Add support for documentation content exceeding token limits (#1670)

* - Add support for documentation content exceeding token limits via two phase operation:
1. Ask LLM to rank headings which are most likely to contain an answer to a user question
2. Provide the corresponding files for the LLM to search for an answer.

- Refactor of help_docs to make the code more readable
- For the purpose of getting canonical path: git providers to use default branch and not the PR's source branch.
- Refactor of token counting and making it clear on when an estimate factor will be used.

* Code review changes:
1. Correctly handle exception during retry_with_fallback_models (to allow fallback model to run in case of failure)
2. Better naming for default_branch in bitbucket cloud provider

pr_agent/settings/configuration.toml

@@ -9,7 +9,6 @@
 model="o3-mini"
 fallback_models=["gpt-4o-2024-11-20"]
 #model_weak="gpt-4o-mini-2024-07-18" # optional, a weaker model to use for some easier tasks
-model_token_count_estimate_factor=0.3 # factor to increase the token count estimate, in order to reduce likelihood of model failure due to too many tokens.
 # CLI
 git_provider="github"
 publish_output=true
@@ -30,6 +29,7 @@ max_description_tokens = 500
 max_commits_tokens = 500
 max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities.
 custom_model_max_tokens=-1 # for models not in the default list
+model_token_count_estimate_factor=0.3 # factor to increase the token count estimate, in order to reduce likelihood of model failure due to too many tokens - applicable only when requesting an accurate estimate.
 # patch extension logic
 patch_extension_skip_types =[".md",".txt"]
 allow_dynamic_context=true