', 'date': datetime.date(2024, 8, 6), 'versions': '0.48.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.0}, {'dirname': '2024-08-14-13-07-12--chatgpt-4o-latest-diff', 'test_cases': 133, 'model': 'chatgpt-4o-latest', 'edit_format': 'diff', 'commit_hash': 'b1c3769', 'pass_rate_1': 53.4, 'pass_rate_2': 69.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 27, 'num_malformed_responses': 5, 'num_with_malformed_responses': 3, 'user_asks': 7, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openai/chatgpt-4o-latest', 'date': datetime.date(2024, 8, 14), 'released': datetime.date(2024, 8, 8), 'versions': '0.50.2-dev', 'seconds_per_case': 26.3, 'total_cost': 3.6113}]2024-08-14 06:20:48.437 Python[6129:11424500] ApplePersistenceIgnoreState: Existing state will not be touched. New state will be written to /var/folders/49/kxrdwwbx0h9bchx99397477c0000gn/T/org.python.python.savedState ]1337;File=inline=1;size=92534;height=29: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 Debug: Processed data: @@ -66085,7 +66085,7 @@ Models: ['claude-3-opus-20240229', 'claude-3-sonnet-20240229', 'gpt-3.5-turbo-01 > Add the output to the chat? (y/n/instructions) y > Debug: Raw data from YAML file: -> [{'dirname': '2024-05-01-20-05-59--direct-opus-filenames-outside-fence', 'test_cases': 133, 'model': 'claude-3-opus-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'diff', 'commit_hash': 'f4b1797-dirty, f4b1797', 'pass_rate_1': 53.4, 'pass_rate_2': 68.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 2, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --opus', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 32.4, 'total_cost': 13.8395}, {'dirname': '2024-03-06-16-42-00--claude3-sonnet-whole', 'test_cases': 133, 'model': 'claude-3-sonnet-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'whole', 'commit_hash': 'a5f8076-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 54.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --sonnet', 'date': datetime.date(2024, 3, 6), 'versions': '0.25.1-dev', 'seconds_per_case': 23.1, 'total_cost': 0.0}, {'dirname': '2024-05-03-20-47-24--gemini-1.5-pro-diff-fenced', 'test_cases': 133, 'model': 'gemini-1.5-pro-latest', 'edit_format': 'diff-fenced', 'commit_hash': '3a48dfb, 5d32dd7', 'pass_rate_1': 45.9, 'pass_rate_2': 57.1, 'percent_cases_well_formed': 87.2, 'error_outputs': 60, 'num_malformed_responses': 17, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 8, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-pro-latest', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 21.3, 'total_cost': 0.0}, {'dirname': '2024-05-08-20-59-15--may-gpt-3.5-turbo-whole', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0125', 'released': datetime.date(2024, 1, 25), 'edit_format': 'whole', 'commit_hash': '1d55f74', 'pass_rate_1': 41.4, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider -3', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.5032}, {'dirname': '2023-11-06-21-23-59--gpt-3.5-turbo-0301', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0301', 'released': datetime.date(2023, 3, 1), 'edit_format': 'whole', 'commit_hash': '44388db-dirty', 'pass_rate_1': 50.4, 'pass_rate_2': 57.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 8, 'command': 'aider --model gpt-3.5-turbo-0301', 'date': datetime.date(2023, 11, 6), 'versions': '0.16.4-dev', 'seconds_per_case': 6.5, 'total_cost': 0.4822}, {'dirname': '2023-11-07-02-41-07--gpt-3.5-turbo-0613', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'whole', 'commit_hash': '93aa497-dirty', 'pass_rate_1': 38.3, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'command': 'aider --model gpt-3.5-turbo-0613', 'date': datetime.date(2023, 11, 7), 'versions': '0.16.4-dev', 'seconds_per_case': 18.0, 'total_cost': 0.5366}, {'dirname': '2024-04-30-21-40-51--litellm-gpt-3.5-turbo-1106-again', 'test_cases': 132, 'model': 'gpt-3.5-turbo-1106', 'edit_format': 'whole', 'commit_hash': '7b14d77', 'pass_rate_1': 45.5, 'pass_rate_2': 56.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 19, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-3.5-turbo-1106', 'date': datetime.date(2024, 4, 30), 'versions': '0.30.2-dev', 'seconds_per_case': 5.3, 'total_cost': 0.3261}, {'dirname': '2024-01-25-23-37-15--jan-exercism-gpt-4-0125-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-0125-preview', 'released': datetime.date(2024, 1, 25), 'edit_format': 'udiff', 'commit_hash': 'edcf9b1', 'pass_rate_1': 55.6, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 6, 'num_malformed_responses': 3, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model gpt-4-0125-preview', 'date': datetime.date(2024, 1, 25), 'versions': '0.22.1-dev', 'seconds_per_case': 44.8, 'total_cost': 14.6428}, {'dirname': '2024-05-04-15-07-30--redo-gpt-4-0314-diff-reminder-rules', 'test_cases': 133, 'model': 'gpt-4-0314', 'released': datetime.date(2023, 3, 14), 'edit_format': 'diff', 'commit_hash': '0d43468', 'pass_rate_1': 50.4, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 93.2, 'error_outputs': 28, 'num_malformed_responses': 9, 'user_asks': 1, 'lazy_comments': 3, 'syntax_errors': 9, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gpt-4-0314', 'date': datetime.date(2024, 5, 4), 'versions': '0.31.2-dev', 'seconds_per_case': 19.8, 'total_cost': 16.2689}, {'dirname': '2023-12-16-21-24-28--editblock-gpt-4-0613-actual-main', 'test_cases': 133, 'model': 'gpt-4-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'diff', 'commit_hash': '3aa17c4', 'pass_rate_1': 46.6, 'pass_rate_2': 67.7, 'percent_cases_well_formed': 100.0, 'error_outputs': 14, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider -4', 'date': datetime.date(2023, 12, 16), 'versions': '0.18.2-dev', 'seconds_per_case': 33.6, 'total_cost': 17.4657}, {'dirname': '2024-05-08-21-16-03--may-gpt-4-1106-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-1106-preview', 'released': datetime.date(2023, 11, 6), 'edit_format': 'udiff', 'commit_hash': '87664dc', 'pass_rate_1': 51.9, 'pass_rate_2': 65.4, 'percent_cases_well_formed': 92.5, 'error_outputs': 30, 'num_malformed_responses': 10, 'user_asks': 0, 'lazy_comments': 3, 'syntax_errors': 11, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model gpt-4-1106-preview', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 20.4, 'total_cost': 6.6061}, {'dirname': '2024-05-01-02-09-20--gpt-4-turbo-examples', 'test_cases': 133, 'model': 'gpt-4-turbo-2024-04-09 (udiff)', 'released': datetime.date(2024, 4, 9), 'edit_format': 'udiff', 'commit_hash': 'e610e5b-dirty', 'pass_rate_1': 48.1, 'pass_rate_2': 63.