@workweave/router 0.2.11 → 0.2.12

package/README.md

@@ -15,11 +15,13 @@ npx @workweave/router --non-interactive     # reads $WEAVE_ROUTER_KEY, no prompt
 ```
 
 Re-running the installer to pick up changes reuses the key already on disk, so
-you paste it once and never again. `update` is the never-prompting form of that
-(safe for cron; errors instead of asking when no key can be found):
+you paste it once and never again — for every client, not just Claude Code.
+`update` is the never-prompting form of that (safe for cron; errors instead of
+asking when no key can be found):
 
 ```bash
 npx @workweave/router --claude                # reuses the installed key
+npx @workweave/router --codex                 # same for Codex, opencode, and pi
 npx @workweave/router --claude --rotate-key   # ignore it and prompt for a new one
 npx @workweave/router update --claude         # non-interactive refresh in place
 ```
@@ -27,8 +29,11 @@ npx @workweave/router update --claude         # non-interactive refresh in place
 For Claude Code the installed statusline and `/force-model`, `/router-*` slash
 commands also refresh themselves in the background about once a week (never
 overwriting a wrapper you edited). Opt out with `WEAVE_STATUSLINE_UPDATE=0`, or
-just the commands with `WEAVE_COMMANDS_UPDATE=0`. Codex, opencode, and pi have
-no per-turn hook to refresh from — re-run the installer for those.
+just the commands with `WEAVE_COMMANDS_UPDATE=0`. Codex installs native `$` skills
+plus managed `SessionStart`/`Stop` hooks: the latest routed model is reflected in
+the terminal title and a compact `Weave Router · …` status message is shown when
+the router reports a new route. Existing Codex hooks are preserved. OpenCode and pi
+have their own target-specific integrations.
 
 Version-pin for reproducible setups:
 
@@ -48,7 +53,9 @@ npx @workweave/router status --codex    # is Codex on the router or direct?
 Claude Code reads its router setting at launch, so quit and reopen it after an
 on/off. Codex and opencode pick it up on their next run. Inside Claude Code the
 slash commands `/router-off`, `/router-on`, and `/router-status` do the same.
-Codex installs a `$disable-routing` skill that switches its next session back
+Codex installs `$router-status`, `$router-off`, `$router-on`, and
+`$router-models` skills that call the same CLI verbs, plus a
+`$disable-routing` skill that switches its next session back
 to the normal provider; Codex does not support third-party `/disable-routing`
 slash commands. The shell equivalent is `npx @workweave/router disable-routing`.
 Cursor has no config file we own — toggle its base URL override in **Settings →
@@ -58,6 +65,7 @@ Pick which models the router is allowed to route to:
 
 ```bash
 npx @workweave/router models --claude                  # list every model, with its on/off state
+npx @workweave/router models --codex                   # same, for a Codex install
 npx @workweave/router models disable gpt-5.6 --claude  # take one out of rotation
 npx @workweave/router models enable gpt-5.6 --claude   # put it back
 ```
@@ -102,10 +110,17 @@ Four install targets:
   The block lives between begin/end markers
   so re-running the installer rewrites it cleanly and `--uninstall --codex`
   removes it without touching the rest of your config. Codex does not load
-  third-party slash-command files; to send a router directive, type it with
-  one leading space (for example, ` /force-model gpt-5.6-terra`). Its
-  `$disable-routing` skill returns the next Codex session to the default
-  provider without logging out or deleting the router configuration.
+  third-party slash-command files; the installer provides native skills
+  `$force-model` (`$fm`), `$unforce-model` (`$ufm`), and `$router-feedback`
+  (`$rf`), each of which execs a local `scripts/emit.sh` that prints the same
+  leading-space directive Claude Code uses (for example,
+  ` /force-model gpt-5.6-terra`) — you can also type that form directly. It
+  also installs `$router-status`, `$router-off`, `$router-on`, and
+  `$router-models`, which call this installer's own verbs, plus a
+  `$disable-routing` skill that returns the next Codex session to the default
+  provider without logging out or deleting the router configuration. The
+  managed lifecycle hooks also keep the latest routed model in the terminal
+  title and emit a compact status message when the router reports a new route.
