@bastani/atomic 0.9.11-alpha.4 → 0.9.11-alpha.5

package/dist/builtin/workflows/src/extension/workflow-prompts.ts

@@ -12,12 +12,19 @@ export const WORKFLOW_TOOL_DESCRIPTION =
 
 export const DEFAULT_PROMPT_GUIDANCE: string[] = [
   `**Workflows**: Treat workflows as the default execution path for any non-trivial task and for any request that has inherent structure plus an objective you can make verifiable. Use the \`workflow\` tool for existing named workflows; when the task needs a graph that is not installed, author a custom TypeScript \`workflow({...})\` inline with normal coding tools, reload workflow resources, and run it.
-  - Decide the execution mode before your first tool call on a new request and state it in one short line: inline (tiny, deterministic, low-risk) or workflow. Reconnaissance counts as inline execution, so an unstated "explore first" default must not silently commit you to an unbounded inline session.
   - Workflow fit check: prefer a workflow for implementation, build, debug/diagnosis, bug-fix, migration, new-feature, scoped multi-file, or docs/code changes with validation; and whenever there are multiple steps, dependencies, handoffs, uncertainty, review/validation needs, long-running work, measurable done criteria, or an outcome that needs evidence.
   - Treat loop or stop-condition wording as a strong workflow signal, especially "do X until Y", "repeat until", "iterate until", "review/fix until passing", "run checks and fix until green", "keep going until done", or any prompt that names an approval gate or evidence requirement.
-  - Do not force-fit an installed workflow or builtin such as \`goal\` or \`ralph\`. When another graph better matches the task, write a task-specific TypeScript workflow inline. Use and combine the documented starter patterns: Classify-and-act for runtime routing, Fan-out-and-synthesize for independent slices, Adversarial verification for worker/reviewer/reducer repair, Generate-and-filter or Tournament for competing candidates, and Loop until done for bounded convergence. Rich custom workflows may use deterministic branching, dynamic fan-out, child workflows, artifacts, structured outputs, human-in-the-loop prompts, gates, retries, and explicit stop conditions.
-  - Compose workflows instead of rebuilding every capability in one graph. Workflow definitions are normal TypeScript modules: import reusable project/package definitions or builtins from \`@bastani/workflows/builtin\`, then call \`ctx.workflow(childDefinition, { inputs, stageName })\`. Imported children may nest more workflows up to \`maxDepth\`; their stages, HIL prompts, control, durability, and declared outputs remain part of the expanded parent graph. Pass definitions, not registry-name strings or paths.
-  - Composition examples: import \`deepResearchCodebase\`, then conditionally nest \`goal\` or \`ralph\` for implementation; wrap \`openClaudeDesign\` with project-specific approval/export stages; or build a reusable user-defined research child and import it into several parent workflows. Prefer composing a proven builtin or shared child over copying its prompt/graph.
+  - Do not force-fit an installed workflow or builtin such as \`goal\` or \`ralph\`. When another graph better matches the task, write a task-specific TypeScript workflow inline. Rich custom workflows may use deterministic branching, dynamic fan-out, child workflows, artifacts, structured outputs, human-in-the-loop prompts, gates, retries, and explicit stop conditions.
+  - Before launching any workflow for a non-trivial task, perform a short workflow-architecture pass. Derive implementation lifecycle needs, whole-codebase research needs, independent slices, competing strategies, exact API/type/build contracts, schema or generated-artifact contracts, state transitions/lifecycle behavior, deterministic stop conditions, and required evidence. Use a compact internal coverage matrix: \`requirement/risk | required evidence | workflow/stage that produces it | gap\`. Unresolved material rows must change graph selection.
+  - Compare candidate workflows by guarantees, not broad objectives: run one named workflow only when it covers the lifecycle and produces evidence for every material requirement/risk. A generic implementation workflow may cover the lifecycle without covering exact API/type/build contracts, schemas/generated artifacts, state transitions, or domain-specific gates. Do not treat "has reviewers" as proof that a task-specific risk is covered.
+  - Use these routing signals without adding decorative stages: broad repository uncertainty → \`deep-research-codebase\`; independent slices → Fan-out-and-synthesize; plausible-but-wrong contract risk → Adversarial verification or a task-specific verification stage; competing architectures or implementations → Generate-and-filter or Tournament; an explicit repeat-until condition → Loop until done; implementation lifecycle → \`goal\` or \`ralph\`, potentially as a child; exact API/build/schema requirements → dedicated deterministic gates.
+  - A first named workflow launch commits the execution shape for the turn, after which the parent ends its turn. Do not plan to chain unrelated top-level workflow launches afterward. When multiple capabilities are needed, design one custom parent before launch, import reusable project/package definitions or builtins from \`@bastani/workflows/builtin\`, and compose them with \`ctx.workflow(childDefinition, { inputs, stageName })\`. Imported children may nest more workflows up to \`maxDepth\`; their stages, HIL prompts, control, durability, and declared outputs remain part of the expanded parent graph. Pass definitions, not registry-name strings or paths.
+  - Workflow definitions are normal TypeScript modules. Composition examples: import \`deepResearchCodebase\`, then conditionally nest \`goal\` or \`ralph\` for implementation; wrap \`openClaudeDesign\` with project-specific approval/export stages; or build a reusable user-defined research child and import it into several parent workflows. Map typed inputs and consume only declared outputs.
+  - When plausible-but-wrong behavior is a material risk in an arbitrary task-specific workflow, prefer a bounded evidence-backed adversarial loop. Give a fresh-context grumpy/skeptical-but-fair reviewer the literal objective and require actionable, evidence-backed falsification probes without invented requirements. Have it emit a structured verifier plan containing each exact probe, inputs, command/assertion, expected success condition, and requirement/risk covered.
+  - Support both verifier shapes: for explicit known contracts, author direct task-specific \`ctx.tool(...)\` gates before launch; for risks requiring adversarial discovery, let the model select high-value probes through structured output, then execute the selected compile, test, schema generation/validation, runtime, or artifact-inspection checks authoritatively through durable \`ctx.tool(...)\` calls. Actual tool results—not model self-report—must feed skeptical evaluation, consolidated evidence-backed repair findings, and reruns after the implementation child repairs them.
+  - Define bounded pass, repair, failure, and iteration-limit conditions before launch. Use \`ctx.tool\` for workflow-owned external checks and side effects that benefit from durable checkpointing; keep pure transformations as ordinary TypeScript, and do not wrap every model-stage action in a tool call.
+  - Choose the cheapest graph that covers every material coverage row. Avoid decorative composition and duplicated research or review loops. Prefer composing a proven builtin or shared child over copying its prompt/graph.
+  - Before the first launch, state the selected graph, why one broad builtin is sufficient or insufficient, the evidence each major stage produces, and the stop/repair conditions. A simple direct match may use one sentence; a composed graph must briefly name its children and task-specific gates. For a custom adversarial loop, also name the skeptical reviewer, deterministic \`ctx.tool\` verifier gates, how model-selected plans become tool executions, and how failures reach bounded repair.
   - Example custom shapes: classify a request and dispatch category-specific stages; fan out per package and synthesize artifact-backed results; implement, run fresh-context verifiers, reduce findings, and loop through repairs until approved; generate several plans and filter or tournament-rank them; or rerun checks and fixes until green with a progress ledger and max-iteration escape hatch.
   - Budget reconnaissance: once workflow fit is clear, keep pre-workflow exploration to a few quick reads that sharpen the objective and validation criteria. Put deep research, upstream/design comparison, and behavior probing inside the workflow. Pass large context through files/artifacts and \`reads\` rather than injecting it into prompts.
   - Course-correct instead of drifting: after roughly ten exploratory tool calls with no artifact, edit, or commit, or repeated "let me verify one more thing" loops, stop, write findings to a context file, and hand the task to the best-fit named or custom workflow. Sunk inline research transfers through files; it is not a reason to stay inline.

package/dist/core/atomic-guide-command.js

@@ -33,7 +33,7 @@ Atomic turns non-trivial work into executable, inspectable workflows. Default to
 | Workflow | When to use | How to run |
 |---|---|---|
 | \`deep-research-codebase\` | broad repo or cross-cutting research before you decide what to change (for one area, use \`/skill:research-codebase\`; this indexes the whole repo) | \`/workflow deep-research-codebase prompt="How do payment retries work end to end?"\` |
-| \`goal\` | autonomous work that benefits from a durable goal ledger, bounded worker turns, named validation, and reviewer-gated completion; add \`create_pr=true\` only for final PR handoff after approval | \`/workflow goal objective="Implement specs/<date>-<topic>.md, run focused tests, and validate the changed behavior"\` |
+| \`goal\` | autonomous work that benefits from a durable goal ledger, bounded sub-agent orchestration turns, named validation, and reviewer-gated completion; add \`create_pr=true\` only for final PR handoff after approval | \`/workflow goal objective="Implement specs/<date>-<topic>.md, run focused tests, and validate the changed behavior"\` |
 | \`ralph\` | autonomous work that benefits from a durable research-first pipeline, delegated implementation, and iterative review | \`/workflow ralph prompt="Migrate the database layer to Drizzle" create_pr=true\` |
 | \`open-claude-design\` | UI and design-system work that benefits from generation and refinement loops | \`/workflow open-claude-design prompt="Refresh the settings page hierarchy"\` |
 
@@ -100,7 +100,7 @@ Skip this if the implementation request is already precise.
 
 Default to a workflow for non-trivial implementation and review. Use direct chat only for tiny deterministic low-risk edits; use focused subagents inside workflow stages or for bounded specialist passes. Choose an installed workflow when it fits, or author a custom TypeScript workflow inline from the starter patterns when the task needs a richer graph.
 
-For work that fits a durable goal ledger, bounded worker turns, and reviewer-gated completion, use \`goal\`:
+For work that fits a durable goal ledger, bounded sub-agent orchestration turns, and reviewer-gated completion, use \`goal\`:
 
 \`/workflow goal objective="Implement specs/<date>-<topic>.md, run focused tests, and finish when the documented behavior is validated"\`
 
@@ -145,7 +145,7 @@ Workflow-first is not builtin-only or monolithic. Atomic can author custom TypeS
 | Workflow | When to use | How to run |
 |---|---|---|
 | \`deep-research-codebase\` | broad repo or cross-cutting research before you decide what to change (for one area, use \`/skill:research-codebase\`; this indexes the whole repo) | \`/workflow deep-research-codebase prompt="How do payment retries work end to end?"\` |
-| \`goal\` | autonomous work that benefits from a durable goal ledger, bounded worker turns, named validation, and reviewer-gated completion; add \`create_pr=true\` only for final PR handoff after approval | \`/workflow goal objective="Update the CLI docs, include one usage example, and verify the docs build passes"\` |
+| \`goal\` | autonomous work that benefits from a durable goal ledger, bounded sub-agent orchestration turns, named validation, and reviewer-gated completion; add \`create_pr=true\` only for final PR handoff after approval | \`/workflow goal objective="Update the CLI docs, include one usage example, and verify the docs build passes"\` |
 | \`ralph\` | autonomous work that benefits from a durable research-first pipeline, delegated implementation, and iterative review | \`/workflow ralph prompt="Migrate the database layer to Drizzle" create_pr=true\` |
 | \`open-claude-design\` | frontend and product design work | \`/workflow open-claude-design prompt="Refresh the settings page hierarchy"\` |
 