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 12, 'num_malformed_responses': 4, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 4, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --gpt-4-turbo', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 22.8, 'total_cost': 6.3337}, {'dirname': '2024-05-03-22-24-48--openrouter--llama3-diff-examples-sys-msg', 'test_cases': 132, 'model': 'llama3-70b-8192', 'released': datetime.date(2024, 4, 18), 'edit_format': 'diff', 'commit_hash': 'b5bb453', 'pass_rate_1': 38.6, 'pass_rate_2': 49.2, 'percent_cases_well_formed': 73.5, 'error_outputs': 105, 'num_malformed_responses': 35, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model groq/llama3-70b-8192', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 14.5, 'total_cost': 0.4311}, {'dirname': '2024-05-06-18-31-08--command-r-plus-whole-final', 'test_cases': 133, 'model': 'command-r-plus', 'released': datetime.date(2024, 4, 4), 'edit_format': 'whole', 'commit_hash': 'fc3a43e-dirty', 'pass_rate_1': 21.8, 'pass_rate_2': 31.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --model command-r-plus', 'date': datetime.date(2024, 5, 6), 'versions': '0.31.2-dev', 'seconds_per_case': 22.9, 'total_cost': 2.7494}, {'dirname': '2024-05-09-18-57-52--deepseek-chat-v2-diff-reverted-and-helpful-assistant2', 'test_cases': 133, 'model': 'DeepSeek Chat V2 (original)', 'released': datetime.date(2024, 5, 6), 'edit_format': 'diff', 'commit_hash': '80a3f6d', 'pass_rate_1': 44.4, 'pass_rate_2': 60.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 14, 'num_malformed_responses': 4, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 13, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 5, 9), 'versions': '0.33.1-dev', 'seconds_per_case': 86.8, 'total_cost': 0.0941}, {'dirname': '2024-05-07-20-32-37--qwen1.5-110b-chat-whole', 'test_cases': 133, 'model': 'qwen1.5-110b-chat', 'released': datetime.date(2024, 2, 4), 'edit_format': 'whole', 'commit_hash': '70b1c0c', 'pass_rate_1': 30.8, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 20, 'syntax_errors': 0, 'indentation_errors': 6, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model together_ai/qwen/qwen1.5-110b-chat', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 46.9, 'total_cost': 0.0}, {'dirname': '2024-05-07-20-57-04--wizardlm-2-8x22b-whole', 'test_cases': 133, 'model': 'WizardLM-2 8x22B', 'edit_format': 'whole', 'commit_hash': '8e272bf, bbe8639', 'pass_rate_1': 27.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openrouter/microsoft/wizardlm-2-8x22b', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 36.6, 'total_cost': 0.0}, {'dirname': '2024-05-13-17-39-05--gpt-4o-diff', 'test_cases': 133, 'model': 'gpt-4o', 'released': datetime.date(2024, 5, 13), 'edit_format': 'diff', 'commit_hash': 'b6cd852', 'pass_rate_1': 60.2, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 96.2, 'error_outputs': 103, 'num_malformed_responses': 5, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider', 'date': datetime.date(2024, 5, 13), 'versions': '0.34.1-dev', 'seconds_per_case': 6.0, 'total_cost': 0.0}, {'dirname': '2024-04-12-22-18-20--gpt-4-turbo-2024-04-09-plain-diff', 'test_cases': 33, 'model': 'gpt-4-turbo-2024-04-09 (diff)', 'edit_format': 'diff', 'commit_hash': '9b2e697-dirty', 'pass_rate_1': 48.5, 'pass_rate_2': 57.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 15, 'num_malformed_responses': 0, 'user_asks': 15, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-4-turbo-2024-04-09', 'date': datetime.date(2024, 4, 12), 'versions': '0.28.1-dev', 'seconds_per_case': 17.6, 'total_cost': 1.6205}, {'dirname': '2024-06-08-22-37-55--qwen2-72b-instruct-whole', 'test_cases': 133, 'model': 'Qwen2 72B Instruct', 'edit_format': 'whole', 'commit_hash': '02c7335-dirty, 1a97498-dirty', 'pass_rate_1': 44.4, 'pass_rate_2': 55.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model together_ai/qwen/Qwen2-72B-Instruct', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 14.3, 'total_cost': 0.0}, {'dirname': '2024-06-08-23-45-41--gemini-1.5-flash-latest-whole', 'test_cases': 133, 'model': 'gemini-1.5-flash-latest', 'edit_format': 'whole', 'commit_hash': '86ea47f-dirty', 'pass_rate_1': 33.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 16, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 12, 'lazy_comments': 0, 'syntax_errors': 9, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-flash-latest', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 7.2, 'total_cost': 0.0}, {'dirname': '2024-06-09-03-28-21--codestral-whole', 'test_cases': 133, 'model': 'codestral-2405', 'edit_format': 'whole', 'commit_hash': 'effc88a', 'pass_rate_1': 35.3, 'pass_rate_2': 51.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 4, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 4, 'lazy_comments': 1, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model mistral/codestral-2405', 'date': datetime.date(2024, 6, 9), 'versions': '0.37.1-dev', 'seconds_per_case': 7.5, 'total_cost': 0.6805}, {'dirname': '2024-06-08-19-25-26--codeqwen:7b-chat-v1.5-q8_0-whole', 'test_cases': 133, 'model': 'codeqwen:7b-chat-v1.5-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 32.3, 'pass_rate_2': 34.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model ollama/codeqwen:7b-chat-v1.5-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 15.6, 'total_cost': 0.0}, {'dirname': '2024-06-08-16-12-31--codestral:22b-v0.1-q8_0-whole', 'test_cases': 133, 'model': 'codestral:22b-v0.1-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 35.3, 'pass_rate_2': 48.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/codestral:22b-v0.1-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 46.4, 'total_cost': 0.0}, {'dirname': '2024-06-08-17-54-04--qwen2:72b-instruct-q8_0-whole', 'test_cases': 133, 'model': 'qwen2:72b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': '74e51d5-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 49.