roadmodel 0.2.94__tar.gz → 0.2.96__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (75) hide show
  1. {roadmodel-0.2.94 → roadmodel-0.2.96}/PKG-INFO +1 -1
  2. {roadmodel-0.2.94/roadmodel/data → roadmodel-0.2.96/docs}/catalog.json +1 -1
  3. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/claude-commands/roadmap-refresh.md +33 -31
  4. {roadmodel-0.2.94/roadmodel/data → roadmodel-0.2.96/docs/claude-commands}/roadmap-step.md +17 -8
  5. {roadmodel-0.2.94/roadmodel/data → roadmodel-0.2.96/docs/claude-commands}/roadmodel-upgrade.md +19 -1
  6. {roadmodel-0.2.94/roadmodel/data → roadmodel-0.2.96/docs/templates}/phase-roadmap-template.md +91 -70
  7. {roadmodel-0.2.94/roadmodel/data → roadmodel-0.2.96/docs/templates}/planning-kit-how-to-use.md +2 -2
  8. {roadmodel-0.2.94/roadmodel/data → roadmodel-0.2.96/docs/templates}/project-roadmap-template.md +72 -53
  9. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/templates/prompt-phase-roadmap.md +8 -8
  10. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/templates/prompt-project-roadmap.md +1 -1
  11. {roadmodel-0.2.94 → roadmodel-0.2.96}/pyproject.toml +1 -1
  12. {roadmodel-0.2.94/docs → roadmodel-0.2.96/roadmodel/data}/catalog.json +1 -1
  13. {roadmodel-0.2.94/docs/templates → roadmodel-0.2.96/roadmodel/data}/phase-roadmap-template.md +91 -70
  14. {roadmodel-0.2.94/docs/templates → roadmodel-0.2.96/roadmodel/data}/planning-kit-how-to-use.md +2 -2
  15. {roadmodel-0.2.94/docs/templates → roadmodel-0.2.96/roadmodel/data}/project-roadmap-template.md +72 -53
  16. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/prompt-phase-roadmap.md +8 -8
  17. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/prompt-project-roadmap.md +1 -1
  18. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/roadmap-refresh.md +33 -31
  19. {roadmodel-0.2.94/docs/claude-commands → roadmodel-0.2.96/roadmodel/data}/roadmap-step.md +17 -8
  20. {roadmodel-0.2.94/docs/claude-commands → roadmodel-0.2.96/roadmodel/data}/roadmodel-upgrade.md +19 -1
  21. {roadmodel-0.2.94 → roadmodel-0.2.96}/scripts/update_projects.py +291 -1
  22. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/__init__.py +1 -1
  23. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/cli.py +37 -12
  24. roadmodel-0.2.96/src/roadmodel/ladder_layout.py +422 -0
  25. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/scoring.py +44 -4
  26. roadmodel-0.2.94/src/roadmodel/ladder_layout.py +0 -242
  27. {roadmodel-0.2.94 → roadmodel-0.2.96}/.github/README.md +0 -0
  28. {roadmodel-0.2.94 → roadmodel-0.2.96}/.gitignore +0 -0
  29. {roadmodel-0.2.94 → roadmodel-0.2.96}/LICENSE +0 -0
  30. {roadmodel-0.2.94 → roadmodel-0.2.96}/NOTICE +0 -0
  31. {roadmodel-0.2.94 → roadmodel-0.2.96}/README.md +0 -0
  32. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/benchmarks.json +0 -0
  33. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/claude-commands/roadmap-phase.md +0 -0
  34. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/claude-commands/roadmap-project.md +0 -0
  35. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/context-windows.json +0 -0
  36. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/effort-tokens.json +0 -0
  37. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/model-selector.txt +0 -0
  38. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/model-tier-cost-scale.md +0 -0
  39. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/settings-display.md +0 -0
  40. {roadmodel-0.2.94 → roadmodel-0.2.96}/docs/user-context.example.md +0 -0
  41. {roadmodel-0.2.94 → roadmodel-0.2.96}/hatch_build.py +0 -0
  42. {roadmodel-0.2.94 → roadmodel-0.2.96}/infra/README.md +0 -0
  43. {roadmodel-0.2.94 → roadmodel-0.2.96}/infra/gcp-killswitch/README.md +0 -0
  44. {roadmodel-0.2.94 → roadmodel-0.2.96}/infra/supabase/README.md +0 -0
  45. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/benchmarks.json +0 -0
  46. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/context-windows.json +0 -0
  47. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/effort-tokens.json +0 -0
  48. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/model-selector.txt +0 -0
  49. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/model-tier-cost-scale.md +0 -0
  50. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/roadmap-phase.md +0 -0
