agent/codex
2
0
Fork 0
mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add the utility to truncate by tokens (#6746)

Browse Source 
- This PR is to make it on path for truncating by tokens. This path will
be initially used by unified exec and context manager (responsible for
MCP calls mainly).
- We are exposing new config `calls_output_max_tokens`
- Use `tokens` as the main budget unit but truncate based on the model
family by Introducing `TruncationPolicy`.
- Introduce `truncate_text` as a router for truncation based on the
mode.

In next PRs:
- remove truncate_with_line_bytes_budget
- Add the ability to the model to override the token budget.
This commit is contained in:
Ahmed Ibrahim
2025-11-18 11:36:23 -08:00
committed by GitHub
parent b035c604b0
commit 3de8790714
21 changed files with 770 additions and 549 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/config.md
+1
View File
@@ -925,6 +925,7 @@ Valid values:
| `model_provider` | string | Provider id from `model_providers` (default: `openai`). |
| `model_context_window` | number | Context window tokens. |
| `model_max_output_tokens` | number | Max output tokens. |
| `tool_output_token_limit` | number | Token budget for stored function/tool outputs in history (default: 2,560 tokens). |
| `approval_policy` | `untrusted` \| `on-failure` \| `on-request` \| `never` | When to prompt for approval. |
| `sandbox_mode` | `read-only` \| `workspace-write` \| `danger-full-access` | OS sandbox policy. |
| `sandbox_workspace_write.writable_roots` | array<string> | Extra writable roots in workspace‑write. |
docs/example-config.md
+1
View File
@@ -33,6 +33,7 @@ model_provider = "openai"
# model_context_window = 128000 # tokens; default: auto for model
# model_max_output_tokens = 8192 # tokens; default: auto for model
# model_auto_compact_token_limit = 0 # disable/override auto; default: model family specific
# tool_output_token_limit = 10000 # tokens stored per tool output; default: 10000 for gpt-5.1-codex
################################################################################
# Reasoning & Verbosity (Responses API capable models)