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 27, 'lazy_comments': 0, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model ollama/qwen2:72b-instruct-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 280.6, 'total_cost': 0.0}, {'dirname': '2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue', 'test_cases': 133, 'model': 'claude-3.5-sonnet', 'edit_format': 'diff', 'commit_hash': '35f21b5', 'pass_rate_1': 57.1, 'pass_rate_2': 77.4, 'percent_cases_well_formed': 99.2, 'error_outputs': 23, 'released': datetime.date(2024, 6, 20), 'num_malformed_responses': 4, 'num_with_malformed_responses': 1, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --sonnet', 'date': datetime.date(2024, 7, 4), 'versions': '0.42.1-dev', 'seconds_per_case': 17.6, 'total_cost': 3.6346}, {'dirname': '2024-07-01-21-41-48--haiku-whole', 'test_cases': 133, 'model': 'claude-3-haiku-20240307', 'edit_format': 'whole', 'commit_hash': '75f506d', 'pass_rate_1': 40.6, 'pass_rate_2': 47.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 6, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 3, 13), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model claude-3-haiku-20240307', 'date': datetime.date(2024, 7, 1), 'versions': '0.41.1-dev', 'seconds_per_case': 7.1, 'total_cost': 0.1946}, {'dirname': '2024-07-09-10-12-27--gemma2:27b-instruct-q8_0', 'test_cases': 133, 'model': 'gemma2:27b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': 'f9d96ac-dirty', 'pass_rate_1': 31.6, 'pass_rate_2': 36.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 35, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 35, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/gemma2:27b-instruct-q8_0', 'date': datetime.date(2024, 7, 9), 'versions': '0.43.0', 'seconds_per_case': 101.3, 'total_cost': 0.0}, {'dirname': '2024-07-18-18-57-46--gpt-4o-mini-whole', 'test_cases': 133, 'model': 'gpt-4o-mini', 'edit_format': 'whole', 'commit_hash': 'd31eef3-dirty', 'pass_rate_1': 40.6, 'pass_rate_2': 55.6, 'released': datetime.date(2024, 7, 18), 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model gpt-4o-mini', 'date': datetime.date(2024, 7, 18), 'versions': '0.44.1-dev', 'seconds_per_case': 7.8, 'total_cost': 0.0916}, {'dirname': '2024-07-19-08-57-13--openrouter-deepseek-chat-v2-0628', 'test_cases': 133, 'model': 'DeepSeek Chat V2 0628', 'edit_format': 'diff', 'commit_hash': '96ff06e-dirty', 'pass_rate_1': 60.9, 'pass_rate_2': 69.9, 'percent_cases_well_formed': 97.7, 'released': datetime.date(2024, 6, 28), 'error_outputs': 58, 'num_malformed_responses': 13, 'num_with_malformed_responses': 3, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 7, 19), 'versions': '0.45.2-dev', 'seconds_per_case': 37.1, 'total_cost': 0.0}, {'dirname': '2024-07-23-22-07-08--llama-205b-diff', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (diff)', 'edit_format': 'diff', 'commit_hash': 'f7ce78b-dirty', 'pass_rate_1': 46.6, 'pass_rate_2': 63.9, 'released': datetime.date(2024, 7, 23), 'percent_cases_well_formed': 92.5, 'error_outputs': 84, 'num_malformed_responses': 19, 'num_with_malformed_responses': 10, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 23), 'versions': '0.45.2-dev', 'seconds_per_case': 56.8, 'total_cost': 0.0}, {'dirname': '2024-07-24-06-30-29--llama-405b-whole', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (whole)', 'edit_format': 'whole', 'commit_hash': 'a362dea-dirty', 'pass_rate_1': 48.9, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 18.1, 'total_cost': 0.0}, {'dirname': '2024-07-24-07-10-58--deepseek-coder2-0724-diff-direct', 'test_cases': 133, 'model': 'DeepSeek Coder V2 0724', 'edit_format': 'diff', 'commit_hash': '89965bf', 'pass_rate_1': 57.9, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 97.7, 'error_outputs': 13, 'released': datetime.date(2024, 7, 24), 'num_malformed_responses': 3, 'num_with_malformed_responses': 3, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-coder', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 36.2, 'total_cost': 0.0981}, {'dirname': '2024-07-24-19-08-47--mistral-large-2407-whole', 'test_cases': 133, 'model': 'Mistral Large 2 (2407)', 'edit_format': 'whole', 'commit_hash': '859a13e', 'pass_rate_1': 39.8, 'pass_rate_2': 60.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'released': datetime.date(2024, 7, 24), 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model mistral/mistral-large-2407', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 26.6, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-12-27--fireworks-llama-8b-whole', 'test_cases': 133, 'model': 'llama-3.1-8b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 26.3, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 23, 'lazy_comments': 8, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 4, 'test_timeouts': 7, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 3.8, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-07-45--fireworks-llama-70b-whole', 'test_cases': 133, 'model': 'llama-3.1-70b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 43.6, 'pass_rate_2': 58.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 7, 23), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 6, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 7.3, 'total_cost': 0.0}, {'dirname': '2024-08-06-18-28-39--gpt-4o-2024-08-06-diff-again', 'test_cases': 133, 'model': 'gpt-4o-2024-08-06', 'edit_format': 'diff', 'commit_hash': 'ed9ed89', 'pass_rate_1': 57.1, 'pass_rate_2': 71.4, 'percent_cases_well_formed': 98.5, 'error_outputs': 18, 'num_malformed_responses': 2, 'num_with_malformed_responses': 2, 'user_asks': 10, 'lazy_comments': 0, 'syntax_errors': 6, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'released': datetime.date(2024, 8, 6), 'command': 'aider --model openai/gpt-4o-2024-08-06', 'date': datetime.date(2024, 8, 6), 'versions': '0.48.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.0}, {'dirname': '2024-08-14-13-07-12--chatgpt-4o-latest-diff', 'test_cases': 133, 'model': 'chatgpt-4o-latest', 'edit_format': 'diff', 'commit_hash': 'b1c3769', 'pass_rate_1': 53.4, 'pass_rate_2': 69.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 27, 'num_malformed_responses': 5, 'num_with_malformed_responses': 3, 'user_asks': 7, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openai/chatgpt-4o-latest', 'date': datetime.date(2024, 8, 14), 'released': datetime.date(2024, 8, 8), 'versions': '0.50.2-dev', 'seconds_per_case': 26.3, 'total_cost': 3.6113}]2024-08-14 06:20:48.437 Python[6129:11424500] ApplePersistenceIgnoreState: Existing state will not be touched. New state will be written to /var/folders/49/kxrdwwbx0h9bchx99397477c0000gn/T/org.python.python.savedState +> [{'dirname': '2024-05-01-20-05-59--direct-opus-filenames-outside-fence', 'test_cases': 133, 'model': 'claude-3-opus-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'diff', 'commit_hash': 'f4b1797-dirty, f4b1797', 'pass_rate_1': 53.4, 'pass_rate_2': 68.