mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-10-11 03:40:05 +00:00
Fabro
parent
c6f55528fa
commit
ccfab315a2
3 changed files with 172 additions and 7 deletions
168
run.json
168
run.json
|
|
@ -515,14 +515,106 @@
|
|||
}
|
||||
},
|
||||
"web_url": "http://127.0.0.1:32276/runs/01KSAPQQSVK4FY3CWHYVZYD7T6",
|
||||
"start": null,
|
||||
"status": {
|
||||
"kind": "starting"
|
||||
"start": {
|
||||
"start_time": "2026-05-23T15:20:09.658986Z",
|
||||
"run_branch": "fabro/run/01KSAPQQSVK4FY3CWHYVZYD7T6",
|
||||
"base_sha": "a64a58d567e3de775aff86503703934c64fe2d38"
|
||||
},
|
||||
"status_updated_at": "2026-05-23T15:19:53.456033Z",
|
||||
"last_event_at": "2026-05-23T15:20:08.819373Z",
|
||||
"status": {
|
||||
"kind": "running"
|
||||
},
|
||||
"status_updated_at": "2026-05-23T15:20:09.659052Z",
|
||||
"last_event_at": "2026-05-23T15:20:11.504629Z",
|
||||
"pending_control": null,
|
||||
"checkpoints": [],
|
||||
"checkpoints": [
|
||||
{
|
||||
"seq": 19,
|
||||
"checkpoint": {
|
||||
"timestamp": "2026-05-23T15:20:11.504317Z",
|
||||
"current_node": "start",
|
||||
"completed_nodes": [
|
||||
"start"
|
||||
],
|
||||
"node_retries": {},
|
||||
"context_values": {
|
||||
"failure_signature": "",
|
||||
"graph.rankdir": "LR",
|
||||
"current_node": "start",
|
||||
"graph.model_stylesheet": "\n * { model: claude-opus-4-7; }\n ",
|
||||
"internal.node_visit_count": 1,
|
||||
"graph.goal": "# Agent Compaction API Usage Baseline Plan\n\nDate: 2026-05-23\n\n## Summary\n\nChange Fabro's agent compaction trigger from a whole-history `chars / 4`\nestimate to a Claude Code-style hot-path estimate: use the latest real\nassistant response's stored `usage.total_tokens()` as the baseline, then add\nlocal estimates for turns appended after that response. This avoids token-count\nprovider API calls while making compaction sensitive to actual\nprovider-reported context usage, including cache and reasoning tokens.\n\nNo provider token-count API calls should be added in this change.\n\n## Key Changes\n\n- Replace the current compaction estimate in `fabro-agent` with a new\n active-context estimator.\n- Find the newest assistant turn whose `usage.total_tokens() > 0`.\n- Use that `usage.total_tokens()` as the baseline.\n- Add local estimates only for turns after that assistant turn.\n- If no usable assistant usage exists, fall back to the existing local\n whole-history estimate.\n- Reuse a shared per-turn local estimate helper so fallback and post-baseline\n delta counting stay consistent.\n- Keep the estimator local and in-process. Do not call\n `llm_client.count_input_tokens()` from `compact_if_needed()`.\n\n## Implementation Details\n\n- Update `lib/crates/fabro-agent/src/compaction.rs`:\n - Add an estimator that returns both token count and method, for example\n `ApiUsagePlusLocalDelta` or `LocalEstimate`.\n - Make `check_context_usage()` use the new estimator and include the method\n in warning `details`.\n - Make `compact_context()` report the same improved estimate in\n `CompactionStarted`.\n - Move `CompactionStarted` emission after the\n `original_turn_count <= preserve_count` no-op check, so a no-op compact\n cannot emit started without completed.\n- Update `lib/crates/fabro-agent/src/history.rs`:\n - In `History::compact()`, invalidate preserved assistant usage by replacing\n preserved assistant `usage` with `TokenCounts::default()`.\n - Keep provider parts, response IDs, text, and tool calls unchanged.\n - Rationale: preserved assistant usage reflects the pre-compaction context and\n must not become the next baseline. Billing remains available from emitted\n run events, so mutable runtime history should prefer compaction correctness.