Open-source AI browser agent for Chrome and Firefox (monorepo) π§
JavaScript ai-agentai-agentsai-toolsbrowser-aibrowser-automationbrowser-extensionchrome-aichrome-devtoolschrome-extensionchrome-extensionsfirefox-addonfirefox-addonsfirefox-extensionfirefox-extensionsgemmagemma4minimaxoffline-aioffline-llmqwen
Lean mode: regenerate the comparison for the longer clarify schema
Barack Sokullua111dac790b6
diff --git a/docs/lean-mode-comparison.md b/docs/lean-mode-comparison.mdindex 7b827688b..ebf85e6d8 100644--- a/docs/lean-mode-comparison.md+++ b/docs/lean-mode-comparison.md@@ -8,12 +8,12 @@ The system prompt and tool schemas a model receives on each Act turn, with produ| Build | Provider model | Lean mode | System prompt | Tools | Tool schemas | Per turn || --- | --- | --- | ---: | ---: | ---: | ---: |-| Chrome | `claude-sonnet-4-5`, `gpt-5` | Off | 53,276 chars, β13,320 tokens | 58 | 83,121 chars, β20,781 tokens | β34,101 tokens |-| Chrome | `claude-sonnet-4-5`, `gpt-5` | Auto β lean (strong_cloud_model) | 8,366 chars, β2,092 tokens | 17 | 30,151 chars, β7,538 tokens | β9,630 tokens |-| Firefox | `claude-sonnet-4-5`, `gpt-5` | Off | 43,691 chars, β10,924 tokens | 57 | 80,050 chars, β20,013 tokens | β30,937 tokens |-| Firefox | `claude-sonnet-4-5`, `gpt-5` | Auto β lean (strong_cloud_model) | 8,265 chars, β2,067 tokens | 17 | 29,117 chars, β7,280 tokens | β9,347 tokens |+| Chrome | `claude-sonnet-4-5`, `gpt-5` | Off | 53,324 chars, β13,332 tokens | 58 | 83,327 chars, β20,832 tokens | β34,164 tokens |+| Chrome | `claude-sonnet-4-5`, `gpt-5` | Auto β lean (strong_cloud_model) | 8,366 chars, β2,092 tokens | 17 | 30,357 chars, β7,590 tokens | β9,682 tokens |+| Firefox | `claude-sonnet-4-5`, `gpt-5` | Off | 43,739 chars, β10,936 tokens | 57 | 80,256 chars, β20,064 tokens | β31,000 tokens |+| Firefox | `claude-sonnet-4-5`, `gpt-5` | Auto β lean (strong_cloud_model) | 8,265 chars, β2,067 tokens | 17 | 29,323 chars, β7,331 tokens | β9,398 tokens |-Lean mode cuts this fixed per-turn input by 72% in the Chrome build (β34,101 β β9,630 tokens) and by 70% in the Firefox build. Tool schemas are unchanged; lean mode offers fewer of them.+Lean mode cuts this fixed per-turn input by 72% in the Chrome build (β34,164 β β9,682 tokens) and by 70% in the Firefox build. Tool schemas are unchanged; lean mode offers fewer of them.The lean Act tools (17): `calculate`, `get_accessibility_tree`, `click_ax`, `set_checked`, `type_ax`, `set_field`, `inspect_viewport`, `read_page`, `click`, `type_text`, `press_keys`, `scroll`, `navigate`, `wait_for_stable`, `done`, `clarify`, `upload_file`. `generate_image`, `carousel_navigate`, `gmail_count_results` and enabled skills' tools are added when they apply, as in a full run.@@ -35,9 +35,9 @@ The model is a fixed script: it reads the page, acts on the targets it names by| Task | Lean mode | Model turns | Tool calls | Refused | Notes | Caveat | LLM side calls | Cards | Page probes | Input tokens | On the page | Result || --- | --- | ---: | ---: | ---: | ---: | --- | ---: | ---: | ---: | ---: | --- | --- || GitHub edit + commit | Off | 8 | 8 | 1 | 0 | yes | 5 | 3 | 229 | β296k | committed once, file text exact | done, answer carries a caveat |-| GitHub edit + commit | Auto β lean | 7 | 7 | 0 | 0 | no | 4 | 3 | 174 | β86k | committed once, file text exact | success |+| GitHub edit + commit | Auto β lean | 7 | 7 | 0 | 0 | no | 4 | 3 | 174 | β87k | committed once, file text exact | success || Contact form | Off | 7 | 7 | 0 | 0 | no | 3 | 2 | 136 | β250k | sent once with the requested values | success |-| Contact form | Auto β lean | 7 | 7 | 0 | 0 | no | 1 | 2 | 102 | β78k | sent once with the requested values | success |+| Contact form | Auto β lean | 7 | 7 | 0 | 0 | no | 1 | 2 | 102 | β79k | sent once with the requested values | success || Read-only lookup | Off | 2 | 2 | 0 | 0 | no | 1 | 0 | 34 | β70k | answered $129.00 | success || Read-only lookup | Auto β lean | 2 | 2 | 0 | 0 | no | 0 | 0 | 9 | β21k | answered $129.00 | success |@@ -49,7 +49,7 @@ The case that motivated lean mode. The task replaces NOTES.md with a three-parag- **Auto β lean:** `get_accessibility_tree` β `set_field` β `click_ax` β `get_accessibility_tree` β `click_ax` β `get_accessibility_tree` β `done`.- **LLM side calls** (besides the planner's intent call, 1 in each mode): Off 5 (intent, reading: control_effect Γ2, reading: page_blocker, completion_verification); lean 4 (intent, reading: control_effect Γ2, reading: page_blocker).- **Cards shown to the user:** Off site permission, submit confirmation Γ2; lean site permission, submit confirmation Γ2.-- **Model input:** Off 295,587 tokens over 8 turns (58 tools offered, a 54,706-character system prompt); lean 86,298 tokens over 7 turns (17 tools, 9,796 characters).+- **Model input:** Off 296,096 tokens over 8 turns (58 tools offered, a 54,754-character system prompt); lean 86,659 tokens over 7 turns (17 tools, 9,796 characters).### 2. Fill a simple form and submit it@@ -59,7 +59,7 @@ Three fields and a Send button on a plain page; the page posts with fetch and sh- **Auto β lean:** `get_accessibility_tree` β `set_field` β `set_field` β `set_field` β `click_ax` β `get_accessibility_tree` β `done`.- **LLM side calls** (besides the planner's intent call, 1 in each mode): Off 3 (reading: control_effect, reading: status_message, completion_verification); lean 1 (reading: control_effect).- **Cards shown to the user:** Off site permission, submit confirmation; lean site permission, submit confirmation.-- **Model input:** Off 249,715 tokens over 7 turns (58 tools offered, a 53,848-character system prompt); lean 78,425 tokens over 7 turns (17 tools, 8,938 characters).+- **Model input:** Off 250,157 tokens over 7 turns (58 tools offered, a 53,896-character system prompt); lean 78,783 tokens over 7 turns (17 tools, 8,938 characters).### 3. Read-only lookup on the current page@@ -69,7 +69,7 @@ A question about the open product page: what does the Trail Runner 2 cost? The a- **Auto β lean:** `read_page` β `done`.- **LLM side calls** (besides the planner's intent call, 1 in each mode): Off 1 (completion_verification); lean 0.- **Cards shown to the user:** Off none; lean none.-- **Model input:** Off 70,233 tokens over 2 turns (58 tools offered, a 53,848-character system prompt); lean 21,293 tokens over 2 turns (17 tools, 8,938 characters).+- **Model input:** Off 70,360 tokens over 2 turns (58 tools offered, a 53,896-character system prompt); lean 21,396 tokens over 2 turns (17 tools, 8,938 characters).## Limits