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 2, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --opus', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 32.4, 'total_cost': 13.8395}, {'dirname': '2024-03-06-16-42-00--claude3-sonnet-whole', 'test_cases': 133, 'model': 'claude-3-sonnet-20240229', 'released': datetime.date(2024, 2, 29), 'edit_format': 'whole', 'commit_hash': 'a5f8076-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 54.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --sonnet', 'date': datetime.date(2024, 3, 6), 'versions': '0.25.1-dev', 'seconds_per_case': 23.1, 'total_cost': 0.0}, {'dirname': '2024-05-03-20-47-24--gemini-1.5-pro-diff-fenced', 'test_cases': 133, 'model': 'gemini-1.5-pro-latest', 'edit_format': 'diff-fenced', 'commit_hash': '3a48dfb, 5d32dd7', 'pass_rate_1': 45.9, 'pass_rate_2': 57.1, 'percent_cases_well_formed': 87.2, 'error_outputs': 60, 'num_malformed_responses': 17, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 8, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-pro-latest', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 21.3, 'total_cost': 0.0}, {'dirname': '2024-05-08-20-59-15--may-gpt-3.5-turbo-whole', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0125', 'released': datetime.date(2024, 1, 25), 'edit_format': 'whole', 'commit_hash': '1d55f74', 'pass_rate_1': 41.4, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider -3', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.5032}, {'dirname': '2023-11-06-21-23-59--gpt-3.5-turbo-0301', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0301', 'released': datetime.date(2023, 3, 1), 'edit_format': 'whole', 'commit_hash': '44388db-dirty', 'pass_rate_1': 50.4, 'pass_rate_2': 57.9, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 8, 'command': 'aider --model gpt-3.5-turbo-0301', 'date': datetime.date(2023, 11, 6), 'versions': '0.16.4-dev', 'seconds_per_case': 6.5, 'total_cost': 0.4822}, {'dirname': '2023-11-07-02-41-07--gpt-3.5-turbo-0613', 'test_cases': 133, 'model': 'gpt-3.5-turbo-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'whole', 'commit_hash': '93aa497-dirty', 'pass_rate_1': 38.3, 'pass_rate_2': 50.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'command': 'aider --model gpt-3.5-turbo-0613', 'date': datetime.date(2023, 11, 7), 'versions': '0.16.4-dev', 'seconds_per_case': 18.0, 'total_cost': 0.5366}, {'dirname': '2024-04-30-21-40-51--litellm-gpt-3.5-turbo-1106-again', 'test_cases': 132, 'model': 'gpt-3.5-turbo-1106', 'edit_format': 'whole', 'commit_hash': '7b14d77', 'pass_rate_1': 45.5, 'pass_rate_2': 56.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 19, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-3.5-turbo-1106', 'date': datetime.date(2024, 4, 30), 'versions': '0.30.2-dev', 'seconds_per_case': 5.3, 'total_cost': 0.3261}, {'dirname': '2024-01-25-23-37-15--jan-exercism-gpt-4-0125-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-0125-preview', 'released': datetime.date(2024, 1, 25), 'edit_format': 'udiff', 'commit_hash': 'edcf9b1', 'pass_rate_1': 55.6, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 6, 'num_malformed_responses': 3, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 3, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model gpt-4-0125-preview', 'date': datetime.date(2024, 1, 25), 'versions': '0.22.1-dev', 'seconds_per_case': 44.8, 'total_cost': 14.6428}, {'dirname': '2024-05-04-15-07-30--redo-gpt-4-0314-diff-reminder-rules', 'test_cases': 133, 'model': 'gpt-4-0314', 'released': datetime.date(2023, 3, 14), 'edit_format': 'diff', 'commit_hash': '0d43468', 'pass_rate_1': 50.4, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 93.2, 'error_outputs': 28, 'num_malformed_responses': 9, 'user_asks': 1, 'lazy_comments': 3, 'syntax_errors': 9, 'indentation_errors': 7, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gpt-4-0314', 'date': datetime.date(2024, 5, 4), 'versions': '0.31.2-dev', 'seconds_per_case': 19.8, 'total_cost': 16.2689}, {'dirname': '2023-12-16-21-24-28--editblock-gpt-4-0613-actual-main', 'test_cases': 133, 'model': 'gpt-4-0613', 'released': datetime.date(2023, 6, 13), 'edit_format': 'diff', 'commit_hash': '3aa17c4', 'pass_rate_1': 46.6, 'pass_rate_2': 67.7, 'percent_cases_well_formed': 100.0, 'error_outputs': 14, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider -4', 'date': datetime.date(2023, 12, 16), 'versions': '0.18.2-dev', 'seconds_per_case': 33.6, 'total_cost': 17.4657}, {'dirname': '2024-05-08-21-16-03--may-gpt-4-1106-preview-udiff', 'test_cases': 133, 'model': 'gpt-4-1106-preview', 'released': datetime.date(2023, 11, 6), 'edit_format': 'udiff', 'commit_hash': '87664dc', 'pass_rate_1': 51.9, 'pass_rate_2': 65.4, 'percent_cases_well_formed': 92.5, 'error_outputs': 30, 'num_malformed_responses': 10, 'user_asks': 0, 'lazy_comments': 3, 'syntax_errors': 11, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model gpt-4-1106-preview', 'date': datetime.date(2024, 5, 8), 'versions': '0.33.1-dev', 'seconds_per_case': 20.4, 'total_cost': 6.6061}, {'dirname': '2024-05-01-02-09-20--gpt-4-turbo-examples', 'test_cases': 133, 'model': 'gpt-4-turbo-2024-04-09 (udiff)', 'released': datetime.date(2024, 4, 9), 'edit_format': 'udiff', 'commit_hash': 'e610e5b-dirty', 'pass_rate_1': 48.1, 'pass_rate_2': 63.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 12, 'num_malformed_responses': 4, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 4, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --gpt-4-turbo', 'date': datetime.date(2024, 5, 1), 'versions': '0.30.2-dev', 'seconds_per_case': 22.8, 'total_cost': 6.3337}, {'dirname': '2024-05-03-22-24-48--openrouter--llama3-diff-examples-sys-msg', 'test_cases': 132, 'model': 'llama3-70b-8192', 'released': datetime.date(2024, 4, 18), 'edit_format': 'diff', 'commit_hash': 'b5bb453', 'pass_rate_1': 38.6, 'pass_rate_2': 49.2, 'percent_cases_well_formed': 73.5, 'error_outputs': 105, 'num_malformed_responses': 35, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model groq/llama3-70b-8192', 'date': datetime.date(2024, 5, 3), 'versions': '0.31.2-dev', 'seconds_per_case': 14.5, 'total_cost': 0.4311}, {'dirname': '2024-05-06-18-31-08--command-r-plus-whole-final', 'test_cases': 133, 'model': 'command-r-plus', 'released': datetime.date(2024, 4, 4), 'edit_format': 'whole', 'commit_hash': 'fc3a43e-dirty', 'pass_rate_1': 21.8, 'pass_rate_2': 31.