@gajae-code/coding-agent 0.12.1 → 0.12.2

package/src/internal-urls/docs-index.generated.ts

@@ -57,7 +57,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"onboarding-packet.md": "# Gajae-Code Onboarding Packet\n\nThis packet is a docs-only, public-safe context seed for the `gajae-code` repository as inspected on 2026-06-01. It is intentionally a no-new-skill artifact: not a new workflow skill, command, agent, configuration surface, issue template, or runtime behavior.\n\n## Purpose in one paragraph\n\nGajae-Code is the `gjc` coding-agent CLI and supporting monorepo. The product centers on a small public workflow loop: clarify with `deep-interview`, plan with `ralplan`, execute and verify through `ultragoal`, and use `team` only when parallel tmux workers are useful. The main product package is `packages/coding-agent/`; supporting packages provide LLM/provider access, agent runtime, TUI rendering, native helpers, stats, utilities, benchmarks, and SDK machine interfaces.\n\n## Fixed public surface\n\nKeep this invariant front-and-center when onboarding to the repo:\n\n- Default workflow skills: `deep-interview`, `ralplan`, `team`, `ultragoal`.\n- Public role agents: `executor`, `architect`, `planner`, `critic`.\n- Bundled default workflow skill sources live under `packages/coding-agent/src/defaults/gjc/skills/`.\n- Bundled role-agent prompt sources live under `packages/coding-agent/src/prompts/agents/`.\n- Runtime state, specs, plans, goals, team state, and local overrides belong under `.gjc/` for the product and `.omx/` only for this agent-run orchestration.\n\nDo not add a fifth default skill, fifth public role agent, new command, new config surface, or feature-intake behavior unless that product decision has already been made and the default-surface gates are updated.\n\n## Primary entrypoints\n\n| Area             | Repo-relative path                                   | Why it matters                                                                                    |\n| ---------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| CLI bootstrap    | `packages/coding-agent/src/cli.ts`                   | Registers top-level CLI commands and routes default launch behavior.                              |\n| Session launch   | `packages/coding-agent/src/main.ts`                  | Converts CLI/runtime settings into agent-session creation and mode dispatch.                      |\n| Agent assembly   | `packages/coding-agent/src/sdk/session.ts`           | Loads settings, default skills, rules, tools, auth/model state, system prompt, and agent runtime. |\n| Built-in tools   | `packages/coding-agent/src/tools/index.ts`           | Registers file, shell, edit, search, browser, task/subagent, and related public coding-harness tools. Memory backends are private integrations, not public tools. |\n| Default skills   | `packages/coding-agent/src/defaults/gjc-defaults.ts` | Embeds and installs the four default workflow skills plus deep-interview fragments.               |\n| Role agents      | `packages/coding-agent/src/task/agents.ts`           | Embeds bundled task-agent prompts; tests enforce public role-agent expectations.                  |\n| Product overview | `README.md`                                          | Explains installation, product story, fixed workflow surface, and development entry commands.     |\n| Architecture map | `docs/codebase-overview.md`                          | Public package map and runtime-flow reference.                                                    |\n\n## Package map\n\n- `packages/coding-agent/` — main `gjc` CLI, workflows, session runtime, tool registry, discovery, settings, prompts, and tests.\n- `packages/ai/` — provider/model boundary, streaming, auth, model registry, retries, and provider integrations.\n- `packages/agent/` — stateful agent loop and append-only context runtime.\n- `packages/tui/` — terminal UI framework and rendering primitives.\n- `packages/natives/` plus `crates/*` — native helpers, Rust/N-API bindings, shell/PTY, text search, AST, filesystem, and media utilities.\n- `packages/utils/` — shared TypeScript utilities, logging, formatting, process helpers, JSON/frontmatter, and sanitization.\n- `packages/stats/` — local observability dashboard and session/model usage aggregation.\n- `packages/typescript-edit-benchmark/` — TypeScript edit benchmark tooling.\n- External machine clients use the SDK WebSocket interface documented in `docs/sdk.md`; `--mode rpc`, `--mode rpc-ui`, and `--mode bridge` were removed.\n\n## Build, test, and validation commands\n\nPrefer targeted checks first, then broader checks when code changes justify them. For this docs-only packet, lightweight validation is enough.\n\n| Command                                                               | Scope                               | When to use                                                                 |\n| --------------------------------------------------------------------- | ----------------------------------- | --------------------------------------------------------------------------- |\n| `bun install`                                                         | Workspace dependencies              | Initial local setup.                                                        |\n| `bun run install:defaults`                                            | Local default install               | Installs source-bundled default workflow definitions for local development. |\n| `bun packages/coding-agent/src/cli.ts --help`                         | CLI smoke/discovery                 | Fast source checkout CLI sanity check.                                      |\n| `bun run check:ts`                                                    | Type/lint/default UI checks         | Broad TypeScript validation; heavier than docs-only changes.                |\n| `bun run test`                                                        | Full TS + Rust tests                | Broad regression check; use for runtime/product changes.                    |\n| `bun run ci:test:smoke`                                               | CLI version/help/stats worker smoke | Useful before release/install changes.                                      |\n| `bun scripts/check-visible-definitions.ts`                            | Default surface gate                | Required after workflow-definition changes.                                 |\n| `bun scripts/verify-g002-gates.ts`                                    | Rebrand/default-surface gate        | Required after workflow-definition or public-surface changes.               |\n| `bun scripts/rebrand-inventory.ts --strict`                           | Rebrand inventory gate              | Required after workflow-definition or public-surface changes.               |\n| `bun test packages/coding-agent/test/default-gjc-definitions.test.ts` | Four-skills/four-agents contract    | Required after default workflow/agent surface changes.                      |\n\nRepository rule: do not run `tsc` or `npx tsc`; use the Bun scripts above.\n\n## Danger zones\n\n- **Default surface expansion:** `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/defaults/gjc-defaults.ts`, `packages/coding-agent/src/prompts/agents/`, and model-assignment tests are contract-heavy. Changes here can accidentally alter the fixed four-skills/four-agents shape.\n- **CLI commands:** `packages/coding-agent/src/cli.ts` and `packages/coding-agent/src/commands/` define visible behavior. Adding commands or aliases is a product-surface change.\n- **Runtime/session assembly:** `packages/coding-agent/src/main.ts`, `packages/coding-agent/src/sdk/session.ts`, discovery, settings, tools, and system-prompt paths can affect every session.\n- **TUI/logging:** Avoid `console.log`, `console.warn`, or `console.error` inside `packages/coding-agent/`; use the centralized logger to avoid corrupting TUI rendering.\n- **Secrets/auth/config:** Keep `docs/secrets.md`, auth broker/gateway code, settings, and environment-variable docs public-safe. Do not expose tokens or private infrastructure.\n- **Native/Rust build:** `packages/natives/` and `crates/*` can require platform-specific toolchains and CI artifact behavior.\n- **Generated model data:** Do not edit `packages/ai/src/models.json` directly; update generators/descriptors/resolvers and regenerate with `bun --cwd=packages/ai run generate-models`.\n\n## Unknowns worth preserving\n\n- Which onboarding packet shape will be most useful for future `gjc` context ingestion is still an experiment, not a product contract.