@fro.bot/systematic 3.27.2 → 3.28.1
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.
- package/ATTRIBUTIONS.md +2 -2
- package/HARNESSES.md +23 -10
- package/agents/research/learnings-researcher.md +49 -9
- package/dist/claude-code-search.d.ts +30 -0
- package/dist/claude-code-validator-bin.d.ts +17 -0
- package/dist/cli.d.ts +18 -0
- package/dist/cli.js +335 -108
- package/dist/{index-608preny.js → index-9chxhh5j.js} +1120 -72
- package/dist/index.js +117 -3
- package/dist/lib/agent-resolver.d.ts +15 -3
- package/dist/lib/config-protected-fields.d.ts +1 -1
- package/dist/lib/config-schema.d.ts +6 -0
- package/dist/lib/config.d.ts +13 -0
- package/dist/lib/main-module.d.ts +30 -0
- package/dist/lib/opencode-v2-skills.d.ts +12 -2
- package/dist/lib/opencode-v2.d.ts +1 -0
- package/dist/lib/pi-delegate-session.d.ts +3 -1
- package/dist/lib/pi-delegate-tool.d.ts +12 -1
- package/dist/lib/search-cli.d.ts +52 -0
- package/dist/lib/search-core.d.ts +128 -0
- package/dist/lib/search-corpus.d.ts +105 -0
- package/dist/lib/search-lexical.d.ts +136 -0
- package/dist/lib/search-render.d.ts +69 -0
- package/dist/lib/search-tool.d.ts +53 -0
- package/dist/lib/search-user-config.d.ts +96 -0
- package/dist/pi.js +1169 -82
- package/package.json +5 -5
- package/skills/ce-review/SKILL.md +1 -1
- package/skills/ce-review/references/review-output-template.md +1 -1
- package/skills/ce-review/scripts/validate-review.mjs +1 -3
- package/skills/using-systematic/references/claude-code-profile.md +1 -0
- package/skills/using-systematic/references/opencode-profile.md +1 -0
- package/skills/using-systematic/references/opencode-v2-profile.md +1 -0
- package/skills/using-systematic/references/pi-profile.md +1 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@fro.bot/systematic",
|
|
3
|
-
"version": "3.
|
|
3
|
+
"version": "3.28.1",
|
|
4
4
|
"description": "Compound-engineering loops for OpenCode, Pi, and Claude Code",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"homepage": "https://fro.bot/systematic",
|
|
@@ -92,7 +92,7 @@
|
|
|
92
92
|
"url": "https://github.com/marcusrbrown/systematic.git"
|
|
93
93
|
},
|
|
94
94
|
"engines": {
|
|
95
|
-
"node": ">=
|
|
95
|
+
"node": ">=20.11"
|
|
96
96
|
},
|
|
97
97
|
"peerDependencies": {
|
|
98
98
|
"@opencode-ai/plugin": ">=1.18.29",
|
|
@@ -117,8 +117,8 @@
|
|
|
117
117
|
"devDependencies": {
|
|
118
118
|
"@biomejs/biome": "2.6.3",
|
|
119
119
|
"@earendil-works/pi-coding-agent": "1.4.0",
|
|
120
|
-
"@opencode-ai/plugin": "1.19.
|
|
121
|
-
"@opencode-ai/sdk": "1.19.
|
|
120
|
+
"@opencode-ai/plugin": "1.19.5",
|
|
121
|
+
"@opencode-ai/sdk": "1.19.5",
|
|
122
122
|
"@opencode/client": "2.2.0",
|
|
123
123
|
"@opencode/plugin": "2.2.0",
|
|
124
124
|
"@opencode/sdk": "2.2.0",
|
|
@@ -127,7 +127,7 @@
|
|
|
127
127
|
"@types/bun": "latest",
|
|
128
128
|
"@types/js-yaml": "4.0.9",
|
|
129
129
|
"@types/node": "26.6.5",
|
|
130
|
-
"agent-browser": "0.39.
|
|
130
|
+
"agent-browser": "0.39.4",
|
|
131
131
|
"ajv": "8.20.0",
|
|
132
132
|
"ajv-formats": "3.0.1",
|
|
133
133
|
"conventional-changelog-conventionalcommits": "10.4.1",
|
|
@@ -548,7 +548,7 @@ Assemble the final report using **pipe-delimited markdown tables for findings**
|
|
|
548
548
|
5. **Residual Actionable Work.** Render `report.queues.residual` as a table of findings whose owner is `downstream-resolver`, using `report.input_dispositions` to resolve each entry's fields.
