CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-05 13:15:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

refactor: don't hardcode model — use codex default (always latest)

Browse Source
This commit is contained in:
Garry Tan
2026-03-18 21:32:58 -07:00
parent 6294c5a74a
commit 5ec2dd05a5
2 changed files with 12 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex/SKILL.md
+6 -11
View File
@@ -410,11 +410,9 @@ Session saved — run /codex again to continue this conversation.
## Model & Reasoning
**Models** (with ChatGPT login):
- `gpt-5.2-codex` (default) — frontier agentic coding model, best overall
- `gpt-5.2` — deeper reasoning for non-coding analysis
- `gpt-5.1-codex-max` — deep and fast reasoning, 30% cheaper
- `gpt-5.1-codex-mini` — faster and cheaper, less capable
**Model:** No model is hardcoded — codex uses whatever its current default is (the frontier
agentic coding model). This means as OpenAI ships newer models, /codex automatically
uses them. If the user wants a specific model, pass `-m` through to codex.
**Reasoning effort** varies by mode — use the right level for each task:
- **Review mode:** `high` — thorough but not slow. Diff review benefits from depth but doesn't need maximum compute.
@@ -424,19 +422,16 @@ Session saved — run /codex again to continue this conversation.
**Web search:** All codex commands use `--enable web_search_cached` so Codex can look up
docs and APIs during review. This is OpenAI's cached index — fast, no extra cost.
If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`),
pass the `-m` flag through to codex.
If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`
or `/codex challenge -m gpt-5.2`), pass the `-m` flag through to codex.
---
## Cost Estimation
Parse token count from stderr. Codex prints `tokens used\nN` to stderr.
Estimate cost based on the model:
- gpt-5.2-codex: ~$0.008 per 1K tokens (estimate)
- o3: ~$0.01 per 1K tokens (estimate)
Display as: `Tokens: N | Est. cost: ~$X.XX`
Display as: `Tokens: N`
If token count is not available, display: `Tokens: unknown`
codex/SKILL.md.tmpl
+6 -11
View File
@@ -264,11 +264,9 @@ Session saved — run /codex again to continue this conversation.
## Model & Reasoning
**Models** (with ChatGPT login):
- `gpt-5.2-codex` (default) — frontier agentic coding model, best overall
- `gpt-5.2` — deeper reasoning for non-coding analysis
- `gpt-5.1-codex-max` — deep and fast reasoning, 30% cheaper
- `gpt-5.1-codex-mini` — faster and cheaper, less capable
**Model:** No model is hardcoded — codex uses whatever its current default is (the frontier
agentic coding model). This means as OpenAI ships newer models, /codex automatically
uses them. If the user wants a specific model, pass `-m` through to codex.
**Reasoning effort** varies by mode — use the right level for each task:
- **Review mode:** `high` — thorough but not slow. Diff review benefits from depth but doesn't need maximum compute.
@@ -278,19 +276,16 @@ Session saved — run /codex again to continue this conversation.
**Web search:** All codex commands use `--enable web_search_cached` so Codex can look up
docs and APIs during review. This is OpenAI's cached index — fast, no extra cost.
If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`),
pass the `-m` flag through to codex.
If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`
or `/codex challenge -m gpt-5.2`), pass the `-m` flag through to codex.
---
## Cost Estimation
Parse token count from stderr. Codex prints `tokens used\nN` to stderr.
Estimate cost based on the model:
- gpt-5.2-codex: ~$0.008 per 1K tokens (estimate)
- o3: ~$0.01 per 1K tokens (estimate)
Display as: `Tokens: N | Est. cost: ~$X.XX`
Display as: `Tokens: N`
If token count is not available, display: `Tokens: unknown`