@selesai/code 0.5.19 → 0.5.21

package/dist/extensions/pi-subagents/package.json

@@ -1,10 +1,17 @@
 {
   "name": "pi-subagents",
-  "version": "0.33.1",
-  "description": "Pi extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification",
+  "version": "0.37.0",
+  "description": "Selesai extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification",
   "author": "Nico Bailon",
   "license": "MIT",
   "type": "module",
+  "exports": {
+    ".": "./index.ts",
+    "./background-work": "./src/api/background-work.ts",
+    "./delegation": "./src/api/delegation.ts",
+    "./capability-ceiling": "./src/api/capability-ceiling.ts",
+    "./preflight": "./src/api/preflight.ts"
+  },
   "repository": {
     "type": "git",
     "url": "git+https://github.com/nicobailon/pi-subagents.git"
@@ -16,17 +23,17 @@
   "keywords": [
     "pi-package",
     "pi",
-    "selesai",
-    "selesai-code",
     "subagents",
     "ai",
     "agents",
-    "cli"
+    "cli",
+    "selesai"
   ],
   "bin": {
     "pi-subagents": "install.mjs"
   },
   "files": [
+    "index.ts",
     "src/**/*.ts",
     "*.mjs",
     "agents/",
@@ -44,7 +51,7 @@
   },
   "pi": {
     "extensions": [
-      "./src/extension/index.ts"
+      "./index.ts"
     ],
     "skills": [
       "./skills"
@@ -58,8 +65,9 @@
   },
   "peerDependencies": {
     "@earendil-works/pi-agent-core": "*",
-    "@earendil-works/pi-ai": "*",
-    "@selesai/code": "*"
+    "@earendil-works/pi-ai": ">=0.80.0",
+    "@selesai/code": "*",
+    "@earendil-works/pi-tui": "*"
   },
   "peerDependenciesMeta": {
     "@earendil-works/pi-agent-core": {
@@ -70,16 +78,20 @@
     },
     "@selesai/code": {
       "optional": true
+    },
+    "@earendil-works/pi-tui": {
+      "optional": true
     }
   },
   "dependencies": {
-    "@earendil-works/pi-tui": "0.74.0",
     "jiti": "2.7.0",
-    "typebox": "1.1.24"
+    "typebox": "1.1.38",
+    "yaml": "2.8.3"
   },
   "devDependencies": {
-    "@earendil-works/pi-agent-core": "0.74.0",
-    "@earendil-works/pi-ai": "0.74.0",
-    "@selesai/code": "0.74.0"
+    "@earendil-works/pi-agent-core": "0.81.0",
+    "@earendil-works/pi-ai": "0.81.0",
+    "@selesai/code": "0.81.0",
+    "@earendil-works/pi-tui": "0.81.0"
   }
-}
+}

package/dist/extensions/pi-subagents/prompts/gather-context-and-clarify.md

@@ -4,7 +4,7 @@ description: Use subagents to gather context, then ask clarifying questions
 
 Based on our discussion and my intent, launch focused context-gathering subagents before planning or implementing.
 
-Use `scout` to inspect the relevant local files, existing patterns, constraints, tests, and likely integration points. Use `researcher` when external docs, recent sources, ecosystem context, or primary evidence would improve the answer.
+Use `explorer` to inspect the relevant local files, existing patterns, constraints, tests, and likely integration points. Use `researcher` when external docs, recent sources, ecosystem context, or primary evidence would improve the answer.
 
 Give each subagent a specific meta prompt. Ask them to return concise findings plus the remaining clarification questions that matter for implementation confidence.
 

package/dist/extensions/pi-subagents/prompts/parallel-cleanup.md

@@ -4,13 +4,13 @@ description: Parallel cleanup review
 
 Run a fresh-context parallel cleanup review of the current work.
 