  51. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/roadmap-project.md +0 -0
  52. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/settings-display.md +0 -0
  53. {roadmodel-0.2.94 → roadmodel-0.2.96}/roadmodel/data/user-context.example.md +0 -0
  54. {roadmodel-0.2.94 → roadmodel-0.2.96}/scripts/agent_context.py +0 -0
  55. {roadmodel-0.2.94 → roadmodel-0.2.96}/scripts/agent_rules.py +0 -0
  56. {roadmodel-0.2.94 → roadmodel-0.2.96}/scripts/updater_lock.py +0 -0
  57. {roadmodel-0.2.94 → roadmodel-0.2.96}/scripts/upgrade_fleet.py +0 -0
  58. {roadmodel-0.2.94 → roadmodel-0.2.96}/scripts/worktree_memory.py +0 -0
  59. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/__main__.py +0 -0
  60. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/config.py +0 -0
  61. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/cost.py +0 -0
  62. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/errors.py +0 -0
  63. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/mcp_server.py +0 -0
  64. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/private_files.py +0 -0
  65. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/providers/__init__.py +0 -0
  66. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/providers/_safety.py +0 -0
  67. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/providers/anthropic.py +0 -0
  68. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/providers/google.py +0 -0
  69. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/providers/openai.py +0 -0
  70. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/providers/openai_compatible.py +0 -0
  71. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/providers/registry.py +0 -0
  72. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/recommend.py +0 -0
  73. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/series.py +0 -0
  74. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/usage.py +0 -0
  75. {roadmodel-0.2.94 → roadmodel-0.2.96}/src/roadmodel/user_context.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.5
2
2
  Name: roadmodel
3
- Version: 0.2.94
3
+ Version: 0.2.96
4
4
  Summary: BYO-key CLI that recommends the right AI model, platform, and settings for a prompt.
5
5
  Project-URL: Homepage, https://roadmodel.ai
6
6
  Project-URL: Repository, https://github.com/nathanramoscfa/roadmodel
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "schema_version": "4",
3
3
  "output_contract_version": 2,
4
- "generated_at_utc": "2026-10-24T19:01:39Z",
4
+ "generated_at_utc": "2026-10-25T19:01:45Z",
5
5
  "source_doc_sha256": {
6
6
  "model-selector.txt": "e2ef6c5a18f05ff952fad9f576720b8fc4637f563f60ce5c077c5501fc21d1b7",
7
7
  "model-tier-cost-scale.md": "dad707e59d0f3e75cf699d81368ba66783cc2a6a0bf625c430e8f884ef844a1c"
@@ -176,7 +176,7 @@ complexity, novel or not; its Model rationale names them), then:
176
176
  for that classification (MCP tool: `roadmap_settings`), pasted as
177
177
  printed with its **Runs:** line: Cost, Balanced and Quality, each
178
178
  ranked three deep (Pick, Runner-up, and a Backup from another maker),
179
- each option on one list line with its own effort and AA Index, read with every usage
179
+ each option with its own level, AA Index and price, read with every usage
180
180
  pool at headroom, so the step's runner picks the column from the pools
181
181
  on the day. A single-column table becomes the ladder: that is a
182
182
  difference. Its models are always the latest version of their series.
@@ -203,31 +203,34 @@ complexity, novel or not; its Model rationale names them), then:
203
203
  sentence, or its entry in the Model selection blocks) — a layout
204
204
  fix, not a new pick, so it takes no `Settings updated` line.
205
205
  - Every ladder, a step's Settings and a phase's Phase roadmap settings
206
- alike, takes the list layout (roadmodel 0.2.94 on), as `roadmodel
207
- ladder` prints it: a bold heading per column (**Cost**, **Balanced**,
208
- **Quality**, the column its **Runs:** line names reading `— runs by
209
- default`), each over one list line per rank — `- Pick:`,
210
- `- Runner-up:`, `- Backup:` — giving the option's **model**, platform,
211
- dial and level, `Thinking On` where the surface has that toggle, and
212
- `AA` with its AA Intelligence Index there (`AA not measured` where AA