 - **opencode** (`--opencode`) — merges a `provider.weave` entry (backed by
   opencode's built-in `@ai-sdk/anthropic` provider) into
   `~/.config/opencode/opencode.json` (or `<repo>/opencode.json` with
@@ -127,8 +142,7 @@ for the full reference.
 
 - Node ≥ 18 (ships with `npx`)
 - `bash` on PATH (macOS / Linux native; Windows needs Git Bash or WSL)
-- `jq` on PATH — used by the Claude Code status line and the opencode/pi JSON
-  merges. Not required for the Codex path.
+- `jq` on PATH — used by the Claude Code status line, the Codex lifecycle helper, and the opencode/pi JSON merges.
 
 ## Why npx
 

package/cc-statusline.sh

@@ -16,9 +16,9 @@
 # Renders:
 #   WEAVE ROUTER — claude-sonnet-4-5 ← claude-opus-4-7 · saved $1.23 · 12.4k in / 3.1k out / 45.2k cached
 #
-# Pricing source of truth: router/eval/pricing.py. Keep these maps in lockstep
-# when prices change. Cache multipliers (1.25× / 0.1×) follow Anthropic's
-# published cache pricing and are stable across the Claude family.
+# Pricing source of truth: internal/router/catalog. Input/output prices and
+# cache-read multipliers are generated by cmd/genprices. Cache creation remains
+# at 1.25× input pending TTL-aware pricing.
 
 set -euo pipefail
 
@@ -530,6 +530,7 @@ prices='{
     "z-ai/glm-5":                       0.001,
     "z-ai/glm-5.1":                     0.0014,
     "z-ai/glm-5.2":                     0.0014,
+    "z-ai/glm-5.3":                     0.0014,
     "z-ai/glm-5.3-flash":               0.00015
   },
   "output": {
@@ -606,7 +607,85 @@ prices='{
     "z-ai/glm-5":                       0.0032,
     "z-ai/glm-5.1":                     0.0044,
     "z-ai/glm-5.2":                     0.0044,
+    "z-ai/glm-5.3":                     0.0044,
     "z-ai/glm-5.3-flash":               0.0005
+  },
+  "cache_read": {
+    "claude-fable-5":                   0.1,
+    "claude-haiku-4-5":                 0.1,
+    "claude-opus-4-0":                  0.1,
+    "claude-opus-4-1":                  0.1,
+    "claude-opus-4-5":                  0.1,
+    "claude-opus-4-6":                  0.1,
+    "claude-opus-4-7":                  0.1,
+    "claude-opus-4-8":                  0.1,
+    "claude-opus-5":                    0.1,
+    "claude-sonnet-4-5":                0.1,
+    "claude-sonnet-4-6":                0.1,
+    "claude-sonnet-5":                  0.1,
+    "deepseek/deepseek-v4-flash":       0.2,
+    "deepseek/deepseek-v4-pro":         0.11494252873563218,
+    "deepseek/deepseek-v4-pro-0813":    0.11494252873563218,
+    "gemini-2.0-flash":                 0.25,
+    "gemini-2.0-flash-lite":            0.25,
+    "gemini-2.5-flash":                 0.1,
+    "gemini-2.5-flash-lite":            0.1,
+    "gemini-2.5-pro":                   0.1,
+    "gemini-3-flash-preview":           0.1,
+    "gemini-3-pro-preview":             0.1,
+    "gemini-3.1-flash-lite-preview":    0.1,
+    "gemini-3.1-pro-preview":           0.1,
+    "gemini-3.5-flash":                 0.1,
+    "gemini-3.5-flash-lite":            0.1,
+    "gemini-3.6-flash":                 0.1,
+    "gemini-3.7-flash":                 0.1,