\n- Public issue #158 / `gajae-deep-onboarding` context is summarized only from the user-provided prompt in this run; this packet does not add issue intake or feature workflow behavior.\n- Full CI may depend on runner/system dependencies and native artifacts; docs-only changes usually do not need the full matrix locally.\n- Some packages contain internal or hidden utility prompts/agents beyond the four public role agents. Public-facing docs should keep the four-role contract clear.\n\n## First safe tasks for a new contributor or agent\n\n1. Read `README.md`, `docs/codebase-overview.md`, and this packet.\n2. Run `bun packages/coding-agent/src/cli.ts --help` for a fast CLI surface check after dependencies are installed.\n3. For docs-only edits, run formatting/check commands that do not mutate runtime behavior.\n4. For default-surface edits, run the four required gates listed in the command table before claiming completion.\n5. For package code edits, start with the nearest package test, then escalate to `bun run check:ts` or `bun run test` as risk increases.\n6. Before changing `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/prompts/agents/`, `packages/coding-agent/src/commands/`, or config/settings paths, write down whether the change alters public surface area.\n\n## Context seed checklist\n\nA future agent can use this packet as context if it preserves these constraints:\n\n- Keep changes public-safe and repo-relative.\n- Prefer docs and tests over new runtime abstractions for onboarding experiments.\n- Treat the fixed four-skills/four-agents shape as a product constraint.\n- Verify claims with repo files before summarizing them.\n- Report validation evidence and caveats instead of implying hidden automation.\n",
 	"onboarding-receipt.md": "# Onboarding Packet Receipt\n\n- Date: 2026-06-01\n- Scope: docs-only no-new-skill onboarding packet experiment for this repository.\n- Output files:\n  - `docs/onboarding-packet.md`\n  - `docs/onboarding-receipt.md`\n- Public-safe boundary: no secrets, tokens, hidden prompts, private infrastructure, internal ops, or private paths beyond repo-relative paths.\n- Product boundary: no new skill, command, agent slot, issue, config, or runtime behavior.\n\n## Evidence inspected\n\n- `README.md`\n- `docs/codebase-overview.md`\n- `package.json`\n- `packages/coding-agent/package.json`\n- `packages/coding-agent/src/cli.ts`\n- `packages/coding-agent/src/main.ts`\n- `packages/coding-agent/src/sdk/session.ts`\n- `packages/coding-agent/src/defaults/gjc-defaults.ts`\n- `packages/coding-agent/src/task/agents.ts`\n- `packages/coding-agent/test/default-gjc-definitions.test.ts`\n- `.github/workflows/ci.yml`\n- `.github/workflows/dev-ci.yml`\n\n## Result\n\nThe packet records repo purpose, package layout, main entrypoints, build/test commands, danger zones, unknowns, and first safe tasks without changing the product surface. It is suitable as a public context seed for future onboarding experiments, not as a feature intake mechanism.\n\n## Caveats\n\n- The attempted `omx question --input '<json>' --json` interview round failed before user input because the runtime reported no attached tmux client; no human answer was inferred from that failed call.\n- Public issue context is limited to the user-provided prompt summary for this run.\n- Full CI was not required for the docs-only artifact unless later code/runtime files change.\n",
 	"ooo-bridge-extension-contract.md": "# Ouroboros `ooo` bridge extension contract\n\nGJC exposes the `ooo` bridge through the existing extension input-event surface. It is not a default workflow skill, hook, slash command, or built-in agent.\n\n## Interception surface\n\nExtensions register an `input` handler:\n\n```ts\nimport { createOuroborosOooBridge } from \"@gajae-code/coding-agent/extensibility/extensions\";\n\nexport default function activate(gjc) {\n  gjc.on(\"input\", createOuroborosOooBridge());\n}\n```\n\nThe handler matches only the bare exact prefix:\n\n- `ooo`\n- `ooo ...`\n\nIt does not match embedded or longer-token text such as `please ooo status`, `oooo`, or `/ooo`.\n\nThe extension runner already treats `InputEventResult.handled === true` as terminal: the input is not sent through normal model flow. An empty result (`{}`) means continue/pass-through, preserving existing chained input handlers and normal prompt handling.\n\n## Dispatch and result semantics\n\n`createOuroborosOooBridge()` is a small specialization of `createExactPrefixCommandBridge()`:\n\n- command: `ouroboros`\n- arguments: `dispatch`, then the full submitted input text\n- recursion guard variable: the Ouroboros bridge recursion-depth environment variable\n\n- continue/pass-through exit code: `78`\n\nExit-code mapping:\n\n| Dispatch result | GJC input result |\n| --- | --- |\n| `0` | `{ handled: true }`; do not send input to the model. |\n| `78` | `{}`; continue/pass-through so GJC processes the input normally. |\n| any other non-zero | Surface an extension error notification using stderr, then stdout, then a generic exit-code message, and return `{ handled: true }`; the failed `ooo` command is terminal and is not sent to the model. |\n\n## Recursion guard\n\nBefore dispatch, the helper increments the Ouroboros bridge recursion-depth environment variable and restores its previous value after dispatch finishes. A current numeric depth of `0` or `1` is dispatchable, which preserves concurrent independent interactive inputs while marking child dispatcher processes with depth `1`. A current numeric depth greater than `1`, or any non-empty non-numeric value, returns `{}` without dispatching.\n\nThis means the bridge allows exactly one inherited bridge-marked dispatcher level and blocks recursive re-entry from deeper bridge-marked children. The guard also passes through `event.source === \"extension\"` to avoid extension-originated messages re-entering the bridge.\n\n## Installation and discovery\n\nThe canonical install location is the agent extensions directory discovered by the native GJC provider:\n\n- user-level: `$HOME/${GJC_CONFIG_DIR:-.gjc}/agent/extensions`\n- project-level: `<cwd>/.gjc/extensions`\n\nFor native discovery, install one of:\n\n- `extensions/<name>.ts` or `extensions/<name>.js`\n- `extensions/<name>/index.ts` or `extensions/<name>/index.js`\n- `extensions/<name>/package.json` declaring extension entries\n\nThe loader scans one level under each `extensions` directory. Complex packages should use a package manifest instead of relying on recursive discovery.\n\n`GJC_CONFIG_DIR` selects the **home-relative** config directory name: the config root is `<home>/<GJC_CONFIG_DIR>`, defaulting to `~/.gjc`. It does not select a project directory — the project-level path is the constant `.gjc` (`discovery/helpers.ts`, `getProjectAgentDir()`), so `GJC_CONFIG_DIR` never moves it. `GJC_CODING_AGENT_DIR` overrides the agent directory **path** rather than naming one under `$HOME`; it is resolved with `path.resolve`, so an absolute value is used as-is and a relative value is resolved against the current working directory.\n\nDiscovery is the exception to that second override. The native provider builds its user-level root from `GJC_CONFIG_DIR` alone (`<home>/<config-dir>/agent`) and never consults `getAgentDir()`, so an operator who sets `GJC_CODING_AGENT_DIR` moves the agent directory for the rest of the product but **not** for extension, skill, rule, or hook discovery.\n\nHooks are not the input bridge surface: `packages/coding-agent/src/capability/hook.ts` defines pre/post tool hooks only.\n",