\n- Leave public run event names and schemas unchanged:\n - `agent.compaction.started`\n - `agent.compaction.completed`\n - Existing warning event remains a warning with richer `details`.\n\n## Test Plan\n\n- Add unit coverage in `lib/crates/fabro-agent/src/compaction.rs`:\n - No assistant usage: estimator matches current local whole-history behavior.\n - Latest assistant usage present: estimator uses `usage.total_tokens()` plus\n only later tool/user/steering turns.\n - Usage fields include cache and reasoning through `TokenCounts::total_tokens()`.\n - Earlier assistant usage is ignored when a later assistant usage exists.\n- Add unit coverage in `lib/crates/fabro-agent/src/history.rs`:\n - `History::compact()` preserves assistant content, tool calls, and provider\n parts, but resets preserved assistant usage to default.\n - Existing OpenAI opaque stripping and Anthropic thinking preservation tests\n still pass.\n- Add session coverage in `lib/crates/fabro-agent/src/session.rs`:\n - A short assistant response with high `usage.total_tokens()` triggers\n compaction even when text length is small.\n - A compact no-op due to `turns.len() <= preserve_count` does not emit\n `CompactionStarted`.\n - Compaction disabled still prevents compaction even if the API usage\n baseline exceeds threshold.\n- Run targeted verification:\n - `cargo nextest run -p fabro-agent compaction`\n - `cargo nextest run -p fabro-agent history`\n - If those pass, run `cargo nextest run -p fabro-agent`.\n\n## Assumptions\n\n- Runtime/session `Message::Assistant.usage` is safe to invalidate after\n compaction because authoritative billing comes from emitted workflow/run\n events, not preserved mutable agent history.\n- A zero-token `TokenCounts::default()` should be treated as no usable API\n baseline.\n- Provider token-count APIs remain available for future near-threshold\n confirmation, but are intentionally out of scope for this change.\n",
|
||||
"internal.run_id": "01KSAPQQSVK4FY3CWHYVZYD7T6",
|
||||
"internal.fidelity": "compact",
|
||||
"internal.retry_count.start": 0,
|
||||
"internal.thread_id": null,
|
||||
"failure_class": "",
|
||||
"internal.work_dir": "/home/daytona/workspace/fabro",
|
||||
"outcome": "succeeded"
|
||||
},
|
||||
"node_outcomes": {
|
||||
"start": {
|
||||
"status": "succeeded",
|
||||
"usage": null
|
||||
}
|
||||
},
|
||||
"next_node_id": "toolchain",
|
||||
"node_visits": {
|
||||
"start": 1
|
||||
}
|
||||
},
|
||||
"diff": {}
|
||||
},
|
||||
{
|
||||
"seq": 0,
|
||||
"checkpoint": {
|
||||
"timestamp": "2026-05-23T15:20:14.019032Z",
|
||||
"current_node": "toolchain",
|
||||
"completed_nodes": [
|
||||
"start",
|
||||
"toolchain"
|
||||
],
|
||||
"node_retries": {},
|
||||
"context_values": {
|
||||
"internal.work_dir": "/home/daytona/workspace/fabro",
|
||||
"current_node": "toolchain",
|
||||
"graph.rankdir": "LR",
|
||||
"internal.run_id": "01KSAPQQSVK4FY3CWHYVZYD7T6",
|
||||
"outcome": "succeeded",
|
||||
"internal.thread_id": "start",
|
||||
"thread.start.current_node": "toolchain",
|
||||
"internal.retry_count.toolchain": 0,
|
||||
"internal.node_visit_count": 1,
|
||||
"failure_class": "",
|
||||
"graph.model_stylesheet": "\n * { model: claude-opus-4-7; }\n ",
|
||||
"internal.retry_count.start": 0,
|
||||
"internal.fidelity": "compact",
|
||||
"command.output": "blob://sha256/fc14b2ba2d770e5cd3169df7a29525c962adfc4cfa3097b9098c63ebd61a748c",
|
||||