+    "google/gemma-4-26b-a4b-it":        0.1,
+    "gpt-4.1":                          0.25,
+    "gpt-4.1-mini":                     0.25,
+    "gpt-4.1-nano":                     0.25,
+    "gpt-4o":                           0.5,
+    "gpt-4o-mini":                      0.5,
+    "gpt-5":                            0.1,
+    "gpt-5-chat":                       0.1,
+    "gpt-5-mini":                       0.1,
+    "gpt-5-nano":                       0.1,
+    "gpt-5.4":                          0.1,
+    "gpt-5.4-mini":                     0.1,
+    "gpt-5.4-nano":                     0.1,
+    "gpt-5.4-pro":                      1,
+    "gpt-5.5":                          0.1,
+    "gpt-5.5-mini":                     0.1,
+    "gpt-5.5-nano":                     0.1,
+    "gpt-5.5-pro":                      1,
+    "gpt-5.6-luna":                     0.1,
+    "gpt-5.6-luna-pro":                 0.1,
+    "gpt-5.6-sol":                      0.1,
+    "gpt-5.6-sol-pro":                  0.1,
+    "gpt-5.6-terra":                    0.1,
+    "grok-4.5":                         0.25,
+    "grok-4.6":                         0.25,
+    "minimax/minimax-m2.7":             0.2,
+    "minimax/minimax-m3":               0.2,
+    "mistralai/mistral-small-2603":     0.1,
+    "moonshotai/kimi-k2.5":             0.5,
+    "moonshotai/kimi-k2.6":             0.1684,
+    "moonshotai/kimi-k2.7":             0.2,
+    "moonshotai/kimi-k3":               0.1,
+    "qwen/qwen3-235b-a22b-2507":        0.5,
+    "qwen/qwen3-30b-a3b-instruct-2507": 0.1684,
+    "qwen/qwen3-coder":                 0.1684,
+    "qwen/qwen3-coder-next":            0.5,
+    "qwen/qwen3-next-80b-a3b-instruct": 0.5,
+    "qwen/qwen3.5-flash-02-23":         0.1,
+    "qwen/qwen3.6-35b-a3b":             0.1,
+    "qwen/qwen3.7-plus":                0.2,
+    "qwen/qwen3.8-max":                 0.125,
+    "xiaomi/mimo-v2.5-pro":             0.1,
+    "z-ai/glm-5":                       0.2,
+    "z-ai/glm-5.1":                     0.18571428571428572,
+    "z-ai/glm-5.2":                     0.18571428571428572,
+    "z-ai/glm-5.3":                     0.18571428571428572,
+    "z-ai/glm-5.3-flash":               0.2
   }
 }'
 # END_GENERATED_PRICES
@@ -691,12 +770,9 @@ if [[ -n "$transcript_path" && -f "$transcript_path" ]]; then
   # Compute a session running total: savings across every assistant turn
   # whose marker reports a requested ≠ routed swap, plus cumulative token
   # counts across every assistant turn (rerouted or not — total work the
-  # session has done). cache_creation is priced at 1.25× input, cache_read
-  # at 0.1× — both ratios are stable across the Claude family and a no-op
-  # when the provider doesn't return those fields. Cache reads ARE included
-  # in the savings comparison: both costs apply the same 0.1× weight to
-  # cache_read_input_tokens, so the delta reflects the model-price
-  # difference on the cached portion as well.
+  # session has done). cache_creation is priced at 1.25× input; cache_read
+  # uses each model's generated catalog multiplier. Both are no-ops when the
+  # provider does not return those fields.