-	"perf-profiling-corpus.md": "# Perf profiling corpus\n\nThe profiling corpus is the **successor** to the static [`cpu-hotspot-map.json`](./cpu-hotspot-map.json) ranking (see [`hotspot-map-successor.md`](./hotspot-map-successor.md)). The static map ranked hotspots by complexity × trigger frequency but never measured real CPU self-time. The corpus replaces that guess with measured, separated evidence and is the source of future perf prioritization.\n\nImplementation:\n\n- Schema + evidence taxonomy + validation: `packages/coding-agent/bench/perf-corpus-schema.ts`\n- Runner: `packages/coding-agent/bench/perf-corpus.bench.ts`\n- Threshold/evidence ledger: `packages/coding-agent/bench/perf-threshold.ledger.ts`\n- Tests: `packages/coding-agent/test/perf-corpus.test.ts`\n- Deterministic memory surface workloads: `packages/coding-agent/bench/memory-baseline-workloads.ts`\n\n## Evidence taxonomy\n\nEach metric and optimization claim is classified by **evidence class**. These classes must never be conflated:\n\n| Class | Meaning | Sufficient for CPU self-time? |\n|---|---|---|\n| `wall-clock-proxy` | elapsed time around a phase/operation | No |\n| `process-cpu-usage` | `process.cpuUsage()` user/system deltas | No |\n| `profiler-self-time` | profiler/sampled attribution of self-time to a symbol | **Yes (required)** |\n| `rss-memory` | RSS/heap baseline/growth/return | No (memory only) |\n| `byte-parity` | golden rendered/persisted/provider/materialized comparisons | n/a (safety) |\n| `ledger-approved-threshold` | human-approved threshold change | n/a (process) |\n\nOptimization **status vocabulary** for a hotspot:\n\n- `CPU-self-time confirmed` — requires `profiler-self-time` evidence (an `artifactPath` or non-empty `samples`).\n- `fallback-toggle-confirmed` — comparable before/after or feature/fallback-toggle evidence proves an end-to-end win without byte changes.\n- `covered-current` — the corpus exercises the path but has no comparable before/after evidence.\n- `not-visible` — the path was not exercised or showed no measurable impact.\n- `needs-trace-coverage` — the corpus lacks fixture coverage for the path.\n\nA v1–v3 win is **never** called \"confirmed\" from current-only coverage. `validatePerfCorpusReport()` enforces this: a `CPU-self-time confirmed` classification is rejected unless the report carries profiler self-time evidence.\n\n## Schema (gjc.perf-corpus/2)\n\n`PerfCorpusReport` keeps the evidence classes as **separate named fields** per fixture:\n\n- `wallClockPhase: Record<string, { elapsedMs, p50Ms?, p95Ms?, advisoryOnly }>`\n- `processCpuUsage: Record<string, { userMicros, systemMicros, elapsedMs, cpuFraction? }>`\n- `profilerSelfTime: { profiler, artifactPath?, samples? }`\n- `rssMemory: { baselineBytes, peakBytes?, growthBytes, returnBytes, ... }`\n- `byteParity: { renderedGolden?, persistedJsonlGolden?, providerPayloadGolden?, materializedSessionGolden? }`\n- `memoryBaseline?: { surface, profile, iterations, operations, operationsPerSecond, samples, postTeardown, rssSlopeBytesPerSecond, heapSlopeBytesPerSecond, processTreeBaselineRssBytes, processTreePostTeardownRssBytes, processTreeSampler }`\n- `runner: { command, argv, environment, platform, arch, bunVersion?, ci?, profile, durationTargetMs?, memoryIsolation, iterationsTarget, gcExposed, memoryChildGcExposed, memoryChildExecArgv }` pins the actual parent argv, normalized workload controls, isolation, parent GC availability, and the fixed isolated-child runtime flags separately.\n- `gitSha` is the full checked-out `HEAD` when Git is available, with `GITHUB_SHA` used only as a fallback; `gitDirty` explicitly marks tracked or untracked worktree changes so local evidence cannot silently masquerade as a clean commit. The runner captures SHA and the complete porcelain worktree fingerprint before and after the workloads and rejects any in-flight source-state change.\n- Every detailed sample separates `rssBytes`, `heapUsedBytes`, `heapTotalBytes`, `externalBytes`, `arrayBuffersBytes`, and `activeResourceCount`.\n\n`hotspotClassifications: HotspotClassification[]` carry `{ hotspotId, status, evidenceClass, artifactRefs, notes }`. The current v1–v3 reclassification lives in `V1_V3_RECLASSIFICATION`; no entry is `CPU-self-time confirmed` because no profiler artifacts have been captured yet.\n\n## Privacy rules\n\n- Never commit raw private session transcripts.\n- Default fixtures are `synthetic` (deterministic PRNG, no real data).\n- `sanitized-real` / `dogfood-redacted` fixtures are allowed only with documented redaction in `privacy.redactionNotes`; `privacy.rawPrivateTranscriptCommitted` must be `false`.\n\n## Commands\n\n```bash\n# Emit a corpus report (stable JSON)\nbun packages/coding-agent/bench/perf-corpus.bench.ts\n\n# Run the corpus schema/classification/ledger tests\nbun test packages/coding-agent/test/perf-corpus.test.ts\n```\n\n```bash\n# Emit the detailed short memory profile with explicit GC return samples\nbun --smol --expose-gc packages/coding-agent/bench/perf-corpus.bench.ts\n\n# Opt into the longer bounded soak profile\nGJC_MEMORY_PROFILE=soak bun --smol --expose-gc packages/coding-agent/bench/perf-corpus.bench.ts\n\n# Override the per-surface duration (250–60000 ms) and minimum iterations\nGJC_MEMORY_PROFILE=soak GJC_MEMORY_DURATION_MS=10000 GJC_MEMORY_ITERATIONS=100000 bun --smol --expose-gc packages/coding-agent/bench/perf-corpus.bench.ts\n```\n\n## Profiler-artifact expectations\n\nThe base runner attaches no profiler (`profilerSelfTime.profiler: \"none\"`), so it can never promote a hotspot to `CPU-self-time confirmed`. To confirm CPU self-time:\n\n1. Capture a profiler artifact (e.g. a `.cpuprofile`) while running the relevant fixture.\n2. Record it in the fixture's `profilerSelfTime` as `{ profiler, artifactPath, samples }`.\n3. Set the hotspot classification to `CPU-self-time confirmed` with `evidenceClass: \"profiler-self-time\"` and the artifact in `artifactRefs`.\n4. `validatePerfCorpusReport()` will then accept the claim.\n\n## Threshold-promotion process\n\nWall-clock and RSS thresholds are noisy. Promotion is gradual:\n\n1. **Advisory** — reported in the corpus JSON / console; never fails CI. All thresholds start here (`APPLIED_PERF_THRESHOLDS`, `advisoryOrEnforced: \"advisory\"`, `varianceCharacterized: false`).\n2. **Opt-in numeric** — exercised under `PI_TUI_PERF_GATES=1` (see `packages/tui/test/perf-gates.test.ts`).\n3. **Enforced** — a hard CI gate, allowed only with `varianceCharacterized: true`, passed before/after `benchmarkEvidence`, and human approval. `validatePerfThresholdLedger()` rejects enforced thresholds lacking this evidence.\n\nHeld thresholds (`HELD_PERF_THRESHOLDS`) name candidates that need variance characterization before enforcement.\n\n## Memory baseline protocol\n\nDetailed memory fixtures cover seven explicit surfaces: CLI startup/configuration, AgentSession-style message/context lifecycle, blob/external buffers, worker generations, Telegram reconnect/queue settlement, TUI render/dispose churn, and shared/native transfer boundaries. The fixtures are synthetic lifecycle proxies: they establish a reproducible allocation and teardown envelope but do not by themselves prove a production leak. A production optimization claim still requires a workload adapter that exercises the implicated owner and a same-host before/after artifact.\nThe command-line runner executes each memory surface in a fresh Bun subprocess and records `runner.memoryIsolation: \"process-per-surface\"` so allocator high-water state from one fixture cannot contaminate the next surface's baseline. Programmatic `runPerfCorpusBenchmark()` defaults to in-process fixtures and records `\"in-process\"` for focused contract tests; pass `{ isolatedMemory: true }` for acceptance-equivalent evidence. Process-tree RSS snapshots exclude the `ps` sampler process and degrade both endpoints to `\"unavailable\"` when either snapshot fails. The process-tree baseline is captured after GC, followed by another GC that clears sampler allocations before the local baseline and workload begin. Soak workloads use single-iteration batches so approximately 50 ms sampling cannot be hidden behind a large synchronous chunk. Post-teardown return fields remain `null` when GC is unavailable.\n\nUse the `short` profile for deterministic contract and shape checks; its bounded iteration window intentionally reports `null` slopes when less than 250 ms is observed. Use `soak` for repeated sampling and slope characterization. For decision evidence:\nThe soak default runs each surface for at least one second and samples at approximately 50 ms intervals. `GJC_MEMORY_DURATION_MS` accepts 250–60000 ms and `GJC_MEMORY_ITERATIONS` accepts 1–10000000; record overrides with the artifact.\n\n1. Pin the source SHA, Bun version, platform/architecture, profile, fixture inputs, and command.\n2. Run at least five short repetitions and three independent soak repetitions on an otherwise idle runner.\n3. Exclude warm-up from slope decisions and report the raw samples, median, p95, variance/confidence interval, peak, and post-teardown values. The runner discards the first quarter of the observed window, capped at 250 ms, before calculating a slope and requires at least 250 ms of steady-state samples.\n4. Interpret heap, external/array-buffer, RSS, and process-tree evidence separately. A high post-GC RSS with a returned heap may be allocator high-water residency, not a reachability leak.