213
- has no row); then a `**Conversation:**` line and the **Runs:** line,
214
- every line within 80 columns. Before re-selecting anything, run
215
- `roadmodel relayout <every roadmap file>`: it rewrites each ladder
216
- table roadmodel 0.2.86–0.2.93 wrote (a `| Rank |` or `| Setting |`
217
- table with Cost / Balanced / Quality columns) as those lists, every
218
- model, platform, dial and AA Index kept as written. That is a layout
219
- fix, not a new pick: it reaches every step and every phase, Complete
220
- steps and written phases included, and takes no `Settings updated`
221
- line. A ladder written before roadmodel 0.2.93 has Model / Backup /
222
- Platform / Effort (/ AA Index) / Thinking rows and no Runner-up: on a
223
- step that has not shipped, or a phase not yet written, replace it with
224
- the ladder printed for that classification, even where every pick
225
- still matches — a layout fix, not a new pick, so it takes no `Settings
226
- updated` line unless the Pick of the column its **Runs:** line names
227
- changed. Without roadmodel, leave every ladder as it is.
228
- - A Complete step's ladder keeps its values (see below): `roadmodel
229
- relayout` changes its layout alone, and its `> Ran` and `> Settings
230
- updated` lines stay beneath it.
206
+ alike, takes the table layout (roadmodel 0.2.95 on), as `roadmodel
207
+ ladder` prints it: Cost, Balanced and Quality columns (the one its
208
+ **Runs:** line names marked ✓), each rank a bold group row (**Pick**,
209
+ **Runner‑up**, **Backup**) over indented Model / Platform / Level / AA /
210
+ Price rows — Level the bare level of the platform's own dial, AA its AA
211
+ Intelligence Index there (`not measured` where AA has no row), Price its
212
+ blended list price per 1M tokens times the tokens it uses at that level —
213
+ then a note line, a `**Conversation:**` line and the **Runs:** line. It
214
+ has no Thinking row: Thinking is always On where the platform has the
215
+ toggle. Before re-selecting anything, run `roadmodel relayout <every
216
+ roadmap file>`: it rewrites each ladder roadmodel 0.2.86–0.2.94 wrote (a
217
+ `| Rank |` or `| Setting |` table with Cost / Balanced / Quality columns,
218
+ or 0.2.94's `- Pick:` lists) as that table, every model, platform, level
219
+ and AA Index kept as written and Price filled in from the catalog. It
220
+ reaches only steps that read `Not started` and phases whose roadmap does
221
+ not exist: a Complete step's ladder is the record of what ran, an `In
222
+ progress` step's is what an agent is running, and a written phase's
223
+ records what wrote its roadmap, so those keep their layout. That is a
224
+ layout fix, not a new pick, and takes no `Settings updated` line. A
225
+ ladder written before roadmodel 0.2.93 has Model / Backup / Platform /
226
+ Effort (/ AA Index) / Thinking rows and no Runner-up: on a step that has
227
+ not shipped, or a phase not yet written, replace it with the ladder
228
+ printed for that classification, even where every pick still matches —
229
+ a layout fix, not a new pick, so it takes no `Settings updated` line
230
+ unless the Pick of the column its **Runs:** line names changed. Without
231
+ roadmodel, leave every ladder as it is.
232
+ - A Complete step's ladder keeps its values and its layout (see below),
233
+ with its `> Ran` and `> Settings updated` lines beneath it.
231
234
  - Keep the step's selection block in the Model selection blocks equal
232
235
  to the column its **Runs:** line names (its `BACKUP:` line to that
233
236
  column's Backup), and its Summary Table row's Model to that column's
@@ -242,9 +245,8 @@ complexity, novel or not; its Model rationale names them), then:
242
245
  included, with no `Settings updated` line.
243
246
  - If it matches, leave the step exactly as it is.
244
247
  - **Never touch a step that reads `Complete`.** Its settings are the
245
- record of what ran. Only the layout fixes above (`roadmodel relayout`
246
- and the Summary Table's columns) reach it, because they change no
247
- value.
248
+ record of what ran. Only the Summary Table's column fix reaches it,
249
+ because it changes no value.
248
250
  - Keep each step's Conversation row as written — it is session hygiene,
249
251
  not a model choice.
250
252
 
