chore: bump default Codex model from gpt-5.4 to gpt-5.5

Author: SihaoLiu

config/default_config.json

@@ -1,5 +1,5 @@
 {
-  "codex_model": "gpt-5.4",
+  "codex_model": "gpt-5.5",
   "codex_effort": "high",
   "bitlesson_model": "haiku",
   "agent_teams": false,

docs/install-for-codex.md

@@ -29,7 +29,7 @@ This will:
 - Enable the experimental `codex_hooks` feature in `${CODEX_HOME:-~/.codex}/config.toml` when `codex` is available
 - Seed `~/.config/humanize/config.json` with a Codex/OpenAI `bitlesson_model` when that key is not already set
 - Mark the install as `provider_mode: "codex-only"` when using `--target codex`
-- Use RLCR defaults: `codex exec` with `gpt-5.4:high`, `codex review` with `gpt-5.4:high`
+- Use RLCR defaults: `codex exec` with `gpt-5.5:high`, `codex review` with `gpt-5.5:high`
 
 Requires Codex CLI `0.114.0` or newer for native hooks. Older Codex builds are not supported by the Codex install path.
 
@@ -77,7 +77,7 @@ sed -n '1,220p' "${CODEX_HOME:-$HOME/.codex}/hooks.json"
 Expected:
 - `codex_hooks` is `true`
 - `hooks.json` contains `loop-codex-stop-hook.sh`
-- `${XDG_CONFIG_HOME:-~/.config}/humanize/config.json` contains `bitlesson_model` set to a Codex/OpenAI model such as `gpt-5.4`
+- `${XDG_CONFIG_HOME:-~/.config}/humanize/config.json` contains `bitlesson_model` set to a Codex/OpenAI model such as `gpt-5.5`
 - for `--target codex`, `${XDG_CONFIG_HOME:-~/.config}/humanize/config.json` also contains `provider_mode: "codex-only"`
 