\n5. Do not enforce a numeric threshold until variance is characterized and recorded in the threshold ledger. A claimed optimization needs either a statistically supported improvement on the same workload or removal of a reproducible unbounded slope.\n6. Treat active handles and post-teardown residue as lifecycle signals, not byte-parity proof. Behavior, transcript/blob integrity, throughput, and latency remain independent gates.\n\nThe default fixtures contain no user or provider data. Raw private transcripts remain prohibited.\n\n## Memory retention & fail-closed materialization\n\nResident-memory retention (hotspots M01–M05) was bounded in Optimization Suite v3 (#548): `EphemeralBlobStore` externalizes large resident text to a session-scoped disk cache with an 8 MiB LRU buffer budget, `getEntries()`/`buildSessionContext()` are served from revision-keyed WeakRef caches and return caller-owned clones, and `captureState`/`restoreState` bump revision domains. Materialization is split by byte sensitivity:\n\n- **Resident byte-sensitive TEXT** (`resolveTextBlobSync`) is **fail-closed**: a missing resident blob throws `ResidentBlobMissingError` rather than degrading, so a missing blob can never silently leak a `blob:sha256:` reference into provider payloads, UI, or exports.\n- **Persisted images** (`resolveImageData`/`resolveImageDataUrl` and sync variants) are the **legacy persisted-image compatibility boundary**: a missing blob warns and returns the reference as-is so legacy-session resume degrades gracefully. New byte-sensitive resident data must NOT use this warn-and-return path.\n\nThis contract is locked by `packages/coding-agent/test/resident-materialization.test.ts`. Retained growth and post-GC return are measured by `packages/coding-agent/bench/session-memory.bench.ts` (emits the corpus `rssMemory` shape).\n\n**Measured deferral:** further memory rewrites beyond these byte-parity-preserving bounds are deferred to corpus prioritization. Per [`native-ffi-optimization-policy.md`](./native-ffi-optimization-policy.md) and the byte-parity principle, speculative memory rewrites wait for profiler/RSS corpus evidence rather than being undertaken on a static-ranking guess.\n",
+	"perf-profiling-corpus.md": "# Perf profiling corpus\n\nThe profiling corpus is the **successor** to the static [`cpu-hotspot-map.json`](./cpu-hotspot-map.json) ranking (see [`hotspot-map-successor.md`](./hotspot-map-successor.md)). The static map ranked hotspots by complexity × trigger frequency but never measured real CPU self-time. The corpus replaces that guess with measured, separated evidence and is the source of future perf prioritization.\n\nImplementation:\n\n- Schema + evidence taxonomy + validation: `packages/coding-agent/bench/perf-corpus-schema.ts`\n- Runner: `packages/coding-agent/bench/perf-corpus.bench.ts`\n- Threshold/evidence ledger: `packages/coding-agent/bench/perf-threshold.ledger.ts`\n- Tests: `packages/coding-agent/test/perf-corpus.test.ts`\n- Deterministic memory surface workloads: `packages/coding-agent/bench/memory-baseline-workloads.ts`\n\n## Evidence taxonomy\n\nEach metric and optimization claim is classified by **evidence class**. These classes must never be conflated:\n\n| Class | Meaning | Sufficient for CPU self-time? |\n|---|---|---|\n| `wall-clock-proxy` | elapsed time around a phase/operation | No |\n| `process-cpu-usage` | `process.cpuUsage()` user/system deltas | No |\n| `profiler-self-time` | profiler/sampled attribution of self-time to a symbol | **Yes (required)** |\n| `rss-memory` | RSS/heap baseline/growth/return | No (memory only) |\n| `byte-parity` | golden rendered/persisted/provider/materialized comparisons | n/a (safety) |\n| `ledger-approved-threshold` | human-approved threshold change | n/a (process) |\n\nOptimization **status vocabulary** for a hotspot:\n\n- `CPU-self-time confirmed` — requires `profiler-self-time` evidence (an `artifactPath` or non-empty `samples`).\n- `fallback-toggle-confirmed` — comparable before/after or feature/fallback-toggle evidence proves an end-to-end win without byte changes.\n- `covered-current` — the corpus exercises the path but has no comparable before/after evidence.\n- `not-visible` — the path was not exercised or showed no measurable impact.\n- `needs-trace-coverage` — the corpus lacks fixture coverage for the path.\n\nA v1–v3 win is **never** called \"confirmed\" from current-only coverage. `validatePerfCorpusReport()` enforces this: a `CPU-self-time confirmed` classification is rejected unless the report carries profiler self-time evidence.\n\n## Schema (gjc.perf-corpus/2)\n\n`PerfCorpusReport` keeps the evidence classes as **separate named fields** per fixture:\n\n- `wallClockPhase: Record<string, { elapsedMs, p50Ms?, p95Ms?, advisoryOnly }>`\n- `processCpuUsage: Record<string, { userMicros, systemMicros, elapsedMs, cpuFraction? }>`\n- `profilerSelfTime: { profiler, artifactPath?, samples? }`\n- `rssMemory: { baselineBytes, peakBytes?, growthBytes, returnBytes, ... }`\n- `byteParity: { renderedGolden?, persistedJsonlGolden?, providerPayloadGolden?, materializedSessionGolden? }`\n- `memoryBaseline?: { surface, profile, iterations, operations, operationsPerSecond, samples, postTeardown, rssSlopeBytesPerSecond, heapSlopeBytesPerSecond, processTreeBaselineRssBytes, processTreePostTeardownRssBytes, processTreeSampler }`\n- `runner: { command, argv, environment, platform, arch, bunVersion?, ci?, profile, durationTargetMs?, memoryIsolation, iterationsTarget, gcExposed, memoryChildGcExposed, memoryChildExecArgv }` pins the actual parent argv, normalized workload controls, isolation, parent GC availability, and the fixed isolated-child runtime flags separately.\n- `gitSha` is the full checked-out `HEAD` when Git is available, with `GITHUB_SHA` used only as a fallback; `gitDirty` explicitly marks tracked or untracked worktree changes so local evidence cannot silently masquerade as a clean commit. The runner captures SHA and the complete porcelain worktree fingerprint before and after the workloads and rejects any in-flight source-state change.\n- Every detailed sample separates `rssBytes`, `heapUsedBytes`, `heapTotalBytes`, `externalBytes`, `arrayBuffersBytes`, and `activeResourceCount`.\n\n`hotspotClassifications: HotspotClassification[]` carry `{ hotspotId, status, evidenceClass, artifactRefs, notes }`. The current v1–v3 reclassification lives in `V1_V3_RECLASSIFICATION`; no entry is `CPU-self-time confirmed` because no profiler artifacts have been captured yet.\n\n## Privacy rules\n\n- Never commit raw private session transcripts.\n- Default fixtures are `synthetic` (deterministic PRNG, no real data).\n- `sanitized-real` / `dogfood-redacted` fixtures are allowed only with documented redaction in `privacy.redactionNotes`; `privacy.rawPrivateTranscriptCommitted` must be `false`.\n\n## Commands\n\n```bash\n# Emit a corpus report (stable JSON)\nbun packages/coding-agent/bench/perf-corpus.bench.ts\n\n# Run the corpus schema/classification/ledger tests\nbun test packages/coding-agent/test/perf-corpus.test.ts\n```\n\n```bash\n# Emit the detailed short memory profile with explicit GC return samples\nbun --smol --expose-gc packages/coding-agent/bench/perf-corpus.bench.ts\n\n# Opt into the longer bounded soak profile\nGJC_MEMORY_PROFILE=soak bun --smol --expose-gc packages/coding-agent/bench/perf-corpus.bench.ts\n\n# Override the per-surface duration (250–60000 ms) and minimum iterations\nGJC_MEMORY_PROFILE=soak GJC_MEMORY_DURATION_MS=10000 GJC_MEMORY_ITERATIONS=100000 bun --smol --expose-gc packages/coding-agent/bench/perf-corpus.bench.ts\n```\n\n## Profiler-artifact expectations\n\nThe base runner attaches no profiler (`profilerSelfTime.profiler: \"none\"`), so it can never promote a hotspot to `CPU-self-time confirmed`. To confirm CPU self-time:\n\n1. Capture a profiler artifact (e.g. a `.cpuprofile`) while running the relevant fixture.\n2. Record it in the fixture's `profilerSelfTime` as `{ profiler, artifactPath, samples }`.\n3. Set the hotspot classification to `CPU-self-time confirmed` with `evidenceClass: \"profiler-self-time\"` and the artifact in `artifactRefs`.\n4. `validatePerfCorpusReport()` will then accept the claim.\n\n## Threshold-promotion process\n\nWall-clock and RSS thresholds are noisy. Promotion is gradual:\n\n1. **Advisory** — reported in the corpus JSON / console; never fails CI. All thresholds start here (`APPLIED_PERF_THRESHOLDS`, `advisoryOrEnforced: \"advisory\"`, `varianceCharacterized: false`).\n2. **Opt-in numeric** — exercised under `PI_TUI_PERF_GATES=1` (see `packages/tui/test/perf-gates.test.ts`).