-Use the `subagent` tool. First inspect available agents/skills if needed, then launch two reviewer subagents in parallel with `context: "fresh"`. Do not use forked context unless I explicitly ask for it. Reviewers must inspect the repository, relevant instructions, and current diff directly from files and commands. They must not rely on the main conversation history.
+Use the `subagent` tool. First inspect available agents/skills if needed, then launch two commentator subagents in parallel with `context: "fresh"`. Do not use forked context unless I explicitly ask for it. Reviewers must inspect the repository, relevant instructions, and current diff directly from files and commands. They must not rely on the main conversation history.
 
-Do not write reviewer output files into the repository unless I explicitly ask for artifacts. Prefer `output: false` for each reviewer task.
+Do not write commentator output files into the repository unless I explicitly ask for artifacts. Prefer `output: false` for each commentator task.
 
 Reviewer 1: deslop pass.
 
-If the `deslop` skill is available, pass it to this reviewer. If not, inline the guidance below. Ask this reviewer to look for AI-slop patterns in the changed scope:
+If the `deslop` skill is available, pass it to this commentator. If not, inline the guidance below. Ask this commentator to look for AI-slop patterns in the changed scope:
 - comments that restate code, placeholder text, stale rationale, or debug leftovers;
 - defensive checks that hide useful errors, return vague defaults, or validate trusted internal data after a real boundary was already crossed;
 - type escapes, broad casts, duplicated type definitions, or object-bag typing where a local source-of-truth type exists;
@@ -19,11 +19,11 @@ If the `deslop` skill is available, pass it to this reviewer. If not, inline the
 - pass-through wrappers, dead helpers, duplicate helper signatures, duplicated test harness setup, or abstractions that do not enforce an invariant;
 - UI or CLI copy that is noisy, vague, brittle, or makes the user do extra interpretation.
 
-Tell this reviewer to treat tool output and slop-scan-style findings as leads, not verdicts. It should flag only concrete issues in the requested scope with evidence, severity, file/line references, and the smallest safe fix.
+Tell this commentator to treat tool output and slop-scan-style findings as leads, not verdicts. It should flag only concrete issues in the requested scope with evidence, severity, file/line references, and the smallest safe fix.
 
 Reviewer 2: verbosity pass.
 
-If the `verbosity-cleaner` skill is available, pass it to this reviewer. If not, inline the guidance below. Ask this reviewer to look for needless verbosity in code, tests, docs, status text, grouped messages, receipts, and changelog wording:
+If the `verbosity-cleaner` skill is available, pass it to this commentator. If not, inline the guidance below. Ask this commentator to look for needless verbosity in code, tests, docs, status text, grouped messages, receipts, and changelog wording:
 - single-use helpers that merely paraphrase an expression;
 - temporary variables that only name obvious expressions;
 - nested returns or branches that can become direct returns without hiding intent;
@@ -33,16 +33,16 @@ If the `verbosity-cleaner` skill is available, pass it to this reviewer. If not,
 - regression tests where one focused assertion would cover the bug but wrapper/API-adjacent tests only repeat the same claim;
 - prose that says the same thing twice, sounds generic, or buries the important rule.
 
-Tell this reviewer that shorter is only better when it is clearer and preserves behavior, error signals, cleanup semantics, useful invariants, and local style.
+Tell this commentator that shorter is only better when it is clearer and preserves behavior, error signals, cleanup semantics, useful invariants, and local style.
 
-Both reviewers are review-only. They must not edit files unless I explicitly ask for a writer pass. Their response should be review feedback, not a context summary. Ask them to return concise, evidence-backed findings with file/line references and suggested fixes.
+Both commentators are review-only. They must not edit files unless I explicitly ask for a writer pass. Their response should be review feedback, not a context summary. Ask them to return concise, evidence-backed findings with file/line references and suggested fixes.
 
-While reviewers run, do your own narrow inspection if useful. After they return, synthesize the feedback into:
+While commentators run, do your own narrow inspection if useful. After they return, synthesize the feedback into:
 - fixes worth doing now;
 - optional improvements;
 - feedback to ignore or defer, with a short reason.
 