"graph.goal": "# Agent Compaction API Usage Baseline Plan\n\nDate: 2026-05-23\n\n## Summary\n\nChange Fabro's agent compaction trigger from a whole-history `chars / 4`\nestimate to a Claude Code-style hot-path estimate: use the latest real\nassistant response's stored `usage.total_tokens()` as the baseline, then add\nlocal estimates for turns appended after that response. This avoids token-count\nprovider API calls while making compaction sensitive to actual\nprovider-reported context usage, including cache and reasoning tokens.\n\nNo provider token-count API calls should be added in this change.\n\n## Key Changes\n\n- Replace the current compaction estimate in `fabro-agent` with a new\n active-context estimator.\n- Find the newest assistant turn whose `usage.total_tokens() > 0`.\n- Use that `usage.total_tokens()` as the baseline.\n- Add local estimates only for turns after that assistant turn.\n- If no usable assistant usage exists, fall back to the existing local\n whole-history estimate.\n- Reuse a shared per-turn local estimate helper so fallback and post-baseline\n delta counting stay consistent.\n- Keep the estimator local and in-process. Do not call\n `llm_client.count_input_tokens()` from `compact_if_needed()`.\n\n## Implementation Details\n\n- Update `lib/crates/fabro-agent/src/compaction.rs`:\n - Add an estimator that returns both token count and method, for example\n `ApiUsagePlusLocalDelta` or `LocalEstimate`.\n - Make `check_context_usage()` use the new estimator and include the method\n in warning `details`.\n - Make `compact_context()` report the same improved estimate in\n `CompactionStarted`.\n - Move `CompactionStarted` emission after the\n `original_turn_count <= preserve_count` no-op check, so a no-op compact\n cannot emit started without completed.\n- Update `lib/crates/fabro-agent/src/history.rs`:\n - In `History::compact()`, invalidate preserved assistant usage by replacing\n preserved assistant `usage` with `TokenCounts::default()`.\n - Keep provider parts, response IDs, text, and tool calls unchanged.\n - Rationale: preserved assistant usage reflects the pre-compaction context and\n must not become the next baseline. Billing remains available from emitted\n run events, so mutable runtime history should prefer compaction correctness.\n- Leave public run event names and schemas unchanged:\n - `agent.compaction.started`\n - `agent.compaction.completed`\n - Existing warning event remains a warning with richer `details`.\n\n## Test Plan\n\n- Add unit coverage in `lib/crates/fabro-agent/src/compaction.rs`:\n - No assistant usage: estimator matches current local whole-history behavior.\n - Latest assistant usage present: estimator uses `usage.total_tokens()` plus\n only later tool/user/steering turns.\n - Usage fields include cache and reasoning through `TokenCounts::total_tokens()`.\n - Earlier assistant usage is ignored when a later assistant usage exists.\n- Add unit coverage in `lib/crates/fabro-agent/src/history.rs`:\n - `History::compact()` preserves assistant content, tool calls, and provider\n parts, but resets preserved assistant usage to default.\n - Existing OpenAI opaque stripping and Anthropic thinking preservation tests\n still pass.\n- Add session coverage in `lib/crates/fabro-agent/src/session.rs`:\n - A short assistant response with high `usage.total_tokens()` triggers\n compaction even when text length is small.\n - A compact no-op due to `turns.len() <= preserve_count` does not emit\n `CompactionStarted`.\n - Compaction disabled still prevents compaction even if the API usage\n baseline exceeds threshold.\n- Run targeted verification:\n - `cargo nextest run -p fabro-agent compaction`\n - `cargo nextest run -p fabro-agent history`\n - If those pass, run `cargo nextest run -p fabro-agent`.\n\n## Assumptions\n\n- Runtime/session `Message::Assistant.usage` is safe to invalidate after\n compaction because authoritative billing comes from emitted workflow/run\n events, not preserved mutable agent history.\n- A zero-token `TokenCounts::default()` should be treated as no usable API\n baseline.\n- Provider token-count APIs remain available for future near-threshold\n confirmation, but are intentionally out of scope for this change.\n",