\n3. **Enforced** — a hard CI gate, allowed only with `varianceCharacterized: true`, passed before/after `benchmarkEvidence`, and human approval. `validatePerfThresholdLedger()` rejects enforced thresholds lacking this evidence.\n\nHeld thresholds (`HELD_PERF_THRESHOLDS`) name candidates that need variance characterization before enforcement.\n\n## Memory baseline protocol\n\nDetailed memory fixtures cover seven explicit surfaces: CLI startup/configuration, AgentSession-style message/context lifecycle, blob/external buffers, worker generations, Telegram reconnect/queue settlement, TUI render/dispose churn, and shared/native transfer boundaries. The fixtures are synthetic lifecycle proxies: they establish a reproducible allocation and teardown envelope but do not by themselves prove a production leak. A production optimization claim still requires a workload adapter that exercises the implicated owner and a same-host before/after artifact.\nThe command-line runner executes each memory surface in a fresh Bun subprocess and records `runner.memoryIsolation: \"process-per-surface\"` so allocator high-water state from one fixture cannot contaminate the next surface's baseline. Programmatic `runPerfCorpusBenchmark()` defaults to in-process fixtures and records `\"in-process\"` for focused contract tests; pass `{ isolatedMemory: true }` for acceptance-equivalent evidence. Process-tree RSS snapshots exclude the `ps` sampler process and degrade both endpoints to `\"unavailable\"` when either snapshot fails. The process-tree baseline is captured after GC, followed by another GC that clears sampler allocations before the local baseline and workload begin. Soak workloads use single-iteration batches so approximately 50 ms sampling cannot be hidden behind a large synchronous chunk. Post-teardown return fields remain `null` when GC is unavailable.\n\nUse the `short` profile for deterministic contract and shape checks; its bounded iteration window intentionally reports `null` slopes when less than 250 ms is observed. Use `soak` for repeated sampling and slope characterization. For decision evidence:\nThe soak default runs each surface for at least one second and samples at approximately 50 ms intervals. `GJC_MEMORY_DURATION_MS` accepts 250–60000 ms and `GJC_MEMORY_ITERATIONS` accepts 1–10000000; record overrides with the artifact.\n\n1. Pin the source SHA, Bun version, platform/architecture, profile, fixture inputs, and command.\n2. Run at least five short repetitions and three independent soak repetitions on an otherwise idle runner.\n3. Exclude warm-up from slope decisions and report the raw samples, median, p95, variance/confidence interval, peak, and post-teardown values. The runner discards the first quarter of the observed window, capped at 250 ms, before calculating a slope and requires at least 250 ms of steady-state samples.\n4. Interpret heap, external/array-buffer, RSS, and process-tree evidence separately. A high post-GC RSS with a returned heap may be allocator high-water residency, not a reachability leak.\n5. Do not enforce a numeric threshold until variance is characterized and recorded in the threshold ledger. A claimed optimization needs either a statistically supported improvement on the same workload or removal of a reproducible unbounded slope.\n6. Treat active handles and post-teardown residue as lifecycle signals, not byte-parity proof. Behavior, transcript/blob integrity, throughput, and latency remain independent gates.\n\nThe default fixtures contain no user or provider data. Raw private transcripts remain prohibited.\n\n## Memory retention & fail-closed materialization\n\nResident-memory retention (hotspots M01–M05) was bounded in Optimization Suite v3 (#548): `EphemeralBlobStore` externalizes large resident text to a session-scoped disk cache with an 8 MiB LRU buffer budget, `getEntries()`/`buildSessionContext()` are served from revision-keyed WeakRef caches and return caller-owned clones, and `captureState`/`restoreState` bump revision domains. Materialization is split by byte sensitivity:\n\n- **Resident byte-sensitive TEXT** (`resolveTextBlobSync`) is **fail-closed**: a missing resident blob throws `ResidentBlobMissingError` rather than degrading, so a missing blob can never silently leak a `blob:sha256:` reference into provider payloads, UI, or exports.\n- **Persisted images** (`resolveImageData`/`resolveImageDataUrl` and sync variants) are the **legacy persisted-image compatibility boundary**: a missing blob warns and returns the reference as-is so legacy-session resume degrades gracefully. New byte-sensitive resident data must NOT use this warn-and-return path.\n\nThis contract is locked by `packages/coding-agent/test/resident-materialization.test.ts`. Retained growth and post-GC return are measured by `packages/coding-agent/bench/session-memory.bench.ts` (emits the corpus `rssMemory` shape).\n\n**Measured deferral:** further memory rewrites beyond these byte-parity-preserving bounds are deferred to corpus prioritization. Per [`native-ffi-optimization-policy.md`](./native-ffi-optimization-policy.md) and the byte-parity principle, speculative memory rewrites wait for profiler/RSS corpus evidence rather than being undertaken on a static-ranking guess.\n\n## Authenticated sealed-corpus result\n\n- Evidence status: `SUFFICIENT_EVIDENCE`\n- Action decision: `ACTION`\n- Action family: `sustained-heap-growth`\n- Measurement head: `ae37704ea58c5181043ef2a325c3aa1878884c25`\n- Admission: short 5/5, soak 24/24\n- `agent-session` endpoint median: 2232879.966 B/s, BCa lower 2198738.248, Theil-Sen median 917654.71\n- `tui` endpoint median: 170829.216 B/s, BCa lower 154600.451, Theil-Sen median 4391.02\n- p95: `OMITTED_IMPOSSIBLE` (24 blocks insufficient for 95% empirical coverage per exact-order-statistic method)\n- All five preregistered limitations preserved\n- JS heap separated from process RSS/external/native; no production leak or causal site claimed\n- Raw corpus retained outside git, read-only, access-restricted, hash-bound by external receipt\n- Published files:\n  - `artifacts/perf-corpus-memory-evidence-report.json`\n  - `artifacts/perf-corpus-memory-evidence-manifest.json`\n  - `artifacts/perf-corpus-memory-evidence-notebook.ipynb`\n",
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/gajae-code` → `@gajae-code/coding-agent`\n  - `@mariozechner/pi-agent-core` → `@gajae-code/agent-core`\n  - `@mariozechner/pi-tui` → `@gajae-code/tui`\n  - `@mariozechner/pi-ai` → `@gajae-code/ai`\n\n## 4) Use Bun APIs where they improve on Node\n\nWe run on Bun, but the current source intentionally mixes Bun APIs with small Node standard-library APIs. Replace Node APIs only when Bun provides a clearer, safer, or simpler implementation; do not mechanically rewrite every Node import.\n\n**Prefer replacing when porting new code:**\n\n- Process spawning: prefer Bun Shell `$` for simple commands; use `Bun.spawn`/`Bun.spawnSync` for streaming or process control. Keep existing `child_process` only where its exact semantics are needed.\n- HTTP clients: `node-fetch`, `axios` → native `fetch`\n- SQLite: `better-sqlite3` → `bun:sqlite`\n- Env loading: `dotenv` → Bun loads `.env` automatically\n- Runtime text/assets: prefer Bun imports such as `with { type: \"text\" }` or `Bun.file()` over copy steps or bundled fallback file reads.\n\n**DO NOT replace (these work fine in Bun):**\n\n- `os.homedir()` — do NOT replace with `Bun.env.HOME` or literal `\"~\"`\n- `os.tmpdir()` — do NOT replace with `Bun.env.TMPDIR || \"/tmp\"` or hardcoded paths\n- `fs.mkdtempSync()` — do NOT replace with manual path construction\n- `path.join()`, `path.resolve()`, etc. — these are fine\n\n**Import style:** Use the `node:` prefix for Node standard-library imports. Namespace imports are common, but named imports are acceptable where the surrounding code already uses them.\n\n**Additional Bun conventions:**\n\n- Prefer Bun Shell `$` for short, non-streaming commands; use `Bun.spawn` only when you need streaming I/O or process control.\n- Use `Bun.file()`/`Bun.write()` for simple files and `node:fs/promises` for directory-oriented operations. Existing synchronous `node:fs` calls are acceptable when the calling flow is intentionally synchronous.\n- Avoid `Bun.file().exists()` checks; use `isEnoent` handling in try/catch.\n- Prefer `Bun.sleep(ms)` over `setTimeout` wrappers.