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 7, 'command': 'aider --model command-r-plus', 'date': datetime.date(2024, 5, 6), 'versions': '0.31.2-dev', 'seconds_per_case': 22.9, 'total_cost': 2.7494}, {'dirname': '2024-05-09-18-57-52--deepseek-chat-v2-diff-reverted-and-helpful-assistant2', 'test_cases': 133, 'model': 'DeepSeek Chat V2 (original)', 'released': datetime.date(2024, 5, 6), 'edit_format': 'diff', 'commit_hash': '80a3f6d', 'pass_rate_1': 44.4, 'pass_rate_2': 60.9, 'percent_cases_well_formed': 97.0, 'error_outputs': 14, 'num_malformed_responses': 4, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 13, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 5, 9), 'versions': '0.33.1-dev', 'seconds_per_case': 86.8, 'total_cost': 0.0941}, {'dirname': '2024-05-07-20-32-37--qwen1.5-110b-chat-whole', 'test_cases': 133, 'model': 'qwen1.5-110b-chat', 'released': datetime.date(2024, 2, 4), 'edit_format': 'whole', 'commit_hash': '70b1c0c', 'pass_rate_1': 30.8, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 20, 'syntax_errors': 0, 'indentation_errors': 6, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model together_ai/qwen/qwen1.5-110b-chat', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 46.9, 'total_cost': 0.0}, {'dirname': '2024-05-07-20-57-04--wizardlm-2-8x22b-whole', 'test_cases': 133, 'model': 'WizardLM-2 8x22B', 'edit_format': 'whole', 'commit_hash': '8e272bf, bbe8639', 'pass_rate_1': 27.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 1, 'syntax_errors': 2, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openrouter/microsoft/wizardlm-2-8x22b', 'date': datetime.date(2024, 5, 7), 'versions': '0.31.2-dev', 'seconds_per_case': 36.6, 'total_cost': 0.0}, {'dirname': '2024-05-13-17-39-05--gpt-4o-diff', 'test_cases': 133, 'model': 'gpt-4o', 'released': datetime.date(2024, 5, 13), 'edit_format': 'diff', 'commit_hash': 'b6cd852', 'pass_rate_1': 60.2, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 96.2, 'error_outputs': 103, 'num_malformed_responses': 5, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider', 'date': datetime.date(2024, 5, 13), 'versions': '0.34.1-dev', 'seconds_per_case': 6.0, 'total_cost': 0.0}, {'dirname': '2024-04-12-22-18-20--gpt-4-turbo-2024-04-09-plain-diff', 'test_cases': 33, 'model': 'gpt-4-turbo-2024-04-09 (diff)', 'edit_format': 'diff', 'commit_hash': '9b2e697-dirty', 'pass_rate_1': 48.5, 'pass_rate_2': 57.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 15, 'num_malformed_responses': 0, 'user_asks': 15, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model gpt-4-turbo-2024-04-09', 'date': datetime.date(2024, 4, 12), 'versions': '0.28.1-dev', 'seconds_per_case': 17.6, 'total_cost': 1.6205}, {'dirname': '2024-06-08-22-37-55--qwen2-72b-instruct-whole', 'test_cases': 133, 'model': 'Qwen2 72B Instruct', 'edit_format': 'whole', 'commit_hash': '02c7335-dirty, 1a97498-dirty', 'pass_rate_1': 44.4, 'pass_rate_2': 55.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model together_ai/qwen/Qwen2-72B-Instruct', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 14.3, 'total_cost': 0.0}, {'dirname': '2024-06-08-23-45-41--gemini-1.5-flash-latest-whole', 'test_cases': 133, 'model': 'gemini-1.5-flash-latest', 'edit_format': 'whole', 'commit_hash': '86ea47f-dirty', 'pass_rate_1': 33.8, 'pass_rate_2': 44.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 16, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 12, 'lazy_comments': 0, 'syntax_errors': 9, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model gemini/gemini-1.5-flash-latest', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 7.2, 'total_cost': 0.0}, {'dirname': '2024-06-09-03-28-21--codestral-whole', 'test_cases': 133, 'model': 'codestral-2405', 'edit_format': 'whole', 'commit_hash': 'effc88a', 'pass_rate_1': 35.3, 'pass_rate_2': 51.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 4, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 4, 'lazy_comments': 1, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model mistral/codestral-2405', 'date': datetime.date(2024, 6, 9), 'versions': '0.37.1-dev', 'seconds_per_case': 7.5, 'total_cost': 0.6805}, {'dirname': '2024-06-08-19-25-26--codeqwen:7b-chat-v1.5-q8_0-whole', 'test_cases': 133, 'model': 'codeqwen:7b-chat-v1.5-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 32.3, 'pass_rate_2': 34.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --model ollama/codeqwen:7b-chat-v1.5-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 15.6, 'total_cost': 0.0}, {'dirname': '2024-06-08-16-12-31--codestral:22b-v0.1-q8_0-whole', 'test_cases': 133, 'model': 'codestral:22b-v0.1-q8_0', 'edit_format': 'whole', 'commit_hash': 'be0520f-dirty', 'pass_rate_1': 35.3, 'pass_rate_2': 48.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 8, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 8, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/codestral:22b-v0.1-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 46.4, 'total_cost': 0.0}, {'dirname': '2024-06-08-17-54-04--qwen2:72b-instruct-q8_0-whole', 'test_cases': 133, 'model': 'qwen2:72b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': '74e51d5-dirty', 'pass_rate_1': 43.6, 'pass_rate_2': 49.