@@ -279,10 +281,10 @@ sentences on why.
279
281
  beneath it.
280
282
  - A table that matches ⇒ leave the phase exactly as it is, except
281
283
  that a ladder written before roadmodel 0.2.93 becomes the ranked
282
- ladder, as a step's does, and every ladder takes the list layout.
284
+ ladder, as a step's does, and its ladder takes the table layout.
283
285
  - **Never add, re-pick or rewrite the table of a phase whose roadmap
284
286
  exists.** Its table, or the lack of one, is the record of what wrote
285
- that roadmap; `roadmodel relayout` alone reaches it, as a layout fix.
287
+ that roadmap, layout included.
286
288
 
287
289
  Print the phase · was · now · changed table.
288
290
 
@@ -101,16 +101,25 @@ Print one line: `Step {{STEP}} requires: Model <M> · Platform <P> ·
101
101
  <the dials the table carries, e.g. Effort <E>[ · Thinking <T>], or
102
102
  Intelligence <I>>. This session: <your own model> on <this surface>.`
103
103
 
104
+ **Thinking is always On** wherever the platform has a Thinking toggle
105
+ (Antigravity, the Gemini app, the APIs that expose one). A ladder carries
106
+ no Thinking row because it never recommends Off: every AA Index and Price
107
+ in it assumes thinking on. On such a platform, print `Thinking On` among
108
+ the dials and make sure it is set.
109
+
104
110
  - **Ladders** (Cost / Balanced / Quality columns, roadmodel 0.2.86
105
111
  on) carry every column the step may run, so pick one before the checks
106
- below. From roadmodel 0.2.94 each column is a bold heading (**Cost**,
107
- **Balanced**, **Quality**) over one list line per option: `- Pick:`,
108
- `- Runner-up:`, `- Backup:`, each naming its **model**, then its
109
- platform, its dial and level, `Thinking On` where the surface has that
110
- toggle, and its AA Index (a line past 80 columns continues on the next,
111
- indented). A 0.2.93 ladder is a table with rows `1 · Pick`,
112
- `2 · Runner-up` and `3 · Backup`, each followed by that option's
113
- Platform, Effort, Thinking and AA Index rows. An older ladder has Model /
112
+ below. From roadmodel 0.2.95 a ladder is one table: Cost, Balanced and
113
+ Quality are its columns, and each rank is a bold group row (**Pick**,
114
+ **Runner‑up**, **Backup**) over indented Model, Platform, Level, AA and
115
+ Price rows. Level is the bare level of that platform's own dial (`High`
116
+ is Intelligence High on Codex, Effort High on Claude Code and
117
+ Antigravity). The ✓ in a column's header marks the one its **Runs:**
118
+ line names. A 0.2.94 ladder is three lists instead (`- Pick:`,
119
+ `- Runner-up:`, `- Backup:` under each column's bold heading), and a
120
+ 0.2.93 one a table with rows `1 · Pick`, `2 · Runner-up` and
121
+ `3 · Backup`, each followed by Platform, Effort, Thinking and AA Index
122
+ rows. An older ladder has Model /
114
123
  Backup / Platform / Effort rows instead: its Model, Platform and Effort
115
124
  cells are the Pick, its Backup the Backup (split into `Backup`, `Backup
116
125
  on` and `Backup effort` rows on a Complete step since 0.2.93), and it
@@ -1,5 +1,5 @@
1
1
  ---
2
- description: Upgrade roadmodel and shared agent context across registered projects and configured machines (usage: /roadmodel-upgrade [project dirs to register…] [--sync-only | --check] [--local-only] [--skip-roadmap-refresh] [--refresh-roadmaps] [--install-schedule HH:MM])
2
+ description: Upgrade roadmodel and shared agent context across registered projects and configured machines (usage: /roadmodel-upgrade [project dirs to register…] [--sync-only | --check] [--local-only] [--skip-roadmap-refresh] [--refresh-roadmaps] [--install-schedule HH:MM] [--install-sync-schedule [MINUTES]])
3
3
  ---
4
4
  Upgrade roadmodel in every registered project's own environment, refresh its
5
5
  `planning/` kit and agent commands, and maintain live shared rules, full
@@ -172,6 +172,24 @@ and registries are local; installing one schedule does not install another
172
172
  on a peer. When the operator has requested automatic upkeep, install and
173
173
  verify it within that authorization.
174
174
 
175
+ **Checkout sync (roadmodel 0.2.96 on).** A roadmap change merged on GitHub
176
+ reaches a project's checkout only when it pulls, so the editor kept showing
177
+ the old version. `--install-sync-schedule [MINUTES]` (default 15) registers
178
+ `--sync-checkouts` on its own schedule: launchd, Task Scheduler while the user
179
+ is logged on, or cron. Every full run also syncs, after its roadmap refresh.
180
+ For each registered checkout that sits on its default branch, it fetches
181
+ origin and fast-forwards (`git merge --ff-only`). It never merges, rebases,
182
+ stashes, resets or cleans. It leaves alone, and reports in the log, any
183
+ checkout that:
184
+ - is on a feature branch (an agent's step, which gets main when it rebases);
185
+ - has local commits;
186
+ - has a merge or rebase in progress;
187
+ - has uncommitted changes to a file the update changes.
188
+
189
+ Untracked files are never touched. `--uninstall-sync-schedule` removes it.
190
+ The operator asked for this on 2026-10-25: install it on every machine, peers
191
+ included (over SSH: `<python> <launcher> --install-sync-schedule`).
192
+
175
193
  ## 6. Refresh every project's roadmaps
176
194
 