package/dist/core/atomic-guide-command.js.map

@@ -1 +1 @@
-{"version":3,"file":"atomic-guide-command.js","sourceRoot":"","sources":["../../src/core/atomic-guide-command.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,IAAI,MAAM,WAAW,CAAC;AAElC,OAAO,EAAE,gBAAgB,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AAEzE,MAAM,CAAC,MAAM,yBAAyB,GAAG,QAAQ,CAAC;AAClD,MAAM,CAAC,MAAM,gCAAgC,GAC3C,kCAAkC,CAAC;AAErC,MAAM,QAAQ,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;oDAqEmC,CAAC;AAErD,MAAM,OAAO,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;qCA2DqB,CAAC;AAEtC,MAAM,SAAS,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;qCAuFmB,CAAC;AAEtC,MAAM,cAAc,GAAG;IACrB;QACE,IAAI,EAAE,UAAU;QAChB,OAAO,EAAE,EAAE;QACX,KAAK,EAAE,UAAU;QACjB,WAAW,EAAE,oBAAoB;QACjC,MAAM,EAAE,GAAG,EAAE,CAAC,QAAQ;KACvB;IACD;QACE,IAAI,EAAE,WAAW;QACjB,OAAO,EAAE,CAAC,UAAU,CAAC;QACrB,KAAK,EAAE,WAAW;QAClB,WAAW,EAAE,iBAAiB;QAC9B,MAAM,EAAE,GAAG,EAAE,CAAC,SAAS;KACxB;IACD;QACE,IAAI,EAAE,SAAS;QACf,OAAO,EAAE,CAAC,UAAU,CAAC;QACrB,KAAK,EAAE,SAAS;QAChB,WAAW,EAAE,0BAA0B;QACvC,MAAM,EAAE,GAAG,EAAE,CAAC,OAAO;KACtB;IACD;QACE,IAAI,EAAE,WAAW;QACjB,OAAO,EAAE,CAAC,YAAY,EAAE,WAAW,EAAE,MAAM,EAAE,SAAS,EAAE,WAAW,CAAC;QACpE,KAAK,EAAE,YAAY;QACnB,WAAW,EAAE,sBAAsB;QACnC,MAAM,EAAE,yBAAyB;KAClC;CAOA,CAAC;AASJ,MAAM,CAAC,MAAM,yBAAyB,GACpC,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;AAEjD,MAAM,sBAAsB,GAAG,IAAI,GAAG,CAGpC,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC;AAC5D,MAAM,uBAAuB,GAAG,IAAI,GAAG,CACrC,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC,CAC1D,CAAC;AACF,MAAM,uBAAuB,GAAG,IAAI,GAAG,CACrC,cAAc,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CACjC,CAAC,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC,KAAK,EAAE,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC,GAAG,CACnD,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,OAAO,CAAU,CACrC,CACF,CACF,CAAC;AAEF,MAAM,UAAU,uBAAuB,CACrC,MAAc;IAEd,OAAO,uBAAuB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED,MAAM,iCAAiC,GAAG,QAAQ,CAAC;AAEnD,SAAS,mCAAmC,CAAC,KAAa;IACxD,IAAI,GAAG,GAAG,KAAK,CAAC,MAAM,CAAC;IACvB,OACE,GAAG,GAAG,CAAC;QACP,iCAAiC,CAAC,QAAQ,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,EACjE,CAAC;QACD,GAAG,EAAE,CAAC;IACR,CAAC;IACD,OAAO,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;AAC7B,CAAC;AAED,SAAS,wBAAwB,CAC/B,MAAc;IAEd,OAAO,uBAAuB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED,SAAS,sBAAsB,CAC7B,IAA4B;IAE5B,MAAM,OAAO,GAAG,sBAAsB,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;IACjD,IAAI,CAAC,OAAO;QAAE,MAAM,IAAI,KAAK,CAAC,iCAAiC,IAAI,EAAE,CAAC,CAAC;IACvE,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,sBAAsB;IAC7B,MAAM,WAAW,GAAG,cAAc,CAAC,GAAG,CACpC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,OAAO,CAAC,KAAK,sBAAsB,OAAO,CAAC,KAAK,IAAI,CACzE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACb,OAAO,yCAAyC,WAAW,EAAE,CAAC;AAChE,CAAC;AAED,MAAM,UAAU,wBAAwB,CAAC,IAAY;IACnD,MAAM,UAAU,GAAG,mCAAmC,CACpD,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAC1B,CAAC;IACF,IAAI,CAAC,UAAU;QAAE,OAAO,MAAM,CAAC;IAE/B,OAAO,uBAAuB,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,IAAI,IAAI,MAAM,CAAC;AACjE,CAAC;AAED,MAAM,UAAU,iCAAiC,CAC/C,MAAc;IAEd,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;IAC1C,MAAM,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;QAC7C,KAAK,EAAE,OAAO,CAAC,KAAK;QACpB,KAAK,EAAE,OAAO,CAAC,KAAK;QACpB,WAAW,EAAE,OAAO,CAAC,WAAW;KACjC,CAAC,CAAC,CAAC;IACJ,MAAM,QAAQ,GAAG,KAAK;QACpB,CAAC,CAAC,KAAK,CAAC,MAAM,CACV,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,CACvE;QACH,CAAC,CAAC,KAAK,CAAC;IACV,OAAO,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC;AAC/C,CAAC;AAED,SAAS,yBAAyB,CAAC,GAAW;IAC5C,MAAM,aAAa,GAAG,gBAAgB,EAAE,CAAC;IACzC,MAAM,cAAc,GAAG,cAAc,CAAC,aAAa,CAAC;SACjD,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,UAAU,KAAK,IAAI,CAAC;SAC5C,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC;SACX,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC;SACpC,MAAM,CAAC,OAAO,CAAC,CAAC;IAEnB,IAAI,cAAc,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAChC,OAAO,sSAAsS,CAAC;IAChT,CAAC;IAED,MAAM,YAAY,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,EAAE,aAAa,CAAC,IAAI,aAAa,CAAC;IACxE,OAAO,mBAAmB,cAAc,CAAC,IAAI,CAAC,MAAM,CAAC,iBAAiB,YAAY,yLAAyL,CAAC;AAC9Q,CAAC;AAED,MAAM,UAAU,qBAAqB,CACnC,IAAqB,EACrB,GAAW;IAEX,IAAI,IAAI,KAAK,MAAM;QAAE,OAAO,sBAAsB,EAAE,CAAC;IACrD,OAAO,sBAAsB,CAAC,IAAI,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;AAClD,CAAC;AAED,MAAM,UAAU,wBAAwB,CACtC,MAA6B;IAE7B,OAAO,wBAAwB,CAAC,MAAM,CAAC,EAAE,IAAI,IAAI,MAAM,CAAC;AAC1D,CAAC","sourcesContent":["import * as path from \"node:path\";\nimport type { AutocompleteItem } from \"@earendil-works/pi-tui\";\nimport { getChangelogPath, parseChangelog } from \"../utils/changelog.ts\";\n\nexport const ATOMIC_GUIDE_COMMAND_NAME = \"atomic\";\nexport const ATOMIC_GUIDE_COMMAND_DESCRIPTION =\n  \"Atomic onboarding and help guide\";\n\nconst OVERVIEW = `# Atomic overview\n\nAtomic turns non-trivial work into executable, inspectable workflows. Default to a workflow for implementation, build, debugging, bug fixes, migrations, features, scoped multi-file changes, and validated docs/code work, or whenever a request has dependencies, handoffs, uncertainty, review gates, measurable done criteria, or evidence requirements. Use direct chat for tiny deterministic low-risk answers or edits. Loop-shaped prompts such as \\`do X until Y\\`, \\`review/fix until passing\\`, or \\`run checks and fix until green\\` are especially strong workflow signals. Workflow-first is not builtin-only or monolithic: use named workflows, direct modes, author a custom TypeScript \\`workflow({...})\\` inline, or import reusable project/package and builtin definitions from \\`@bastani/workflows/builtin\\` and nest them with \\`ctx.workflow(...)\\`. Nested children may compose further children within \\`maxDepth\\`, enabling powerful research → implementation → verification → approval graphs from reusable parts. Start Atomic in a project with \\`atomic\\`, then talk to it normally. Use \\`@file\\` to attach files, \\`!command\\` to run shell output through the model, and \\`!!command\\` to run shell output without adding it to context.\n\n## Core session commands\n\n| Command | Use |\n|---|---|\n| \\`/login\\` | configure auth |\n| \\`/model\\` | switch model |\n| \\`/settings\\` | thinking level, theme, message delivery, transport |\n| \\`/new\\`, \\`/resume\\` | start or resume sessions |\n| \\`/tree\\`, \\`/fork\\`, \\`/clone\\` | branch or navigate session history |\n| \\`/compact\\` | delete safe older context verbatim |\n| \\`/hotkeys\\`, \\`/changelog\\` | local help and release notes |\n\n## Examples of using Atomic\n\n| Goal | How to use |\n|---|---|\n| On-call / broken behavior | Use a focused workflow to reproduce, diagnose, repair, and validate; direct debugger/subagent calls remain useful as stages or for tiny deterministic diagnosis |\n| Research → spec → implementation | Chain \\`/skill:research-codebase\\` → \\`/skill:create-spec\\` → a named or custom implementation workflow with explicit validation and review |\n| Testing / regression hardening | Use a workflow for test/fix loops so retries, evidence, and the passing stop condition are tracked |\n| Large repo discovery | Run \\`/parallel codebase-locator \"map the area\" -> codebase-analyzer \"trace the current flow\" -> codebase-pattern-finder \"find patterns\" --bg\\`, or \\`/workflow deep-research-codebase\\` for whole-repo synthesis |\n| UI / product polish | Run \\`/skill:impeccable\\` for interface critique and refinement, or \\`/workflow open-claude-design\\` for generation + refinement loops |\n\n## Built-in workflows\n\n| Workflow | When to use | How to run |\n|---|---|---|\n| \\`deep-research-codebase\\` | broad repo or cross-cutting research before you decide what to change (for one area, use \\`/skill:research-codebase\\`; this indexes the whole repo) | \\`/workflow deep-research-codebase prompt=\"How do payment retries work end to end?\"\\` |\n| \\`goal\\` | autonomous work that benefits from a durable goal ledger, bounded worker turns, named validation, and reviewer-gated completion; add \\`create_pr=true\\` only for final PR handoff after approval | \\`/workflow goal objective=\"Implement specs/<date>-<topic>.md, run focused tests, and validate the changed behavior\"\\` |\n| \\`ralph\\` | autonomous work that benefits from a durable research-first pipeline, delegated implementation, and iterative review | \\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\" create_pr=true\\` |\n| \\`open-claude-design\\` | UI and design-system work that benefits from generation and refinement loops | \\`/workflow open-claude-design prompt=\"Refresh the settings page hierarchy\"\\` |\n\nUse \\`/workflow list\\` to see what is available and \\`/workflow inputs <name>\\` to inspect inputs in your environment.\n\n## Top skills\n\n| Skill | When to use | How to run |\n|---|---|---|\n| \\`research-codebase\\` | write a grounded research artifact for one subsystem or question | \\`/skill:research-codebase how the rate limiter works in src/middleware/\\` |\n| \\`create-spec\\` | turn research into an implementation-ready plan | \\`/skill:create-spec from research/docs/<date>-<topic>.md\\` |\n| \\`tdd\\` | do test-first feature or bug work | \\`/skill:tdd\\` |\n| \\`prompt-engineer\\` | tighten a vague prompt before a long run | \\`/skill:prompt-engineer Draft a sharper implementation prompt for ...\\` |\n| \\`subagent\\` | learn delegation patterns and exact \\`/run\\`, \\`/parallel\\`, and \\`/chain\\` usage | \\`/skill:subagent\\` |\n| \\`impeccable\\` | critique or refine frontend and product UI | \\`/skill:impeccable\\` |\n\n## Subagents\n\nSubagents are focused child Atomic sessions you can point at one job inside the repo.\n\n| Built-in subagent | Use |\n|---|---|\n| \\`codebase-locator\\` | find relevant files, tests, entrypoints, and configs |\n| \\`codebase-analyzer\\` | explain current behavior with file:line refs |\n| \\`codebase-pattern-finder\\` | find existing code to model after |\n| \\`debugger\\` | reproduce, diagnose, and fix broken behavior |\n\nHow the direct commands map to repo work:\n- \\`/run\\` = one specialist on one job, for example \\`/run codebase-locator \"Map the webhook retry flow\"\\`\n- \\`/parallel\\` = several independent specialists at once, for example \\`/parallel codebase-locator \"map retry files\" -> codebase-pattern-finder \"find existing retry/backoff patterns\" -> codebase-online-researcher \"research current retry guidance\" --bg\\`\n- \\`/chain\\` = ordered handoffs, for example \\`/chain codebase-locator \"find the auth files\" -> codebase-analyzer \"trace the auth flow\" -> debugger \"patch the failing auth edge case\"\\`\n\n─────────────────────────────────────────────────────────────────\n\nWhere to next:\n\n\\`/atomic example\\` — see the pieces used on a code task\n\\`/atomic workflows\\` — learn when to use workflows`;\n\nconst EXAMPLE = `# Practical example\n\nThis example shows a spec-driven development process whose clearly delegated autonomous implementation benefits from durable workflow execution. For interactive or conversation-led work, stay inline or use bounded subagents while the parent remains in control. Type the examples below into the Atomic TUI chat after starting \\`atomic\\` in your project.\n\n## 1. Research what exists\n\nUse \\`/skill:research-codebase\\` for a scoped area, subsystem, or directory:\n\n\\`/skill:research-codebase how the rate limiter works in src/middleware/\\`\n\nUse \\`deep-research-codebase\\` when the answer spans the whole repo or a cross-cutting implementation path:\n\n\\`/workflow deep-research-codebase prompt=\"How do payment retries work end to end?\"\\`\n\nIf the research prompt is vague, tighten it first with \\`/skill:prompt-engineer\\`:\n\n\\`/skill:prompt-engineer Draft a sharper repo-research prompt for understanding payment retries end to end, including retries, queues, and failure handling.\\`\n\n## 2. Create a spec when requirements are fuzzy\n\nSkip this if the implementation request is already precise.\n\n\\`/skill:create-spec from research/docs/<date>-<topic>.md\\`\n\n## 3. Implement with review built in\n\nDefault to a workflow for non-trivial implementation and review. Use direct chat only for tiny deterministic low-risk edits; use focused subagents inside workflow stages or for bounded specialist passes. Choose an installed workflow when it fits, or author a custom TypeScript workflow inline from the starter patterns when the task needs a richer graph.\n\nFor work that fits a durable goal ledger, bounded worker turns, and reviewer-gated completion, use \\`goal\\`:\n\n\\`/workflow goal objective=\"Implement specs/<date>-<topic>.md, run focused tests, and finish when the documented behavior is validated\"\\`\n\nLoop or stop-condition phrasing is a key workflow signal. When the user delegates a loop such as \\`do X until Y\\`, \\`repeat until\\`, \\`iterate until\\`, \\`review/fix until passing\\`, \\`run checks and fix until green\\`, or \\`keep going until done\\`, make the stop condition explicit in the Goal objective:\n\n\\`/workflow goal objective=\"Fix the flaky checkout test, adjust the smallest necessary code, and finish when the focused test passes three times\"\\`\n\nWhen a clearly delegated autonomous job benefits from a durable research-first pipeline with orchestration and iterative review, use \\`ralph\\`:\n\n\\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\"\\`\n\nAdd \\`create_pr=true\\` only when you want the final pull-request stage and report after the review gate approves.\n\n## 4. Decide and land\n\nIf you used \\`goal\\`, the workflow already persisted receipts in a goal ledger and reviewer-gated completion. Use its final status — \\`complete\\`, \\`blocked\\`, or \\`needs_human\\` — plus the remaining-work report to decide whether to ship, unblock, or clarify. If you enabled \\`create_pr=true\\`, use its final pull-request report to decide whether to ship or iterate again.\n\nIf you used \\`ralph\\`, the workflow transformed the prompt into a research question, researched the codebase, delegated implementation through sub-agents, reviewed, and iterated. If you enabled \\`create_pr=true\\`, use its final pull-request report to decide whether to ship or iterate again.\n\nIf you implemented directly instead of using a workflow, you can still run:\n\n\\`/parallel-review current diff\\`\n\nAtomic will synthesize reviewer feedback and ask before applying fixes.\n\n─────────────────────────────────────────────────────────────────\n\nWhere to next:\n\n\\`/atomic workflows\\` — learn when to use workflows\n\\`/atomic overview\\` — quick refresh`;\n\nconst WORKFLOWS = `# Workflows primer\n\nA workflow is a TypeScript-defined pipeline exported from \\`workflow({...})\\`. It can run tasks, chains, parallel fan-out, human-in-the-loop prompts, background status, and model fallback chains.\n\nDefault to workflows for non-trivial work and requests with inherent structure plus a verifiable objective. Implementation, debugging, migrations, multi-file changes, validation, review, evidence requirements, and explicit stop conditions are workflow-shaped; use direct chat only for tiny deterministic low-risk answers or edits.\n\nWorkflow-first is not builtin-only or monolithic. Atomic can author custom TypeScript \\`workflow({...})\\` definitions inline, and workflows can import reusable project/package definitions or builtins from \\`@bastani/workflows/builtin\\`, then nest them with \\`ctx.workflow(...)\\`. Imported children can nest further children within \\`maxDepth\\`, so compose proven research, implementation, design, verification, and approval workflows instead of copying their stages. Use the documented starter patterns for classify-and-act routing, dynamic fan-out and synthesis, adversarial verification, candidate selection, and bounded convergence. Atomic writes the parent definition, reloads it, and runs the composed graph.\n\n## Built-in workflows\n\n| Workflow | When to use | How to run |\n|---|---|---|\n| \\`deep-research-codebase\\` | broad repo or cross-cutting research before you decide what to change (for one area, use \\`/skill:research-codebase\\`; this indexes the whole repo) | \\`/workflow deep-research-codebase prompt=\"How do payment retries work end to end?\"\\` |\n| \\`goal\\` | autonomous work that benefits from a durable goal ledger, bounded worker turns, named validation, and reviewer-gated completion; add \\`create_pr=true\\` only for final PR handoff after approval | \\`/workflow goal objective=\"Update the CLI docs, include one usage example, and verify the docs build passes\"\\` |\n| \\`ralph\\` | autonomous work that benefits from a durable research-first pipeline, delegated implementation, and iterative review | \\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\" create_pr=true\\` |\n| \\`open-claude-design\\` | frontend and product design work | \\`/workflow open-claude-design prompt=\"Refresh the settings page hierarchy\"\\` |\n\nUse \\`/workflow inputs <name>\\` to inspect the exact inputs in your environment.\n\nUse \\`/skill:research-codebase ...\\` when you want research on one subsystem, directory, or focused question. Use \\`/workflow deep-research-codebase ...\\` when the answer needs end-to-end tracing across many parts of the repo.\n\nIf you are drafting research, reviewer, or synthesis prompts for a workflow, use \\`/skill:prompt-engineer\\` first. It is a good fit when a stage prompt feels vague, overloaded, or underspecified.\n\n## What good workflow authoring looks like\n\nA good workflow request is explicit about stage purpose, model choice, handoff, and the decision each step must return.\n\nFor workflow-owned side effects such as filesystem writes, network mutations, and external API actions, prefer \\`ctx.tool(name, args, fn)\\`: completed calls are durably cached, so resume returns the saved result without rerunning \\`fn\\`. Keep pure computation as ordinary TypeScript, and do not wrap agent-stage internals or every function call indiscriminately.\n\nExample: ask Atomic in chat with something like this:\n\n~~~text\nCreate a reusable workflow called review-changes.\n\nIt should accept one required text input called target for a diff, PR summary, or review target.\n\nRun two independent review stages in parallel with fresh context:\n- one reviewer focused on correctness, regressions, and missing tests using openai-codex/gpt-5.5 at xhigh thinking\n- one reviewer focused on edge cases, maintainability, and hidden risks using anthropic/claude-opus-4-8 at xhigh thinking\n\nThen add an aggregate stage that consolidates both reviews, deduplicates overlap, keeps only evidence-backed issues, and separates blockers from optional suggestions using openai/gpt-5.5 at high thinking.\n\nFinally add an adjudicate stage using anthropic/claude-sonnet-4 at high thinking that decides what to fix now, what to defer, and what to reject. Return a short action list with rationale.\n\nThe workflow should return structured output with consolidated_review and decision fields.\n~~~\n\nWhy this is good:\n- it names the workflow and required input\n- it specifies which stages are parallel vs sequential\n- each stage has one job\n- it defines the handoff and final outputs\n- it calls out model choice and thinking level where that matters\n\n## Run and inspect\n\n\\`/workflow list\\`\n\n\\`/workflow inputs goal\\`\n\n\\`/workflow goal objective=\"Fix the settings form validation bug, add the focused test, and finish when invalid emails show the inline error without submitting\"\\`\n\n\\`/workflow inputs ralph\\`\n\n\\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\" create_pr=true\\`\n\n\\`/workflow status\\`\n\n\\`/workflow connect <run-id>\\`\n\n\\`/workflow interrupt <run-id>\\`\n\n\\`/workflow quit <run-id>\\`\n\n\\`/workflow resume <run-id>\\`\n\nWorkflows run as background tasks. Use F2 or \\`/workflow connect <run-id>\\` for the graph viewer. Human-in-the-loop prompts appear there, not as chat modals, and awaiting-input states do not wake the main chat agent. Completion and failure notices are steered back into the main chat; answers submitted in the workflow UI interrupt stale main-chat questions so the model does not ask again.\n\n## Author your own\n\nDescribe your workflow in plain chat — say what you want the workflow to accomplish, what inputs it should accept, what stages should run, and what final output or decision it should return. Atomic will use the workflow docs to scaffold a reusable definition under \\`.atomic/workflows/\\`, ask clarifying questions when stage purpose, models, or handoffs are ambiguous, and run \\`/workflow reload\\` so you can launch it immediately.\n\n─────────────────────────────────────────────────────────────────\n\nWhere to next:\n\n\\`/atomic example\\` — see workflows in a normal task flow\n\\`/atomic overview\\` — quick refresh`;\n\nconst GUIDE_SECTIONS = [\n  {\n    name: \"overview\",\n    aliases: [],\n    label: \"overview\",\n    description: \"30-second overview\",\n    render: () => OVERVIEW,\n  },\n  {\n    name: \"workflows\",\n    aliases: [\"workflow\"],\n    label: \"workflows\",\n    description: \"Workflow primer\",\n    render: () => WORKFLOWS,\n  },\n  {\n    name: \"example\",\n    aliases: [\"examples\"],\n    label: \"example\",\n    description: \"Practical first workflow\",\n    render: () => EXAMPLE,\n  },\n  {\n    name: \"whats-new\",\n    aliases: [\"what's new\", \"whats new\", \"news\", \"updates\", \"changelog\"],\n    label: \"what's new\",\n    description: \"Recent release notes\",\n    render: readLatestStableChangelog,\n  },\n] as const satisfies readonly {\n  readonly name: string;\n  readonly aliases: readonly string[];\n  readonly label: string;\n  readonly description: string;\n  readonly render: (cwd: string) => string;\n}[];\n\ntype AtomicGuideSection = (typeof GUIDE_SECTIONS)[number];\ntype AtomicGuideSectionName = AtomicGuideSection[\"name\"];\n\nexport type AtomicGuideHelpChoice = AtomicGuideSection[\"label\"];\n\nexport type AtomicGuideMode = \"help\" | AtomicGuideSectionName;\n\nexport const ATOMIC_GUIDE_HELP_CHOICES: readonly AtomicGuideHelpChoice[] =\n  GUIDE_SECTIONS.map((section) => section.label);\n\nconst GUIDE_SECTIONS_BY_NAME = new Map<\n  AtomicGuideSectionName,\n  AtomicGuideSection\n>(GUIDE_SECTIONS.map((section) => [section.name, section]));\nconst GUIDE_SECTIONS_BY_LABEL = new Map<string, AtomicGuideSection>(\n  GUIDE_SECTIONS.map((section) => [section.label, section]),\n);\nconst GUIDE_SECTIONS_BY_INPUT = new Map<string, AtomicGuideSection>(\n  GUIDE_SECTIONS.flatMap((section) =>\n    [section.name, section.label, ...section.aliases].map(\n      (input) => [input, section] as const,\n    ),\n  ),\n);\n\nexport function isAtomicGuideHelpChoice(\n  choice: string,\n): choice is AtomicGuideHelpChoice {\n  return GUIDE_SECTIONS_BY_LABEL.has(choice);\n}\n\nconst ATOMIC_GUIDE_TRAILING_PUNCTUATION = \"?!.,;:\";\n\nfunction stripTrailingAtomicGuidePunctuation(value: string): string {\n  let end = value.length;\n  while (\n    end > 0 &&\n    ATOMIC_GUIDE_TRAILING_PUNCTUATION.includes(value.charAt(end - 1))\n  ) {\n    end--;\n  }\n  return value.slice(0, end);\n}\n\nfunction getGuideSectionForChoice(\n  choice: string,\n): AtomicGuideSection | undefined {\n  return GUIDE_SECTIONS_BY_LABEL.get(choice);\n}\n\nfunction getGuideSectionForMode(\n  mode: AtomicGuideSectionName,\n): AtomicGuideSection {\n  const section = GUIDE_SECTIONS_BY_NAME.get(mode);\n  if (!section) throw new Error(`Unknown Atomic guide section: ${mode}`);\n  return section;\n}\n\nfunction getAtomicGuideHelpMenu(): string {\n  const sectionHelp = GUIDE_SECTIONS.map(\n    (section) => `- \\`${section.label}\\` — run \\`/atomic ${section.label}\\``,\n  ).join(\"\\n\");\n  return `# Atomic\\n\\nSelect where to start:\\n\\n${sectionHelp}`;\n}\n\nexport function normalizeAtomicGuideMode(args: string): AtomicGuideMode {\n  const normalized = stripTrailingAtomicGuidePunctuation(\n    args.trim().toLowerCase(),\n  );\n  if (!normalized) return \"help\";\n\n  return GUIDE_SECTIONS_BY_INPUT.get(normalized)?.name ?? \"help\";\n}\n\nexport function getAtomicGuideArgumentCompletions(\n  prefix: string,\n): AutocompleteItem[] | null {\n  const query = prefix.trim().toLowerCase();\n  const items = GUIDE_SECTIONS.map((section) => ({\n    value: section.label,\n    label: section.label,\n    description: section.description,\n  }));\n  const filtered = query\n    ? items.filter(\n        (item) => item.value.startsWith(query) || item.label.startsWith(query),\n      )\n    : items;\n  return filtered.length > 0 ? filtered : null;\n}\n\nfunction readLatestStableChangelog(cwd: string): string {\n  const changelogPath = getChangelogPath();\n  const stableSections = parseChangelog(changelogPath)\n    .filter((entry) => entry.prerelease === null)\n    .slice(0, 3)\n    .map((entry) => entry.content.trim())\n    .filter(Boolean);\n\n  if (stableSections.length === 0) {\n    return `# What's new\\n\\nNo stable release sections were found. Try \\`/changelog\\` for the interactive changelog viewer.\\n\\n─────────────────────────────────────────────────────────────────\\n\\nWhere to next:\\n\\n\\`/atomic example\\` — see a practical first workflow\\n\\`/atomic overview\\` — quick refresh`;\n  }\n\n  const relativePath = path.relative(cwd, changelogPath) || changelogPath;\n  return `# What's new\\n\\n${stableSections.join(\"\\n\\n\")}\\n\\nSource: \\`${relativePath}\\`\\n\\n─────────────────────────────────────────────────────────────────\\n\\nWhere to next:\\n\\n\\`/atomic example\\` — see a practical first workflow\\n\\`/atomic overview\\` — quick refresh`;\n}\n\nexport function getAtomicGuideMessage(\n  mode: AtomicGuideMode,\n  cwd: string,\n): string {\n  if (mode === \"help\") return getAtomicGuideHelpMenu();\n  return getGuideSectionForMode(mode).render(cwd);\n}\n\nexport function atomicGuideModeForChoice(\n  choice: AtomicGuideHelpChoice,\n): AtomicGuideMode {\n  return getGuideSectionForChoice(choice)?.name ?? \"help\";\n}\n"]}