\n\n**Wrong:**\n\n```typescript\n// BROKEN: env vars may be undefined, \"~\" is not expanded\nconst home = Bun.env.HOME || \"~\";\nconst tmp = Bun.env.TMPDIR || \"/tmp\";\n```\n\n**Correct:**\n\n```typescript\nimport * as os from \"node:os\";\nimport * as fs from \"node:fs\";\nimport * as path from \"node:path\";\n\nconst configDir = path.join(os.homedir(), \".config\", \"myapp\");\nconst tempDir = fs.mkdtempSync(path.join(os.tmpdir(), \"myapp-\"));\n```\n\n## 5) Prefer Bun embeds (no copying)\n\nDo not add new runtime asset copy steps. Keep assets in repo and prefer Bun embeds/imports; preserve existing explicit generation workflows such as `packages/coding-agent/src/export/html/template.generated.ts`.\n\n- If upstream copies assets into a dist folder, replace with Bun-friendly embeds.\n- Prompts are static `.md` files; use Bun text imports (`with { type: \"text\" }`) and Handlebars instead of inline prompt strings.\n- Use `import.meta.dir` + `Bun.file` to load adjacent non-text resources.\n- Keep assets in-repo and let the bundler include them.\n- Eliminate copy scripts unless the user explicitly requests them or the package already has an intentional generation step.\n- If upstream reads a bundled fallback file at runtime, replace filesystem reads with a Bun text embed import unless the current package already uses a generated asset pipeline.\n  - Example (provider instructions fallback):\n    - `const FALLBACK_PROMPT_PATH = join(import.meta.dir, \"openai-code-instructions.md\");` -> removed\n    - `import FALLBACK_INSTRUCTIONS from \"./openai-code-instructions.md\" with { type: \"text\" };`\n    - Use `return FALLBACK_INSTRUCTIONS;` instead of `readFileSync(FALLBACK_PROMPT_PATH, \"utf8\")`\n\n## 6) Port `package.json` carefully\n\nTreat `package.json` as a contract. Merge intentionally.\n\n- Keep existing `name`, `version`, `type`, `exports`, and `bin` unless the port requires changes.\n- Replace npm/node scripts with Bun equivalents (e.g., `bun check`, `bun test`).\n- Ensure dependencies use the correct scope.\n- Do not downgrade dependencies to fix type errors; upgrade instead.\n- Validate workspace package links and `peerDependencies`.\n\n## 7) Align code style and tooling\n\n- Keep existing formatting conventions.\n- Do not introduce `any` unless required.\n- Avoid dynamic imports unless they are required for optional dependencies, startup cost, or runtime-only modules; prefer top-level imports otherwise.\n- Never build prompts in code; prompts are static `.md` files rendered with Handlebars.\n- In `packages/coding-agent`, use `logger` from `@gajae-code/utils` for internal/runtime logging; CLI command files may use `console.*` for intentional user-facing output.\n- Use `Promise.withResolvers()` instead of `new Promise((resolve, reject) => ...)`.\n- Prefer ES `#` private fields for new encapsulated state. Constructor parameter properties already exist in current code and are acceptable; do not churn unrelated access modifiers while porting.\n- Prefer existing helpers and utilities over new ad-hoc code.\n  Preserve Bun-first infrastructure changes already made in this repo:\n  - Runtime is Bun (no Node entry points for the main CLI).\n  - Package manager is Bun (no npm lockfiles).\n  - Heavy Node APIs should not be introduced casually; current source still uses selected Node APIs (`node:crypto`, `node:readline`, synchronous `node:fs`, and `child_process`) where they fit provider, CLI, or process-control semantics.\n  - Lightweight Node APIs (`os.homedir`, `os.tmpdir`, `fs.mkdtempSync`, `path.*`) are kept.\n  - CLI shebangs use `bun` (not `node`, not `tsx`).\n  - TypeScript packages generally use source files directly; `@gajae-code/natives` exports generated native bindings from `packages/natives/native`.\n  - CI workflows run Bun for install/check/test.\n\n## 8) Remove old compatibility layers\n\nUnless requested, remove upstream compatibility shims.\n\n- Delete old APIs that were replaced.\n- Update all call sites to the new API directly.\n- Do not keep `*_v2` or parallel versions.\n\n## 9) Update docs and references\n\n- Replace pi-mono repo links where appropriate.\n- Update examples to use Bun and correct package scopes.\n- Ensure README instructions still match the current repo behavior.\n\n## 10) Validate the port\n\nRun the standard checks after changes:\n\n- `bun check`\n\nIf the repo already has failing checks unrelated to your changes, call that out.\nTests use Bun's runner (not Vitest), but only run `bun test` when explicitly requested.\n\n## 11) Protect improved features (regression trap list)\n\nIf you already improved behavior locally, treat those as **non‑negotiable**. Before porting, write down\nthe improvements and add explicit checks so they don’t get lost in the merge.\n\n- **Freeze the expected behavior**: add a short “before/after” note for each improvement (inputs, outputs,\n  defaults, edge cases). This prevents silent rollback.\n- **Map old → new APIs**: if upstream renamed concepts (hooks → extensions, custom tools → tools, etc.),\n  ensure every old entry point still wires through. One missed flag or export equals lost functionality.\n- **Verify exports**: check `package.json` `exports`, public types, and barrel files. Upstream ports often\n  forget to re-export local additions.\n- **Cover non‑happy paths**: if you fixed error handling, timeouts, or fallback logic, add a test or at\n  least a manual checklist that exercises those paths.\n- **Check defaults and config merge order**: improvements often live in defaults. Confirm new defaults\n  didn’t revert (e.g., new config precedence, disabled features, tool lists).\n- **Audit env/shell behavior**: if you fixed execution or sandboxing, verify the new path still uses your\n  sanitized env and does not reintroduce alias/function overrides.\n- **Re-run targeted samples**: keep a minimal set of \"known good\" examples and run them after the port\n  (CLI flags, extension registration, tool execution).\n\n## 12) Detect and handle reworked code\n\nBefore porting a file, check if upstream significantly refactored it:\n\n```bash\n# Compare the file you're about to port against what you have locally\ngit diff HEAD upstream/main -- path/to/file.ts\n```\n\nIf the diff shows the file was **reworked** (not just patched):\n\n- New abstractions, renamed concepts, merged modules, changed data flow\n\nThen you must **read the new implementation thoroughly** before porting. Blind merging of reworked code loses functionality because:\n\nNote: interactive mode was recently split into controllers/utils/types. When backporting related changes, port updates into the individual files we created and ensure `interactive-mode.ts` wiring stays in sync.\n\n1. **Defaults change silently** - A new variable `defaultFoo = [a, b]` may replace an old `getAllFoo()` that returned `[a, b, c, d, e]`.\n\n2. **API options get dropped** - When systems merge (e.g., `hooks` + `customTools` → `extensions`), old options may not wire through to the new implementation.\n\n3. **Code paths go stale** - A renamed concept (e.g., `hookMessage` → `custom`) needs updates in every switch statement, type guard, and handler—not just the definition.\n\n4. **Context/capabilities shrink** - Old APIs may have exposed `{ logger, typebox, pi }` that new APIs forgot to include.\n\n### Semantic porting process\n\nWhen upstream reworked a module:\n\n1. **Read the old implementation** - Understand what it did, what options it accepted, what it exposed.\n\n2. **Read the new implementation** - Understand the new abstractions and how they map to old behavior.\n\n3. **Verify feature parity** - For each capability in the old code, confirm the new code preserves it or explicitly removes it.\n\n4. **Grep for stragglers** - Search for old names/concepts that may have been missed in switch statements, handlers, UI components.\n\n5. **Test the boundaries** - CLI flags, SDK options, event handlers, default values—these are where regressions hide.\n\n### Quick checks\n\n```bash\n# Find all uses of an old concept that may need updating\nrg \"oldConceptName\" --type ts\n\n# Compare default values between versions\ngit show upstream/main:path/to/file.ts | rg \"default|DEFAULT\"\n\n# Check if all enum/union values have handlers\nrg \"case \\\"\" path/to/file.ts\n```\n\n## 13) Quick audit checklist\n\nUse this as a final pass before you finish:\n\n- [ ] Import extensions follow the local package convention (no blanket `.js` stripping)\n- [ ] No newly introduced Node-only APIs unless they match an existing justified pattern\n- [ ] All package scopes updated\n- [ ] `package.json` scripts use Bun\n- [ ] Prompts are `.md` text imports (no inline prompt strings)\n- [ ] No internal/runtime `console.