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 27, 'lazy_comments': 0, 'syntax_errors': 5, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model ollama/qwen2:72b-instruct-q8_0', 'date': datetime.date(2024, 6, 8), 'versions': '0.37.1-dev', 'seconds_per_case': 280.6, 'total_cost': 0.0}, {'dirname': '2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue', 'test_cases': 133, 'model': 'claude-3.5-sonnet', 'edit_format': 'diff', 'commit_hash': '35f21b5', 'pass_rate_1': 57.1, 'pass_rate_2': 77.4, 'percent_cases_well_formed': 99.2, 'error_outputs': 23, 'released': datetime.date(2024, 6, 20), 'num_malformed_responses': 4, 'num_with_malformed_responses': 1, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 1, 'command': 'aider --sonnet', 'date': datetime.date(2024, 7, 4), 'versions': '0.42.1-dev', 'seconds_per_case': 17.6, 'total_cost': 3.6346}, {'dirname': '2024-07-01-21-41-48--haiku-whole', 'test_cases': 133, 'model': 'claude-3-haiku-20240307', 'edit_format': 'whole', 'commit_hash': '75f506d', 'pass_rate_1': 40.6, 'pass_rate_2': 47.4, 'percent_cases_well_formed': 100.0, 'error_outputs': 6, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 3, 13), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model claude-3-haiku-20240307', 'date': datetime.date(2024, 7, 1), 'versions': '0.41.1-dev', 'seconds_per_case': 7.1, 'total_cost': 0.1946}, {'dirname': '2024-07-09-10-12-27--gemma2:27b-instruct-q8_0', 'test_cases': 133, 'model': 'gemma2:27b-instruct-q8_0', 'edit_format': 'whole', 'commit_hash': 'f9d96ac-dirty', 'pass_rate_1': 31.6, 'pass_rate_2': 36.1, 'percent_cases_well_formed': 100.0, 'error_outputs': 35, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 35, 'lazy_comments': 2, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model ollama/gemma2:27b-instruct-q8_0', 'date': datetime.date(2024, 7, 9), 'versions': '0.43.0', 'seconds_per_case': 101.3, 'total_cost': 0.0}, {'dirname': '2024-07-18-18-57-46--gpt-4o-mini-whole', 'test_cases': 133, 'model': 'gpt-4o-mini', 'edit_format': 'whole', 'commit_hash': 'd31eef3-dirty', 'pass_rate_1': 40.6, 'pass_rate_2': 55.6, 'released': datetime.date(2024, 7, 18), 'percent_cases_well_formed': 100.0, 'error_outputs': 1, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model gpt-4o-mini', 'date': datetime.date(2024, 7, 18), 'versions': '0.44.1-dev', 'seconds_per_case': 7.8, 'total_cost': 0.0916}, {'dirname': '2024-07-19-08-57-13--openrouter-deepseek-chat-v2-0628', 'test_cases': 133, 'model': 'DeepSeek Chat V2 0628', 'edit_format': 'diff', 'commit_hash': '96ff06e-dirty', 'pass_rate_1': 60.9, 'pass_rate_2': 69.9, 'percent_cases_well_formed': 97.7, 'released': datetime.date(2024, 6, 28), 'error_outputs': 58, 'num_malformed_responses': 13, 'num_with_malformed_responses': 3, 'user_asks': 2, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 7, 19), 'versions': '0.45.2-dev', 'seconds_per_case': 37.1, 'total_cost': 0.0}, {'dirname': '2024-07-23-22-07-08--llama-205b-diff', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (diff)', 'edit_format': 'diff', 'commit_hash': 'f7ce78b-dirty', 'pass_rate_1': 46.6, 'pass_rate_2': 63.9, 'released': datetime.date(2024, 7, 23), 'percent_cases_well_formed': 92.5, 'error_outputs': 84, 'num_malformed_responses': 19, 'num_with_malformed_responses': 10, 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 4, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 23), 'versions': '0.45.2-dev', 'seconds_per_case': 56.8, 'total_cost': 0.0}, {'dirname': '2024-07-24-06-30-29--llama-405b-whole', 'test_cases': 133, 'model': 'llama-3.1-405b-instruct (whole)', 'edit_format': 'whole', 'commit_hash': 'a362dea-dirty', 'pass_rate_1': 48.9, 'pass_rate_2': 66.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 0, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model openrouter/meta-llama/llama-3.1-405b-instruct', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 18.1, 'total_cost': 0.0}, {'dirname': '2024-07-24-07-10-58--deepseek-chat2-0724-diff-direct', 'test_cases': 133, 'model': 'DeepSeek Coder V2 0724', 'edit_format': 'diff', 'commit_hash': '89965bf', 'pass_rate_1': 57.9, 'pass_rate_2': 72.9, 'percent_cases_well_formed': 97.7, 'error_outputs': 13, 'released': datetime.date(2024, 7, 24), 'num_malformed_responses': 3, 'num_with_malformed_responses': 3, 'user_asks': 1, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 1, 'exhausted_context_windows': 0, 'test_timeouts': 2, 'command': 'aider --model deepseek/deepseek-chat', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 36.2, 'total_cost': 0.0981}, {'dirname': '2024-07-24-19-08-47--mistral-large-2407-whole', 'test_cases': 133, 'model': 'Mistral Large 2 (2407)', 'edit_format': 'whole', 'commit_hash': '859a13e', 'pass_rate_1': 39.8, 'pass_rate_2': 60.2, 'percent_cases_well_formed': 100.0, 'error_outputs': 3, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'released': datetime.date(2024, 7, 24), 'user_asks': 3, 'lazy_comments': 0, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 3, 'command': 'aider --model mistral/mistral-large-2407', 'date': datetime.date(2024, 7, 24), 'versions': '0.45.2-dev', 'seconds_per_case': 26.6, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-12-27--fireworks-llama-8b-whole', 'test_cases': 133, 'model': 'llama-3.1-8b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 26.3, 'pass_rate_2': 37.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 27, 'num_malformed_responses': 0, 'released': datetime.date(2024, 7, 23), 'num_with_malformed_responses': 0, 'user_asks': 23, 'lazy_comments': 8, 'syntax_errors': 1, 'indentation_errors': 0, 'exhausted_context_windows': 4, 'test_timeouts': 7, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 3.8, 'total_cost': 0.0}, {'dirname': '2024-07-25-08-07-45--fireworks-llama-70b-whole', 'test_cases': 133, 'model': 'llama-3.1-70b-instruct', 'edit_format': 'whole', 'commit_hash': 'ffcced8', 'pass_rate_1': 43.6, 'pass_rate_2': 58.6, 'percent_cases_well_formed': 100.0, 'error_outputs': 0, 'num_malformed_responses': 0, 'num_with_malformed_responses': 0, 'user_asks': 0, 'released': datetime.date(2024, 7, 23), 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 6, 'command': 'aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct', 'date': datetime.date(2024, 7, 25), 'versions': '0.45.2-dev', 'seconds_per_case': 7.3, 'total_cost': 0.0}, {'dirname': '2024-08-06-18-28-39--gpt-4o-2024-08-06-diff-again', 'test_cases': 133, 'model': 'gpt-4o-2024-08-06', 'edit_format': 'diff', 'commit_hash': 'ed9ed89', 'pass_rate_1': 57.1, 'pass_rate_2': 71.4, 'percent_cases_well_formed': 98.5, 'error_outputs': 18, 'num_malformed_responses': 2, 'num_with_malformed_responses': 2, 'user_asks': 10, 'lazy_comments': 0, 'syntax_errors': 6, 'indentation_errors': 2, 'exhausted_context_windows': 0, 'test_timeouts': 5, 'released': datetime.date(2024, 8, 6), 'command': 'aider --model openai/gpt-4o-2024-08-06', 'date': datetime.date(2024, 8, 6), 'versions': '0.48.1-dev', 'seconds_per_case': 6.5, 'total_cost': 0.0}, {'dirname': '2024-08-14-13-07-12--chatgpt-4o-latest-diff', 'test_cases': 133, 'model': 'chatgpt-4o-latest', 'edit_format': 'diff', 'commit_hash': 'b1c3769', 'pass_rate_1': 53.4, 'pass_rate_2': 69.2, 'percent_cases_well_formed': 97.7, 'error_outputs': 27, 'num_malformed_responses': 5, 'num_with_malformed_responses': 3, 'user_asks': 7, 'lazy_comments': 0, 