+{"version":3,"file":"atomic-guide-command.js","sourceRoot":"","sources":["../../src/core/atomic-guide-command.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,IAAI,MAAM,WAAW,CAAC;AAElC,OAAO,EAAE,gBAAgB,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AAEzE,MAAM,CAAC,MAAM,yBAAyB,GAAG,QAAQ,CAAC;AAClD,MAAM,CAAC,MAAM,gCAAgC,GAC3C,kCAAkC,CAAC;AAErC,MAAM,QAAQ,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;oDAqEmC,CAAC;AAErD,MAAM,OAAO,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;qCA2DqB,CAAC;AAEtC,MAAM,SAAS,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;qCAuFmB,CAAC;AAEtC,MAAM,cAAc,GAAG;IACrB;QACE,IAAI,EAAE,UAAU;QAChB,OAAO,EAAE,EAAE;QACX,KAAK,EAAE,UAAU;QACjB,WAAW,EAAE,oBAAoB;QACjC,MAAM,EAAE,GAAG,EAAE,CAAC,QAAQ;KACvB;IACD;QACE,IAAI,EAAE,WAAW;QACjB,OAAO,EAAE,CAAC,UAAU,CAAC;QACrB,KAAK,EAAE,WAAW;QAClB,WAAW,EAAE,iBAAiB;QAC9B,MAAM,EAAE,GAAG,EAAE,CAAC,SAAS;KACxB;IACD;QACE,IAAI,EAAE,SAAS;QACf,OAAO,EAAE,CAAC,UAAU,CAAC;QACrB,KAAK,EAAE,SAAS;QAChB,WAAW,EAAE,0BAA0B;QACvC,MAAM,EAAE,GAAG,EAAE,CAAC,OAAO;KACtB;IACD;QACE,IAAI,EAAE,WAAW;QACjB,OAAO,EAAE,CAAC,YAAY,EAAE,WAAW,EAAE,MAAM,EAAE,SAAS,EAAE,WAAW,CAAC;QACpE,KAAK,EAAE,YAAY;QACnB,WAAW,EAAE,sBAAsB;QACnC,MAAM,EAAE,yBAAyB;KAClC;CAOA,CAAC;AASJ,MAAM,CAAC,MAAM,yBAAyB,GACpC,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;AAEjD,MAAM,sBAAsB,GAAG,IAAI,GAAG,CAGpC,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC;AAC5D,MAAM,uBAAuB,GAAG,IAAI,GAAG,CACrC,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC,CAC1D,CAAC;AACF,MAAM,uBAAuB,GAAG,IAAI,GAAG,CACrC,cAAc,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CACjC,CAAC,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC,KAAK,EAAE,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC,GAAG,CACnD,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,OAAO,CAAU,CACrC,CACF,CACF,CAAC;AAEF,MAAM,UAAU,uBAAuB,CACrC,MAAc;IAEd,OAAO,uBAAuB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED,MAAM,iCAAiC,GAAG,QAAQ,CAAC;AAEnD,SAAS,mCAAmC,CAAC,KAAa;IACxD,IAAI,GAAG,GAAG,KAAK,CAAC,MAAM,CAAC;IACvB,OACE,GAAG,GAAG,CAAC;QACP,iCAAiC,CAAC,QAAQ,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,EACjE,CAAC;QACD,GAAG,EAAE,CAAC;IACR,CAAC;IACD,OAAO,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;AAC7B,CAAC;AAED,SAAS,wBAAwB,CAC/B,MAAc;IAEd,OAAO,uBAAuB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED,SAAS,sBAAsB,CAC7B,IAA4B;IAE5B,MAAM,OAAO,GAAG,sBAAsB,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;IACjD,IAAI,CAAC,OAAO;QAAE,MAAM,IAAI,KAAK,CAAC,iCAAiC,IAAI,EAAE,CAAC,CAAC;IACvE,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,sBAAsB;IAC7B,MAAM,WAAW,GAAG,cAAc,CAAC,GAAG,CACpC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,OAAO,CAAC,KAAK,sBAAsB,OAAO,CAAC,KAAK,IAAI,CACzE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACb,OAAO,yCAAyC,WAAW,EAAE,CAAC;AAChE,CAAC;AAED,MAAM,UAAU,wBAAwB,CAAC,IAAY;IACnD,MAAM,UAAU,GAAG,mCAAmC,CACpD,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAC1B,CAAC;IACF,IAAI,CAAC,UAAU;QAAE,OAAO,MAAM,CAAC;IAE/B,OAAO,uBAAuB,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,IAAI,IAAI,MAAM,CAAC;AACjE,CAAC;AAED,MAAM,UAAU,iCAAiC,CAC/C,MAAc;IAEd,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;IAC1C,MAAM,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;QAC7C,KAAK,EAAE,OAAO,CAAC,KAAK;QACpB,KAAK,EAAE,OAAO,CAAC,KAAK;QACpB,WAAW,EAAE,OAAO,CAAC,WAAW;KACjC,CAAC,CAAC,CAAC;IACJ,MAAM,QAAQ,GAAG,KAAK;QACpB,CAAC,CAAC,KAAK,CAAC,MAAM,CACV,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,CACvE;QACH,CAAC,CAAC,KAAK,CAAC;IACV,OAAO,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC;AAC/C,CAAC;AAED,SAAS,yBAAyB,CAAC,GAAW;IAC5C,MAAM,aAAa,GAAG,gBAAgB,EAAE,CAAC;IACzC,MAAM,cAAc,GAAG,cAAc,CAAC,aAAa,CAAC;SACjD,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,UAAU,KAAK,IAAI,CAAC;SAC5C,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC;SACX,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC;SACpC,MAAM,CAAC,OAAO,CAAC,CAAC;IAEnB,IAAI,cAAc,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAChC,OAAO,sSAAsS,CAAC;IAChT,CAAC;IAED,MAAM,YAAY,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,EAAE,aAAa,CAAC,IAAI,aAAa,CAAC;IACxE,OAAO,mBAAmB,cAAc,CAAC,IAAI,CAAC,MAAM,CAAC,iBAAiB,YAAY,yLAAyL,CAAC;AAC9Q,CAAC;AAED,MAAM,UAAU,qBAAqB,CACnC,IAAqB,EACrB,GAAW;IAEX,IAAI,IAAI,KAAK,MAAM;QAAE,OAAO,sBAAsB,EAAE,CAAC;IACrD,OAAO,sBAAsB,CAAC,IAAI,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;AAClD,CAAC;AAED,MAAM,UAAU,wBAAwB,CACtC,MAA6B;IAE7B,OAAO,wBAAwB,CAAC,MAAM,CAAC,EAAE,IAAI,IAAI,MAAM,CAAC;AAC1D,CAAC","sourcesContent":["import * as path from \"node:path\";\nimport type { AutocompleteItem } from \"@earendil-works/pi-tui\";\nimport { getChangelogPath, parseChangelog } from \"../utils/changelog.ts\";\n\nexport const ATOMIC_GUIDE_COMMAND_NAME = \"atomic\";\nexport const ATOMIC_GUIDE_COMMAND_DESCRIPTION =\n  \"Atomic onboarding and help guide\";\n\nconst OVERVIEW = `# Atomic overview\n\nAtomic turns non-trivial work into executable, inspectable workflows. Default to a workflow for implementation, build, debugging, bug fixes, migrations, features, scoped multi-file changes, and validated docs/code work, or whenever a request has dependencies, handoffs, uncertainty, review gates, measurable done criteria, or evidence requirements. Use direct chat for tiny deterministic low-risk answers or edits. Loop-shaped prompts such as \\`do X until Y\\`, \\`review/fix until passing\\`, or \\`run checks and fix until green\\` are especially strong workflow signals. Workflow-first is not builtin-only or monolithic: use named workflows, direct modes, author a custom TypeScript \\`workflow({...})\\` inline, or import reusable project/package and builtin definitions from \\`@bastani/workflows/builtin\\` and nest them with \\`ctx.workflow(...)\\`. Nested children may compose further children within \\`maxDepth\\`, enabling powerful research → implementation → verification → approval graphs from reusable parts. Start Atomic in a project with \\`atomic\\`, then talk to it normally. Use \\`@file\\` to attach files, \\`!command\\` to run shell output through the model, and \\`!!command\\` to run shell output without adding it to context.\n\n## Core session commands\n\n| Command | Use |\n|---|---|\n| \\`/login\\` | configure auth |\n| \\`/model\\` | switch model |\n| \\`/settings\\` | thinking level, theme, message delivery, transport |\n| \\`/new\\`, \\`/resume\\` | start or resume sessions |\n| \\`/tree\\`, \\`/fork\\`, \\`/clone\\` | branch or navigate session history |\n| \\`/compact\\` | delete safe older context verbatim |\n| \\`/hotkeys\\`, \\`/changelog\\` | local help and release notes |\n\n## Examples of using Atomic\n\n| Goal | How to use |\n|---|---|\n| On-call / broken behavior | Use a focused workflow to reproduce, diagnose, repair, and validate; direct debugger/subagent calls remain useful as stages or for tiny deterministic diagnosis |\n| Research → spec → implementation | Chain \\`/skill:research-codebase\\` → \\`/skill:create-spec\\` → a named or custom implementation workflow with explicit validation and review |\n| Testing / regression hardening | Use a workflow for test/fix loops so retries, evidence, and the passing stop condition are tracked |\n| Large repo discovery | Run \\`/parallel codebase-locator \"map the area\" -> codebase-analyzer \"trace the current flow\" -> codebase-pattern-finder \"find patterns\" --bg\\`, or \\`/workflow deep-research-codebase\\` for whole-repo synthesis |\n| UI / product polish | Run \\`/skill:impeccable\\` for interface critique and refinement, or \\`/workflow open-claude-design\\` for generation + refinement loops |\n\n## Built-in workflows\n\n| Workflow | When to use | How to run |\n|---|---|---|\n| \\`deep-research-codebase\\` | broad repo or cross-cutting research before you decide what to change (for one area, use \\`/skill:research-codebase\\`; this indexes the whole repo) | \\`/workflow deep-research-codebase prompt=\"How do payment retries work end to end?\"\\` |\n| \\`goal\\` | autonomous work that benefits from a durable goal ledger, bounded sub-agent orchestration turns, named validation, and reviewer-gated completion; add \\`create_pr=true\\` only for final PR handoff after approval | \\`/workflow goal objective=\"Implement specs/<date>-<topic>.md, run focused tests, and validate the changed behavior\"\\` |\n| \\`ralph\\` | autonomous work that benefits from a durable research-first pipeline, delegated implementation, and iterative review | \\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\" create_pr=true\\` |\n| \\`open-claude-design\\` | UI and design-system work that benefits from generation and refinement loops | \\`/workflow open-claude-design prompt=\"Refresh the settings page hierarchy\"\\` |\n\nUse \\`/workflow list\\` to see what is available and \\`/workflow inputs <name>\\` to inspect inputs in your environment.\n\n## Top skills\n\n| Skill | When to use | How to run |\n|---|---|---|\n| \\`research-codebase\\` | write a grounded research artifact for one subsystem or question | \\`/skill:research-codebase how the rate limiter works in src/middleware/\\` |\n| \\`create-spec\\` | turn research into an implementation-ready plan | \\`/skill:create-spec from research/docs/<date>-<topic>.md\\` |\n| \\`tdd\\` | do test-first feature or bug work | \\`/skill:tdd\\` |\n| \\`prompt-engineer\\` | tighten a vague prompt before a long run | \\`/skill:prompt-engineer Draft a sharper implementation prompt for ...\\` |\n| \\`subagent\\` | learn delegation patterns and exact \\`/run\\`, \\`/parallel\\`, and \\`/chain\\` usage | \\`/skill:subagent\\` |\n| \\`impeccable\\` | critique or refine frontend and product UI | \\`/skill:impeccable\\` |\n\n## Subagents\n\nSubagents are focused child Atomic sessions you can point at one job inside the repo.\n\n| Built-in subagent | Use |\n|---|---|\n| \\`codebase-locator\\` | find relevant files, tests, entrypoints, and configs |\n| \\`codebase-analyzer\\` | explain current behavior with file:line refs |\n| \\`codebase-pattern-finder\\` | find existing code to model after |\n| \\`debugger\\` | reproduce, diagnose, and fix broken behavior |\n\nHow the direct commands map to repo work:\n- \\`/run\\` = one specialist on one job, for example \\`/run codebase-locator \"Map the webhook retry flow\"\\`\n- \\`/parallel\\` = several independent specialists at once, for example \\`/parallel codebase-locator \"map retry files\" -> codebase-pattern-finder \"find existing retry/backoff patterns\" -> codebase-online-researcher \"research current retry guidance\" --bg\\`\n- \\`/chain\\` = ordered handoffs, for example \\`/chain codebase-locator \"find the auth files\" -> codebase-analyzer \"trace the auth flow\" -> debugger \"patch the failing auth edge case\"\\`\n\n─────────────────────────────────────────────────────────────────\n\nWhere to next:\n\n\\`/atomic example\\` — see the pieces used on a code task\n\\`/atomic workflows\\` — learn when to use workflows`;\n\nconst EXAMPLE = `# Practical example\n\nThis example shows a spec-driven development process whose clearly delegated autonomous implementation benefits from durable workflow execution. For interactive or conversation-led work, stay inline or use bounded subagents while the parent remains in control. Type the examples below into the Atomic TUI chat after starting \\`atomic\\` in your project.\n\n## 1. Research what exists\n\nUse \\`/skill:research-codebase\\` for a scoped area, subsystem, or directory:\n\n\\`/skill:research-codebase how the rate limiter works in src/middleware/\\`\n\nUse \\`deep-research-codebase\\` when the answer spans the whole repo or a cross-cutting implementation path:\n\n\\`/workflow deep-research-codebase prompt=\"How do payment retries work end to end?\"\\`\n\nIf the research prompt is vague, tighten it first with \\`/skill:prompt-engineer\\`:\n\n\\`/skill:prompt-engineer Draft a sharper repo-research prompt for understanding payment retries end to end, including retries, queues, and failure handling.\\`\n\n## 2. Create a spec when requirements are fuzzy\n\nSkip this if the implementation request is already precise.\n\n\\`/skill:create-spec from research/docs/<date>-<topic>.md\\`\n\n## 3. Implement with review built in\n\nDefault to a workflow for non-trivial implementation and review. Use direct chat only for tiny deterministic low-risk edits; use focused subagents inside workflow stages or for bounded specialist passes. Choose an installed workflow when it fits, or author a custom TypeScript workflow inline from the starter patterns when the task needs a richer graph.\n\nFor work that fits a durable goal ledger, bounded sub-agent orchestration turns, and reviewer-gated completion, use \\`goal\\`:\n\n\\`/workflow goal objective=\"Implement specs/<date>-<topic>.md, run focused tests, and finish when the documented behavior is validated\"\\`\n\nLoop or stop-condition phrasing is a key workflow signal. When the user delegates a loop such as \\`do X until Y\\`, \\`repeat until\\`, \\`iterate until\\`, \\`review/fix until passing\\`, \\`run checks and fix until green\\`, or \\`keep going until done\\`, make the stop condition explicit in the Goal objective:\n\n\\`/workflow goal objective=\"Fix the flaky checkout test, adjust the smallest necessary code, and finish when the focused test passes three times\"\\`\n\nWhen a clearly delegated autonomous job benefits from a durable research-first pipeline with orchestration and iterative review, use \\`ralph\\`:\n\n\\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\"\\`\n\nAdd \\`create_pr=true\\` only when you want the final pull-request stage and report after the review gate approves.\n\n## 4. Decide and land\n\nIf you used \\`goal\\`, the workflow already persisted receipts in a goal ledger and reviewer-gated completion. Use its final status — \\`complete\\`, \\`blocked\\`, or \\`needs_human\\` — plus the remaining-work report to decide whether to ship, unblock, or clarify. If you enabled \\`create_pr=true\\`, use its final pull-request report to decide whether to ship or iterate again.\n\nIf you used \\`ralph\\`, the workflow transformed the prompt into a research question, researched the codebase, delegated implementation through sub-agents, reviewed, and iterated. If you enabled \\`create_pr=true\\`, use its final pull-request report to decide whether to ship or iterate again.\n\nIf you implemented directly instead of using a workflow, you can still run:\n\n\\`/parallel-review current diff\\`\n\nAtomic will synthesize reviewer feedback and ask before applying fixes.\n\n─────────────────────────────────────────────────────────────────\n\nWhere to next:\n\n\\`/atomic workflows\\` — learn when to use workflows\n\\`/atomic overview\\` — quick refresh`;\n\nconst WORKFLOWS = `# Workflows primer\n\nA workflow is a TypeScript-defined pipeline exported from \\`workflow({...})\\`. It can run tasks, chains, parallel fan-out, human-in-the-loop prompts, background status, and model fallback chains.\n\nDefault to workflows for non-trivial work and requests with inherent structure plus a verifiable objective. Implementation, debugging, migrations, multi-file changes, validation, review, evidence requirements, and explicit stop conditions are workflow-shaped; use direct chat only for tiny deterministic low-risk answers or edits.\n\nWorkflow-first is not builtin-only or monolithic. Atomic can author custom TypeScript \\`workflow({...})\\` definitions inline, and workflows can import reusable project/package definitions or builtins from \\`@bastani/workflows/builtin\\`, then nest them with \\`ctx.workflow(...)\\`. Imported children can nest further children within \\`maxDepth\\`, so compose proven research, implementation, design, verification, and approval workflows instead of copying their stages. Use the documented starter patterns for classify-and-act routing, dynamic fan-out and synthesis, adversarial verification, candidate selection, and bounded convergence. Atomic writes the parent definition, reloads it, and runs the composed graph.\n\n## Built-in workflows\n\n| Workflow | When to use | How to run |\n|---|---|---|\n| \\`deep-research-codebase\\` | broad repo or cross-cutting research before you decide what to change (for one area, use \\`/skill:research-codebase\\`; this indexes the whole repo) | \\`/workflow deep-research-codebase prompt=\"How do payment retries work end to end?\"\\` |\n| \\`goal\\` | autonomous work that benefits from a durable goal ledger, bounded sub-agent orchestration turns, named validation, and reviewer-gated completion; add \\`create_pr=true\\` only for final PR handoff after approval | \\`/workflow goal objective=\"Update the CLI docs, include one usage example, and verify the docs build passes\"\\` |\n| \\`ralph\\` | autonomous work that benefits from a durable research-first pipeline, delegated implementation, and iterative review | \\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\" create_pr=true\\` |\n| \\`open-claude-design\\` | frontend and product design work | \\`/workflow open-claude-design prompt=\"Refresh the settings page hierarchy\"\\` |\n\nUse \\`/workflow inputs <name>\\` to inspect the exact inputs in your environment.\n\nUse \\`/skill:research-codebase ...\\` when you want research on one subsystem, directory, or focused question. Use \\`/workflow deep-research-codebase ...\\` when the answer needs end-to-end tracing across many parts of the repo.\n\nIf you are drafting research, reviewer, or synthesis prompts for a workflow, use \\`/skill:prompt-engineer\\` first. It is a good fit when a stage prompt feels vague, overloaded, or underspecified.\n\n## What good workflow authoring looks like\n\nA good workflow request is explicit about stage purpose, model choice, handoff, and the decision each step must return.\n\nFor workflow-owned side effects such as filesystem writes, network mutations, and external API actions, prefer \\`ctx.tool(name, args, fn)\\`: completed calls are durably cached, so resume returns the saved result without rerunning \\`fn\\`. Keep pure computation as ordinary TypeScript, and do not wrap agent-stage internals or every function call indiscriminately.\n\nExample: ask Atomic in chat with something like this:\n\n~~~text\nCreate a reusable workflow called review-changes.\n\nIt should accept one required text input called target for a diff, PR summary, or review target.\n\nRun two independent review stages in parallel with fresh context:\n- one reviewer focused on correctness, regressions, and missing tests using openai-codex/gpt-5.5 at xhigh thinking\n- one reviewer focused on edge cases, maintainability, and hidden risks using anthropic/claude-opus-4-8 at xhigh thinking\n\nThen add an aggregate stage that consolidates both reviews, deduplicates overlap, keeps only evidence-backed issues, and separates blockers from optional suggestions using openai/gpt-5.5 at high thinking.\n\nFinally add an adjudicate stage using anthropic/claude-sonnet-4 at high thinking that decides what to fix now, what to defer, and what to reject. Return a short action list with rationale.\n\nThe workflow should return structured output with consolidated_review and decision fields.\n~~~\n\nWhy this is good:\n- it names the workflow and required input\n- it specifies which stages are parallel vs sequential\n- each stage has one job\n- it defines the handoff and final outputs\n- it calls out model choice and thinking level where that matters\n\n## Run and inspect\n\n\\`/workflow list\\`\n\n\\`/workflow inputs goal\\`\n\n\\`/workflow goal objective=\"Fix the settings form validation bug, add the focused test, and finish when invalid emails show the inline error without submitting\"\\`\n\n\\`/workflow inputs ralph\\`\n\n\\`/workflow ralph prompt=\"Migrate the database layer to Drizzle\" create_pr=true\\`\n\n\\`/workflow status\\`\n\n\\`/workflow connect <run-id>\\`\n\n\\`/workflow interrupt <run-id>\\`\n\n\\`/workflow quit <run-id>\\`\n\n\\`/workflow resume <run-id>\\`\n\nWorkflows run as background tasks. Use F2 or \\`/workflow connect <run-id>\\` for the graph viewer. Human-in-the-loop prompts appear there, not as chat modals, and awaiting-input states do not wake the main chat agent. Completion and failure notices are steered back into the main chat; answers submitted in the workflow UI interrupt stale main-chat questions so the model does not ask again.\n\n## Author your own\n\nDescribe your workflow in plain chat — say what you want the workflow to accomplish, what inputs it should accept, what stages should run, and what final output or decision it should return. Atomic will use the workflow docs to scaffold a reusable definition under \\`.atomic/workflows/\\`, ask clarifying questions when stage purpose, models, or handoffs are ambiguous, and run \\`/workflow reload\\` so you can launch it immediately.\n\n─────────────────────────────────────────────────────────────────\n\nWhere to next:\n\n\\`/atomic example\\` — see workflows in a normal task flow\n\\`/atomic overview\\` — quick refresh`;\n\nconst GUIDE_SECTIONS = [\n  {\n    name: \"overview\",\n    aliases: [],\n    label: \"overview\",\n    description: \"30-second overview\",\n    render: () => OVERVIEW,\n  },\n  {\n    name: \"workflows\",\n    aliases: [\"workflow\"],\n    label: \"workflows\",\n    description: \"Workflow primer\",\n    render: () => WORKFLOWS,\n  },\n  {\n    name: \"example\",\n    aliases: [\"examples\"],\n    label: \"example\",\n    description: \"Practical first workflow\",\n    render: () => EXAMPLE,\n  },\n  {\n    name: \"whats-new\",\n    aliases: [\"what's new\", \"whats new\", \"news\", \"updates\", \"changelog\"],\n    label: \"what's new\",\n    description: \"Recent release notes\",\n    render: readLatestStableChangelog,\n  },\n] as const satisfies readonly {\n  readonly name: string;\n  readonly aliases: readonly string[];\n  readonly label: string;\n  readonly description: string;\n  readonly render: (cwd: string) => string;\n}[];\n\ntype AtomicGuideSection = (typeof GUIDE_SECTIONS)[number];\ntype AtomicGuideSectionName = AtomicGuideSection[\"name\"];\n\nexport type AtomicGuideHelpChoice = AtomicGuideSection[\"label\"];\n\nexport type AtomicGuideMode = \"help\" | AtomicGuideSectionName;\n\nexport const ATOMIC_GUIDE_HELP_CHOICES: readonly AtomicGuideHelpChoice[] =\n  GUIDE_SECTIONS.map((section) => section.label);\n\nconst GUIDE_SECTIONS_BY_NAME = new Map<\n  AtomicGuideSectionName,\n  AtomicGuideSection\n>(GUIDE_SECTIONS.map((section) => [section.name, section]));\nconst GUIDE_SECTIONS_BY_LABEL = new Map<string, AtomicGuideSection>(\n  GUIDE_SECTIONS.map((section) => [section.label, section]),\n);\nconst GUIDE_SECTIONS_BY_INPUT = new Map<string, AtomicGuideSection>(\n  GUIDE_SECTIONS.flatMap((section) =>\n    [section.name, section.label, ...section.aliases].map(\n      (input) => [input, section] as const,\n    ),\n  ),\n);\n\nexport function isAtomicGuideHelpChoice(\n  choice: string,\n): choice is AtomicGuideHelpChoice {\n  return GUIDE_SECTIONS_BY_LABEL.has(choice);\n}\n\nconst ATOMIC_GUIDE_TRAILING_PUNCTUATION = \"?!.,;:\";\n\nfunction stripTrailingAtomicGuidePunctuation(value: string): string {\n  let end = value.length;\n  while (\n    end > 0 &&\n    ATOMIC_GUIDE_TRAILING_PUNCTUATION.includes(value.charAt(end - 1))\n  ) {\n    end--;\n  }\n  return value.slice(0, end);\n}\n\nfunction getGuideSectionForChoice(\n  choice: string,\n): AtomicGuideSection | undefined {\n  return GUIDE_SECTIONS_BY_LABEL.get(choice);\n}\n\nfunction getGuideSectionForMode(\n  mode: AtomicGuideSectionName,\n): AtomicGuideSection {\n  const section = GUIDE_SECTIONS_BY_NAME.get(mode);\n  if (!section) throw new Error(`Unknown Atomic guide section: ${mode}`);\n  return section;\n}\n\nfunction getAtomicGuideHelpMenu(): string {\n  const sectionHelp = GUIDE_SECTIONS.map(\n    (section) => `- \\`${section.label}\\` — run \\`/atomic ${section.label}\\``,\n  ).join(\"\\n\");\n  return `# Atomic\\n\\nSelect where to start:\\n\\n${sectionHelp}`;\n}\n\nexport function normalizeAtomicGuideMode(args: string): AtomicGuideMode {\n  const normalized = stripTrailingAtomicGuidePunctuation(\n    args.trim().toLowerCase(),\n  );\n  if (!normalized) return \"help\";\n\n  return GUIDE_SECTIONS_BY_INPUT.get(normalized)?.name ?? \"help\";\n}\n\nexport function getAtomicGuideArgumentCompletions(\n  prefix: string,\n): AutocompleteItem[] | null {\n  const query = prefix.trim().toLowerCase();\n  const items = GUIDE_SECTIONS.map((section) => ({\n    value: section.label,\n    label: section.label,\n    description: section.description,\n  }));\n  const filtered = query\n    ? items.filter(\n        (item) => item.value.startsWith(query) || item.label.startsWith(query),\n      )\n    : items;\n  return filtered.length > 0 ? filtered : null;\n}\n\nfunction readLatestStableChangelog(cwd: string): string {\n  const changelogPath = getChangelogPath();\n  const stableSections = parseChangelog(changelogPath)\n    .filter((entry) => entry.prerelease === null)\n    .slice(0, 3)\n    .map((entry) => entry.content.trim())\n    .filter(Boolean);\n\n  if (stableSections.length === 0) {\n    return `# What's new\\n\\nNo stable release sections were found. Try \\`/changelog\\` for the interactive changelog viewer.\\n\\n─────────────────────────────────────────────────────────────────\\n\\nWhere to next:\\n\\n\\`/atomic example\\` — see a practical first workflow\\n\\`/atomic overview\\` — quick refresh`;\n  }\n\n  const relativePath = path.relative(cwd, changelogPath) || changelogPath;\n  return `# What's new\\n\\n${stableSections.join(\"\\n\\n\")}\\n\\nSource: \\`${relativePath}\\`\\n\\n─────────────────────────────────────────────────────────────────\\n\\nWhere to next:\\n\\n\\`/atomic example\\` — see a practical first workflow\\n\\`/atomic overview\\` — quick refresh`;\n}\n\nexport function getAtomicGuideMessage(\n  mode: AtomicGuideMode,\n  cwd: string,\n): string {\n  if (mode === \"help\") return getAtomicGuideHelpMenu();\n  return getGuideSectionForMode(mode).render(cwd);\n}\n\nexport function atomicGuideModeForChoice(\n  choice: AtomicGuideHelpChoice,\n): AtomicGuideMode {\n  return getGuideSectionForChoice(choice)?.name ?? \"help\";\n}\n"]}