 ## Optional: Install for Both Codex and Kimi

docs/install-for-kimi.md

@@ -169,7 +169,7 @@ Look for the "Skills" section in the help output.
 |--------|-------------|---------|
 | `path/to/plan.md` | Plan file path | Required (unless --skip-impl) |
 | `--max N` | Maximum iterations | 42 |
-| `--codex-model MODEL:EFFORT` | Codex model | gpt-5.4:high |
+| `--codex-model MODEL:EFFORT` | Codex model | gpt-5.5:high |
 | `--codex-timeout SECONDS` | Review timeout | 5400 |
 | `--base-branch BRANCH` | Base for code review | auto-detect |
 | `--full-review-round N` | Full alignment check interval | 5 |
@@ -191,7 +191,7 @@ Ensure you have `codex` CLI installed:
 codex --version
 ```
 
-The skills will use `gpt-5.4` with `high` effort level by default.
+The skills will use `gpt-5.5` with `high` effort level by default.
 
 ## Uninstall
 

docs/usage.md

@@ -76,7 +76,7 @@ OPTIONS:
   --plan-file <path>     Explicit plan file path (alternative to positional arg)
   --max <N>              Maximum iterations before auto-stop (default: 42)
   --codex-model <MODEL:EFFORT>
-                         Codex model and reasoning effort (default from config, fallback gpt-5.4:high)
+                         Codex model and reasoning effort (default from config, fallback gpt-5.5:high)
   --codex-timeout <SECONDS>
                          Timeout for each Codex review in seconds (default: 5400)
   --track-plan-file      Indicate plan file should be tracked in git (must be clean)
@@ -240,7 +240,7 @@ translated plan and QA variants by inserting `_<code>` before the file extension
 
 OPTIONS:
   --codex-model <MODEL:EFFORT>
-                         Codex model and reasoning effort (default from config, fallback gpt-5.4:high)
+                         Codex model and reasoning effort (default from config, fallback gpt-5.5:high)
   --codex-timeout <SECONDS>
                          Timeout for the Codex query in seconds (default: 3600)
   -h, --help             Show help message
@@ -265,7 +265,7 @@ Current built-in keys:
 
 | Key | Default | Description |
 |-----|---------|-------------|
-| `codex_model` | `gpt-5.4` | Shared default model for Codex-backed review and analysis |
+| `codex_model` | `gpt-5.5` | Shared default model for Codex-backed review and analysis |
 | `codex_effort` | `high` | Shared default reasoning effort (`xhigh`, `high`, `medium`, `low`) |
 | `bitlesson_model` | `haiku` | Model used by the BitLesson selector agent |
 | `provider_mode` | unset | Optional runtime mode hint such as `codex-only` |
@@ -279,7 +279,7 @@ All Codex-using features (RLCR loop, ask-codex) share the same model configurati
 
 | Key | Default | Description |
 |-----|---------|-------------|
-| `codex_model` | `gpt-5.4` | Model used for Codex operations (reviews, analysis, queries) |
+| `codex_model` | `gpt-5.5` | Model used for Codex operations (reviews, analysis, queries) |
 | `codex_effort` | `high` | Reasoning effort (`xhigh`, `high`, `medium`, `low`) |
 
 To override, add to `.humanize/config.json`:
@@ -300,7 +300,7 @@ Codex model is resolved with this precedence:
 1. CLI `--codex-model` flag (highest priority)
 2. Feature-specific defaults
 3. Config-backed defaults from the 4-layer hierarchy above
-4. Hardcoded fallback (`gpt-5.4:high`)
+4. Hardcoded fallback (`gpt-5.5:high`)
 
 **Migration note**: If your `.humanize/config.json` contains the legacy keys
 `loop_reviewer_model` or `loop_reviewer_effort`, they are silently ignored.

hooks/lib/loop-common.sh

@@ -54,7 +54,7 @@ readonly DRIFT_STATUS_REPLAN_REQUIRED="replan_required"
 # Default Codex configuration (single source of truth - all scripts reference this)
 # Scripts can pre-set DEFAULT_CODEX_MODEL/DEFAULT_CODEX_EFFORT before sourcing to override.
 # Config-backed defaults are loaded from the merge hierarchy after config-loader.sh is sourced.
-# Precedence: pre-set value > config value > hardcoded fallback (gpt-5.4/high)
+# Precedence: pre-set value > config value > hardcoded fallback (gpt-5.5/high)
 #
 # The actual assignment happens in the "Config-backed defaults" section below,
 # after config-loader.sh has been sourced and merged config is available.
@@ -207,7 +207,7 @@ DEFAULT_BITLESSON_MODEL="${DEFAULT_BITLESSON_MODEL:-haiku}"
 
 # Load codex model/effort from merged config so .humanize/config.json can set persistent
 # defaults for all Codex-using features (RLCR, ask-codex).
-# Precedence: pre-set by caller > config value > hardcoded fallback (gpt-5.4/high)
+# Precedence: pre-set by caller > config value > hardcoded fallback (gpt-5.5/high)
 _cfg_codex_model="$(get_config_value "$_LOOP_COMMON_CONFIG" "codex_model" 2>/dev/null || true)"
 if [[ -n "$_cfg_codex_model" && ! "$_cfg_codex_model" =~ ^[a-zA-Z0-9._-]+$ ]]; then
     echo "Warning: Invalid codex_model in merged config: $_cfg_codex_model" >&2
@@ -219,7 +219,7 @@ elif [[ -n "$_cfg_codex_model" && ! "$_cfg_codex_model" =~ ^(gpt-|o[0-9]) ]]; th
     echo "  Ignoring configured codex_model; using caller preset or fallback" >&2
     _cfg_codex_model=""
 fi
-DEFAULT_CODEX_MODEL="${DEFAULT_CODEX_MODEL:-${_cfg_codex_model:-gpt-5.4}}"
+DEFAULT_CODEX_MODEL="${DEFAULT_CODEX_MODEL:-${_cfg_codex_model:-gpt-5.5}}"
 _cfg_codex_effort="$(get_config_value "$_LOOP_COMMON_CONFIG" "codex_effort" 2>/dev/null || true)"
 if [[ -n "$_cfg_codex_effort" && ! "$_cfg_codex_effort" =~ ^(xhigh|high|medium|low)$ ]]; then
     echo "Warning: Invalid codex_effort in merged config: $_cfg_codex_effort" >&2

scripts/ask-codex.sh

@@ -55,7 +55,7 @@ USAGE:
 
 OPTIONS:
   --codex-model <MODEL:EFFORT>
-                       Codex model and reasoning effort (default from config, fallback gpt-5.4:high)
+                       Codex model and reasoning effort (default from config, fallback gpt-5.5:high)
   --codex-timeout <SECONDS>
                        Timeout for the Codex query in seconds (default: 3600)
   -h, --help           Show this help message
@@ -68,7 +68,7 @@ DESCRIPTION:
 
 EXAMPLES:
   /humanize:ask-codex How should I structure the authentication module?
-  /humanize:ask-codex --codex-model gpt-5.4:high What are the performance bottlenecks?
+  /humanize:ask-codex --codex-model gpt-5.5:high What are the performance bottlenecks?
   /humanize:ask-codex --codex-timeout 300 Review the error handling in src/api/
 
 ENVIRONMENT:

scripts/install-skill.sh

@@ -296,7 +296,7 @@ user_config = pathlib.Path(sys.argv[2])
 install_target = sys.argv[3]
 
 defaults = json.loads(default_config.read_text(encoding="utf-8"))
-default_codex_model = defaults.get("codex_model") or "gpt-5.4"
+default_codex_model = defaults.get("codex_model") or "gpt-5.5"
 
 if user_config.exists():
     try:

skills/ask-codex/SKILL.md

@@ -24,7 +24,7 @@ If the user supplied flags such as `--codex-model` or `--codex-timeout`, reconst
 Example:
 