'syntax_errors': 0, 'indentation_errors': 0, 'exhausted_context_windows': 0, 'test_timeouts': 0, 'command': 'aider --model openai/chatgpt-4o-latest', 'date': datetime.date(2024, 8, 14), 'released': datetime.date(2024, 8, 8), 'versions': '0.50.2-dev', 'seconds_per_case': 26.3, 'total_cost': 3.6113}]2024-08-14 06:20:48.437 Python[6129:11424500] ApplePersistenceIgnoreState: Existing state will not be touched. New state will be written to /var/folders/49/kxrdwwbx0h9bchx99397477c0000gn/T/org.python.python.savedState > ]1337;File=inline=1;size=92534;height=29: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 > > Debug: Processed data: @@ -67854,7 +67854,7 @@ def get_parser(default_config_files, git_root): const=gpt_3_model_name, help=f"Utiliser le modèle {gpt_3_model_name} pour la discussion principale", ) - deepseek_model = "deepseek/deepseek-coder" + deepseek_model = "deepseek/deepseek-chat" group.add_argument( "--deepseek", action="store_const", @@ -68550,7 +68550,7 @@ document.addEventListener('DOMContentLoaded', function () { var ctx = document.getElementById('passRateChart').getContext('2d'); var data = { - labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-coder'], + labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-chat'], datasets: [ { label: 'Markdown', @@ -68645,7 +68645,7 @@ document.addEventListener('DOMContentLoaded', function () { var ctx = document.getElementById('passRateChart').getContext('2d'); var data = { - labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-coder'], + labels: ['gpt-4o-2024-08-06', 'claude-3.5-sonnet', 'deepseek-chat'], datasets: [ { label: 'Markdown', @@ -69086,14 +69086,14 @@ MODELS=<>>>>>> REPLACE ``` @@ -80945,7 +80945,7 @@ Bonjour! > Model openrouter/deepseek/deepseek-chat: Unknown context window size and costs, using sane defaults. > Did you mean one of these? > - deepseek/deepseek-chat -> - openrouter/deepseek/deepseek-coder +> - openrouter/deepseek/deepseek-chat > For more info, see: https://aider.chat/docs/llms/warnings.html > Aider v0.50.2-dev > Model: openrouter/deepseek/deepseek-chat with whole edit format @@ -80959,7 +80959,7 @@ Bonjour! > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with ♾️ diff edit format +> Model: deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -80968,9 +80968,9 @@ Bonjour! # aider chat started at 2024-08-19 10:20:55 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder HISTORY.md --dry-run --msg translate it all to french +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat HISTORY.md --dry-run --msg translate it all to french > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Added HISTORY.md to the chat. @@ -80980,9 +80980,9 @@ Bonjour! # aider chat started at 2024-08-19 10:21:28 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -80998,7 +80998,7 @@ Bonjour! > Loaded /Users/gauthier/.env > Loaded /Users/gauthier/Projects/aider/.env > Too soon to check version: 21.3 hours -> Command Line Args: --model openrouter/deepseek/deepseek-coder --verbose +> Command Line Args: --model openrouter/deepseek/deepseek-chat --verbose Environment Variables: OPENAI_API_KEY: ...9doi @@ -81064,7 +81064,7 @@ Option settings: - max_chat_history_tokens: None - message: None - message_file: None - - model: openrouter/deepseek/deepseek-coder + - model: openrouter/deepseek/deepseek-chat - model_metadata_file: .aider.model.metadata.json - model_settings_file: .aider.model.settings.yml - models: None @@ -81094,7 +81094,7 @@ Option settings: - voice_language: en - weak_model: None - yes: None -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --verbose +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --verbose > No model settings files loaded > Searched for model settings files: > - /Users/gauthier/.aider.model.settings.yml @@ -81102,7 +81102,7 @@ Option settings: > Loaded model metadata from: > - /Users/gauthier/Projects/aider/.aider.model.metadata.json > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -81114,7 +81114,7 @@ Option settings: > Loaded /Users/gauthier/.env > Loaded /Users/gauthier/Projects/aider/.env > Too soon to check version: 21.3 hours -> Command Line Args: --model openrouter/deepseek/deepseek-coder --verbose +> Command Line Args: --model openrouter/deepseek/deepseek-chat --verbose Environment Variables: OPENAI_API_KEY: ...9doi @@ -81180,7 +81180,7 @@ Option settings: - max_chat_history_tokens: None - message: None - message_file: None - - model: openrouter/deepseek/deepseek-coder + - model: openrouter/deepseek/deepseek-chat - model_metadata_file: .aider.model.metadata.json - model_settings_file: .aider.model.settings.yml - models: None @@ -81210,7 +81210,7 @@ Option settings: - voice_language: en - weak_model: None - yes: None -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --verbose +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --verbose > No model settings files loaded > Searched for model settings files: > - /Users/gauthier/.aider.model.settings.yml @@ -81218,7 +81218,7 @@ Option settings: > Loaded model metadata from: > - /Users/gauthier/Projects/aider/.aider.model.metadata.json > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -81227,9 +81227,9 @@ Option settings: # aider chat started at 2024-08-19 10:27:58 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -81246,70 +81246,70 @@ Option settings: # aider chat started at 2024-08-19 10:28:38 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:29:42 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:32:30 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:33:16 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with ♾️ diff edit format +> Model: openrouter/deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:34:03 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:34:35 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:34:53 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with diff edit format +> Model: openrouter/deepseek/deepseek-chat with diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:35:01 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit # aider chat started at 2024-08-19 10:35:15 @@ -81340,18 +81340,18 @@ Option settings: # aider chat started at 2024-08-19 10:38:32 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder --exit +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat --exit > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with ♾️ diff edit