|
||||
"failure_signature": ""
|
||||
},
|
||||
"node_outcomes": {
|
||||
"start": {
|
||||
"status": "succeeded",
|
||||
"usage": null
|
||||
},
|
||||
"toolchain": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/fc14b2ba2d770e5cd3169df7a29525c962adfc4cfa3097b9098c63ebd61a748c"
|
||||
},
|
||||
"notes": "Script completed: command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1",
|
||||
"usage": null
|
||||
}
|
||||
},
|
||||
"next_node_id": "preflight_compile",
|
||||
"node_visits": {
|
||||
"toolchain": 1,
|
||||
"start": 1
|
||||
}
|
||||
},
|
||||
"diff": {}
|
||||
}
|
||||
],
|
||||
"conclusion": null,
|
||||
"sandbox": {
|
||||
"provider": "daytona",
|
||||
|
|
@ -543,5 +635,67 @@
|
|||
"pull_request": null,
|
||||
"superseded_by": null,
|
||||
"pending_interviews": {},
|
||||
"stages": {}
|
||||
"stages": {
|
||||
"start@1": {
|
||||
"first_event_seq": 16,
|
||||
"prompt": null,
|
||||
"response": null,
|
||||
"completion": {
|
||||
"outcome": "succeeded",
|
||||
"notes": null,
|
||||
"failure_reason": null,
|
||||
"timestamp": "2026-05-23T15:20:11.504080Z"
|
||||
},
|
||||
"provider_used": null,
|
||||
"diff": null,
|
||||
"script_invocation": null,
|
||||
"script_timing": null,
|
||||
"parallel_results": null,
|
||||
"output": null,
|
||||
"started_at": "2026-05-23T15:20:11.503608Z",
|
||||
"handler": "start",
|
||||
"timing": {
|
||||
"wall_time_ms": 0,
|
||||
"inference_time_ms": 0,
|
||||
"tool_time_ms": 0,
|
||||
"active_time_ms": 0
|
||||
},
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"output_tokens": 0,
|
||||
"total_tokens": 0,
|
||||
"reasoning_tokens": 0,
|
||||
"cache_read_tokens": 0,
|
||||
"cache_write_tokens": 0
|
||||
},
|
||||
"state": "succeeded"
|
||||
},
|
||||
"toolchain@1": {
|
||||
"first_event_seq": 20,
|
||||
"prompt": null,
|
||||
"response": null,
|
||||
"completion": null,
|
||||
"provider_used": null,
|
||||
"diff": null,
|
||||
"script_invocation": {
|
||||
"script": "command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1",
|
||||
"command": "exec 2>&1\ncommand -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1",
|
||||
"language": "shell"
|
||||
},
|
||||
"script_timing": null,
|
||||
"parallel_results": null,
|
||||
"output": null,
|
||||
"started_at": "2026-05-23T15:20:11.504411Z",
|
||||
"handler": "command",
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"output_tokens": 0,
|
||||
"total_tokens": 0,
|
||||
"reasoning_tokens": 0,
|
||||
"cache_read_tokens": 0,
|
||||
"cache_write_tokens": 0
|
||||
},
|
||||
"state": "running"
|
||||
}
|
||||
}
|
||||
}
|
||||
6
stages/001-start@1/status.json
Normal file
6
stages/001-start@1/status.json
Normal file
|
|
@ -0,0 +1,6 @@
|
|||
{
|
||||
"outcome": "succeeded",
|
||||
"notes": null,
|
||||
"failure_reason": null,
|
||||
"timestamp": "2026-05-23T15:20:11.504080Z"
|
||||
}
|
||||
5
stages/002-toolchain@1/script_invocation.json
Normal file
5
stages/002-toolchain@1/script_invocation.json
Normal file
|
|
@ -0,0 +1,5 @@
|
|||
{
|
||||
"script": "command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1",
|
||||
"command": "exec 2>&1\ncommand -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1",
|
||||
"language": "shell"
|
||||
}
|
||||
Loading…
Add table
Reference in a new issue