|
|
549
549
|
6. **Pre-existing.** Render `report.pre_existing_findings`. Separate section, does not count toward verdict.
|
|
550
550
|
7. **Filtered (not validated).** Include when `report.findings` contains any entry with `validated: false`. Render as a pipe-delimited table with columns `#`, `File`, `Issue`, `Reviewer`, `Confidence`, `Validator reason`. These findings are surfaced for human review — they are not removed from the report. The validator found evidence that the issue may not be real in the code as written, was not introduced by this diff, or is already handled elsewhere; the human reviewer makes the final call. Omit this section when no findings were filtered.
|
|
551
|
-
8. **Learnings & Past Solutions.** Render only when CE `learnings-researcher` was selected and returned relevant output: if past solutions are relevant, flag them as "Known Pattern" with links to docs/solutions/ files, and carry any `Supersedes
|
|
551
|
+
8. **Learnings & Past Solutions.** Render only when CE `learnings-researcher` was selected and returned relevant output: if past solutions are relevant, flag them as "Known Pattern" with links to docs/solutions/ files, and carry any `Supersedes:` and `Caution:` lines from the researcher output into the Known Pattern entry. Omit the section otherwise.
|
|
552
552
|
9. **Agent-Native Gaps.** Render only when CE `agent-native-reviewer` was selected and returned relevant output. Omit the section otherwise.
|
|
553
553
|
10. **Deployment Notes.** If deployment-verification-agent ran, surface the key Go/No-Go items: blocking pre-deploy checks, the most important verification queries, rollback caveats, and monitoring focus areas. Keep the checklist actionable rather than dropping it into Coverage.
|
|
554
554
|
11. **Coverage.** Render `report.coverage` directly: suppressed count, residual risks, testing gaps, failed/timed-out reviewers, validator lifecycle failures (`failed`/`unavailable` outcomes from Stage 5b), risk-coverage entries with citing input finding IDs and exit conditions for blocked entries, and any intent uncertainty carried by non-interactive modes. For raw returns, state each selected persona's admission state — `findings`, `empty`, `malformed`, `never_returned`, `validation_unavailable` (the persisted raw dispatch outcome; distinct from the artifact-level `validation.status: "unavailable"`) — and what was admitted or withheld. Report admission states here only; do not add fields to `review-summary.v1`. Distinguish core reviewers, each selected conditional with its one-line rationale and triggering repository-relative paths, an explicit "no conditional selected" case, and any selected-but-failed/malformed/validation-unavailable reviewer; never label an unselected reviewer as failed.
|
|
@@ -135,7 +135,7 @@ This fails because: no pipe-delimited tables, no severity-grouped `###` headers,
|
|
|
135
135
|
- **Residual Actionable Work section** -- include only when unresolved actionable findings were handed off for later work
|
|
136
136
|
- **Pre-existing section** -- separate table, no confidence column (these are informational)
|
|
137
137
|
- **Filtered (not validated) section** -- findings where Stage 5b returned `validated: false`. Rendered as a pipe-delimited table with columns `#`, `File`, `Issue`, `Reviewer`, `Confidence`, `Validator reason`. These findings are surfaced for human review, not removed. Omit this section when Stage 5b produced no filtered findings.
|
|
138
|
-
- **Learnings & Past Solutions section** -- render only when CE `learnings-researcher` was selected and returned relevant output; results with links to docs/solutions/ files; carry any `Supersedes
|
|
138
|
+
- **Learnings & Past Solutions section** -- render only when CE `learnings-researcher` was selected and returned relevant output; results with links to docs/solutions/ files; carry any `Supersedes:` and `Caution:` lines from the researcher output into each Known Pattern entry. Omit otherwise.
|
|
139
139
|
- **Agent-Native Gaps section** -- render only when CE `agent-native-reviewer` was selected and returned relevant output. Omit otherwise.
|
|
140
140
|
- **Deployment Notes section** -- key checklist items from deployment-verification-agent. Omit if the agent did not run.
|
|
141
141
|
- **Coverage section** -- suppressed count with original confidences, residual risks, testing gaps, failed reviewers, disposition reconciliation, and risk-coverage entries with their citing input finding IDs and blocked-entry exit conditions. For raw returns, distinguish `findings`, `empty`, `malformed`, `never_returned`, and `validation_unavailable` (the persisted raw dispatch outcome, distinct from the artifact-level `validation.status: "unavailable"`), and state what was admitted or withheld
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
// biome-ignore-all assist/source/organizeImports: generated bundle
|
|
3
3
|
// Generated by scripts/generate-ce-review-validator.ts; do not edit by hand.