-Do not blindly apply every reviewer suggestion.
+Do not blindly apply every commentator suggestion.
 
 Autofix mode: if the invocation contains the exact word `autofix`, treat it as workflow control, not cleanup scope. Remove it before deciding the cleanup target. After synthesis, apply only fixes worth doing now, validate, and summarize. Do not apply optional improvements unless explicitly requested. If there are no fixes worth doing now, do not edit.
 

package/dist/extensions/pi-subagents/prompts/parallel-context-build.md

@@ -2,7 +2,7 @@
 description: Parallel context builders for planning handoff
 ---
 
-Launch fresh-context `context-builder` subagents in parallel to build grounded handoff context for planning or implementation.
+Launch fresh-context `explorer` subagents in parallel to build grounded handoff context for planning or implementation.
 
 Use the `subagent` tool in chain mode with a single parallel step, not top-level parallel tasks, so relative output files live under the temporary chain directory. Use `context: "fresh"` unless I explicitly ask for forked context. Give every parallel task a distinct `output` path, `label`, and `as` name, for example:
 
@@ -18,7 +18,7 @@ Treat the slash command arguments as the primary request, target, or focus:
 
 $@
 
-If the invocation provides a URL, issue link, file path, plan path, or freeform request, read or fetch that target before assigning builder angles, then pass the target explicitly into every `context-builder` task.
+If the invocation provides a URL, issue link, file path, plan path, or freeform request, read or fetch that target before assigning builder angles, then pass the target explicitly into every `explorer` task.
 
 Choose two or three strong builders based on the request. Prefer three only when the scope benefits from independent context slices. These are examples, not fixed defaults:
 
@@ -44,7 +44,7 @@ Ask each builder to produce a compact handoff file with:
 - constraints and invariants;
 - risks and unknowns;
 - validation commands or next-best checks;
-- a `meta-prompt` section for the next planner or role subagent.
+- a `meta-prompt` section for the next architect or role subagent.
 
 After the builders return, synthesize their outputs into:
 - the most important context the next agent needs;

package/dist/extensions/pi-subagents/prompts/parallel-handoff-plan.md

@@ -14,10 +14,10 @@ Use the `subagent` tool in chain mode:
 
 1. First step: a parallel group.
    - `researcher`, when the request includes external references, APIs, libraries, docs, current best practices, or prompt-guidance research.
-   - `context-builder` for local codebase context.
-   - Add a second `context-builder` only when the scope is large enough to benefit from a separate implementation-strategy pass.
+   - `explorer` for local codebase context.
+   - Add a second `explorer` only when the scope is large enough to benefit from a separate implementation-strategy pass.
 
-2. Second step: a synthesis `context-builder` that reads the parallel findings and writes the final handoff plan and meta-prompt.
+2. Second step: a synthesis `explorer` that reads the parallel findings and writes the final handoff plan and meta-prompt.
 
 Use distinct output paths, `label` values, and `as` names under the chain directory. Example outputs:
 - `handoff/external-reference.md`
@@ -37,20 +37,20 @@ External reference researcher:
 - Conduct web research if needed. Use `web_search` if it is available; otherwise use whatever equivalent research capability is available.
 - Return source links, repo paths, key evidence, risks, and what matters for this implementation.
 
-Local context-builder:
+Local explorer:
 - Read all files needed to fully understand the local issue, not just the first match.
 - Follow imports, callers, tests, fixtures, configuration, docs, and adjacent patterns until the local problem, solution space, and validation path are clear.
 - Return relevant file paths and line ranges, current architecture, constraints, tests, risks, and open questions.
 
-Implementation-strategy context-builder, when used:
+Implementation-strategy explorer, when used:
 - Compare the external evidence against the local architecture.
 - Propose the safest implementation shape, files likely to change, edge cases, validation commands, and decisions that need approval.
 - Stay review/planning-only unless I explicitly ask for implementation.
 