177
195
  `--refresh-roadmaps` runs `/roadmap-refresh` in every registered project on
@@ -757,24 +757,27 @@ that owns it.}}
757
757
  **Runs:** line exactly as `roadmodel ladder --category
758
758
  <c> --complexity <x> [--novel]` prints them for the
759
759
  step's classification (MCP tool: `roadmap_settings`).
760
- Layout (roadmodel 0.2.94 on): a bold heading per column
761
- (**Cost**, **Balanced**, **Quality**; the column the
762
- **Runs:** line names reads `— runs by default`), then
763
- one list line per rank — `- Pick:`, `- Runner-up:`,
764
- `- Backup:` — giving the option's **model**; its
765
- platform; its own dial and level (`Intelligence Medium`
766
- on Codex, `Effort High` on Claude Code, no field where
767
- the surface has none); `Thinking On` where the surface
768
- has that toggle, no field where it has none; and `AA`,
769
- the model's Artificial Analysis Intelligence Index at
770
- that effort (`AA not measured` where AA has no row for
771
- it there). A `**Conversation:**` line closes the ladder.
772
- One option a line reads in a narrow Markdown preview,
773
- where a table wrapped every cell; a line past 80 columns
774
- wraps before a field. The ranks follow the column's own
775
- rule, not the AA Index: Cost ranks the cheapest first,
776
- so its AA Index may rise down the column. The Backup
777
- line reads `none` when the Runner-up already holds the
760
+ Layout (roadmodel 0.2.95 on): one table whose columns
761
+ are Cost, Balanced and Quality (the column the **Runs:**
762
+ line names marked ✓). Each rank is a bold group row —
763
+ **Pick**, **Runner‑up**, **Backup** — over indented
764
+ field rows: Model (bold); Platform; Level, the bare
765
+ level the platform's own dial sets (`High` is
766
+ Intelligence High on Codex and Effort High on Claude
767
+ Code and Antigravity; `—` where the surface has no
768
+ dial); AA, the model's Artificial Analysis Intelligence
769
+ Index at that level (`not measured` where AA has no row
770
+ for it there); and Price, its blended list price per 1M
771
+ tokens (3 in : 1 out) times the tokens it uses at that
772
+ level (`*` where that use is not yet measured). There is
773
+ no Thinking row: Thinking is always On wherever the
774
+ platform has the toggle, and every AA Index and Price
775
+ already assumes it. A note line under the table explains
776
+ ✓ and Price, and a `**Conversation:**` line closes the
777
+ ladder. The ranks follow the column's own rule, not the
778
+ AA Index: Cost ranks the cheapest first, so its AA Index
779
+ may rise down the column. The Backup reads `none` when
780
+ the Runner-up already holds the
778
781
  only other maker's models. Every model is the latest
779
782
  version of its series, never an older one (GPT-6 Sol
780
783
  where GPT-6.1 Sol runs, Opus 5 where Opus 5.5 does).
@@ -875,29 +878,35 @@ that owns it.}}
875
878
  -->
876
879
 
877
880
  Settings — ladder ({{the default wherever roadmodel is
878
- installed: the lists and **Runs:** line `roadmodel ladder
881
+ installed: the table and **Runs:** line `roadmodel ladder
879
882
  --category <c> --complexity <x> [--novel]` prints for the
880
883
  step's classification, pasted as printed. The three table
881
884
  shapes after it are the fallback where roadmodel cannot be
882
885
  reached}}):
883
886
 
884
- **Cost**
885
-
886
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
887
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
888
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
889
-
890
- **Balanced** — runs by default
891
-
892
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
893
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
894
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
895
-
896
- **Quality**
897
-
898
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
899
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
900
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
887
+ | | Cost | Balanced ✓ | Quality |
888
+ | -------------------------------- | --------------------- | --------------------- | --------------------- |
889
+ | **Pick** | | | |
890
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model}}** | **{{Model}}** | **{{Model}}** |
891
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
892
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
893
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
894
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
895
+ | **Runner‑up** | | | |
896
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model}}** | **{{Model}}** | **{{Model}}** |
897
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
898
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
899
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
900
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
901
+ | **Backup** | | | |
902
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model or none}}** | **{{Model or none}}** | **{{Model or none}}** |
903
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
904
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
905
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
906
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
907
+
908
+ ✓ runs by default. Price: list $ per 1M tokens (3 in : 1 out) × the tokens the
909
+ model uses at that level.
901
910
 