   #
   # The marker regex tolerates the optional "(<provider>)" segment and a
   # `[1m]` / `-YYYYMMDD` suffix on either model name so transcripts written
@@ -729,14 +805,17 @@ if [[ -n "$transcript_path" && -f "$transcript_path" ]]; then
       } as $t |
       (if $requested == "" or $requested == $rm then 0
        else
-         ($p.input[$rm] // null)        as $rin  | ($p.output[$rm] // null)        as $rout |
-         ($p.input[$requested] // null) as $sin  | ($p.output[$requested] // null) as $sout |
-         if ($rin == null or $rout == null or $sin == null or $sout == null) then 0
+         ($p.input[$rm] // null)             as $rin  | ($p.output[$rm] // null)             as $rout |
+         ($p.cache_read[$rm] // null)        as $rcr  |
+         ($p.input[$requested] // null)      as $sin  | ($p.output[$requested] // null)      as $sout |
+         ($p.cache_read[$requested] // null) as $scr  |
+         if ($rin == null or $rout == null or $rcr == null or $sin == null or $sout == null or $scr == null) then 0
          else
-           (($t.in + 1.25 * $t.cwrt + 0.1 * $t.crd) / 1000) as $input_units |
-           ($t.out / 1000)                                  as $output_units |
-           ($input_units * $rin + $output_units * $rout)    as $routed_cost |
-           ($input_units * $sin + $output_units * $sout)    as $requested_cost |
+           (($t.in + 1.25 * $t.cwrt + $rcr * $t.crd) / 1000) as $routed_input_units |
+           (($t.in + 1.25 * $t.cwrt + $scr * $t.crd) / 1000) as $requested_input_units |
+           ($t.out / 1000)                                    as $output_units |
+           ($routed_input_units * $rin + $output_units * $rout)       as $routed_cost |
+           ($requested_input_units * $sin + $output_units * $sout)    as $requested_cost |
            ($requested_cost - $routed_cost)
          end
        end) as $savings |

package/codex-skills/fm/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: fm
+description: "Alias for force-model — pin this Codex session to a specific model through the Weave Router."
+---
+
+<!-- weave-router managed fm skill -->
+
+When the user invokes `$fm <model-id>`, run this skill's `scripts/emit.sh` using the
+absolute path shown in this skill's `<path>` (its directory + `/scripts/emit.sh`).
+Pass the model id as arguments, quoted as a single argument list.
+Do not send a user message and do not type a Codex slash command.
+
+The script prints a leading-space `/force-model` line. The Weave Router reads that
+exec output, pins the session, and continues this turn — so run the script once and
+do not repeat its output as your answer. Then report the router's response.

package/codex-skills/fm/scripts/emit.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+# Alias of force-model/scripts/emit.sh
+set -euo pipefail
+if [ "$#" -eq 0 ] || [ -z "${1:-}" ]; then
+  echo "usage: emit.sh <model-id>" >&2
+  exit 1
+fi
+printf ' /force-model %s\n' "$*"

package/codex-skills/force-model/SKILL.md

@@ -5,10 +5,11 @@ description: "Pin this Codex session to a specific model through the Weave Route
 
 <!-- weave-router managed force-model skill -->
 
-When the user invokes `$force-model <model-id>` (or asks to use the `$fm` alias), send a normal user message whose first character is one literal space, followed by `/force-model ` and the requested model id. Do not use a Codex slash command and do not omit the leading space. For example, send exactly:
-
-```text
- /force-model gpt-5.6-terra
-```
-
-Preserve any model id exactly as provided. Report the router's response after it returns.
+When the user invokes `$force-model <model-id>` (or `$fm`), run this skill's `scripts/emit.sh` using the
+absolute path shown in this skill's `<path>` (its directory + `/scripts/emit.sh`).
+Pass the model id as arguments, quoted as a single argument list.
+Do not send a user message and do not type a Codex slash command.
+
+The script prints a leading-space `/force-model` line. The Weave Router reads that
+exec output, pins the session, and continues this turn — so run the script once and
+do not repeat its output as your answer. Then report the router's response.

package/codex-skills/force-model/scripts/emit.sh

@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+# Print a leading-space /force-model directive. Codex runs this via exec;
+# the Weave Router intercepts the tool output and pins the session.
+set -euo pipefail
+if [ "$#" -eq 0 ] || [ -z "${1:-}" ]; then
+  echo "usage: emit.sh <model-id>" >&2
+  exit 1
+fi
+printf ' /force-model %s\n' "$*"

package/codex-skills/rf/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: rf
+description: "Alias for router-feedback — submit feedback about a Weave Router decision or model performance."
+---
+
+<!-- weave-router managed rf skill -->
+
+When the user invokes `$rf <feedback>`, run this skill's `scripts/emit.sh` using the
+absolute path shown in this skill's `<path>` (its directory + `/scripts/emit.sh`).