package/dist/core/slash-commands.js

@@ -24,11 +24,11 @@ const BUNDLED_WORKFLOW_COMPLETION_METADATA = [
     },
     {
         name: "goal",
-        description: "Goal Runner workflow with bounded LM turns, acceptance criteria, ledger artifacts, reviewers, and reducer-gated completion.",
+        description: "Goal Runner workflow with bounded sub-agent orchestration turns, acceptance criteria, ledger artifacts, reviewers, and reducer-gated completion.",
         inputs: {
             objective: { description: "The objective or delta for this Goal Runner workflow run.", kind: "string" },
             acceptance_criteria: { description: "Original immutable task contract this run must remain consistent with.", kind: "string" },
-            max_turns: { description: "Maximum worker/review turns before Goal Runner stops as needs_human.", kind: "number" },
+            max_turns: { description: "Maximum orchestrator/review turns before Goal Runner stops as needs_human.", kind: "number" },
             base_branch: { description: "Optional branch reviewers compare the current code delta against.", kind: "string" },
             git_worktree_dir: { description: "Optional Git worktree path.", kind: "string" },
             create_pr: { description: "Whether to run the final pull-request creation stage after approval.", kind: "boolean" },

package/dist/core/slash-commands.js.map

@@ -1 +1 @@
-{"version":3,"file":"slash-commands.js","sourceRoot":"","sources":["../../src/core/slash-commands.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAC;AACxC,OAAO,EACN,gCAAgC,EAChC,yBAAyB,EACzB,iCAAiC,GACjC,MAAM,2BAA2B,CAAC;AAgCnC,MAAM,0BAA0B,GAAuB;IACtD,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,EAAE,SAAS,EAAE,WAAW,EAAE,mCAAmC,EAAE;IACzF,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,yCAAyC,EAAE;IAC7F,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,WAAW,EAAE,2BAA2B,EAAE;IAC3E,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,wDAAwD,EAAE;IAC5G,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,WAAW,EAAE,WAAW,EAAE,iBAAiB,EAAE;IAC3E,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,WAAW,EAAE,kCAAkC,EAAE;IAClF,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,sBAAsB,EAAE;IACxE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,2BAA2B,EAAE;IAC/E,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,gCAAgC,EAAE;IACpF,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,2BAA2B,EAAE;CAC/E,CAAC;AAEF,MAAM,oCAAoC,GAAiC;IAC1E;QACC,IAAI,EAAE,wBAAwB;QAC9B,WAAW,EAAE,6EAA6E;QAC1F,MAAM,EAAE;YACP,MAAM,EAAE,EAAE,WAAW,EAAE,4DAA4D,EAAE,IAAI,EAAE,QAAQ,EAAE;YACrG,cAAc,EAAE,EAAE,WAAW,EAAE,+DAA+D,EAAE,IAAI,EAAE,QAAQ,EAAE;YAChH,eAAe,EAAE,EAAE,WAAW,EAAE,6EAA6E,EAAE,IAAI,EAAE,QAAQ,EAAE;SAC/H;KACD;IACD;QACC,IAAI,EAAE,MAAM;QACZ,WAAW,EAAE,6HAA6H;QAC1I,MAAM,EAAE;YACP,SAAS,EAAE,EAAE,WAAW,EAAE,2DAA2D,EAAE,IAAI,EAAE,QAAQ,EAAE;YACvG,mBAAmB,EAAE,EAAE,WAAW,EAAE,wEAAwE,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC9H,SAAS,EAAE,EAAE,WAAW,EAAE,sEAAsE,EAAE,IAAI,EAAE,QAAQ,EAAE;YAClH,WAAW,EAAE,EAAE,WAAW,EAAE,mEAAmE,EAAE,IAAI,EAAE,QAAQ,EAAE;YACjH,gBAAgB,EAAE,EAAE,WAAW,EAAE,6BAA6B,EAAE,IAAI,EAAE,QAAQ,EAAE;YAChF,SAAS,EAAE,EAAE,WAAW,EAAE,sEAAsE,EAAE,IAAI,EAAE,SAAS,EAAE;SACnH;KACD;IACD;QACC,IAAI,EAAE,oBAAoB;QAC1B,WAAW,EAAE,sGAAsG;QACnH,MAAM,EAAE;YACP,MAAM,EAAE,EAAE,WAAW,EAAE,qEAAqE,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC9G,mBAAmB,EAAE,EAAE,WAAW,EAAE,iEAAiE,EAAE,IAAI,EAAE,SAAS,EAAE;YACxH,eAAe,EAAE,EAAE,WAAW,EAAE,iDAAiD,EAAE,IAAI,EAAE,QAAQ,EAAE;SACnG;KACD;IACD;QACC,IAAI,EAAE,OAAO;QACb,WAAW,EAAE,gGAAgG;QAC7G,MAAM,EAAE;YACP,MAAM,EAAE,EAAE,WAAW,EAAE,oDAAoD,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC7F,mBAAmB,EAAE,EAAE,WAAW,EAAE,wEAAwE,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC9H,SAAS,EAAE,EAAE,WAAW,EAAE,iDAAiD,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC7F,WAAW,EAAE,EAAE,WAAW,EAAE,0DAA0D,EAAE,IAAI,EAAE,QAAQ,EAAE;YACxG,gBAAgB,EAAE,EAAE,WAAW,EAAE,6BAA6B,EAAE,IAAI,EAAE,QAAQ,EAAE;YAChF,SAAS,EAAE,EAAE,WAAW,EAAE,uDAAuD,EAAE,IAAI,EAAE,SAAS,EAAE;SACpG;KACD;CACD,CAAC;AAEF,SAAS,qBAAqB,CAAC,YAAoB,EAAE,UAA8B;IAClF,MAAM,UAAU,GAAG,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC;QAC1C,CAAC,CAAC,YAAY,CAAC,MAAM;QACrB,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,YAAY,CAAC,WAAW,CAAC,GAAG,CAAC,EAAE,YAAY,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC;IAC/E,MAAM,IAAI,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC;IAC/C,MAAM,KAAK,GAAG,YAAY,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;IAC7C,MAAM,eAAe,GAAG,KAAK,CAAC,OAAO,EAAE,CAAC;IACxC,MAAM,QAAQ,GAAG,UAAU;SACzB,MAAM,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,SAAS,CAAC,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,SAAS,CAAC,KAAK,CAAC,OAAO,EAAE,KAAK,eAAe,CAAC;SACzG,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC,EAAE,GAAG,SAAS,EAAE,KAAK,EAAE,GAAG,IAAI,GAAG,SAAS,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,CAAC;IAC7E,OAAO,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC;AAC9C,CAAC;AAED,SAAS,wBAAwB;IAChC,OAAO,oCAAoC,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;QAC9D,KAAK,EAAE,GAAG,QAAQ,CAAC,IAAI,GAAG;QAC1B,KAAK,EAAE,QAAQ,CAAC,IAAI;QACpB,WAAW,EAAE,iBAAiB,QAAQ,CAAC,IAAI,EAAE;KAC7C,CAAC,CAAC,CAAC;AACL,CAAC;AAED,MAAM,UAAU,qCAAqC,CAAC,cAAsB;IAC3E,MAAM,KAAK,GAAG,cAAc,CAAC,IAAI,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;IACjE,MAAM,UAAU,GAAG,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IAClC,MAAM,aAAa,GAAG,wBAAwB,EAAE,CAAC;IACjD,IAAI,CAAC,cAAc,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;QACnC,OAAO,qBAAqB,CAAC,cAAc,EAAE,CAAC,GAAG,0BAA0B,EAAE,GAAG,aAAa,CAAC,CAAC,CAAC;IACjG,CAAC;IACD,IAAI,UAAU,KAAK,QAAQ;QAAE,OAAO,qBAAqB,CAAC,cAAc,EAAE,aAAa,CAAC,CAAC;IACzF,IAAI,UAAU,KAAK,WAAW,EAAE,CAAC;QAChC,OAAO,qBAAqB,CAAC,cAAc,EAAE;YAC5C,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,8BAA8B,EAAE;YAChF,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,mBAAmB,EAAE;YACrE,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,WAAW,EAAE,mBAAmB,EAAE;SAC/D,CAAC,CAAC;IACJ,CAAC;IACD,IAAI,UAAU,KAAK,MAAM,EAAE,CAAC;QAC3B,OAAO,qBAAqB,CAAC,cAAc,EAAE;YAC5C,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,4CAA4C,EAAE;SAC9F,CAAC,CAAC;IACJ,CAAC;IACD,IAAI,CAAC,UAAU;QAAE,OAAO,qBAAqB,CAAC,cAAc,EAAE,CAAC,GAAG,0BAA0B,EAAE,GAAG,aAAa,CAAC,CAAC,CAAC;IAEjH,MAAM,QAAQ,GAAG,oCAAoC,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,SAAS,CAAC,IAAI,KAAK,UAAU,CAAC,CAAC;IACzG,IAAI,CAAC,QAAQ;QAAE,OAAO,IAAI,CAAC;IAC3B,MAAM,UAAU,GAAG,KAAK,CAAC,IAAI,CAAC,cAAc,CAAC;QAC5C,CAAC,CAAC,cAAc,CAAC,MAAM;QACvB,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,cAAc,CAAC,WAAW,CAAC,GAAG,CAAC,EAAE,cAAc,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC;IACnF,MAAM,KAAK,GAAG,cAAc,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;IAC/C,MAAM,WAAW,GAAG,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;IACvC,IAAI,WAAW,GAAG,CAAC,EAAE,CAAC;QACrB,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,WAAW,CAAC,CAAC;QAC9C,MAAM,KAAK,GAAG,QAAQ,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;QACzC,IAAI,KAAK,EAAE,IAAI,KAAK,SAAS;YAAE,OAAO,IAAI,CAAC;QAC3C,OAAO,qBAAqB,CAAC,cAAc,EAAE;YAC5C,EAAE,KAAK,EAAE,GAAG,SAAS,QAAQ,EAAE,KAAK,EAAE,MAAM,EAAE,WAAW,EAAE,SAAS,EAAE;YACtE,EAAE,KAAK,EAAE,GAAG,SAAS,SAAS,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,SAAS,EAAE;SACxE,CAAC,CAAC;IACJ,CAAC;IAED,OAAO,qBAAqB,CAAC,cAAc,EAAE;QAC5C,EAAE,KAAK,EAAE,cAAc,EAAE,KAAK,EAAE,aAAa,EAAE,WAAW,EAAE,+BAA+B,EAAE;QAC7F,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,mCAAmC,EAAE;QACvF,GAAG,MAAM,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC;YAC1D,KAAK,EAAE,GAAG,IAAI,GAAG;YACjB,KAAK,EAAE,IAAI;YACX,WAAW,EAAE,KAAK,CAAC,WAAW;SAC9B,CAAC,CAAC;KACH,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,CAAC,MAAM,sBAAsB,GAAuC;IACzE,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,oBAAoB,EAAE;IACvD,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,kCAAkC,EAAE;IAClE,EAAE,IAAI,EAAE,eAAe,EAAE,WAAW,EAAE,0CAA0C,EAAE;IAClF,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,kDAAkD,EAAE;IACjF,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,8DAA8D,EAAE;IAC/F,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,+CAA+C,EAAE;IAChF,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,uCAAuC,EAAE;IACvE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,sCAAsC,EAAE;IACrE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,0BAA0B,EAAE;IACzD,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,6BAA6B,EAAE;IAC/D,EAAE,IAAI,EAAE,WAAW,EAAE,WAAW,EAAE,wBAAwB,EAAE;IAC5D;QACC,IAAI,EAAE,yBAAyB;QAC/B,WAAW,EAAE,gCAAgC;QAC7C,sBAAsB,EAAE,iCAAiC;KACzD;IACD,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,6BAA6B,EAAE;IAC/D,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,gDAAgD,EAAE;IAC/E,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,uDAAuD,EAAE;IACvF,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,yCAAyC,EAAE;IACxE,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,iDAAiD,EAAE;IACjF,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,mCAAmC,EAAE,YAAY,EAAE,YAAY,EAAE;IAC/F,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,gCAAgC,EAAE;IACjE,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,qBAAqB,EAAE;IACnD,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,iDAAiD,EAAE;IACnF,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,4BAA4B,EAAE;IAC7D,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,6DAA6D,EAAE;IAC9F,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,QAAQ,QAAQ,EAAE,EAAE;IACjD,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,QAAQ,QAAQ,EAAE,EAAE;CACjD,CAAC;AAEF,MAAM,CAAC,MAAM,gCAAgC,GAAuC;IACnF;QACC,IAAI,EAAE,UAAU;QAChB,WAAW,EAAE,iKAAiK;QAC9K,sBAAsB,EAAE,qCAAqC;KAC7D;IACD,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,yEAAyE,EAAE;IACvG,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,sEAAsE,EAAE;IACtG,EAAE,IAAI,EAAE,WAAW,EAAE,WAAW,EAAE,iEAAiE,EAAE;IACrG,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,iFAAiF,EAAE;IACpH,EAAE,IAAI,EAAE,kBAAkB,EAAE,WAAW,EAAE,2BAA2B,EAAE;IACtE,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,wBAAwB,EAAE;IACtD,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,yCAAyC,EAAE;IAC5E,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,iDAAiD,EAAE;IACnF,EAAE,IAAI,EAAE,gBAAgB,EAAE,WAAW,EAAE,+CAA+C,EAAE;IACxF,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,kCAAkC,EAAE;IACnE,EAAE,IAAI,EAAE,WAAW,EAAE,WAAW,EAAE,yBAAyB,EAAE;IAC7D,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,+BAA+B,EAAE;CAClE,CAAC","sourcesContent":["import type { AutocompleteItem } from \"@earendil-works/pi-tui\";\nimport { APP_NAME } from \"../config.ts\";\nimport {\n\tATOMIC_GUIDE_COMMAND_DESCRIPTION,\n\tATOMIC_GUIDE_COMMAND_NAME,\n\tgetAtomicGuideArgumentCompletions,\n} from \"./atomic-guide-command.ts\";\nimport type { SourceInfo } from \"./source-info.ts\";\n\nexport type SlashCommandSource = \"extension\" | \"prompt\" | \"skill\";\n\nexport interface SlashCommandInfo {\n\tname: string;\n\tdescription?: string;\n\tsource: SlashCommandSource;\n\tsourceInfo: SourceInfo;\n}\n\nexport interface BuiltinSlashCommand {\n\tname: string;\n\tdescription: string;\n\targumentHint?: string;\n\tgetArgumentCompletions?: (\n\t\targumentPrefix: string,\n\t) => AutocompleteItem[] | null | Promise<AutocompleteItem[] | null>;\n}\n\ntype WorkflowInputCompletionMetadata = {\n\tdescription: string;\n\tkind?: \"boolean\" | \"number\" | \"string\";\n};\n\ntype WorkflowCompletionMetadata = {\n\tname: string;\n\tdescription: string;\n\tinputs: Record<string, WorkflowInputCompletionMetadata>;\n};\n\nconst WORKFLOW_ADMIN_COMPLETIONS: AutocompleteItem[] = [\n\t{ value: \"connect \", label: \"connect\", description: \"Attach to a run (picker if no id)\" },\n\t{ value: \"attach \", label: \"attach\", description: \"Open the in-place attach pane on a node\" },\n\t{ value: \"list \", label: \"list\", description: \"List registered workflows\" },\n\t{ value: \"status \", label: \"status\", description: \"List current-session active and retained terminal runs\" },\n\t{ value: \"interrupt \", label: \"interrupt\", description: \"Interrupt a run\" },\n\t{ value: \"quit \", label: \"quit\", description: \"Quit a run and keep it resumable\" },\n\t{ value: \"pause \", label: \"pause\", description: \"Pause a run or stage\" },\n\t{ value: \"resume \", label: \"resume\", description: \"Re-open overlay for a run\" },\n\t{ value: \"inputs \", label: \"inputs\", description: \"Show a workflow's input schema\" },\n\t{ value: \"reload \", label: \"reload\", description: \"Reload workflow resources\" },\n];\n\nconst BUNDLED_WORKFLOW_COMPLETION_METADATA: WorkflowCompletionMetadata[] = [\n\t{\n\t\tname: \"deep-research-codebase\",\n\t\tdescription: \"Heavy research for tasks requiring comprehensive, whole-repository context.\",\n\t\tinputs: {\n\t\t\tprompt: { description: \"Research question or investigation focus for the codebase.\", kind: \"string\" },\n\t\t\tmax_partitions: { description: \"Maximum number of codebase partitions to explore in parallel.\", kind: \"number\" },\n\t\t\tmax_concurrency: { description: \"Maximum number of workflow stages to run concurrently during deep research.\", kind: \"number\" },\n\t\t},\n\t},\n\t{\n\t\tname: \"goal\",\n\t\tdescription: \"Goal Runner workflow with bounded LM turns, acceptance criteria, ledger artifacts, reviewers, and reducer-gated completion.\",\n\t\tinputs: {\n\t\t\tobjective: { description: \"The objective or delta for this Goal Runner workflow run.\", kind: \"string\" },\n\t\t\tacceptance_criteria: { description: \"Original immutable task contract this run must remain consistent with.\", kind: \"string\" },\n\t\t\tmax_turns: { description: \"Maximum worker/review turns before Goal Runner stops as needs_human.\", kind: \"number\" },\n\t\t\tbase_branch: { description: \"Optional branch reviewers compare the current code delta against.\", kind: \"string\" },\n\t\t\tgit_worktree_dir: { description: \"Optional Git worktree path.\", kind: \"string\" },\n\t\t\tcreate_pr: { description: \"Whether to run the final pull-request creation stage after approval.\", kind: \"boolean\" },\n\t\t},\n\t},\n\t{\n\t\tname: \"open-claude-design\",\n\t\tdescription: \"AI-powered design workflow: discovery, reference research, HTML generation, refinement, and handoff.\",\n\t\tinputs: {\n\t\t\tprompt: { description: \"What to design, such as a dashboard, page, component, or prototype.\", kind: \"string\" },\n\t\t\tdiscover_references: { description: \"Discover current reference designs and feed them to generation.\", kind: \"boolean\" },\n\t\t\tmax_refinements: { description: \"Maximum generate/user-feedback loop iterations.\", kind: \"number\" },\n\t\t},\n\t},\n\t{\n\t\tname: \"ralph\",\n\t\tdescription: \"Raw prompt → research → orchestrate → multi-model parallel review loop with bounded iteration.\",\n\t\tinputs: {\n\t\t\tprompt: { description: \"The task or goal to research, execute, and refine.\", kind: \"string\" },\n\t\t\tacceptance_criteria: { description: \"Original immutable task contract this run must remain consistent with.\", kind: \"string\" },\n\t\t\tmax_loops: { description: \"Maximum research/orchestrate/review iterations.\", kind: \"number\" },\n\t\t\tbase_branch: { description: \"Branch reviewers compare the current code delta against.\", kind: \"string\" },\n\t\t\tgit_worktree_dir: { description: \"Optional Git worktree path.\", kind: \"string\" },\n\t\t\tcreate_pr: { description: \"Whether to run the final pull-request creation stage.\", kind: \"boolean\" },\n\t\t},\n\t},\n];\n\nfunction completeWorkflowToken(argumentText: string, candidates: AutocompleteItem[]): AutocompleteItem[] | null {\n\tconst tokenStart = /\\s$/.test(argumentText)\n\t\t? argumentText.length\n\t\t: Math.max(argumentText.lastIndexOf(\" \"), argumentText.lastIndexOf(\"\\t\")) + 1;\n\tconst head = argumentText.slice(0, tokenStart);\n\tconst token = argumentText.slice(tokenStart);\n\tconst normalizedToken = token.trimEnd();\n\tconst filtered = candidates\n\t\t.filter((candidate) => candidate.value.startsWith(token) && candidate.value.trimEnd() !== normalizedToken)\n\t\t.map((candidate) => ({ ...candidate, value: `${head}${candidate.value}` }));\n\treturn filtered.length > 0 ? filtered : null;\n}\n\nfunction bundledWorkflowNameItems(): AutocompleteItem[] {\n\treturn BUNDLED_WORKFLOW_COMPLETION_METADATA.map((workflow) => ({\n\t\tvalue: `${workflow.name} `,\n\t\tlabel: workflow.name,\n\t\tdescription: `Run workflow: ${workflow.name}`,\n\t}));\n}\n\nexport function getBundledWorkflowArgumentCompletions(argumentPrefix: string): AutocompleteItem[] | null {\n\tconst parts = argumentPrefix.trim().split(/\\s+/).filter(Boolean);\n\tconst subcommand = parts[0] ?? \"\";\n\tconst workflowItems = bundledWorkflowNameItems();\n\tif (!argumentPrefix.includes(\" \")) {\n\t\treturn completeWorkflowToken(argumentPrefix, [...WORKFLOW_ADMIN_COMPLETIONS, ...workflowItems]);\n\t}\n\tif (subcommand === \"inputs\") return completeWorkflowToken(argumentPrefix, workflowItems);\n\tif (subcommand === \"interrupt\") {\n\t\treturn completeWorkflowToken(argumentPrefix, [\n\t\t\t{ value: \"--all \", label: \"--all\", description: \"Interrupt all in-flight runs\" },\n\t\t\t{ value: \"--yes \", label: \"--yes\", description: \"Skip confirmation\" },\n\t\t\t{ value: \"-y \", label: \"-y\", description: \"Skip confirmation\" },\n\t\t]);\n\t}\n\tif (subcommand === \"quit\") {\n\t\treturn completeWorkflowToken(argumentPrefix, [\n\t\t\t{ value: \"--all \", label: \"--all\", description: \"Quit and keep all in-flight runs resumable\" },\n\t\t]);\n\t}\n\tif (!subcommand) return completeWorkflowToken(argumentPrefix, [...WORKFLOW_ADMIN_COMPLETIONS, ...workflowItems]);\n\n\tconst workflow = BUNDLED_WORKFLOW_COMPLETION_METADATA.find((candidate) => candidate.name === subcommand);\n\tif (!workflow) return null;\n\tconst tokenStart = /\\s$/.test(argumentPrefix)\n\t\t? argumentPrefix.length\n\t\t: Math.max(argumentPrefix.lastIndexOf(\" \"), argumentPrefix.lastIndexOf(\"\\t\")) + 1;\n\tconst token = argumentPrefix.slice(tokenStart);\n\tconst equalsIndex = token.indexOf(\"=\");\n\tif (equalsIndex > 0) {\n\t\tconst inputName = token.slice(0, equalsIndex);\n\t\tconst input = workflow.inputs[inputName];\n\t\tif (input?.kind !== \"boolean\") return null;\n\t\treturn completeWorkflowToken(argumentPrefix, [\n\t\t\t{ value: `${inputName}=true `, label: \"true\", description: inputName },\n\t\t\t{ value: `${inputName}=false `, label: \"false\", description: inputName },\n\t\t]);\n\t}\n\n\treturn completeWorkflowToken(argumentPrefix, [\n\t\t{ value: \"--no-picker \", label: \"--no-picker\", description: \"Skip interactive input picker\" },\n\t\t{ value: \"--help \", label: \"--help\", description: \"Show this workflow's input schema\" },\n\t\t...Object.entries(workflow.inputs).map(([name, input]) => ({\n\t\t\tvalue: `${name}=`,\n\t\t\tlabel: name,\n\t\t\tdescription: input.description,\n\t\t})),\n\t]);\n}\n\nexport const BUILTIN_SLASH_COMMANDS: ReadonlyArray<BuiltinSlashCommand> = [\n\t{ name: \"settings\", description: \"Open settings menu\" },\n\t{ name: \"model\", description: \"Select model (opens selector UI)\" },\n\t{ name: \"scoped-models\", description: \"Enable/disable models for ctrl+p cycling\" },\n\t{ name: \"fast\", description: \"Configure Codex fast mode for chat and workflows\" },\n\t{ name: \"export\", description: \"Export session (HTML default, or specify path: .html/.jsonl)\" },\n\t{ name: \"import\", description: \"Import and resume a session from a JSONL file\" },\n\t{ name: \"share\", description: \"Share session as a secret GitHub gist\" },\n\t{ name: \"copy\", description: \"Copy last agent message to clipboard\" },\n\t{ name: \"name\", description: \"Set session display name\" },\n\t{ name: \"session\", description: \"Show session info and stats\" },\n\t{ name: \"changelog\", description: \"Show changelog entries\" },\n\t{\n\t\tname: ATOMIC_GUIDE_COMMAND_NAME,\n\t\tdescription: ATOMIC_GUIDE_COMMAND_DESCRIPTION,\n\t\tgetArgumentCompletions: getAtomicGuideArgumentCompletions,\n\t},\n\t{ name: \"hotkeys\", description: \"Show all keyboard shortcuts\" },\n\t{ name: \"fork\", description: \"Create a new fork from a previous user message\" },\n\t{ name: \"clone\", description: \"Duplicate the current session at the current position\" },\n\t{ name: \"tree\", description: \"Navigate session tree (switch branches)\" },\n\t{ name: \"trust\", description: \"Save project trust decision for future sessions\" },\n\t{ name: \"login\", description: \"Configure provider authentication\", argumentHint: \"<provider>\" },\n\t{ name: \"logout\", description: \"Remove provider authentication\" },\n\t{ name: \"new\", description: \"Start a new session\" },\n\t{ name: \"compact\", description: \"Compact older context with verbatim line ranges\" },\n\t{ name: \"resume\", description: \"Resume a different session\" },\n\t{ name: \"reload\", description: \"Reload keybindings, extensions, skills, prompts, and themes\" },\n\t{ name: \"exit\", description: `Exit ${APP_NAME}` },\n\t{ name: \"quit\", description: `Quit ${APP_NAME}` },\n];\n\nexport const BUNDLED_EXTENSION_SLASH_COMMANDS: ReadonlyArray<BuiltinSlashCommand> = [\n\t{\n\t\tname: \"workflow\",\n\t\tdescription: \"Run or inspect Atomic workflows. Usage: /workflow <name> [key=value…] | /workflow [list|status|connect|attach|interrupt|quit|pause|resume|inputs|reload] [args]\",\n\t\tgetArgumentCompletions: getBundledWorkflowArgumentCompletions,\n\t},\n\t{ name: \"run\", description: \"Run a subagent directly: /run agent[output=file] [task] [--bg] [--fork]\" },\n\t{ name: \"chain\", description: \"Run agents in sequence: /chain scout task -> planner [--bg] [--fork]\" },\n\t{ name: \"run-chain\", description: \"Run a saved chain: /run-chain chainName -- task [--bg] [--fork]\" },\n\t{ name: \"parallel\", description: \"Run agents in parallel: /parallel scout task1 -> reviewer task2 [--bg] [--fork]\" },\n\t{ name: \"subagents-doctor\", description: \"Show subagent diagnostics\" },\n\t{ name: \"mcp\", description: \"Show MCP server status\" },\n\t{ name: \"mcp-auth\", description: \"Authenticate with an MCP server (OAuth)\" },\n\t{ name: \"curator\", description: \"Toggle or configure the search curator workflow\" },\n\t{ name: \"google-account\", description: \"Show the active Google account for Gemini Web\" },\n\t{ name: \"search\", description: \"Browse stored web search results\" },\n\t{ name: \"websearch\", description: \"Open web search curator\" },\n\t{ name: \"intercom\", description: \"Open session intercom overlay\" },\n];\n"]}