902
911
  **Conversation:** New
903
912
 
@@ -1317,23 +1326,29 @@ printed with its **Runs:** line. Where roadmodel cannot be
1317
1326
  reached, the single-column variant that matches PLATFORM,
1318
1327
  carrying ONLY the rows that platform's panel exposes.}}
1319
1328
 
1320
- **Cost**
1321
-
1322
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1323
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1324
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1325
-
1326
- **Balanced** — runs by default
1327
-
1328
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1329
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1330
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1331
-
1332
- **Quality**
1333
-
1334
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1335
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1336
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1329
+ | | Cost | Balanced ✓ | Quality |
1330
+ | -------------------------------- | --------------------- | --------------------- | --------------------- |
1331
+ | **Pick** | | | |
1332
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model}}** | **{{Model}}** | **{{Model}}** |
1333
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
1334
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
1335
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
1336
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
1337
+ | **Runner‑up** | | | |
1338
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model}}** | **{{Model}}** | **{{Model}}** |
1339
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
1340
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
1341
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
1342
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
1343
+ | **Backup** | | | |
1344
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model or none}}** | **{{Model or none}}** | **{{Model or none}}** |
1345
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
1346
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
1347
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
1348
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
1349
+
1350
+ ✓ runs by default. Price: list $ per 1M tokens (3 in : 1 out) × the tokens the
1351
+ model uses at that level.
1337
1352
 
1338
1353
  **Conversation:** New
1339
1354
 
@@ -1464,23 +1479,29 @@ this step's classification, pasted as printed with its
1464
1479
  **Runs:** line; where roadmodel cannot be reached, the
1465
1480
  single-column variant that matches PLATFORM.}}
1466
1481
 
1467
- **Cost**
1468
-
1469
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1470
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1471
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1472
-
1473
- **Balanced** — runs by default
1474
-
1475
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1476
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1477
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1478
-
1479
- **Quality**
1480
-
1481
- - Pick: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1482
- - Runner-up: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1483
- - Backup: **{{Model}}** · {{Platform}} · {{Dial and level}} · AA {{AA Index}}
1482
+ | | Cost | Balanced ✓ | Quality |
1483
+ | -------------------------------- | --------------------- | --------------------- | --------------------- |
1484
+ | **Pick** | | | |
1485
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model}}** | **{{Model}}** | **{{Model}}** |
1486
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
1487
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
1488
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
1489
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
1490
+ | **Runner‑up** | | | |
1491
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model}}** | **{{Model}}** | **{{Model}}** |
1492
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
1493
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
1494
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
1495
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
1496
+ | **Backup** | | | |
1497
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **{{Model or none}}** | **{{Model or none}}** | **{{Model or none}}** |
1498
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | {{Platform}} | {{Platform}} | {{Platform}} |
1499
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | {{Level}} | {{Level}} | {{Level}} |
1500
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | {{AA Index}} | {{AA Index}} | {{AA Index}} |
1501
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | {{$ per 1M}} | {{$ per 1M}} | {{$ per 1M}} |
1502
+
1503
+ ✓ runs by default. Price: list $ per 1M tokens (3 in : 1 out) × the tokens the
1504
+ model uses at that level.
1484
1505
 
1485
1506
  **Conversation:** New
1486
1507
 
@@ -32,8 +32,8 @@ out would add cost for no benefit.
32
32
  the step (step 1 below), then paste the ladder and **Runs:** line
33
33
  `roadmodel ladder --category <c> --complexity <x> [--novel]` prints: the
34
34
  Cost / Balanced / Quality picks /recommend shows, each ranked three deep (the
35
- Pick, the Runner-up, and a Backup from another maker), each option on one
36
- list line with its effort and AA Index. It is local code — no API
35
+ Pick, the Runner-up, and a Backup from another maker), each option with its
36
+ level, AA Index and price. It is local code — no API
37
37
  call, no engine — and it
38
38
  reads every usage pool at headroom, so the ladder outlives a pool's state: when
39
39
  a pool reads `tight` or `exhausted`, `/roadmap-step` runs another column
@@ -45,12 +45,13 @@ STYLE RULES (the AI MUST follow)
45
45
  in Claude Code, which `/roadmap-phase` sets by itself),
46
46
  with thinking on where the model has a Thinking toggle
47
47
  (Opus 5.5 and the other models that always think have
48
- none: their cell carries no Thinking line). Where `roadmodel` is installed, the table
48
+ none, and the ladder carries no Thinking row: it is always On where a
49
+ toggle exists). Where `roadmodel` is installed, the table
49
50
  is the ladder `roadmodel ladder --category planning
50
51
  --complexity high --phase` prints, pasted as printed with
51
52
  its **Runs:** line: Cost, Balanced and Quality, each ranked
52
53
  three deep (Pick, Runner-up, and a Backup from another
53
- maker), each option with its AA Index, so a pool that reads `tight` or
54
+ maker), each option with its level, AA Index and price, so a pool that reads `tight` or
54
55
  `exhausted` on the day moves the session to another column
55
56
  instead of the table being refreshed. It ranks on measured
56
57
  benchmarks, so a stale catalog letter cannot steer it, and
@@ -249,23 +250,29 @@ dependency graph in §5 is honoured.
249
250
  **Phase roadmap settings** — the session that writes
250
251
  `phase01-roadmap.md` (`/roadmap-phase 1`):
251
252
 