format +> Model: openrouter/deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args # aider chat started at 2024-08-19 10:38:46 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder HISTORY.md --dry-run --msg translate it all to french +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat HISTORY.md --dry-run --msg translate it all to french > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with ♾️ diff edit format +> Model: openrouter/deepseek/deepseek-chat with ♾️ diff edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Added HISTORY.md to the chat. @@ -81419,9 +81419,9 @@ HISTORY.md # aider chat started at 2024-08-19 10:39:14 -> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-coder HISTORY.md --dry-run --msg translate it all to french --edit-format whole +> /Users/gauthier/Projects/aider/.venv/bin/aider --model openrouter/deepseek/deepseek-chat HISTORY.md --dry-run --msg translate it all to french --edit-format whole > Aider v0.50.2-dev -> Model: openrouter/deepseek/deepseek-coder with ♾️ whole edit format +> Model: openrouter/deepseek/deepseek-chat with ♾️ whole edit format > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Added HISTORY.md to the chat. @@ -82485,9 +82485,9 @@ Bonjour! # aider chat started at 2024-08-19 13:19:08 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --cache --read HISTORY.md --no-stream --msg hi -> Prompt caching not supported for deepseek/deepseek-coder. +> Prompt caching not supported for deepseek/deepseek-chat. > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, files refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82501,9 +82501,9 @@ Bonjour! # aider chat started at 2024-08-19 13:19:19 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --cache --read HISTORY.md --no-stream --msg hi -> Prompt caching not supported for deepseek/deepseek-coder. +> Prompt caching not supported for deepseek/deepseek-chat. > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, files refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82518,7 +82518,7 @@ Hello! How can I assist you today? > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82538,9 +82538,9 @@ Hello! How can I assist you today? # aider chat started at 2024-08-19 13:20:53 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --cache -> Prompt caching not supported for deepseek/deepseek-coder. +> Prompt caching not supported for deepseek/deepseek-chat. > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, files refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82560,9 +82560,9 @@ Hello! How can I assist you today? # aider chat started at 2024-08-19 13:21:03 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --cache --read HISTORY.md --no-stream --msg hi -> Prompt caching not supported for deepseek/deepseek-coder. +> Prompt caching not supported for deepseek/deepseek-chat. > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, files refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82577,7 +82577,7 @@ It seems like your request was not specific enough for me to determine which fil > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82587,9 +82587,9 @@ It seems like your request was not specific enough for me to determine which fil # aider chat started at 2024-08-19 13:21:42 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --cache -> Prompt caching not supported for deepseek/deepseek-coder. +> Prompt caching not supported for deepseek/deepseek-chat. > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, files refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82603,9 +82603,9 @@ It seems like your request was not specific enough for me to determine which fil # aider chat started at 2024-08-19 13:21:56 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --cache --read HISTORY.md --no-stream --msg hi -> Prompt caching not supported for deepseek/deepseek-coder. +> Prompt caching not supported for deepseek/deepseek-chat. > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, files refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82619,9 +82619,9 @@ Hello! How can I assist you today? # aider chat started at 2024-08-19 13:22:16 > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --cache --read HISTORY.md --no-stream --msg hi -> Prompt caching not supported for deepseek/deepseek-coder. +> Prompt caching not supported for deepseek/deepseek-chat. > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, files refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82636,7 +82636,7 @@ Hello! How can I assist you today? > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --no-stream --msg hi > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82661,7 +82661,7 @@ Hello! How can I assist you today? > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --no-stream --msg hi > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82691,7 +82691,7 @@ Bonjour! > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --msg hi > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82706,7 +82706,7 @@ Hello! How can I assist you today? > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --msg hi > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82721,7 +82721,7 @@ Hello! How can I assist you today? > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --msg hi --no-stream > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82919,7 +82919,7 @@ Hola! Puedo ayudarte con los cambios que necesites en el código, pero primero n > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --msg hi --no-stream > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82935,7 +82935,7 @@ Cost: $0.0034 message, $0.0034 session. > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --msg hi --no-stream > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82950,7 +82950,7 @@ Hello! How can I assist you today? > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --msg hi > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args @@ -82965,7 +82965,7 @@ Hello! How can I assist you today? > /Users/gauthier/Projects/aider/.venv/bin/aider --deepseek --read HISTORY.md --msg hi --no-stream > Aider v0.50.2-dev -> Model: deepseek/deepseek-coder with diff edit format, infinite output +> Model: deepseek/deepseek-chat with diff edit format, infinite output > Git repo: .git with 308 files > Repo-map: using 1024 tokens, auto refresh > Use /help for help, run "aider --help" to see cmd line args