+{"version":3,"file":"slash-commands.js","sourceRoot":"","sources":["../../src/core/slash-commands.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAC;AACxC,OAAO,EACN,gCAAgC,EAChC,yBAAyB,EACzB,iCAAiC,GACjC,MAAM,2BAA2B,CAAC;AAgCnC,MAAM,0BAA0B,GAAuB;IACtD,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,EAAE,SAAS,EAAE,WAAW,EAAE,mCAAmC,EAAE;IACzF,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,yCAAyC,EAAE;IAC7F,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,WAAW,EAAE,2BAA2B,EAAE;IAC3E,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,wDAAwD,EAAE;IAC5G,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,WAAW,EAAE,WAAW,EAAE,iBAAiB,EAAE;IAC3E,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,WAAW,EAAE,kCAAkC,EAAE;IAClF,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,sBAAsB,EAAE;IACxE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,2BAA2B,EAAE;IAC/E,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,gCAAgC,EAAE;IACpF,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,2BAA2B,EAAE;CAC/E,CAAC;AAEF,MAAM,oCAAoC,GAAiC;IAC1E;QACC,IAAI,EAAE,wBAAwB;QAC9B,WAAW,EAAE,6EAA6E;QAC1F,MAAM,EAAE;YACP,MAAM,EAAE,EAAE,WAAW,EAAE,4DAA4D,EAAE,IAAI,EAAE,QAAQ,EAAE;YACrG,cAAc,EAAE,EAAE,WAAW,EAAE,+DAA+D,EAAE,IAAI,EAAE,QAAQ,EAAE;YAChH,eAAe,EAAE,EAAE,WAAW,EAAE,6EAA6E,EAAE,IAAI,EAAE,QAAQ,EAAE;SAC/H;KACD;IACD;QACC,IAAI,EAAE,MAAM;QACZ,WAAW,EAAE,kJAAkJ;QAC/J,MAAM,EAAE;YACP,SAAS,EAAE,EAAE,WAAW,EAAE,2DAA2D,EAAE,IAAI,EAAE,QAAQ,EAAE;YACvG,mBAAmB,EAAE,EAAE,WAAW,EAAE,wEAAwE,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC9H,SAAS,EAAE,EAAE,WAAW,EAAE,4EAA4E,EAAE,IAAI,EAAE,QAAQ,EAAE;YACxH,WAAW,EAAE,EAAE,WAAW,EAAE,mEAAmE,EAAE,IAAI,EAAE,QAAQ,EAAE;YACjH,gBAAgB,EAAE,EAAE,WAAW,EAAE,6BAA6B,EAAE,IAAI,EAAE,QAAQ,EAAE;YAChF,SAAS,EAAE,EAAE,WAAW,EAAE,sEAAsE,EAAE,IAAI,EAAE,SAAS,EAAE;SACnH;KACD;IACD;QACC,IAAI,EAAE,oBAAoB;QAC1B,WAAW,EAAE,sGAAsG;QACnH,MAAM,EAAE;YACP,MAAM,EAAE,EAAE,WAAW,EAAE,qEAAqE,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC9G,mBAAmB,EAAE,EAAE,WAAW,EAAE,iEAAiE,EAAE,IAAI,EAAE,SAAS,EAAE;YACxH,eAAe,EAAE,EAAE,WAAW,EAAE,iDAAiD,EAAE,IAAI,EAAE,QAAQ,EAAE;SACnG;KACD;IACD;QACC,IAAI,EAAE,OAAO;QACb,WAAW,EAAE,gGAAgG;QAC7G,MAAM,EAAE;YACP,MAAM,EAAE,EAAE,WAAW,EAAE,oDAAoD,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC7F,mBAAmB,EAAE,EAAE,WAAW,EAAE,wEAAwE,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC9H,SAAS,EAAE,EAAE,WAAW,EAAE,iDAAiD,EAAE,IAAI,EAAE,QAAQ,EAAE;YAC7F,WAAW,EAAE,EAAE,WAAW,EAAE,0DAA0D,EAAE,IAAI,EAAE,QAAQ,EAAE;YACxG,gBAAgB,EAAE,EAAE,WAAW,EAAE,6BAA6B,EAAE,IAAI,EAAE,QAAQ,EAAE;YAChF,SAAS,EAAE,EAAE,WAAW,EAAE,uDAAuD,EAAE,IAAI,EAAE,SAAS,EAAE;SACpG;KACD;CACD,CAAC;AAEF,SAAS,qBAAqB,CAAC,YAAoB,EAAE,UAA8B;IAClF,MAAM,UAAU,GAAG,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC;QAC1C,CAAC,CAAC,YAAY,CAAC,MAAM;QACrB,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,YAAY,CAAC,WAAW,CAAC,GAAG,CAAC,EAAE,YAAY,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC;IAC/E,MAAM,IAAI,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC;IAC/C,MAAM,KAAK,GAAG,YAAY,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;IAC7C,MAAM,eAAe,GAAG,KAAK,CAAC,OAAO,EAAE,CAAC;IACxC,MAAM,QAAQ,GAAG,UAAU;SACzB,MAAM,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,SAAS,CAAC,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,SAAS,CAAC,KAAK,CAAC,OAAO,EAAE,KAAK,eAAe,CAAC;SACzG,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC,EAAE,GAAG,SAAS,EAAE,KAAK,EAAE,GAAG,IAAI,GAAG,SAAS,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,CAAC;IAC7E,OAAO,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC;AAC9C,CAAC;AAED,SAAS,wBAAwB;IAChC,OAAO,oCAAoC,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;QAC9D,KAAK,EAAE,GAAG,QAAQ,CAAC,IAAI,GAAG;QAC1B,KAAK,EAAE,QAAQ,CAAC,IAAI;QACpB,WAAW,EAAE,iBAAiB,QAAQ,CAAC,IAAI,EAAE;KAC7C,CAAC,CAAC,CAAC;AACL,CAAC;AAED,MAAM,UAAU,qCAAqC,CAAC,cAAsB;IAC3E,MAAM,KAAK,GAAG,cAAc,CAAC,IAAI,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;IACjE,MAAM,UAAU,GAAG,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IAClC,MAAM,aAAa,GAAG,wBAAwB,EAAE,CAAC;IACjD,IAAI,CAAC,cAAc,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;QACnC,OAAO,qBAAqB,CAAC,cAAc,EAAE,CAAC,GAAG,0BAA0B,EAAE,GAAG,aAAa,CAAC,CAAC,CAAC;IACjG,CAAC;IACD,IAAI,UAAU,KAAK,QAAQ;QAAE,OAAO,qBAAqB,CAAC,cAAc,EAAE,aAAa,CAAC,CAAC;IACzF,IAAI,UAAU,KAAK,WAAW,EAAE,CAAC;QAChC,OAAO,qBAAqB,CAAC,cAAc,EAAE;YAC5C,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,8BAA8B,EAAE;YAChF,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,mBAAmB,EAAE;YACrE,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,WAAW,EAAE,mBAAmB,EAAE;SAC/D,CAAC,CAAC;IACJ,CAAC;IACD,IAAI,UAAU,KAAK,MAAM,EAAE,CAAC;QAC3B,OAAO,qBAAqB,CAAC,cAAc,EAAE;YAC5C,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,4CAA4C,EAAE;SAC9F,CAAC,CAAC;IACJ,CAAC;IACD,IAAI,CAAC,UAAU;QAAE,OAAO,qBAAqB,CAAC,cAAc,EAAE,CAAC,GAAG,0BAA0B,EAAE,GAAG,aAAa,CAAC,CAAC,CAAC;IAEjH,MAAM,QAAQ,GAAG,oCAAoC,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,SAAS,CAAC,IAAI,KAAK,UAAU,CAAC,CAAC;IACzG,IAAI,CAAC,QAAQ;QAAE,OAAO,IAAI,CAAC;IAC3B,MAAM,UAAU,GAAG,KAAK,CAAC,IAAI,CAAC,cAAc,CAAC;QAC5C,CAAC,CAAC,cAAc,CAAC,MAAM;QACvB,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,cAAc,CAAC,WAAW,CAAC,GAAG,CAAC,EAAE,cAAc,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC;IACnF,MAAM,KAAK,GAAG,cAAc,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;IAC/C,MAAM,WAAW,GAAG,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;IACvC,IAAI,WAAW,GAAG,CAAC,EAAE,CAAC;QACrB,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,WAAW,CAAC,CAAC;QAC9C,MAAM,KAAK,GAAG,QAAQ,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;QACzC,IAAI,KAAK,EAAE,IAAI,KAAK,SAAS;YAAE,OAAO,IAAI,CAAC;QAC3C,OAAO,qBAAqB,CAAC,cAAc,EAAE;YAC5C,EAAE,KAAK,EAAE,GAAG,SAAS,QAAQ,EAAE,KAAK,EAAE,MAAM,EAAE,WAAW,EAAE,SAAS,EAAE;YACtE,EAAE,KAAK,EAAE,GAAG,SAAS,SAAS,EAAE,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,SAAS,EAAE;SACxE,CAAC,CAAC;IACJ,CAAC;IAED,OAAO,qBAAqB,CAAC,cAAc,EAAE;QAC5C,EAAE,KAAK,EAAE,cAAc,EAAE,KAAK,EAAE,aAAa,EAAE,WAAW,EAAE,+BAA+B,EAAE;QAC7F,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,mCAAmC,EAAE;QACvF,GAAG,MAAM,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC;YAC1D,KAAK,EAAE,GAAG,IAAI,GAAG;YACjB,KAAK,EAAE,IAAI;YACX,WAAW,EAAE,KAAK,CAAC,WAAW;SAC9B,CAAC,CAAC;KACH,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,CAAC,MAAM,sBAAsB,GAAuC;IACzE,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,oBAAoB,EAAE;IACvD,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,kCAAkC,EAAE;IAClE,EAAE,IAAI,EAAE,eAAe,EAAE,WAAW,EAAE,0CAA0C,EAAE;IAClF,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,kDAAkD,EAAE;IACjF,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,8DAA8D,EAAE;IAC/F,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,+CAA+C,EAAE;IAChF,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,uCAAuC,EAAE;IACvE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,sCAAsC,EAAE;IACrE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,0BAA0B,EAAE;IACzD,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,6BAA6B,EAAE;IAC/D,EAAE,IAAI,EAAE,WAAW,EAAE,WAAW,EAAE,wBAAwB,EAAE;IAC5D;QACC,IAAI,EAAE,yBAAyB;QAC/B,WAAW,EAAE,gCAAgC;QAC7C,sBAAsB,EAAE,iCAAiC;KACzD;IACD,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,6BAA6B,EAAE;IAC/D,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,gDAAgD,EAAE;IAC/E,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,uDAAuD,EAAE;IACvF,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,yCAAyC,EAAE;IACxE,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,iDAAiD,EAAE;IACjF,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,mCAAmC,EAAE,YAAY,EAAE,YAAY,EAAE;IAC/F,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,gCAAgC,EAAE;IACjE,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,qBAAqB,EAAE;IACnD,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,iDAAiD,EAAE;IACnF,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,4BAA4B,EAAE;IAC7D,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,6DAA6D,EAAE;IAC9F,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,QAAQ,QAAQ,EAAE,EAAE;IACjD,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,QAAQ,QAAQ,EAAE,EAAE;CACjD,CAAC;AAEF,MAAM,CAAC,MAAM,gCAAgC,GAAuC;IACnF;QACC,IAAI,EAAE,UAAU;QAChB,WAAW,EAAE,iKAAiK;QAC9K,sBAAsB,EAAE,qCAAqC;KAC7D;IACD,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,yEAAyE,EAAE;IACvG,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,sEAAsE,EAAE;IACtG,EAAE,IAAI,EAAE,WAAW,EAAE,WAAW,EAAE,iEAAiE,EAAE;IACrG,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,iFAAiF,EAAE;IACpH,EAAE,IAAI,EAAE,kBAAkB,EAAE,WAAW,EAAE,2BAA2B,EAAE;IACtE,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,wBAAwB,EAAE;IACtD,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,yCAAyC,EAAE;IAC5E,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,iDAAiD,EAAE;IACnF,EAAE,IAAI,EAAE,gBAAgB,EAAE,WAAW,EAAE,+CAA+C,EAAE;IACxF,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,kCAAkC,EAAE;IACnE,EAAE,IAAI,EAAE,WAAW,EAAE,WAAW,EAAE,yBAAyB,EAAE;IAC7D,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,+BAA+B,EAAE;CAClE,CAAC","sourcesContent":["import type { AutocompleteItem } from \"@earendil-works/pi-tui\";\nimport { APP_NAME } from \"../config.ts\";\nimport {\n\tATOMIC_GUIDE_COMMAND_DESCRIPTION,\n\tATOMIC_GUIDE_COMMAND_NAME,\n\tgetAtomicGuideArgumentCompletions,\n} from \"./atomic-guide-command.ts\";\nimport type { SourceInfo } from \"./source-info.ts\";\n\nexport type SlashCommandSource = \"extension\" | \"prompt\" | \"skill\";\n\nexport interface SlashCommandInfo {\n\tname: string;\n\tdescription?: string;\n\tsource: SlashCommandSource;\n\tsourceInfo: SourceInfo;\n}\n\nexport interface BuiltinSlashCommand {\n\tname: string;\n\tdescription: string;\n\targumentHint?: string;\n\tgetArgumentCompletions?: (\n\t\targumentPrefix: string,\n\t) => AutocompleteItem[] | null | Promise<AutocompleteItem[] | null>;\n}\n\ntype WorkflowInputCompletionMetadata = {\n\tdescription: string;\n\tkind?: \"boolean\" | \"number\" | \"string\";\n};\n\ntype WorkflowCompletionMetadata = {\n\tname: string;\n\tdescription: string;\n\tinputs: Record<string, WorkflowInputCompletionMetadata>;\n};\n\nconst WORKFLOW_ADMIN_COMPLETIONS: AutocompleteItem[] = [\n\t{ value: \"connect \", label: \"connect\", description: \"Attach to a run (picker if no id)\" },\n\t{ value: \"attach \", label: \"attach\", description: \"Open the in-place attach pane on a node\" },\n\t{ value: \"list \", label: \"list\", description: \"List registered workflows\" },\n\t{ value: \"status \", label: \"status\", description: \"List current-session active and retained terminal runs\" },\n\t{ value: \"interrupt \", label: \"interrupt\", description: \"Interrupt a run\" },\n\t{ value: \"quit \", label: \"quit\", description: \"Quit a run and keep it resumable\" },\n\t{ value: \"pause \", label: \"pause\", description: \"Pause a run or stage\" },\n\t{ value: \"resume \", label: \"resume\", description: \"Re-open overlay for a run\" },\n\t{ value: \"inputs \", label: \"inputs\", description: \"Show a workflow's input schema\" },\n\t{ value: \"reload \", label: \"reload\", description: \"Reload workflow resources\" },\n];\n\nconst BUNDLED_WORKFLOW_COMPLETION_METADATA: WorkflowCompletionMetadata[] = [\n\t{\n\t\tname: \"deep-research-codebase\",\n\t\tdescription: \"Heavy research for tasks requiring comprehensive, whole-repository context.\",\n\t\tinputs: {\n\t\t\tprompt: { description: \"Research question or investigation focus for the codebase.\", kind: \"string\" },\n\t\t\tmax_partitions: { description: \"Maximum number of codebase partitions to explore in parallel.\", kind: \"number\" },\n\t\t\tmax_concurrency: { description: \"Maximum number of workflow stages to run concurrently during deep research.\", kind: \"number\" },\n\t\t},\n\t},\n\t{\n\t\tname: \"goal\",\n\t\tdescription: \"Goal Runner workflow with bounded sub-agent orchestration turns, acceptance criteria, ledger artifacts, reviewers, and reducer-gated completion.\",\n\t\tinputs: {\n\t\t\tobjective: { description: \"The objective or delta for this Goal Runner workflow run.\", kind: \"string\" },\n\t\t\tacceptance_criteria: { description: \"Original immutable task contract this run must remain consistent with.\", kind: \"string\" },\n\t\t\tmax_turns: { description: \"Maximum orchestrator/review turns before Goal Runner stops as needs_human.\", kind: \"number\" },\n\t\t\tbase_branch: { description: \"Optional branch reviewers compare the current code delta against.\", kind: \"string\" },\n\t\t\tgit_worktree_dir: { description: \"Optional Git worktree path.\", kind: \"string\" },\n\t\t\tcreate_pr: { description: \"Whether to run the final pull-request creation stage after approval.\", kind: \"boolean\" },\n\t\t},\n\t},\n\t{\n\t\tname: \"open-claude-design\",\n\t\tdescription: \"AI-powered design workflow: discovery, reference research, HTML generation, refinement, and handoff.\",\n\t\tinputs: {\n\t\t\tprompt: { description: \"What to design, such as a dashboard, page, component, or prototype.\", kind: \"string\" },\n\t\t\tdiscover_references: { description: \"Discover current reference designs and feed them to generation.\", kind: \"boolean\" },\n\t\t\tmax_refinements: { description: \"Maximum generate/user-feedback loop iterations.\", kind: \"number\" },\n\t\t},\n\t},\n\t{\n\t\tname: \"ralph\",\n\t\tdescription: \"Raw prompt → research → orchestrate → multi-model parallel review loop with bounded iteration.\",\n\t\tinputs: {\n\t\t\tprompt: { description: \"The task or goal to research, execute, and refine.\", kind: \"string\" },\n\t\t\tacceptance_criteria: { description: \"Original immutable task contract this run must remain consistent with.\", kind: \"string\" },\n\t\t\tmax_loops: { description: \"Maximum research/orchestrate/review iterations.\", kind: \"number\" },\n\t\t\tbase_branch: { description: \"Branch reviewers compare the current code delta against.\", kind: \"string\" },\n\t\t\tgit_worktree_dir: { description: \"Optional Git worktree path.\", kind: \"string\" },\n\t\t\tcreate_pr: { description: \"Whether to run the final pull-request creation stage.\", kind: \"boolean\" },\n\t\t},\n\t},\n];\n\nfunction completeWorkflowToken(argumentText: string, candidates: AutocompleteItem[]): AutocompleteItem[] | null {\n\tconst tokenStart = /\\s$/.test(argumentText)\n\t\t? argumentText.length\n\t\t: Math.max(argumentText.lastIndexOf(\" \"), argumentText.lastIndexOf(\"\\t\")) + 1;\n\tconst head = argumentText.slice(0, tokenStart);\n\tconst token = argumentText.slice(tokenStart);\n\tconst normalizedToken = token.trimEnd();\n\tconst filtered = candidates\n\t\t.filter((candidate) => candidate.value.startsWith(token) && candidate.value.trimEnd() !== normalizedToken)\n\t\t.map((candidate) => ({ ...candidate, value: `${head}${candidate.value}` }));\n\treturn filtered.length > 0 ? filtered : null;\n}\n\nfunction bundledWorkflowNameItems(): AutocompleteItem[] {\n\treturn BUNDLED_WORKFLOW_COMPLETION_METADATA.map((workflow) => ({\n\t\tvalue: `${workflow.name} `,\n\t\tlabel: workflow.name,\n\t\tdescription: `Run workflow: ${workflow.name}`,\n\t}));\n}\n\nexport function getBundledWorkflowArgumentCompletions(argumentPrefix: string): AutocompleteItem[] | null {\n\tconst parts = argumentPrefix.trim().split(/\\s+/).filter(Boolean);\n\tconst subcommand = parts[0] ?? \"\";\n\tconst workflowItems = bundledWorkflowNameItems();\n\tif (!argumentPrefix.includes(\" \")) {\n\t\treturn completeWorkflowToken(argumentPrefix, [...WORKFLOW_ADMIN_COMPLETIONS, ...workflowItems]);\n\t}\n\tif (subcommand === \"inputs\") return completeWorkflowToken(argumentPrefix, workflowItems);\n\tif (subcommand === \"interrupt\") {\n\t\treturn completeWorkflowToken(argumentPrefix, [\n\t\t\t{ value: \"--all \", label: \"--all\", description: \"Interrupt all in-flight runs\" },\n\t\t\t{ value: \"--yes \", label: \"--yes\", description: \"Skip confirmation\" },\n\t\t\t{ value: \"-y \", label: \"-y\", description: \"Skip confirmation\" },\n\t\t]);\n\t}\n\tif (subcommand === \"quit\") {\n\t\treturn completeWorkflowToken(argumentPrefix, [\n\t\t\t{ value: \"--all \", label: \"--all\", description: \"Quit and keep all in-flight runs resumable\" },\n\t\t]);\n\t}\n\tif (!subcommand) return completeWorkflowToken(argumentPrefix, [...WORKFLOW_ADMIN_COMPLETIONS, ...workflowItems]);\n\n\tconst workflow = BUNDLED_WORKFLOW_COMPLETION_METADATA.find((candidate) => candidate.name === subcommand);\n\tif (!workflow) return null;\n\tconst tokenStart = /\\s$/.test(argumentPrefix)\n\t\t? argumentPrefix.length\n\t\t: Math.max(argumentPrefix.lastIndexOf(\" \"), argumentPrefix.lastIndexOf(\"\\t\")) + 1;\n\tconst token = argumentPrefix.slice(tokenStart);\n\tconst equalsIndex = token.indexOf(\"=\");\n\tif (equalsIndex > 0) {\n\t\tconst inputName = token.slice(0, equalsIndex);\n\t\tconst input = workflow.inputs[inputName];\n\t\tif (input?.kind !== \"boolean\") return null;\n\t\treturn completeWorkflowToken(argumentPrefix, [\n\t\t\t{ value: `${inputName}=true `, label: \"true\", description: inputName },\n\t\t\t{ value: `${inputName}=false `, label: \"false\", description: inputName },\n\t\t]);\n\t}\n\n\treturn completeWorkflowToken(argumentPrefix, [\n\t\t{ value: \"--no-picker \", label: \"--no-picker\", description: \"Skip interactive input picker\" },\n\t\t{ value: \"--help \", label: \"--help\", description: \"Show this workflow's input schema\" },\n\t\t...Object.entries(workflow.inputs).map(([name, input]) => ({\n\t\t\tvalue: `${name}=`,\n\t\t\tlabel: name,\n\t\t\tdescription: input.description,\n\t\t})),\n\t]);\n}\n\nexport const BUILTIN_SLASH_COMMANDS: ReadonlyArray<BuiltinSlashCommand> = [\n\t{ name: \"settings\", description: \"Open settings menu\" },\n\t{ name: \"model\", description: \"Select model (opens selector UI)\" },\n\t{ name: \"scoped-models\", description: \"Enable/disable models for ctrl+p cycling\" },\n\t{ name: \"fast\", description: \"Configure Codex fast mode for chat and workflows\" },\n\t{ name: \"export\", description: \"Export session (HTML default, or specify path: .html/.jsonl)\" },\n\t{ name: \"import\", description: \"Import and resume a session from a JSONL file\" },\n\t{ name: \"share\", description: \"Share session as a secret GitHub gist\" },\n\t{ name: \"copy\", description: \"Copy last agent message to clipboard\" },\n\t{ name: \"name\", description: \"Set session display name\" },\n\t{ name: \"session\", description: \"Show session info and stats\" },\n\t{ name: \"changelog\", description: \"Show changelog entries\" },\n\t{\n\t\tname: ATOMIC_GUIDE_COMMAND_NAME,\n\t\tdescription: ATOMIC_GUIDE_COMMAND_DESCRIPTION,\n\t\tgetArgumentCompletions: getAtomicGuideArgumentCompletions,\n\t},\n\t{ name: \"hotkeys\", description: \"Show all keyboard shortcuts\" },\n\t{ name: \"fork\", description: \"Create a new fork from a previous user message\" },\n\t{ name: \"clone\", description: \"Duplicate the current session at the current position\" },\n\t{ name: \"tree\", description: \"Navigate session tree (switch branches)\" },\n\t{ name: \"trust\", description: \"Save project trust decision for future sessions\" },\n\t{ name: \"login\", description: \"Configure provider authentication\", argumentHint: \"<provider>\" },\n\t{ name: \"logout\", description: \"Remove provider authentication\" },\n\t{ name: \"new\", description: \"Start a new session\" },\n\t{ name: \"compact\", description: \"Compact older context with verbatim line ranges\" },\n\t{ name: \"resume\", description: \"Resume a different session\" },\n\t{ name: \"reload\", description: \"Reload keybindings, extensions, skills, prompts, and themes\" },\n\t{ name: \"exit\", description: `Exit ${APP_NAME}` },\n\t{ name: \"quit\", description: `Quit ${APP_NAME}` },\n];\n\nexport const BUNDLED_EXTENSION_SLASH_COMMANDS: ReadonlyArray<BuiltinSlashCommand> = [\n\t{\n\t\tname: \"workflow\",\n\t\tdescription: \"Run or inspect Atomic workflows. Usage: /workflow <name> [key=value…] | /workflow [list|status|connect|attach|interrupt|quit|pause|resume|inputs|reload] [args]\",\n\t\tgetArgumentCompletions: getBundledWorkflowArgumentCompletions,\n\t},\n\t{ name: \"run\", description: \"Run a subagent directly: /run agent[output=file] [task] [--bg] [--fork]\" },\n\t{ name: \"chain\", description: \"Run agents in sequence: /chain scout task -> planner [--bg] [--fork]\" },\n\t{ name: \"run-chain\", description: \"Run a saved chain: /run-chain chainName -- task [--bg] [--fork]\" },\n\t{ name: \"parallel\", description: \"Run agents in parallel: /parallel scout task1 -> reviewer task2 [--bg] [--fork]\" },\n\t{ name: \"subagents-doctor\", description: \"Show subagent diagnostics\" },\n\t{ name: \"mcp\", description: \"Show MCP server status\" },\n\t{ name: \"mcp-auth\", description: \"Authenticate with an MCP server (OAuth)\" },\n\t{ name: \"curator\", description: \"Toggle or configure the search curator workflow\" },\n\t{ name: \"google-account\", description: \"Show the active Google account for Gemini Web\" },\n\t{ name: \"search\", description: \"Browse stored web search results\" },\n\t{ name: \"websearch\", description: \"Open web search curator\" },\n\t{ name: \"intercom\", description: \"Open session intercom overlay\" },\n];\n"]}

