Teknium d15efc9c1b fix: correct GPT-5 family context lengths in fallback defaults (#9309) ...

The generic 'gpt-5' fallback was set to 128,000 — which is the max
OUTPUT tokens, not the context window. GPT-5 base and most variants
(codex, mini) have 400,000 context. This caused /model to report
128k for models like gpt-5.3-codex when models.dev was unavailable.

Added specific entries for GPT-5 variants with different context sizes:
- gpt-5.4, gpt-5.4-pro: 1,050,000 (1.05M)
- gpt-5.4-mini, gpt-5.4-nano: 400,000
- gpt-5.3-codex-spark: 128,000 (reduced)
- gpt-5.1-chat: 128,000 (chat variant)
- gpt-5 (catch-all): 400,000

Sources: https://developers.openai.com/api/docs/models

2026-04-13 19:22:23 -07:00

..

__init__.py

Refactor Terminal and AIAgent cleanup

2026-02-21 22:31:43 -08:00

anthropic_adapter.py

fix: align MiniMax provider with official API docs

2026-04-11 01:04:41 -07:00

auxiliary_client.py

fix: improve ACP type check and restore comment accuracy

2026-04-13 16:17:43 -07:00

context_compressor.py

fix(agent): route compression aux through live session runtime

2026-04-12 01:34:52 -07:00

context_engine.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00

context_references.py

fix(agent): preserve quoted @file references with spaces

2026-04-10 13:05:01 -07:00

copilot_acp_client.py

fix: bridge tool-calls in copilot-acp adapter

2026-04-06 01:47:57 -07:00

credential_pool.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00

display.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00

error_classifier.py

fix: add vLLM/local server error patterns + MCP initial connection retry (#9281)

2026-04-13 18:46:14 -07:00

insights.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00

manual_compression_feedback.py

fix(gateway): make manual compression feedback truthful

2026-04-10 21:16:53 -07:00

memory_manager.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00

memory_provider.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821)

2026-04-07 10:25:31 -07:00

model_metadata.py

fix: correct GPT-5 family context lengths in fallback defaults (#9309)

2026-04-13 19:22:23 -07:00

models_dev.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00

prompt_builder.py

feat(wecom): add platform hint for native media sending

2026-04-13 04:46:04 -07:00

prompt_caching.py

fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter

2026-03-21 16:54:43 -07:00

rate_limit_tracker.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00

redact.py

fix: mem0 API v2 compat, prefetch context fencing, secret redaction (#5423)

2026-04-05 22:43:33 -07:00

retry_utils.py

feat(agent): add jittered retry backoff

2026-04-08 00:41:36 -07:00

skill_commands.py

fix: prevent zombie processes, redact cron stderr, skip symlinks in skill enumeration

2026-04-11 02:03:20 -07:00

skill_utils.py

refactor: extract shared helpers to deduplicate repeated code patterns (#7917)

2026-04-11 13:59:52 -07:00

smart_model_routing.py

fix: UTF-8 config encoding, pairing hint, credential_pool key, header normalization (#7174)

2026-04-10 05:33:48 -07:00

subdirectory_hints.py

fix(agent): catch PermissionError in subdirectory hint discovery

2026-04-09 03:10:30 -07:00

title_generator.py

fix: title_generator no longer logs as 'compression' task

2026-04-12 04:17:18 -07:00

trajectory.py

Refactor Terminal and AIAgent cleanup

2026-02-21 22:31:43 -08:00

usage_pricing.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

2026-04-13 16:32:04 -07:00