|
|
4
4
|
// Run `bun run ce-review-validator:build` to regenerate.
|
|
5
|
-
// source-digest:
|
|
5
|
+
// source-digest: 8efcba72f9317848bb9f5c6c58e71e1f6d69e6330ec724bbd48d5b24ffce2e1a
|
|
6
6
|
var __defProp = Object.defineProperty
|
|
7
7
|
var __returnValue = (v) => v
|
|
8
8
|
function __exportSetter(name, newValue) {
|
|
@@ -7013,8 +7013,6 @@ function runClaudeCodeValidator(options) {
|
|
|
7013
7013
|
)
|
|
7014
7014
|
return 0
|
|
7015
7015
|
}
|
|
7016
|
-
if (false) {
|
|
7017
|
-
}
|
|
7018
7016
|
|
|
7019
7017
|
// src/lib/review-pipeline.ts
|
|
7020
7018
|
import path2 from 'node:path'
|
|
@@ -6,6 +6,7 @@
|
|
|
6
6
|
| Blocking user interaction | `AskUserQuestion` tool | supported | Present numbered options in chat and wait |
|
|
7
7
|
| Task tracking | `TaskCreate` / `TaskGet` / `TaskList` / `TaskUpdate` (`TodoWrite` is deprecated and disabled by default) | supported | Maintain a visible task list in responses |
|
|
8
8
|
| Skill loading | Native Skill tool with `SKILL.md` discovery (`~/.claude/skills/`, `.claude/skills/`, plugin `skills/`); Systematic ships no `systematic_skill` tool on Claude Code | supported | Read the skill instructions listed by the active harness |
|
|
9
|
+
| Durable-output search | `systematic-search` command in the plugin `bin/`; probe with `command -v systematic-search`; user-level config only | supported | Grep `docs/solutions/` |
|
|
9
10
|
|
|
10
11
|
Behavioral enforcement on Claude Code rides a plugin output style (force-for-plugin); a declarative `SessionStart` hook carries state only, since imperative hook content is refused as prompt injection.
|
|
11
12
|
|
|
@@ -8,6 +8,7 @@ Evidence registry: see [`HARNESSES.md`](../../../HARNESSES.md).
|
|
|
8
8
|
| Blocking user interaction | `question` tool | supported | Present numbered options in chat and wait |
|
|
9
9
|
| Task tracking | `todowrite` | supported | Maintain a visible task list in responses |
|
|
10
10
|
| Skill loading | `systematic_skill` for bundled skills; `skill` tool for non-Systematic skills | supported | Read the skill instructions listed by the active harness |
|
|
11
|
+
| Durable-output search | `systematic_search` tool over `docs/solutions/`; absent when `search.enabled` is false | supported | Grep `docs/solutions/` |
|
|
11
12
|
|
|
12
13
|
## Invocation examples
|
|
13
14
|
|
|
@@ -8,6 +8,7 @@ Evidence registry: see [`HARNESSES.md`](../../../HARNESSES.md).
|
|
|
8
8
|
| Blocking user interaction | `question` tool | supported | Present numbered options in chat and wait |
|
|
9
9
|
| Task tracking | `todowrite` tool | conditional: only offered when the host's experimental `todo` option is on | Maintain a visible task list in responses |
|
|
10
10
|
| Skill loading | `systematic_skill` for bundled skills, with arguments; `skill` tool (by `id`) for non-Systematic skills | supported | Read the skill instructions listed by the active harness |
|
|
11
|
+
| Durable-output search | `systematic_search` tool over `docs/solutions/`; absent when `search.enabled` is false | supported | Grep `docs/solutions/` |
|
|
11
12
|
|
|
12
13
|
## Invocation examples
|
|
13
14
|
|
|
@@ -8,6 +8,7 @@ Evidence registry: see [`HARNESSES.md`](../../../HARNESSES.md).
|
|
|
8
8
|
| Blocking user interaction | No native blocking tool | degraded | Present numbered options in chat and wait |
|
|
9
9
|
| Task tracking | No native task-tracking mechanism | unavailable | Maintain a visible task list in responses |
|
|
10
10
|
| Skill loading | `systematic_skill` tool or Pi-native skill activation | supported | Read the skill instructions listed by the active harness |
|
|
11
|
+
| Durable-output search | `systematic_search` tool, delegates included; absent when `search.enabled` is false | supported | Grep `docs/solutions/` |
|
|
11
12
|
|
|
12
13
|
## Invocation examples
|
|
13
14
|
|