252
- **Cost**
253
-
254
- - Pick: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
255
- - Runner-up: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
256
- - Backup: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
257
-
258
- **Balanced**
259
-
260
- - Pick: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
261
- - Runner-up: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
262
- - Backup: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
263
-
264
- **Quality** — runs by default
265
-
266
- - Pick: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
267
- - Runner-up: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
268
- - Backup: **<Model>** · <Platform> · <Dial and level> · AA <AA Index>
253
+ | | Cost | Balanced | Quality ✓ |
254
+ | -------------------------------- | ------------------- | ------------------- | ------------------- |
255
+ | **Pick** | | | |
256
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **<Model>** | **<Model>** | **<Model>** |
257
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | <Platform> | <Platform> | <Platform> |
258
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | <Level> | <Level> | <Level> |
259
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | <AA Index> | <AA Index> | <AA Index> |
260
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | <$ per 1M> | <$ per 1M> | <$ per 1M> |
261
+ | **Runner‑up** | | | |
262
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **<Model>** | **<Model>** | **<Model>** |
263
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | <Platform> | <Platform> | <Platform> |
264
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | <Level> | <Level> | <Level> |
265
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | <AA Index> | <AA Index> | <AA Index> |
266
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | <$ per 1M> | <$ per 1M> | <$ per 1M> |
267
+ | **Backup** | | | |
268
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **<Model or none>** | **<Model or none>** | **<Model or none>** |
269
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | <Platform> | <Platform> | <Platform> |
270
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | <Level> | <Level> | <Level> |
271
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | <AA Index> | <AA Index> | <AA Index> |
272
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | <$ per 1M> | <$ per 1M> | <$ per 1M> |
273
+
274
+ ✓ runs by default. Price: list $ per 1M tokens (3 in : 1 out) × the tokens the
275
+ model uses at that level.
269
276
 
270
277
  **Conversation:** New
271
278
 
@@ -323,23 +330,29 @@ key pays for the platform.>
323
330
  **Phase roadmap settings** — the session that writes
324
331
  `phase02-roadmap.md` (`/roadmap-phase 2`):
325
332
 
326
- **Cost**
327
-
328
- - Pick: **…** · … · … · AA …
329
- - Runner-up: **…** · … · … · AA …
330
- - Backup: **…** · … · … · AA …
331
-
332
- **Balanced**
333
-
334
- - Pick: **…** · … · … · AA …
335
- - Runner-up: **…** · … · … · AA …
336
- - Backup: **…** · … · … · AA …
337
-
338
- **Quality** — runs by default
339
-
340
- - Pick: **…** · … · … · AA …
341
- - Runner-up: **…** · … · … · AA …
342
- - Backup: **…** · … · … · AA …
333
+ | | Cost | Balanced | Quality ✓ |
334
+ | -------------------------------- | ----- | -------- | --------- |
335
+ | **Pick** | | | |
336
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **…** | **…** | **…** |
337
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | … | … | … |
338
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | … | … | … |
339
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | … | … | … |
340
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | … | … | … |
341
+ | **Runner‑up** | | | |
342
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **…** | **…** | **…** |
343
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | … | … | … |
344
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | … | … | … |
345
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | … | … | … |
346
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | … | … | … |
347
+ | **Backup** | | | |
348
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **…** | **…** | **…** |
349
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | … | … | … |
350
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | … | … | … |
351
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | … | … | … |
352
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | … | … | … |
353
+
354
+ ✓ runs by default. Price: list $ per 1M tokens (3 in : 1 out) × the tokens the
355
+ model uses at that level.
343
356
 
344
357
  **Conversation:** New
345
358
 
@@ -371,23 +384,29 @@ key pays for the platform.>
371
384
  **Phase roadmap settings** — the session that writes
372
385
  `phaseNN-roadmap.md` (`/roadmap-phase N`):
373
386
 