-Final synthesis context-builder:
+Final synthesis explorer:
 - Read the parallel outputs and produce one concise handoff plan.
 - Include what the feature/change should do, what the external reference teaches, what the local codebase implies, the recommended approach, likely files to change, constraints, non-goals, validation, risks, and unresolved questions.
-- End with a compact implementation-ready meta-prompt for the next worker/planner.
+- End with a compact implementation-ready meta-prompt for the next builder/architect.
 
 After the chain returns, synthesize the result for me with:
 - the recommended approach;

package/dist/extensions/pi-subagents/prompts/parallel-research.md

@@ -4,11 +4,11 @@ description: Parallel subagents research
 
 Launch parallel research subagents to build a grounded answer to the current question or decision.
 
-Use fresh context, not forked context, unless I explicitly ask for forked context. Researchers and scouts should inspect sources directly instead of relying on the main conversation history.
+Use fresh context, not forked context, unless I explicitly ask for forked context. Researchers and explorers should inspect sources directly instead of relying on the main conversation history.
 
-Use a combination of `researcher` and `scout` subagents:
+Use a combination of `researcher` and `explorer` subagents:
 - Use `researcher` for web, docs, standards, ecosystem, recent changes, benchmarks, and primary-source evidence.
-- Use `scout` for local codebase context, existing implementation patterns, repo constraints, and files that would be affected.
+- Use `explorer` for local codebase context, existing implementation patterns, repo constraints, and files that would be affected.
 
 Give each subagent a distinct angle. Unless I specify angles, use these three:
 
@@ -16,10 +16,10 @@ Give each subagent a distinct angle. Unless I specify angles, use these three:
    Use `researcher` to find current, authoritative sources: official docs, specs, release notes, benchmarks, issue threads, or primary explanations.
 
 2. Local code context
-   Use `scout` to inspect the repository for relevant files, existing patterns, constraints, tests, and likely integration points.
+   Use `explorer` to inspect the repository for relevant files, existing patterns, constraints, tests, and likely integration points.
 
 3. Practical tradeoffs
-   Use `researcher` or `scout`, whichever fits the question, to compare options, risks, edge cases, maintenance cost, and what would be easiest to validate.
+   Use `researcher` or `explorer`, whichever fits the question, to compare options, risks, edge cases, maintenance cost, and what would be easiest to validate.
 
 Adapt the angles when the question calls for it:
 - Library/API questions: include official docs and recent examples.
@@ -28,7 +28,7 @@ Adapt the angles when the question calls for it:
 - UI/product questions: include user flow, accessibility, design precedent, and implementation constraints.
 - Time-sensitive topics: include a recent-developments angle and prefer 2026/2025 sources.
 
-Prefer two or three strong subagents over many vague ones. The parent agent should frame the question and assign angles; the child agents should research or scout, not invent broad plans.
+Prefer two or three strong subagents over many vague ones. The parent agent should frame the question and assign angles; the child agents should research or explorer, not invent broad plans.
 
 Ask each subagent to return concise findings with evidence:
 - file paths and line ranges for local findings

package/dist/extensions/pi-subagents/prompts/parallel-review.md

@@ -2,11 +2,11 @@
 description: Parallel subagents review
 ---
 
-Launch parallel reviewers for an adversarial review of the current work.
+Launch parallel commentators for an adversarial review of the current work.
 
 Use fresh context, not forked context, unless I explicitly ask for forked context. Reviewers should inspect the repository, relevant instructions, and current diff directly from files and commands. Do not rely on the main conversation history.
 
-Give each reviewer a distinct angle. Generate the angles dynamically from the user's intent, the plan, the implemented code, and the current diff. If I specify angles, use mine. Otherwise, choose the highest-value review angles for this specific work.
+Give each commentator a distinct angle. Generate the angles dynamically from the user's intent, the plan, the implemented code, and the current diff. If I specify angles, use mine. Otherwise, choose the highest-value review angles for this specific work.
 