package/dist/core/system-prompt.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"system-prompt.d.ts","sourceRoot":"","sources":["../../src/core/system-prompt.ts"],"names":[],"mappings":"AAAA;;GAEG;AAGH,OAAO,EAAyB,KAAK,KAAK,EAAE,MAAM,aAAa,CAAC;AAahE,MAAM,WAAW,iBAAiB;IAChC,kDAAkD;IAClD,QAAQ,EAAE,MAAM,CAAC;IACjB,iDAAiD;IACjD,EAAE,EAAE,MAAM,CAAC;IACX,iDAAiD;IACjD,IAAI,CAAC,EAAE,MAAM,CAAC;CACf;AAED,MAAM,WAAW,wBAAwB;IACvC,+CAA+C;IAC/C,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,4GAA4G;IAC5G,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,wFAAwF;IACxF,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,0DAA0D;IAC1D,YAAY,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACtC,qFAAqF;IACrF,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;IAC5B,uCAAuC;IACvC,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B,yBAAyB;IACzB,GAAG,EAAE,MAAM,CAAC;IACZ,sEAAsE;IACtE,aAAa,CAAC,EAAE,iBAAiB,CAAC;IAClC,+DAA+D;IAC/D,qBAAqB,CAAC,EAAE,MAAM,CAAC;IAC/B,gCAAgC;IAChC,YAAY,CAAC,EAAE,KAAK,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IACxD,yBAAyB;IACzB,MAAM,CAAC,EAAE,KAAK,EAAE,CAAC;CAClB;AAED,kEAAkE;AAClE,wBAAgB,iBAAiB,CAAC,OAAO,EAAE,wBAAwB,GAAG,MAAM,CAyK3E"}
+{"version":3,"file":"system-prompt.d.ts","sourceRoot":"","sources":["../../src/core/system-prompt.ts"],"names":[],"mappings":"AAAA;;GAEG;AAGH,OAAO,EAAyB,KAAK,KAAK,EAAE,MAAM,aAAa,CAAC;AAsBhE,MAAM,WAAW,iBAAiB;IAChC,kDAAkD;IAClD,QAAQ,EAAE,MAAM,CAAC;IACjB,iDAAiD;IACjD,EAAE,EAAE,MAAM,CAAC;IACX,iDAAiD;IACjD,IAAI,CAAC,EAAE,MAAM,CAAC;CACf;AAED,MAAM,WAAW,wBAAwB;IACvC,+CAA+C;IAC/C,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,4GAA4G;IAC5G,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,wFAAwF;IACxF,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,0DAA0D;IAC1D,YAAY,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACtC,qFAAqF;IACrF,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;IAC5B,uCAAuC;IACvC,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B,yBAAyB;IACzB,GAAG,EAAE,MAAM,CAAC;IACZ,sEAAsE;IACtE,aAAa,CAAC,EAAE,iBAAiB,CAAC;IAClC,+DAA+D;IAC/D,qBAAqB,CAAC,EAAE,MAAM,CAAC;IAC/B,gCAAgC;IAChC,YAAY,CAAC,EAAE,KAAK,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IACxD,yBAAyB;IACzB,MAAM,CAAC,EAAE,KAAK,EAAE,CAAC;CAClB;AAED,kEAAkE;AAClE,wBAAgB,iBAAiB,CAAC,OAAO,EAAE,wBAAwB,GAAG,MAAM,CA6K3E"}

package/dist/core/system-prompt.js

@@ -13,6 +13,14 @@ const DEFAULT_PROMPT_TOOLS = [
     "ask_user_question",
     "todo",
 ];
+const DEFAULT_COMMUNICATION_GUIDELINES = [
+    "Never use a familiar printed metaphor, simile, or figure of speech.",
+    "Never use a long word where a short one will do.",
+    "Cut every word that can be cut.",
+    "Use active rather than passive voice where possible.",
+    "Prefer everyday English to foreign phrases, scientific terms, and jargon.",
+    "Break any rule rather than say anything outright barbarous.",
+];
 /** Build the system prompt with tools, guidelines, and context */
 export function buildSystemPrompt(options) {
     const { customPrompt, selectedTools, excludedTools, toolSnippets, promptGuidelines, appendSystemPrompt, cwd, selectedModel, selectedThinkingLevel, contextFiles: providedContextFiles, skills: providedSkills, } = options;
@@ -100,6 +108,9 @@ export function buildSystemPrompt(options) {
         }
     }
     // Always include these
+    for (const guideline of DEFAULT_COMMUNICATION_GUIDELINES) {
+        addGuideline(guideline);
+    }
     addGuideline("Be concise in your responses");
     addGuideline("Show file paths clearly when working with files");
     const guidelines = guidelinesList.map((g) => `- ${g}`).join("\n");