+Pass the feedback text as arguments, quoted as a single argument list.
+Do not send a user message and do not type a Codex slash command.
+
+The script prints a leading-space `/router-feedback` line. The Weave Router reads that
+exec output, records the feedback, and continues this turn — so run the script once and
+do not repeat its output as your answer. Then report the router's response.

package/codex-skills/rf/scripts/emit.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -euo pipefail
+if [ "$#" -eq 0 ] || [ -z "${1:-}" ]; then
+  echo "usage: emit.sh <feedback>" >&2
+  exit 1
+fi
+printf ' /router-feedback %s\n' "$*"

package/codex-skills/router-feedback/SKILL.md

@@ -5,10 +5,11 @@ description: "Submit feedback about a Weave Router decision or model performance
 
 <!-- weave-router managed router-feedback skill -->
 
-When the user invokes `$router-feedback <feedback>` (or asks to use the `$rf` alias), send a normal user message whose first character is one literal space, followed by `/router-feedback ` and the feedback text. Do not use a Codex slash command and do not omit the leading space. Preserve the feedback text exactly. For example:
-
-```text
- /router-feedback the selected model struggled with this task
-```
-
-Report the router's response after it returns.
+When the user invokes `$router-feedback <feedback>` (or `$rf`), run this skill's `scripts/emit.sh` using the
+absolute path shown in this skill's `<path>` (its directory + `/scripts/emit.sh`).
+Pass the feedback text as arguments, quoted as a single argument list.
+Do not send a user message and do not type a Codex slash command.
+
+The script prints a leading-space `/router-feedback` line. The Weave Router reads that
+exec output, records the feedback, and continues this turn — so run the script once and
+do not repeat its output as your answer. Then report the router's response.

package/codex-skills/router-feedback/scripts/emit.sh

@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+# Print a leading-space /router-feedback directive. Codex runs this via exec;
+# the Weave Router intercepts the tool output and records the feedback.
+set -euo pipefail
+if [ "$#" -eq 0 ] || [ -z "${1:-}" ]; then
+  echo "usage: emit.sh <feedback>" >&2
+  exit 1
+fi
+printf ' /router-feedback %s\n' "$*"

package/codex-skills/router-models/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: router-models
+description: "List the models the Weave Router may route to, and turn them on or off."
+---
+
+<!-- weave-router managed router-models skill -->
+
+# Weave Router model selection
+
+When the user invokes `$router-models`, show which models this
+installation lets the router pick from, and change that selection when asked.
+This is the same list — and the same stored setting — as the checkboxes on the
+router dashboard's settings page.
+
+Start by running:
+
+```bash
+npx --package @workweave/router -y -- weave-router models --codex{{SCOPE}}
+```
+
+That prints every deployed model grouped by provider, with `[x]` for models the
+router may pick and `[ ]` for models it may not. Present it back as a compact
+checklist in that same `[x]` / `[ ]` form, keeping the provider grouping and the
+exact model ids — the user selects models by id.
+
+Then:
+
+- If the user named models or providers, work out whether they want them on or
+  off from how they phrased it, and apply it with
+  `weave-router models enable <id>... --codex{{SCOPE}}` or
+  `weave-router models disable <id>... --codex{{SCOPE}}` (add `providers` before
+  `enable`/`disable` to switch a whole provider). Several ids can go in one
+  call. Then re-run the list and show the result.
+- If they named nothing, stop after the list and ask which ones to change.
+  Never change anything they did not ask for.
+
+Other things they might ask for:
+
+- Rank models by preference:
+  `weave-router models prefer <id> <id>... --codex{{SCOPE}}` (order matters), or
+  `weave-router models prefer clear --codex{{SCOPE}}` to drop the ranking.
+- Providers only: `weave-router models providers --codex{{SCOPE}}`.
+
+If the command reports that this router doesn't expose model selection, that's a
+Weave-hosted router: model selection belongs to the whole organization there, so
+tell the user to change it at https://router.workweave.ai/dashboard/settings —
+don't try to work around it. Its listing carries no on/off state, so present it
+as a plain list; don't infer which models are enabled.