*` in coding-agent; CLI user-facing output is intentional\n- [ ] Assets load via Bun embed/import patterns, or through an existing intentional generation pipeline\n- [ ] Tests or checks run (or explicitly noted as blocked)\n- [ ] No functionality regressions (see sections 11-12)\n\n## 14) Commit message format\n\nWhen committing a backport, follow the repo format `<type>(scope): <past-tense description>` and keep the commit\nrange in the title.\n\n```\nfix(coding-agent): backported pi-mono changes (<from>..<to>)\n\npackages/<package>:\n- <type>: <description>\n- <type>: <description> (#<issue> by @<contributor>)\n\npackages/<other-package>:\n- <type>: <description>\n```\n\n**Example:**\n\n```\nfix(coding-agent): backported pi-mono changes (9f3eef65f..52532c7c0)\n\npackages/ai:\n- fix: handle \"sensitive\" stop reason from Anthropic API\n- fix: normalize tool call IDs with special characters for Responses API\n- fix: add overflow detection for Bedrock, MiniMax, Kimi providers\n- fix: 429 status is rate limiting, not context overflow\n\npackages/tui:\n- fix: refactored autocomplete state tracking\n- fix: file autocomplete should not trigger on empty text\n- fix: configurable autocomplete max visible items\n- fix: improved table column width calculation with word-aware wrapping\n\npackages/coding-agent:\n- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)\n- fix: resolve macOS NFD and curly quote variants in file paths\n```\n\n**Rules:**\n\n- Group changes by package\n- Use conventional commit types (`fix`, `feat`, `refactor`, `perf`, `docs`)\n- Include upstream issue/PR numbers and contributor attribution for external contributions\n- The commit range in the title helps track sync points\n\n## 15) Intentional Divergences\n\nOur fork has architectural decisions that differ from upstream. **Do not port these upstream patterns:**\n\n### UI Architecture\n\n| Upstream                                    | Our Fork                                                  | Reason                                                                |\n| ------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FooterDataProvider` class                  | `StatusLineComponent`                                     | Simpler, integrated status line                                       |\n| `ctx.ui.setHeader()` / `ctx.ui.setFooter()` | No-op stubs in current extension contexts                 | Not currently wired to replace the TUI status/header UI               |\n| `ctx.ui.setEditorComponent()`               | No-op stubs in current extension contexts                 | Custom editor replacement is not currently wired                      |\n| `InteractiveModeOptions` options object     | Positional constructor args (options type still exported) | Keep constructor signature; update the type when upstream adds fields |\n\n### Component Naming\n\n| Upstream                     | Our Fork                |\n| ---------------------------- | ----------------------- |\n| `extension-input.ts`         | `hook-input.ts`         |\n| `extension-selector.ts`      | `hook-selector.ts`      |\n| `ExtensionInputComponent`    | `HookInputComponent`    |\n| `ExtensionSelectorComponent` | `HookSelectorComponent` |\n\n### API Naming\n\n| Upstream                                 | Our Fork                                 | Notes                                     |\n| ---------------------------------------- | ---------------------------------------- | ----------------------------------------- |\n| `sessionManager.appendSessionInfo(name)` | `sessionManager.setSessionName(name)`    | We use `sessionName` throughout           |\n| `sessionManager.getSessionName()`        | `sessionManager.getSessionName()`        | Same (we unified to match upstream's RPC) |\n| `agent.sessionName` / `setSessionName()` | `agent.sessionName` / `setSessionName()` | Same                                      |\n\n### File Consolidation\n\n| Upstream                                           | Our Fork                                                  | Reason                                        |\n| -------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------- |\n| `clipboard.ts` + `clipboard-image.ts` (tool files) | `src/utils/clipboard.ts` backed by `@gajae-code/natives` | Native implementation with a small TS wrapper |\n\n### Test Framework\n\n| Upstream                  | Our Fork                      |\n| ------------------------- | ----------------------------- |\n| `vitest` with `vi.mock()` | `bun:test` with `vi` from bun |\n| `node:test` assertions    | `expect()` matchers           |\n\n### Tool Architecture\n\n| Upstream                            | Our Fork                                                                                                      | Notes                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |\n| `createTool(cwd: string, options?)` | `createTools(session: ToolSession)` via `BUILTIN_TOOLS` registry                                              | Tool factories accept `ToolSession` and can return `null` |\n| Per-tool `*Operations` interfaces   | Only current per-tool override interfaces remain (for example `FindOperations`)                               | Used for SSH/remote overrides where present               |\n| Node.js `fs/promises` everywhere    | Bun file APIs for simple file writes/reads, `node:fs/promises` for dirs, selected sync `node:fs` where needed | Prefer Bun APIs when they simplify                        |\n\n### Auth Storage\n\n| Upstream                        | Our Fork                                    | Notes                                        |\n| ------------------------------- | ------------------------------------------- | -------------------------------------------- |\n| `proper-lockfile` + `auth.json` | `agent.db` (bun:sqlite)                     | Credentials stored exclusively in `agent.db` |\n| Single credential per provider  | Multi-credential with round-robin selection | Session affinity and backoff logic preserved |\n\n### Extensions\n\n| Upstream                      | Our Fork                                          |\n| ----------------------------- | ------------------------------------------------- |\n| `jiti` for TypeScript loading | Native Bun `import()`                             |\n| `pkg.pi` manifest field       | `pkg.gjc` preferred; fallback to `pkg.pi` remains |\n\n### Skip These Upstream Features\n\nWhen porting, **skip** these files/features entirely:\n\n- `footer-data-provider.ts` — we use StatusLineComponent\n- `clipboard-image.ts` — image clipboard support is exposed through `src/utils/clipboard.ts` backed by `@gajae-code/natives`\n- GitHub workflow files — we have our own CI\n- `models.generated.ts` — auto-generated, regenerate locally (as models.json instead)\n\n### Features We Added (Preserve These)\n\nThese exist in our fork but not upstream. **Never overwrite:**\n\n- `StatusLineComponent` in interactive mode\n- Multi-credential auth with session affinity\n- Capability-based discovery system (`defineCapability`, `registerProvider`, `loadCapability`, `skillCapability`, etc.)\n- MCP/Exa/SSH integrations\n- LSP writethrough for format-on-save\n- Bash interception (`checkBashInterception`)\n- Fuzzy path suggestions in read tool\n",