package/dist/core/system-prompt.js.map

@@ -1 +1 @@
-{"version":3,"file":"system-prompt.js","sourceRoot":"","sources":["../../src/core/system-prompt.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,WAAW,EAAE,eAAe,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC;AAC3E,OAAO,EAAE,qBAAqB,EAAc,MAAM,aAAa,CAAC;AAEhE,MAAM,oBAAoB,GAAG;IAC3B,MAAM;IACN,MAAM;IACN,MAAM;IACN,OAAO;IACP,MAAM;IACN,QAAQ;IACR,mBAAmB;IACnB,MAAM;CACE,CAAC;AAoCX,kEAAkE;AAClE,MAAM,UAAU,iBAAiB,CAAC,OAAiC;IACjE,MAAM,EACJ,YAAY,EACZ,aAAa,EACb,aAAa,EACb,YAAY,EACZ,gBAAgB,EAChB,kBAAkB,EAClB,GAAG,EACH,aAAa,EACb,qBAAqB,EACrB,YAAY,EAAE,oBAAoB,EAClC,MAAM,EAAE,cAAc,GACvB,GAAG,OAAO,CAAC;IACZ,MAAM,WAAW,GAAG,GAAG,CAAC;IACxB,MAAM,SAAS,GAAG,WAAW,CAAC,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC;IAElD,MAAM,GAAG,GAAG,IAAI,IAAI,EAAE,CAAC;IACvB,MAAM,IAAI,GAAG,GAAG,CAAC,WAAW,EAAE,CAAC;IAC/B,MAAM,KAAK,GAAG,MAAM,CAAC,GAAG,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;IAC1D,MAAM,GAAG,GAAG,MAAM,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;IACnD,MAAM,IAAI,GAAG,GAAG,IAAI,IAAI,KAAK,IAAI,GAAG,EAAE,CAAC;IAEvC,MAAM,aAAa,GAAG,kBAAkB,CAAC,CAAC,CAAC,OAAO,kBAAkB,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;IAC5E,MAAM,SAAS,GACb,aAAa,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,aAAa,EAAE,EAAE,IAAI,SAAS,CAAC;IAChE,MAAM,mBAAmB,GAAG,qBAAqB,EAAE,IAAI,EAAE,IAAI,KAAK,CAAC;IAEnE,MAAM,YAAY,GAAG,oBAAoB,IAAI,EAAE,CAAC;IAChD,MAAM,MAAM,GAAG,cAAc,IAAI,EAAE,CAAC;IACpC,MAAM,uBAAuB,GAAG,IAAI,GAAG,CAAC,aAAa,IAAI,EAAE,CAAC,CAAC;IAC7D,MAAM,qBAAqB,GAAG,CAAC,IAAY,EAAW,EAAE,CACtD,CAAC,CAAC,aAAa,IAAI,aAAa,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QAChD,CAAC,uBAAuB,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;IAErC,IAAI,YAAY,EAAE,CAAC;QACjB,IAAI,MAAM,GAAG,YAAY,CAAC;QAE1B,IAAI,aAAa,EAAE,CAAC;YAClB,MAAM,IAAI,aAAa,CAAC;QAC1B,CAAC;QAED,+BAA+B;QAC/B,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC5B,MAAM,IAAI,2BAA2B,CAAC;YACtC,MAAM,IAAI,mDAAmD,CAAC;YAC9D,KAAK,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,YAAY,EAAE,CAAC;gBACvD,MAAM,IAAI,wBAAwB,QAAQ,QAAQ,OAAO,uBAAuB,CAAC;YACnF,CAAC;QACH,CAAC;QAED,yDAAyD;QACzD,IAAI,qBAAqB,CAAC,MAAM,CAAC,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACvD,MAAM,IAAI,qBAAqB,CAAC,MAAM,CAAC,CAAC;QAC1C,CAAC;QAED,uDAAuD;QACvD,MAAM,IAAI,+CAA+C,SAAS,EAAE,CAAC;QACrE,MAAM,IAAI,4BAA4B,mBAAmB,EAAE,CAAC;QAC5D,MAAM,IAAI,mBAAmB,IAAI,EAAE,CAAC;QACpC,MAAM,IAAI,gCAAgC,SAAS,EAAE,CAAC;QAEtD,OAAO,MAAM,CAAC;IAChB,CAAC;IAED,mDAAmD;IACnD,MAAM,UAAU,GAAG,aAAa,EAAE,CAAC;IACnC,MAAM,QAAQ,GAAG,WAAW,EAAE,CAAC;IAC/B,MAAM,YAAY,GAAG,eAAe,EAAE,CAAC;IAEvC,4CAA4C;IAC5C,sFAAsF;IACtF,MAAM,KAAK,GAAG,CAAC,aAAa,IAAI,oBAAoB,CAAC,CAAC,MAAM,CAC1D,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,uBAAuB,CAAC,GAAG,CAAC,IAAI,CAAC,CAC7C,CAAC;IACF,MAAM,YAAY,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,CAAC,YAAY,EAAE,CAAC,IAAI,CAAC,CAAC,CAAC;IACpE,MAAM,SAAS,GACb,YAAY,CAAC,MAAM,GAAG,CAAC;QACrB,CAAC,CAAC,YAAY;aACT,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,IAAI,KAAK,YAAa,CAAC,IAAI,CAAC,EAAE,CAAC;aAClD,IAAI,CAAC,IAAI,CAAC;QACf,CAAC,CAAC,QAAQ,CAAC;IAEf,+DAA+D;IAC/D,MAAM,cAAc,GAAa,EAAE,CAAC;IACpC,MAAM,aAAa,GAAG,IAAI,GAAG,EAAU,CAAC;IACxC,MAAM,YAAY,GAAG,CAAC,SAAiB,EAAQ,EAAE;QAC/C,IAAI,aAAa,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC;YACjC,OAAO;QACT,CAAC;QACD,aAAa,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;QAC7B,cAAc,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IACjC,CAAC,CAAC;IAEF,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IACvC,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IACvC,MAAM,KAAK,GAAG,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IACnC,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IACvC,MAAM,oCAAoC,GACxC,aAAa,KAAK,SAAS;QAC3B,KAAK,CAAC,MAAM,GAAG,CAAC;QAChB,CAAC,KAAK,CAAC,QAAQ,CAAC,mBAAmB,CAAC;QACpC,CAAC,uBAAuB,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC;IAEpD,8BAA8B;IAC9B,IAAI,OAAO,IAAI,CAAC,OAAO,IAAI,CAAC,KAAK,EAAE,CAAC;QAClC,YAAY,CAAC,gDAAgD,CAAC,CAAC;IACjE,CAAC;IACD,IAAI,oCAAoC,EAAE,CAAC;QACzC,YAAY,CAAC,+EAA+E,CAAC,CAAC;IAChG,CAAC;IAED,KAAK,MAAM,SAAS,IAAI,gBAAgB,IAAI,EAAE,EAAE,CAAC;QAC/C,MAAM,UAAU,GAAG,SAAS,CAAC,IAAI,EAAE,CAAC;QACpC,IAAI,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC1B,YAAY,CAAC,UAAU,CAAC,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,uBAAuB;IACvB,YAAY,CAAC,8BAA8B,CAAC,CAAC;IAC7C,YAAY,CAAC,iDAAiD,CAAC,CAAC;IAEhE,MAAM,UAAU,GAAG,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAElE,IAAI,MAAM,GAAG;;;EAGb,SAAS;;;;;EAKT,UAAU;;;wBAGY,UAAU;qBACb,QAAQ;cACf,YAAY;yGAC+E,QAAQ,kCAAkC,YAAY;;;8GAGjD,CAAC;IAE7G,IAAI,aAAa,EAAE,CAAC;QAClB,MAAM,IAAI,aAAa,CAAC;IAC1B,CAAC;IAED,+BAA+B;IAC/B,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC5B,MAAM,IAAI,2BAA2B,CAAC;QACtC,MAAM,IAAI,mDAAmD,CAAC;QAC9D,KAAK,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,YAAY,EAAE,CAAC;YACvD,MAAM,IAAI,wBAAwB,QAAQ,QAAQ,OAAO,uBAAuB,CAAC;QACnF,CAAC;IACH,CAAC;IAED,yDAAyD;IACzD,IAAI,OAAO,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACjC,MAAM,IAAI,qBAAqB,CAAC,MAAM,CAAC,CAAC;IAC1C,CAAC;IAED,uDAAuD;IACvD,MAAM,IAAI,+CAA+C,SAAS,EAAE,CAAC;IACrE,MAAM,IAAI,4BAA4B,mBAAmB,EAAE,CAAC;IAC5D,MAAM,IAAI,mBAAmB,IAAI,EAAE,CAAC;IACpC,MAAM,IAAI,gCAAgC,SAAS,EAAE,CAAC;IAEtD,OAAO,MAAM,CAAC;AAChB,CAAC","sourcesContent":["/**\n * System prompt construction and project context loading\n */\n\nimport { getDocsPath, getExamplesPath, getReadmePath } from \"../config.ts\";\nimport { formatSkillsForPrompt, type Skill } from \"./skills.ts\";\n\nconst DEFAULT_PROMPT_TOOLS = [\n  \"read\",\n  \"bash\",\n  \"edit\",\n  \"write\",\n  \"find\",\n  \"search\",\n  \"ask_user_question\",\n  \"todo\",\n] as const;\n\nexport interface SystemPromptModel {\n  /** Provider identifier for the selected model. */\n  provider: string;\n  /** Stable provider-specific model identifier. */\n  id: string;\n  /** Human-readable model name, when available. */\n  name?: string;\n}\n\nexport interface BuildSystemPromptOptions {\n  /** Custom system prompt (replaces default). */\n  customPrompt?: string;\n  /** Tools to include in prompt. Default: [read, bash, edit, write, find, search, ask_user_question, todo] */\n  selectedTools?: string[];\n  /** Tool names explicitly excluded by the caller and omitted from generated guidance. */\n  excludedTools?: string[];\n  /** Optional one-line tool snippets keyed by tool name. */\n  toolSnippets?: Record<string, string>;\n  /** Additional guideline bullets appended to the default system prompt guidelines. */\n  promptGuidelines?: string[];\n  /** Text to append to system prompt. */\n  appendSystemPrompt?: string;\n  /** Working directory. */\n  cwd: string;\n  /** Currently selected model, used for model-aware prompt metadata. */\n  selectedModel?: SystemPromptModel;\n  /** Current reasoning/thinking level for the selected model. */\n  selectedThinkingLevel?: string;\n  /** Pre-loaded context files. */\n  contextFiles?: Array<{ path: string; content: string }>;\n  /** Pre-loaded skills. */\n  skills?: Skill[];\n}\n\n/** Build the system prompt with tools, guidelines, and context */\nexport function buildSystemPrompt(options: BuildSystemPromptOptions): string {\n  const {\n    customPrompt,\n    selectedTools,\n    excludedTools,\n    toolSnippets,\n    promptGuidelines,\n    appendSystemPrompt,\n    cwd,\n    selectedModel,\n    selectedThinkingLevel,\n    contextFiles: providedContextFiles,\n    skills: providedSkills,\n  } = options;\n  const resolvedCwd = cwd;\n  const promptCwd = resolvedCwd.replace(/\\\\/g, \"/\");\n\n  const now = new Date();\n  const year = now.getFullYear();\n  const month = String(now.getMonth() + 1).padStart(2, \"0\");\n  const day = String(now.getDate()).padStart(2, \"0\");\n  const date = `${year}-${month}-${day}`;\n\n  const appendSection = appendSystemPrompt ? `\\n\\n${appendSystemPrompt}` : \"\";\n  const modelName =\n    selectedModel?.name?.trim() || selectedModel?.id || \"unknown\";\n  const modelReasoningLevel = selectedThinkingLevel?.trim() || \"off\";\n\n  const contextFiles = providedContextFiles ?? [];\n  const skills = providedSkills ?? [];\n  const explicitlyExcludedTools = new Set(excludedTools ?? []);\n  const isPromptToolAvailable = (name: string): boolean =>\n    (!selectedTools || selectedTools.includes(name)) &&\n    !explicitlyExcludedTools.has(name);\n\n  if (customPrompt) {\n    let prompt = customPrompt;\n\n    if (appendSection) {\n      prompt += appendSection;\n    }\n\n    // Append project context files\n    if (contextFiles.length > 0) {\n      prompt += \"\\n\\n# Project Context\\n\\n\";\n      prompt += \"Project-specific instructions and guidelines:\\n\\n\";\n      for (const { path: filePath, content } of contextFiles) {\n        prompt += `<context_file path=\\\"${filePath}\\\">\\n${content}\\n</context_file>\\n\\n`;\n      }\n    }\n\n    // Append skills section (only if read tool is available)\n    if (isPromptToolAvailable(\"read\") && skills.length > 0) {\n      prompt += formatSkillsForPrompt(skills);\n    }\n\n    // Add model metadata, date, and working directory last\n    prompt += `\\nModel name (used for commit attribution): ${modelName}`;\n    prompt += `\\nModel reasoning level: ${modelReasoningLevel}`;\n    prompt += `\\nCurrent date: ${date}`;\n    prompt += `\\nCurrent working directory: ${promptCwd}`;\n\n    return prompt;\n  }\n\n  // Get absolute paths to documentation and examples\n  const readmePath = getReadmePath();\n  const docsPath = getDocsPath();\n  const examplesPath = getExamplesPath();\n\n  // Build tools list based on selected tools.\n  // A tool appears in Available tools only when the caller provides a one-line snippet.\n  const tools = (selectedTools ?? DEFAULT_PROMPT_TOOLS).filter(\n    (name) => !explicitlyExcludedTools.has(name),\n  );\n  const visibleTools = tools.filter((name) => !!toolSnippets?.[name]);\n  const toolsList =\n    visibleTools.length > 0\n      ? visibleTools\n          .map((name) => `- ${name}: ${toolSnippets![name]}`)\n          .join(\"\\n\")\n      : \"(none)\";\n\n  // Build guidelines based on which tools are actually available\n  const guidelinesList: string[] = [];\n  const guidelinesSet = new Set<string>();\n  const addGuideline = (guideline: string): void => {\n    if (guidelinesSet.has(guideline)) {\n      return;\n    }\n    guidelinesSet.add(guideline);\n    guidelinesList.push(guideline);\n  };\n\n  const hasBash = tools.includes(\"bash\");\n  const hasFind = tools.includes(\"find\");\n  const hasLs = tools.includes(\"ls\");\n  const hasRead = tools.includes(\"read\");\n  const shouldIncludeAskUserFallbackGuidance =\n    selectedTools !== undefined &&\n    tools.length > 0 &&\n    !tools.includes(\"ask_user_question\") &&\n    !explicitlyExcludedTools.has(\"ask_user_question\");\n\n  // File exploration guidelines\n  if (hasBash && !hasFind && !hasLs) {\n    addGuideline(\"Use bash for file operations like ls, rg, find\");\n  }\n  if (shouldIncludeAskUserFallbackGuidance) {\n    addGuideline(\"Clarify ambiguous requirements using the ask_user_question tool if available.\");\n  }\n\n  for (const guideline of promptGuidelines ?? []) {\n    const normalized = guideline.trim();\n    if (normalized.length > 0) {\n      addGuideline(normalized);\n    }\n  }\n\n  // Always include these\n  addGuideline(\"Be concise in your responses\");\n  addGuideline(\"Show file paths clearly when working with files\");\n\n  const guidelines = guidelinesList.map((g) => `- ${g}`).join(\"\\n\");\n\n  let prompt = `You are an expert coding assistant operating named Atomic, a coding agent harness. You help users by reading files, executing commands, editing code, and writing new files.\n\nAvailable tools:\n${toolsList}\n\nIn addition to the tools above, you may have access to other custom tools depending on the project.\n\nGuidelines:\n${guidelines}\n\nAtomic documentation (read only when the user asks about customizing Atomic itself, its SDK, creating workflows, packages, extensions, themes, skills, or TUI):\n- Main documentation: ${readmePath}\n- Additional docs: ${docsPath}\n- Examples: ${examplesPath} (extensions, custom tools, SDK)\n- Docs/examples references above must be resolved against these absolute roots; e.g. docs/foo.md means ${docsPath}/foo.md and examples/bar means ${examplesPath}/bar.\n- When asked about: atomic workflows (docs/workflows.md), extensions (docs/extensions.md, examples/extensions/), themes (docs/themes.md), skills (docs/skills.md), prompt templates (docs/prompt-templates.md), TUI components (docs/tui.md), keybindings (docs/keybindings.md), SDK integrations (docs/sdk.md), custom providers (docs/custom-provider.md), adding models (docs/models.md), atomic packages (docs/packages.md)\n- When working on Atomic topics, read the docs and examples, and follow .md cross-references before implementing\n- Always read Atomic .md files completely and follow links to related docs (e.g., tui.md for TUI API details)`;\n\n  if (appendSection) {\n    prompt += appendSection;\n  }\n\n  // Append project context files\n  if (contextFiles.length > 0) {\n    prompt += \"\\n\\n# Project Context\\n\\n\";\n    prompt += \"Project-specific instructions and guidelines:\\n\\n\";\n    for (const { path: filePath, content } of contextFiles) {\n      prompt += `<context_file path=\\\"${filePath}\\\">\\n${content}\\n</context_file>\\n\\n`;\n    }\n  }\n\n  // Append skills section (only if read tool is available)\n  if (hasRead && skills.length > 0) {\n    prompt += formatSkillsForPrompt(skills);\n  }\n\n  // Add model metadata, date, and working directory last\n  prompt += `\\nModel name (used for commit attribution): ${modelName}`;\n  prompt += `\\nModel reasoning level: ${modelReasoningLevel}`;\n  prompt += `\\nCurrent date: ${date}`;\n  prompt += `\\nCurrent working directory: ${promptCwd}`;\n\n  return prompt;\n}\n"]}
+{"version":3,"file":"system-prompt.js","sourceRoot":"","sources":["../../src/core/system-prompt.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,WAAW,EAAE,eAAe,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC;AAC3E,OAAO,EAAE,qBAAqB,EAAc,MAAM,aAAa,CAAC;AAEhE,MAAM,oBAAoB,GAAG;IAC3B,MAAM;IACN,MAAM;IACN,MAAM;IACN,OAAO;IACP,MAAM;IACN,QAAQ;IACR,mBAAmB;IACnB,MAAM;CACE,CAAC;AAEX,MAAM,gCAAgC,GAAG;IACvC,qEAAqE;IACrE,kDAAkD;IAClD,iCAAiC;IACjC,sDAAsD;IACtD,2EAA2E;IAC3E,6DAA6D;CACrD,CAAC;AAoCX,kEAAkE;AAClE,MAAM,UAAU,iBAAiB,CAAC,OAAiC;IACjE,MAAM,EACJ,YAAY,EACZ,aAAa,EACb,aAAa,EACb,YAAY,EACZ,gBAAgB,EAChB,kBAAkB,EAClB,GAAG,EACH,aAAa,EACb,qBAAqB,EACrB,YAAY,EAAE,oBAAoB,EAClC,MAAM,EAAE,cAAc,GACvB,GAAG,OAAO,CAAC;IACZ,MAAM,WAAW,GAAG,GAAG,CAAC;IACxB,MAAM,SAAS,GAAG,WAAW,CAAC,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC;IAElD,MAAM,GAAG,GAAG,IAAI,IAAI,EAAE,CAAC;IACvB,MAAM,IAAI,GAAG,GAAG,CAAC,WAAW,EAAE,CAAC;IAC/B,MAAM,KAAK,GAAG,MAAM,CAAC,GAAG,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;IAC1D,MAAM,GAAG,GAAG,MAAM,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;IACnD,MAAM,IAAI,GAAG,GAAG,IAAI,IAAI,KAAK,IAAI,GAAG,EAAE,CAAC;IAEvC,MAAM,aAAa,GAAG,kBAAkB,CAAC,CAAC,CAAC,OAAO,kBAAkB,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;IAC5E,MAAM,SAAS,GACb,aAAa,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,aAAa,EAAE,EAAE,IAAI,SAAS,CAAC;IAChE,MAAM,mBAAmB,GAAG,qBAAqB,EAAE,IAAI,EAAE,IAAI,KAAK,CAAC;IAEnE,MAAM,YAAY,GAAG,oBAAoB,IAAI,EAAE,CAAC;IAChD,MAAM,MAAM,GAAG,cAAc,IAAI,EAAE,CAAC;IACpC,MAAM,uBAAuB,GAAG,IAAI,GAAG,CAAC,aAAa,IAAI,EAAE,CAAC,CAAC;IAC7D,MAAM,qBAAqB,GAAG,CAAC,IAAY,EAAW,EAAE,CACtD,CAAC,CAAC,aAAa,IAAI,aAAa,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QAChD,CAAC,uBAAuB,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;IAErC,IAAI,YAAY,EAAE,CAAC;QACjB,IAAI,MAAM,GAAG,YAAY,CAAC;QAE1B,IAAI,aAAa,EAAE,CAAC;YAClB,MAAM,IAAI,aAAa,CAAC;QAC1B,CAAC;QAED,+BAA+B;QAC/B,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC5B,MAAM,IAAI,2BAA2B,CAAC;YACtC,MAAM,IAAI,mDAAmD,CAAC;YAC9D,KAAK,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,YAAY,EAAE,CAAC;gBACvD,MAAM,IAAI,wBAAwB,QAAQ,QAAQ,OAAO,uBAAuB,CAAC;YACnF,CAAC;QACH,CAAC;QAED,yDAAyD;QACzD,IAAI,qBAAqB,CAAC,MAAM,CAAC,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACvD,MAAM,IAAI,qBAAqB,CAAC,MAAM,CAAC,CAAC;QAC1C,CAAC;QAED,uDAAuD;QACvD,MAAM,IAAI,+CAA+C,SAAS,EAAE,CAAC;QACrE,MAAM,IAAI,4BAA4B,mBAAmB,EAAE,CAAC;QAC5D,MAAM,IAAI,mBAAmB,IAAI,EAAE,CAAC;QACpC,MAAM,IAAI,gCAAgC,SAAS,EAAE,CAAC;QAEtD,OAAO,MAAM,CAAC;IAChB,CAAC;IAED,mDAAmD;IACnD,MAAM,UAAU,GAAG,aAAa,EAAE,CAAC;IACnC,MAAM,QAAQ,GAAG,WAAW,EAAE,CAAC;IAC/B,MAAM,YAAY,GAAG,eAAe,EAAE,CAAC;IAEvC,4CAA4C;IAC5C,sFAAsF;IACtF,MAAM,KAAK,GAAG,CAAC,aAAa,IAAI,oBAAoB,CAAC,CAAC,MAAM,CAC1D,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,uBAAuB,CAAC,GAAG,CAAC,IAAI,CAAC,CAC7C,CAAC;IACF,MAAM,YAAY,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,CAAC,YAAY,EAAE,CAAC,IAAI,CAAC,CAAC,CAAC;IACpE,MAAM,SAAS,GACb,YAAY,CAAC,MAAM,GAAG,CAAC;QACrB,CAAC,CAAC,YAAY;aACT,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,IAAI,KAAK,YAAa,CAAC,IAAI,CAAC,EAAE,CAAC;aAClD,IAAI,CAAC,IAAI,CAAC;QACf,CAAC,CAAC,QAAQ,CAAC;IAEf,+DAA+D;IAC/D,MAAM,cAAc,GAAa,EAAE,CAAC;IACpC,MAAM,aAAa,GAAG,IAAI,GAAG,EAAU,CAAC;IACxC,MAAM,YAAY,GAAG,CAAC,SAAiB,EAAQ,EAAE;QAC/C,IAAI,aAAa,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC;YACjC,OAAO;QACT,CAAC;QACD,aAAa,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;QAC7B,cAAc,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IACjC,CAAC,CAAC;IAEF,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IACvC,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IACvC,MAAM,KAAK,GAAG,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IACnC,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IACvC,MAAM,oCAAoC,GACxC,aAAa,KAAK,SAAS;QAC3B,KAAK,CAAC,MAAM,GAAG,CAAC;QAChB,CAAC,KAAK,CAAC,QAAQ,CAAC,mBAAmB,CAAC;QACpC,CAAC,uBAAuB,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC;IAEpD,8BAA8B;IAC9B,IAAI,OAAO,IAAI,CAAC,OAAO,IAAI,CAAC,KAAK,EAAE,CAAC;QAClC,YAAY,CAAC,gDAAgD,CAAC,CAAC;IACjE,CAAC;IACD,IAAI,oCAAoC,EAAE,CAAC;QACzC,YAAY,CAAC,+EAA+E,CAAC,CAAC;IAChG,CAAC;IAED,KAAK,MAAM,SAAS,IAAI,gBAAgB,IAAI,EAAE,EAAE,CAAC;QAC/C,MAAM,UAAU,GAAG,SAAS,CAAC,IAAI,EAAE,CAAC;QACpC,IAAI,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC1B,YAAY,CAAC,UAAU,CAAC,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,uBAAuB;IACvB,KAAK,MAAM,SAAS,IAAI,gCAAgC,EAAE,CAAC;QACzD,YAAY,CAAC,SAAS,CAAC,CAAC;IAC1B,CAAC;IAED,YAAY,CAAC,8BAA8B,CAAC,CAAC;IAC7C,YAAY,CAAC,iDAAiD,CAAC,CAAC;IAEhE,MAAM,UAAU,GAAG,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAElE,IAAI,MAAM,GAAG;;;EAGb,SAAS;;;;;EAKT,UAAU;;;wBAGY,UAAU;qBACb,QAAQ;cACf,YAAY;yGAC+E,QAAQ,kCAAkC,YAAY;;;8GAGjD,CAAC;IAE7G,IAAI,aAAa,EAAE,CAAC;QAClB,MAAM,IAAI,aAAa,CAAC;IAC1B,CAAC;IAED,+BAA+B;IAC/B,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC5B,MAAM,IAAI,2BAA2B,CAAC;QACtC,MAAM,IAAI,mDAAmD,CAAC;QAC9D,KAAK,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,YAAY,EAAE,CAAC;YACvD,MAAM,IAAI,wBAAwB,QAAQ,QAAQ,OAAO,uBAAuB,CAAC;QACnF,CAAC;IACH,CAAC;IAED,yDAAyD;IACzD,IAAI,OAAO,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACjC,MAAM,IAAI,qBAAqB,CAAC,MAAM,CAAC,CAAC;IAC1C,CAAC;IAED,uDAAuD;IACvD,MAAM,IAAI,+CAA+C,SAAS,EAAE,CAAC;IACrE,MAAM,IAAI,4BAA4B,mBAAmB,EAAE,CAAC;IAC5D,MAAM,IAAI,mBAAmB,IAAI,EAAE,CAAC;IACpC,MAAM,IAAI,gCAAgC,SAAS,EAAE,CAAC;IAEtD,OAAO,MAAM,CAAC;AAChB,CAAC","sourcesContent":["/**\n * System prompt construction and project context loading\n */\n\nimport { getDocsPath, getExamplesPath, getReadmePath } from \"../config.ts\";\nimport { formatSkillsForPrompt, type Skill } from \"./skills.ts\";\n\nconst DEFAULT_PROMPT_TOOLS = [\n  \"read\",\n  \"bash\",\n  \"edit\",\n  \"write\",\n  \"find\",\n  \"search\",\n  \"ask_user_question\",\n  \"todo\",\n] as const;\n\nconst DEFAULT_COMMUNICATION_GUIDELINES = [\n  \"Never use a familiar printed metaphor, simile, or figure of speech.\",\n  \"Never use a long word where a short one will do.\",\n  \"Cut every word that can be cut.\",\n  \"Use active rather than passive voice where possible.\",\n  \"Prefer everyday English to foreign phrases, scientific terms, and jargon.\",\n  \"Break any rule rather than say anything outright barbarous.\",\n] as const;\n\nexport interface SystemPromptModel {\n  /** Provider identifier for the selected model. */\n  provider: string;\n  /** Stable provider-specific model identifier. */\n  id: string;\n  /** Human-readable model name, when available. */\n  name?: string;\n}\n\nexport interface BuildSystemPromptOptions {\n  /** Custom system prompt (replaces default). */\n  customPrompt?: string;\n  /** Tools to include in prompt. Default: [read, bash, edit, write, find, search, ask_user_question, todo] */\n  selectedTools?: string[];\n  /** Tool names explicitly excluded by the caller and omitted from generated guidance. */\n  excludedTools?: string[];\n  /** Optional one-line tool snippets keyed by tool name. */\n  toolSnippets?: Record<string, string>;\n  /** Additional guideline bullets appended to the default system prompt guidelines. */\n  promptGuidelines?: string[];\n  /** Text to append to system prompt. */\n  appendSystemPrompt?: string;\n  /** Working directory. */\n  cwd: string;\n  /** Currently selected model, used for model-aware prompt metadata. */\n  selectedModel?: SystemPromptModel;\n  /** Current reasoning/thinking level for the selected model. */\n  selectedThinkingLevel?: string;\n  /** Pre-loaded context files. */\n  contextFiles?: Array<{ path: string; content: string }>;\n  /** Pre-loaded skills. */\n  skills?: Skill[];\n}\n\n/** Build the system prompt with tools, guidelines, and context */\nexport function buildSystemPrompt(options: BuildSystemPromptOptions): string {\n  const {\n    customPrompt,\n    selectedTools,\n    excludedTools,\n    toolSnippets,\n    promptGuidelines,\n    appendSystemPrompt,\n    cwd,\n    selectedModel,\n    selectedThinkingLevel,\n    contextFiles: providedContextFiles,\n    skills: providedSkills,\n  } = options;\n  const resolvedCwd = cwd;\n  const promptCwd = resolvedCwd.replace(/\\\\/g, \"/\");\n\n  const now = new Date();\n  const year = now.getFullYear();\n  const month = String(now.getMonth() + 1).padStart(2, \"0\");\n  const day = String(now.getDate()).padStart(2, \"0\");\n  const date = `${year}-${month}-${day}`;\n\n  const appendSection = appendSystemPrompt ? `\\n\\n${appendSystemPrompt}` : \"\";\n  const modelName =\n    selectedModel?.name?.trim() || selectedModel?.id || \"unknown\";\n  const modelReasoningLevel = selectedThinkingLevel?.trim() || \"off\";\n\n  const contextFiles = providedContextFiles ?? [];\n  const skills = providedSkills ?? [];\n  const explicitlyExcludedTools = new Set(excludedTools ?? []);\n  const isPromptToolAvailable = (name: string): boolean =>\n    (!selectedTools || selectedTools.includes(name)) &&\n    !explicitlyExcludedTools.has(name);\n\n  if (customPrompt) {\n    let prompt = customPrompt;\n\n    if (appendSection) {\n      prompt += appendSection;\n    }\n\n    // Append project context files\n    if (contextFiles.length > 0) {\n      prompt += \"\\n\\n# Project Context\\n\\n\";\n      prompt += \"Project-specific instructions and guidelines:\\n\\n\";\n      for (const { path: filePath, content } of contextFiles) {\n        prompt += `<context_file path=\\\"${filePath}\\\">\\n${content}\\n</context_file>\\n\\n`;\n      }\n    }\n\n    // Append skills section (only if read tool is available)\n    if (isPromptToolAvailable(\"read\") && skills.length > 0) {\n      prompt += formatSkillsForPrompt(skills);\n    }\n\n    // Add model metadata, date, and working directory last\n    prompt += `\\nModel name (used for commit attribution): ${modelName}`;\n    prompt += `\\nModel reasoning level: ${modelReasoningLevel}`;\n    prompt += `\\nCurrent date: ${date}`;\n    prompt += `\\nCurrent working directory: ${promptCwd}`;\n\n    return prompt;\n  }\n\n  // Get absolute paths to documentation and examples\n  const readmePath = getReadmePath();\n  const docsPath = getDocsPath();\n  const examplesPath = getExamplesPath();\n\n  // Build tools list based on selected tools.\n  // A tool appears in Available tools only when the caller provides a one-line snippet.\n  const tools = (selectedTools ?? DEFAULT_PROMPT_TOOLS).filter(\n    (name) => !explicitlyExcludedTools.has(name),\n  );\n  const visibleTools = tools.filter((name) => !!toolSnippets?.[name]);\n  const toolsList =\n    visibleTools.length > 0\n      ? visibleTools\n          .map((name) => `- ${name}: ${toolSnippets![name]}`)\n          .join(\"\\n\")\n      : \"(none)\";\n\n  // Build guidelines based on which tools are actually available\n  const guidelinesList: string[] = [];\n  const guidelinesSet = new Set<string>();\n  const addGuideline = (guideline: string): void => {\n    if (guidelinesSet.has(guideline)) {\n      return;\n    }\n    guidelinesSet.add(guideline);\n    guidelinesList.push(guideline);\n  };\n\n  const hasBash = tools.includes(\"bash\");\n  const hasFind = tools.includes(\"find\");\n  const hasLs = tools.includes(\"ls\");\n  const hasRead = tools.includes(\"read\");\n  const shouldIncludeAskUserFallbackGuidance =\n    selectedTools !== undefined &&\n    tools.length > 0 &&\n    !tools.includes(\"ask_user_question\") &&\n    !explicitlyExcludedTools.has(\"ask_user_question\");\n\n  // File exploration guidelines\n  if (hasBash && !hasFind && !hasLs) {\n    addGuideline(\"Use bash for file operations like ls, rg, find\");\n  }\n  if (shouldIncludeAskUserFallbackGuidance) {\n    addGuideline(\"Clarify ambiguous requirements using the ask_user_question tool if available.\");\n  }\n\n  for (const guideline of promptGuidelines ?? []) {\n    const normalized = guideline.trim();\n    if (normalized.length > 0) {\n      addGuideline(normalized);\n    }\n  }\n\n  // Always include these\n  for (const guideline of DEFAULT_COMMUNICATION_GUIDELINES) {\n    addGuideline(guideline);\n  }\n\n  addGuideline(\"Be concise in your responses\");\n  addGuideline(\"Show file paths clearly when working with files\");\n\n  const guidelines = guidelinesList.map((g) => `- ${g}`).join(\"\\n\");\n\n  let prompt = `You are an expert coding assistant operating named Atomic, a coding agent harness. You help users by reading files, executing commands, editing code, and writing new files.\n\nAvailable tools:\n${toolsList}\n\nIn addition to the tools above, you may have access to other custom tools depending on the project.\n\nGuidelines:\n${guidelines}\n\nAtomic documentation (read only when the user asks about customizing Atomic itself, its SDK, creating workflows, packages, extensions, themes, skills, or TUI):\n- Main documentation: ${readmePath}\n- Additional docs: ${docsPath}\n- Examples: ${examplesPath} (extensions, custom tools, SDK)\n- Docs/examples references above must be resolved against these absolute roots; e.g. docs/foo.md means ${docsPath}/foo.md and examples/bar means ${examplesPath}/bar.\n- When asked about: atomic workflows (docs/workflows.md), extensions (docs/extensions.md, examples/extensions/), themes (docs/themes.md), skills (docs/skills.md), prompt templates (docs/prompt-templates.md), TUI components (docs/tui.md), keybindings (docs/keybindings.md), SDK integrations (docs/sdk.md), custom providers (docs/custom-provider.md), adding models (docs/models.md), atomic packages (docs/packages.md)\n- When working on Atomic topics, read the docs and examples, and follow .md cross-references before implementing\n- Always read Atomic .md files completely and follow links to related docs (e.g., tui.md for TUI API details)`;\n\n  if (appendSection) {\n    prompt += appendSection;\n  }\n\n  // Append project context files\n  if (contextFiles.length > 0) {\n    prompt += \"\\n\\n# Project Context\\n\\n\";\n    prompt += \"Project-specific instructions and guidelines:\\n\\n\";\n    for (const { path: filePath, content } of contextFiles) {\n      prompt += `<context_file path=\\\"${filePath}\\\">\\n${content}\\n</context_file>\\n\\n`;\n    }\n  }\n\n  // Append skills section (only if read tool is available)\n  if (hasRead && skills.length > 0) {\n    prompt += formatSkillsForPrompt(skills);\n  }\n\n  // Add model metadata, date, and working directory last\n  prompt += `\\nModel name (used for commit attribution): ${modelName}`;\n  prompt += `\\nModel reasoning level: ${modelReasoningLevel}`;\n  prompt += `\\nCurrent date: ${date}`;\n  prompt += `\\nCurrent working directory: ${promptCwd}`;\n\n  return prompt;\n}\n"]}