374
- **Cost**
375
-
376
- - Pick: **…** · … · … · AA …
377
- - Runner-up: **…** · … · … · AA …
378
- - Backup: **…** · … · … · AA …
379
-
380
- **Balanced**
381
-
382
- - Pick: **…** · … · … · AA …
383
- - Runner-up: **…** · … · … · AA …
384
- - Backup: **…** · … · … · AA …
385
-
386
- **Quality** — runs by default
387
-
388
- - Pick: **…** · … · … · AA …
389
- - Runner-up: **…** · … · … · AA …
390
- - Backup: **…** · … · … · AA …
387
+ | | Cost | Balanced | Quality ✓ |
388
+ | -------------------------------- | ----- | -------- | --------- |
389
+ | **Pick** | | | |
390
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **…** | **…** | **…** |
391
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | … | … | … |
392
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | … | … | … |
393
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | … | … | … |
394
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | … | … | … |
395
+ | **Runner‑up** | | | |
396
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **…** | **…** | **…** |
397
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | … | … | … |
398
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | … | … | … |
399
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | … | … | … |
400
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | … | … | … |
401
+ | **Backup** | | | |
402
+ | &nbsp;&nbsp;&nbsp;&nbsp;Model | **…** | **…** | **…** |
403
+ | &nbsp;&nbsp;&nbsp;&nbsp;Platform | … | … | … |
404
+ | &nbsp;&nbsp;&nbsp;&nbsp;Level | … | … | … |
405
+ | &nbsp;&nbsp;&nbsp;&nbsp;AA | … | … | … |
406
+ | &nbsp;&nbsp;&nbsp;&nbsp;Price | … | … | … |
407
+
408
+ ✓ runs by default. Price: list $ per 1M tokens (3 in : 1 out) × the tokens the
409
+ model uses at that level.
391
410
 
392
411
  **Conversation:** New
393
412
 
@@ -28,8 +28,8 @@ Step 1 has `**Status:** Not started` directly under the `## Step 1`
28
28
  heading. If Stage 3 is a bare "OPEN THE PR", Stage 6 tells you to put
29
29
  findings in a "Follow-ups (non-blocking)" note after the completion
30
30
  line, a step's Status line sits after its `**Deploys:**` line, its
31
- Settings tables have no `Backup` row, or its ladders have no
32
- `- Runner-up:` line, STOP
31
+ Settings tables have no `Backup` row, or its ladder tables have no
32
+ `Price` row, STOP
33
33
  and tell me the kit is stale — do not write the roadmap from it.
34
34
 
35
35
  Step 0b — roadmaps live in `docs/roadmap/`: `ROADMAP.md` and every
@@ -70,11 +70,11 @@ own model> on <this surface>.`
70
70
  the model, print `unverified`, ask me which I picked, and go on with my
71
71
  answer.
72
72
  - A ladder (Cost / Balanced / Quality columns): each column ranks a
73
- Pick, a Runner-up and a Backup, one `- Pick:` / `- Runner-up:` /
74
- `- Backup:` line each under the column's bold heading (roadmodel
75
- 0.2.94 on; a 0.2.93 table has `1 · Pick`, `2 · Runner-up` and
76
- `3 · Backup` rows, and an older one Model / Backup rows and no
77
- Runner-up), and its **Runs:** line names the
73
+ Pick, a Runner-up and a Backup — from roadmodel 0.2.95 a bold group
74
+ row each, over indented Model / Platform / Level / AA / Price rows
75
+ (0.2.94 wrote them as `- Pick:` lists, 0.2.93 as `1 · Pick` rows,
76
+ and older ladders Model / Backup rows with no Runner-up) — and its
77
+ **Runs:** line names the
78
78
  column this session runs (Quality, for a phase roadmap). Apply that
79
79
  line's rule to the Usage-pool status table in
80
80
  `planning/user-context.md`: a pool that reads `tight` or `exhausted`
@@ -123,7 +123,7 @@ that classification (MCP tool: `roadmap_settings`), pasted as printed
123
123
  with its **Runs:** line. It carries the full recommendation /recommend
124
124
  shows: Cost, Balanced and Quality, each ranked three deep (the Pick,
125
125
  the Runner-up, and a Backup from another maker), each option on one
126
- list line with its own effort and AA Index. The step's runner picks the column from the
126
+ its own level, AA Index and price. The step's runner picks the column from the
127
127
  usage pools on the day, so the roadmap needs no refresh when a pool
128
128
  tightens. Its models are always the latest version of their series.
129
129
  The Model rationale explains the classification and what sets the