 ```bash
-"${CLAUDE_PLUGIN_ROOT}/scripts/ask-codex.sh" --codex-model gpt-5.4:high "Review the following round summary (M4)..."
+"${CLAUDE_PLUGIN_ROOT}/scripts/ask-codex.sh" --codex-model gpt-5.5:high "Review the following round summary (M4)..."
 ```
 
 Never run this unsafe form:
@@ -53,4 +53,4 @@ because the shell will re-parse the question text and can fail before `ask-codex
 ## Notes
 
 - The response is saved to `.humanize/skill/<timestamp>/output.md` for reference
-- Default model is `gpt-5.4:high` with a 3600-second timeout
+- Default model is `gpt-5.5:high` with a 3600-second timeout

skills/humanize-rlcr/SKILL.md

@@ -83,7 +83,7 @@ Pass these through `setup-rlcr-loop.sh`:
 | `--plan-file <path>` | Explicit plan path | - |
 | `--track-plan-file` | Enforce tracked plan immutability | false |
 | `--max N` | Maximum iterations | 42 |
-| `--codex-model MODEL:EFFORT` | Codex model and effort for `codex exec` | gpt-5.4:high |
+| `--codex-model MODEL:EFFORT` | Codex model and effort for `codex exec` | gpt-5.5:high |
 | `--codex-timeout SECONDS` | Codex timeout | 5400 |
 | `--base-branch BRANCH` | Base for review phase | auto-detect |
 | `--full-review-round N` | Full alignment interval | 5 |
@@ -94,7 +94,7 @@ Pass these through `setup-rlcr-loop.sh`:
 | `--yolo` | Skip quiz and enable --claude-answer-codex | false |
 | `--skip-quiz` | Skip Plan Understanding Quiz (implicit in skill mode) | false |
 
-Review phase `codex review` runs with `gpt-5.4:high`.
+Review phase `codex review` runs with `gpt-5.5:high`.
 
 ## Usage
 

skills/humanize/SKILL.md

@@ -72,8 +72,8 @@ After each round, write the required summary and stop/exit normally. Humanize's
 
 **Common Options:**
 - `--max N` - Maximum iterations before auto-stop (default: 42)
-- `--codex-model MODEL:EFFORT` - Codex model and reasoning effort for `codex exec` (default: gpt-5.4:high)
-- Review phase `codex review` uses `gpt-5.4:high`
+- `--codex-model MODEL:EFFORT` - Codex model and reasoning effort for `codex exec` (default: gpt-5.5:high)
+- Review phase `codex review` uses `gpt-5.5:high`
 - `--codex-timeout SECONDS` - Timeout for each Codex review (default: 5400)
 - `--base-branch BRANCH` - Base branch for code review (auto-detects if not specified)
 - `--full-review-round N` - Interval for full alignment checks (default: 5)