 These are examples, not fixed defaults:
 
@@ -24,18 +24,18 @@ Choose or adapt angles when the work calls for it:
 - UI-heavy changes: include UX, accessibility, copy, and visual quality.
 - Security-sensitive changes: include unsafe input/output handling, auth boundaries, privacy, and data exposure.
 - Docs-heavy changes: include clarity, accuracy, completeness, reader flow, and non-robotic prose.
-- Large multi-file changes: consider a fourth reviewer for structural friction, module boundaries, and testability.
+- Large multi-file changes: consider a fourth commentator for structural friction, module boundaries, and testability.
 
-Prefer three strong reviewers over many vague reviewers.
+Prefer three strong commentators over many vague commentators.
 
-Give every reviewer a specific task prompt naming its angle. Ask reviewers to return concise, evidence-backed findings with file/line references and suggested fixes. The response should be review feedback, not a context summary. Reviewers must not edit files unless I explicitly ask for a writer pass.
+Give every commentator a specific task prompt naming its angle. Ask commentators to return concise, evidence-backed findings with file/line references and suggested fixes. The response should be review feedback, not a context summary. Reviewers must not edit files unless I explicitly ask for a writer pass.
 
-While reviewers run, do your own narrow inspection if useful. After they return, synthesize the feedback into:
+While commentators run, do your own narrow inspection if useful. After they return, synthesize the feedback into:
 - fixes worth doing now
 - optional improvements
 - feedback to ignore or defer, with a short reason
 
-Do not blindly apply every reviewer suggestion.
+Do not blindly apply every commentator suggestion.
 
 Autofix mode: if the invocation contains the exact word `autofix`, treat it as workflow control, not review scope. Remove it before deciding the review target. After synthesis, apply only fixes worth doing now, validate, and summarize. Do not apply optional improvements unless explicitly requested. If there are no fixes worth doing now, do not edit.
 
@@ -51,4 +51,4 @@ Additional review target or focus from the slash command invocation:
 
 $@
 
-If the invocation provides a URL, issue link, file path, plan path, or freeform focus, treat it as the primary review scope. Read or fetch that target before assigning reviewer angles, and pass the target explicitly into each reviewer task.
+If the invocation provides a URL, issue link, file path, plan path, or freeform focus, treat it as the primary review scope. Read or fetch that target before assigning commentator angles, and pass the target explicitly into each commentator task.

package/dist/extensions/pi-subagents/prompts/review-loop.md

@@ -6,32 +6,34 @@ Run a parent-orchestrated review loop for the requested work.
 
 Use the `subagent` tool. Keep the parent session as the loop controller and final decision-maker. Child subagents must receive concrete role-specific tasks; they must not run subagents or manage the loop themselves unless the parent intentionally selected an explicit fanout agent whose builtin `tools` includes `subagent` for that assigned fanout.
 
-Default to a maximum of 3 review rounds unless I specify a different cap. Count a review round each time fresh-context reviewers inspect the current diff after a worker pass. Stop early when reviewers find no blockers or fixes worth doing now.
+Default to a maximum of 3 review rounds unless I specify a different cap. Count a review round each time fresh-context commentators inspect the current diff after a builder pass. Stop early when commentators find no blockers or fixes worth doing now.
 
-If the invocation includes an implementation request, first launch one async `worker` to implement the approved scope. If the current diff is already the target, start with review. The sequence can be launched up front as an async/background chain when the workflow is already clear, or continued as follow-up subagent runs after each async completion. For an initial chain, pass `async: true` so the main chat is unblocked; do not set `clarify: true` unless I explicitly want the foreground clarify UI. Use only one writer against the active worktree at a time unless I explicitly ask for isolated worktrees.
+If the invocation includes an implementation request, first launch one async `builder` to implement the approved scope. If the current diff is already the target, start with review. The sequence can be launched up front as an async/background chain when the workflow is already clear, or continued as follow-up subagent runs after each async completion. For an initial chain, pass `async: true` so the main chat is unblocked; do not set `clarify: true` unless I explicitly want the foreground clarify UI. Use only one writer against the active worktree at a time unless I explicitly ask for isolated worktrees.
 