+
+Disabling a model takes effect on the router's next routing decision; no restart
+is needed.

package/codex-skills/router-off/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: router-off
+description: "Route Codex to its default provider again (turn the Weave Router off)."
+---
+
+<!-- weave-router managed router-off skill -->
+
+# Turn Weave routing off
+
+When the user invokes `$router-off`, switch this Codex installation off the
+Weave Router without logging out or deleting its router configuration.
+
+Run exactly:
+
+```bash
+npx --package @workweave/router -y -- weave-router off --codex{{SCOPE}}
+```
+
+Then report the result and tell the user the change takes effect on their next
+`codex` launch — Codex reads its provider config at startup, so the current
+session keeps routing as it already was. It can be reversed with
+`$router-on`. Do not uninstall the router or alter any other Codex settings.

package/codex-skills/router-on/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: router-on
+description: "Route Codex through the Weave Router again (turn it back on)."
+---
+
+<!-- weave-router managed router-on skill -->
+
+# Turn Weave routing on
+
+When the user invokes `$router-on`, switch this Codex installation back onto
+the Weave Router using the managed configuration already on disk.
+
+Run exactly:
+
+```bash
+npx --package @workweave/router -y -- weave-router on --codex{{SCOPE}}
+```
+
+Then report the result and tell the user the change takes effect on their next
+`codex` launch — Codex reads its provider config at startup, so the current
+session keeps routing as it already was. Do not re-run the installer or alter
+any other Codex settings.

package/codex-skills/router-status/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: router-status
+description: "Show whether Codex is routing through the Weave Router or using its default provider."
+---
+
+<!-- weave-router managed router-status skill -->
+
+# Weave Router status
+
+When the user invokes `$router-status`, report whether this Codex installation
+routes through the Weave Router.
+
+Run exactly:
+
+```bash
+npx --package @workweave/router -y -- weave-router status --codex{{SCOPE}}
+```
+
+Then summarize the result in one line. Do not change any configuration.

package/codex-skills/ufm/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: ufm
+description: "Alias for unforce-model — clear the active Weave Router model pin."
+---
+
+<!-- weave-router managed ufm skill -->
+
+When the user invokes `$ufm`, run this skill's `scripts/emit.sh` using the
+absolute path shown in this skill's `<path>` (its directory + `/scripts/emit.sh`).
+Do not send a user message and do not type a Codex slash command.
+
+The script prints a leading-space `/unforce-model` line. The Weave Router reads that
+exec output, clears the pin, and continues this turn — so run the script once and
+do not repeat its output as your answer. Then report the router's response.

package/codex-skills/ufm/scripts/emit.sh

@@ -0,0 +1,3 @@
+#!/usr/bin/env bash
+set -euo pipefail
+printf ' /unforce-model\n'

package/codex-skills/unforce-model/SKILL.md

@@ -5,10 +5,10 @@ description: "Clear the active Weave Router model pin for this Codex session."
 
 <!-- weave-router managed unforce-model skill -->
 
-When the user invokes `$unforce-model` (or asks to use the `$ufm` alias), send a normal user message whose first character is one literal space, followed by `/unforce-model`. Do not use a Codex slash command and do not omit the leading space. Send exactly:
+When the user invokes `$unforce-model` (or `$ufm`), run this skill's `scripts/emit.sh` using the
+absolute path shown in this skill's `<path>` (its directory + `/scripts/emit.sh`).
+Do not send a user message and do not type a Codex slash command.
 
-```text
- /unforce-model
-```
-
-Report the router's response after it returns.
+The script prints a leading-space `/unforce-model` line. The Weave Router reads that
+exec output, clears the pin, and continues this turn — so run the script once and
+do not repeat its output as your answer. Then report the router's response.

package/codex-skills/unforce-model/scripts/emit.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+# Print a leading-space /unforce-model directive for the Weave Router.
+set -euo pipefail
+printf ' /unforce-model\n'