package/docs/quickstart.md

@@ -103,7 +103,7 @@ Atomic ships with ten workflows you can run immediately. Use `/workflow list` to
 | `tournament` | Compare whole solutions through balanced pairwise judging. | `/workflow tournament prompt="Design the retry strategy"` |
 | `loop-until-done` | Iterate with a durable ledger until completion or bound exhaustion. | `/workflow loop-until-done prompt="Repair failures until the test suite passes"` |
 | `deep-research-codebase` | Heavy research for tasks requiring comprehensive, whole-repository context. | `/workflow deep-research-codebase prompt="How do payment retries work end to end?"` |
-| `goal` | Clearly delegated autonomous work that materially benefits from a durable goal ledger, bounded worker turns, named validation, and reviewer gates. It stops as `complete`, `blocked`, or `needs_human`, with optional final-stage PR creation through `create_pr=true` after approval. | `/workflow goal objective="Update the CLI docs for --json, include one example, run the docs build, and finish when the build passes"` |
+| `goal` | Clearly delegated autonomous work that materially benefits from a durable goal ledger, bounded sub-agent orchestration turns, named validation, and reviewer gates. It stops as `complete`, `blocked`, or `needs_human`, with optional final-stage PR creation through `create_pr=true` after approval. | `/workflow goal objective="Update the CLI docs for --json, include one example, run the docs build, and finish when the build passes"` |
 | `ralph` | Clearly delegated autonomous work that materially benefits from a durable research-first pipeline, delegated implementation, and iterative review. Ralph can start from a spec file, GitHub issue, or crisp ticket description and optionally lets only the final stage attempt PR creation with `create_pr=true`. | `/workflow ralph prompt="Implement specs/2026-03-rate-limit.md and validate burst traffic returns 429"` |
 | `open-claude-design` | UI and design-system work with separate forked generate and feedback chains; renders a live `preview.html` you can iterate against. | `/workflow open-claude-design prompt="Refresh the settings page hierarchy as a page"` |
 
@@ -125,7 +125,7 @@ Atomic picks the workflow, fills in inputs from the request, and confirms before
 
 For a clearly delegated broad autonomous implementation job that benefits from a research/review loop, `ralph` is one available builtin. Give it a spec file, GitHub issue, or crisp ticket description; it refines the prompt, researches as needed, delegates implementation, reviews, records a QA proof video for UI/full-stack changes when practical, and iterates. Add `create_pr=true` only when you want the final PR handoff after the review gate approves.
 
-For an autonomous one-off job that materially benefits from a durable goal ledger, bounded worker turns, and reviewer gates, use `goal` with a concrete task description that names the work surface, desired outcome, and validation. An ordinary small-to-medium change does not require it merely because it has tests, validation, or multiple files, but loop or stop-condition wording is a key workflow signal when the user delegates execution. Goal captures receipts, stops as `complete`, `blocked`, or `needs_human`, and can optionally run only the final PR handoff with `create_pr=true` after approval.
+For an autonomous one-off job that materially benefits from a durable goal ledger, bounded sub-agent orchestration turns, and reviewer gates, use `goal` with a concrete task description that names the work surface, desired outcome, and validation. Goal's orchestrator delegates investigation, edits, and checks through focused subagents, records their work in its receipt, and coordinates follow-up work until the objective is ready for review. An ordinary small-to-medium change does not require it merely because it has tests, validation, or multiple files, but loop or stop-condition wording is a key workflow signal when the user delegates execution. Goal captures receipts, stops as `complete`, `blocked`, or `needs_human`, and can optionally run only the final PR handoff with `create_pr=true` after approval.
 
 ### Monitor and steer a run
 
@@ -159,7 +159,7 @@ Skills are reusable expert instructions. Trigger one with `/skill:<name>` follow
 | `playwright-cli` | Drive a real browser for end-to-end UI checks, screenshots, and reviewable proof videos. | `/skill:playwright-cli` |
 | `liteparse` | Pull text, tables, or values out of PDF, DOCX, PPTX, XLSX, and image files locally. | `/skill:liteparse` |
 
-Use `/skill:research-codebase` for a focused area and `/workflow deep-research-codebase` when a clearly delegated repo-wide research job benefits from durable stages and artifacts. Keep conversation-led planning and implementation inline, or use bounded subagents while the parent remains in control. When an autonomous implementation job needs durable execution, use `/workflow goal` for a goal ledger, bounded worker turns, and reviewer-gated completion, or `/workflow ralph` for a research-first pipeline with delegated implementation and iterative review. Task size alone does not select either workflow. Add `create_pr=true` only when you want the workflow's final pull-request stage after approval.
+Use `/skill:research-codebase` for a focused area and `/workflow deep-research-codebase` when a clearly delegated repo-wide research job benefits from durable stages and artifacts. Keep conversation-led planning and implementation inline, or use bounded subagents while the parent remains in control. When an autonomous implementation job needs durable execution, use `/workflow goal` for a goal ledger, bounded sub-agent orchestration turns, and reviewer-gated completion, or `/workflow ralph` for a research-first pipeline with delegated implementation and iterative review. Task size alone does not select either workflow. Add `create_pr=true` only when you want the workflow's final pull-request stage after approval.
 
 ### Create your own workflow in natural language
 

package/docs/subagents.md

@@ -69,10 +69,10 @@ Atomic currently bundles these agents from `@bastani/subagents`:
 | `codebase-research-locator` | Locate prior `research/` and `specs/` documents related to the task. | No |
 | `codebase-research-analyzer` | Extract decisions, constraints, and still-relevant conclusions from prior local docs. | No |
 | `codebase-online-researcher` | Research official docs, ecosystem behavior, and open-source source references online. | Can write research notes |
-| `debugger` | Reproduce, diagnose, and fix failures or unexpected behavior. | Yes |
+| `debugger` | Reproduce, prove the root cause, apply the smallest code or content fix, and rerun the failing scenario. It has the same write-capable tools as `worker`. | Yes |
 | `code-simplifier` | Clean up recently changed code while preserving behavior. | Yes |
 
-Read-oriented agents should inspect and report. `debugger` and `code-simplifier` can edit files, so run them with an explicit scope and validation target.
+Read-oriented agents should inspect and report. `debugger` and `code-simplifier` can edit files, so run them with an explicit scope and validation target. The debugger should finish an in-scope diagnosis by applying and validating the fix, not stop at a proposed patch.
 
 ## Review compositions
 
@@ -133,6 +133,14 @@ Inside workflow stages, completion delivery observes the stage generation bounda
 
 When a workflow graph overlay is open, Atomic also publishes the live async subagent summary into the shared status surface. The below-editor async widget remains available when the workflow overlay is hidden, and the overlay statusline keeps the run count/state visible while the graph fills the terminal.
 
+## Orchestrator model and group policy
+
+Atomic applies the same delegation policy to any parent chat or workflow stage that orchestrates subagents. A named agent uses the model and fallback chain declared by its agent definition, so the orchestrator normally omits the subagent tool's explicit `model` argument. An override needs either the user's exact model request or a documented task-specific reason recorded before launch; model diversity alone is not enough.
+
+If an agent declares no model or fallback policy, the orchestrator consults the role guidance in [Model selection](/models/model-selection), then calls `workflow({ action: "models" })` when that tool is available. It may pin only a returned `fullId` and may add a thinking suffix only when the model entry lists that level. When the catalog tool is unavailable, the catalog is empty, or no recommended model is present, the child stays unpinned and the orchestrator reports the limit instead of inventing a model or inspecting credentials.
+
+Each workflow or other orchestrator invocation also uses one invocation-specific, non-`default` Intercom group for all of its children, including parallel and follow-up work. This keeps unrelated runs and the main chat isolated while `contact_supervisor` retains its authorized cross-group route.
+
 ## Context and execution modes
 
 Subagents can run with fresh or forked context:

package/docs/usage.md

@@ -109,6 +109,15 @@ Use context files for project conventions, commands, safety rules, and preferenc
 
 ### System Prompt Files
 
+Atomic's default `Guidelines` section applies Orwell's six writing rules to every standard session:
+
+1. Never use a familiar printed metaphor, simile, or figure of speech.
+2. Never use a long word where a short one will do.
+3. Cut every word that can be cut.
+4. Use active rather than passive voice where possible.
+5. Prefer everyday English to foreign phrases, scientific terms, and jargon.
+6. Break any rule rather than say anything outright barbarous.
+
 Replace the default system prompt with:
 
 - `.atomic/SYSTEM.md` for a project