-For each review round, launch fresh-context `reviewer` agents in parallel. Reviewers must inspect the repository, relevant instructions, and current diff directly from files and commands. They must not rely on the main conversation history and must not edit files.
+As a conservative orchestration policy, do not set `turnBudget` or a hard `toolBudget` on implementation or fix builders. A default tool budget blocks read/search tools rather than mutation tools, but count limits still do not measure delivery safety. Give each writer a narrow delivery slice and an outer elapsed deadline with enough margin. Before that deadline, request a checkpoint after the current tool returns with changed files, build/test state, remaining work, and commit or PR state. An elapsed timeout is not a mutation-safe boundary and must not be the checkpoint trigger.
 
-Choose review angles from the actual change. Common angles are correctness/regressions, tests/validation, and simplicity/maintainability. Add security, performance, docs/API contracts, or user-flow validation when the work calls for it. Prefer three strong reviewers over many vague reviewers.
+For each review round, launch fresh-context `commentator` agents in parallel. Reviewers must inspect the repository, relevant instructions, and current diff directly from files and commands. They must not rely on the main conversation history and must not edit files.
 
-After reviewers return, synthesize their feedback into:
+Choose review angles from the actual change. Common angles are correctness/regressions, tests/validation, and simplicity/maintainability. Add security, performance, docs/API contracts, or user-flow validation when the work calls for it. Prefer three strong commentators over many vague commentators.
+
+After commentators return, synthesize their feedback into:
 - blockers or scope/product/architecture decisions that need user approval;
 - fixes worth doing now;
 - optional improvements;
 - feedback to ignore or defer, with a short reason.
 
-Do not blindly apply every reviewer suggestion. If reviewers surface an unapproved product, scope, or architecture decision, pause and ask me before launching a fix worker.
+Do not blindly apply every commentator suggestion. If commentators surface an unapproved product, scope, or architecture decision, pause and ask me before launching a fix builder.
 
-When an async implementation worker completes, treat its handoff as the transition into review, not as final completion, unless I explicitly asked for worker-only work, review-only output, or to stop after implementation.
+When an async implementation builder completes, treat its handoff as the transition into review, not as final completion, unless I explicitly asked for builder-only work, review-only output, or to stop after implementation.
 
-When there are fixes worth doing now and the workflow is implementation-authorized, launch one async forked `worker` to apply only those synthesized fixes. Ask it to preserve the approved scope, run focused validation, and report changed files, commands run with exit codes, validation evidence, surprises, and anything left undone.
+When there are fixes worth doing now and the workflow is implementation-authorized, launch one async forked `builder` without hard turn or tool-call caps to apply only those synthesized fixes. Ask it to preserve the approved scope, run focused validation, and report changed files, commands run with exit codes, validation evidence, surprises, and anything left undone.
 
-After a fix worker returns, run another review round only when it made material changes or addressed non-trivial findings. Do not keep looping for optional polish, speculative improvements, or findings already deferred by the parent.
+After a fix builder returns, run another review round only when it made material changes or addressed non-trivial findings. Do not keep looping for optional polish, speculative improvements, or findings already deferred by the parent.
 
 Stop and summarize when one of these is true:
-- reviewers find no blockers or fixes worth doing now;
+- commentators find no blockers or fixes worth doing now;
 - remaining feedback is optional, speculative, or intentionally deferred;
-- reviewers surface an unapproved decision that needs me;
+- commentators surface an unapproved decision that needs me;
 - the max review-round cap is reached.
 
 On completion, inspect the final diff yourself, run or confirm focused validation where appropriate, and summarize the loop: rounds run, fixes applied, validation, remaining deferred items, and why the loop stopped.