 	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nRust is reserved for native bindings, native OS/process/filesystem integration, and measured hot paths. New crates or Rust source trees must have an explicit native/performance rationale in `scripts/check-rust-scope.ts`; keep product policy, orchestration, and glue code in TypeScript unless the benchmark or native boundary justifies moving it.\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n> **Optimization ports need evidence first.** A native port proposed to optimize a *leftover algorithmic hot path* must clear the gates in [`native-ffi-optimization-policy.md`](./native-ffi-optimization-policy.md) (corpus evidence, `profilerSelfTime` attribution, measured FFI overhead, representative p50/p95 win, byte parity, documented rollback cost). New OS/process/native-primitive bindings follow this guide as usual.\n\n## Current package shape\n\n`@gajae-code/natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@gajae-code/natives`. The generated declarations are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.js`/`index.d.ts`, and appends enum runtime exports.\n- `packages/natives/native/index.js` is the loader that chooses a candidate `.node` file and returns the loaded addon.\n- `packages/natives/package.json` exposes only the package root (`@gajae-code/natives`).\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` still has generated enum exports appended when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@gajae-code/natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. If any earlier candidate is stale, a new export may appear missing.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries, delete the versioned addon cache shown in the loader error (normally under `~/.gjc/natives/<version>` unless `$XDG_DATA_HOME/gjc` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale or from a different platform/variant.\n\nVerify the loaded export set from the actual candidate path:\n\n```bash\nbun -e 'const tag = `${process.platform}-${process.arch}`; const mod = require(`./packages/natives/native/pi_natives.${tag}.node`); console.log(Object.keys(mod).sort())'\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports\n\nnapi-rs declarations alone are not enough for JS callers that use enum objects at runtime. `scripts/gen-enums.ts` appends enum objects to `native/index.js`. If you add or change a native enum, verify both `native/index.d.ts` and the generated enum export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export.\n- Runtime enum objects are present when the change adds/changes enums.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
 	"prompt-architect-reports/README.md": "# Prompt architect reports\n\nGenerated from the four architect subagents spawned to review prompt optimization/enhancement opportunities, then augmented by inspecting failed subagent JSONL contexts.\n\n## Artifacts\n\n- `agent-prompts.raw.json` — usable structured report from `2-AgentPrompts`.\n- `recovery-summary.md` — summary of context recovery for failed/errored agents.\n- `recovered-context/0-ToolPrompts.recovered.md` — recovered tool-prompt review context plus all 34 structured `report_finding` findings.\n- `recovered-context/0-ToolPrompts.findings.json` — recovered tool-prompt findings as JSON.\n- `recovered-context/1-SystemPrompts.recovered.md` — recovered system-prompt context: reads/searches/errors; no findings/yield emitted.\n- `recovered-context/1-SystemPrompts.findings.json` — empty; no `report_finding` calls emitted.\n- `recovered-context/3-SkillMiscPrompts.recovered.md` — recovered skill/misc context: reads/searches/errors; no findings/yield emitted.\n- `recovered-context/3-SkillMiscPrompts.findings.json` — empty; no `report_finding` calls emitted.\n- `tool-prompts.raw.md`, `system-prompts.raw.md`, `skill-misc-prompts.raw.json` — initial raw-stub artifacts kept for audit history; superseded by `recovery-summary.md` and `recovered-context/`.\n- `system-prompts.rerun.json` — successful re-run of the SystemPrompts lane (grade C, 12 findings: 1 P1, 6 P2, 5 P3).\n- `skill-misc-prompts.rerun.json` — successful re-run of the SkillMiscPrompts lane (grade C, 9 findings: 1 P1, 4 P2, 4 P3).\n\n## Usable verdicts\n\n### AgentPrompts\n\nUsable report. Verdict: **B-** with **16 findings**: **2 P1**, **5 P2**, **9 P3**.\n\nTop fixes:\n\n1. Add a persistence-context gate to `architect.md` and `critic.md` so `gjc ralplan --write` is used only inside an active ralplan lane; otherwise return the full review in `yield.result.data`.\n2. Wire `report_finding` into the architect output contract and define the severity mapping `CRITICAL -> P0`, `HIGH -> P1`, `MEDIUM -> P2`, `LOW -> P3`.\n3. Extract the ultragoal red-team executor QA block from the always-loaded executor prompt into an ultragoal-only injected fragment or assignment contract.\n\n### ToolPrompts\n\nNo final `yield` or grade, but context recovery found **34 structured findings** emitted through `report_finding` before stalls/429: **4 P1**, **18 P2**, **12 P3**.\n\nHighest-impact recovered findings:\n\n1. `replace.md` recommends `cat`/`sed` shell alternatives that directly contradict `bash.md`, `read.md`, and `search.md` bans.\n2. `monitor.md` documents invalid `job({op:\"list\"})`; actual schema expects `job({list: true})`.\n3. `apply-patch.md` has a truncated “Within a hunk each line starts with:” sentence.\n4. `ast-edit.md` omits the preview-to-`resolve({action:\"apply\"})` persistence flow.\n\n### SystemPrompts (re-run)\n\nGrade **C**, **12 findings** (1 P1, 6 P2, 5 P3). Top fixes: remove the `<soul>` block contradicting the base prompt's authority/safety contracts; guard `{{toolRefs.search_tool_bm25}}` discovery text on the actual activator tool; make plan-mode subagent output instructions yield-aware. See `system-prompts.rerun.json`.\n\n### SkillMiscPrompts (re-run)\n\nGrade **C**, **9 findings** (1 P1, 4 P2, 4 P3). Top fixes: fix unrendered `{{ARGUMENTS}}` in deep-interview SKILL; remove dead `plan` skill / `--research-setup` / `gjc sparkshell` / `team_cleanup` references; complete the ultragoal `executorQa` replay contract. See `skill-misc-prompts.rerun.json`.\n\n## Status\n\nAll four lanes now have usable reports: AgentPrompts and ToolPrompts findings were applied in this branch's prompt fixes; SystemPrompts and SkillMiscPrompts re-run findings are recorded above and pending application.\n",

package/src/modes/DESIGN.md

@@ -291,6 +291,59 @@ textual state without SGR. Korean, Japanese, Chinese, and mixed CJK/Latin prose
 must wrap at semantic phrase boundaries, never through an action/status label or
 short identifier; a semantic CJK break is a visual-QA failure.
 
+### Direct-root anatomy, IRC lane, and pin boundary
+
+The production root has one ordered, direct-child anatomy. Do not wrap, reorder,
+or independently pin these regions:
+
+1. `ircSplitView` is the viewport anchor and owns the transcript (and the IRC
+   sidebar when effective);
+2. `pendingMessagesContainer`, `statusContainer`, `todoContainer`, and
+   `btwContainer` follow the anchor **before** the pin boundary;
+3. `statusLine` is the pin boundary; and
+4. `hookWidgetContainerAbove`, `editorContainer`, `petFloorContainer`, and
+   `hookWidgetContainerBelow` are the later direct composer children in that
+   order.
+
+`statusContainer` is transient operation/status content in the pre-boundary
+application flow; it is not the persistent `statusLine` telemetry rail. The
+status line begins the fixed suffix. The focused editor, its cursor, and every
+later direct composer child remain below that boundary during manual history,
+streaming, and reflow. Pending messages, todo, and BTW therefore remain
+transcript-adjacent rather than becoming accidental fixed chrome.
+
+IRC has one shared work-lane geometry. At **64 cells or narrower** the IRC lane
+is ineffective and transcript/todo use the full width. At **65 cells** it is
+exactly **32 / 3 / 30** cells (left work lane / separator / IRC lane). At wider
+sizes the same split calculation applies; todo uses the left work lane whenever
+IRC is effective, including empty, streaming, and long IRC histories. Todo
+does not create a second sidebar, a separately rounded width, or a different
+collapse rule.
+
+Todo is absent when empty. Populated todos support long text, multiple phases,
+and collapsed/expanded views without crossing the separator or overflowing
+their work lane. The active phase is retained in collapsed view; expanded view
+keeps phase/task order. IRC empty, streaming, and long states preserve the
+same root order and pin boundary.
+
+Row reservation is content-priority based: reserve the focused composer and
+status line first, then normal hooks; when height is constrained, drop the
+manual-output notice first, then the decorative pet, then low-priority hooks.
+A zero-row transcript capacity is valid. Neither reservation nor degradation
+may hide focus/cursor geometry, move an anchor into pinned chrome, or turn a
+resize into a follow/manual state change. Manual and follow paths, streaming
+updates, width growth/shrink, and height growth/shrink preserve the anchor
+semantics; resize must recompute the shared IRC/todo lane before rendering.
+
+All lane measurement, clipping, and wrapping is ANSI-aware terminal-cell
+measurement. Terminal graphics may be shown only where the effective layout
+permits them and must degrade to the textual graphics fallback without changing
+row ownership. ANSI/color output preserves visible cursor/focus state; ASCII
+and no-color output retains textual selection/status affordances. CJK and mixed
+CJK/Latin todo, IRC, status, and BTW text break at semantic phrase boundaries,
+not inside a phase/action/status label, short identifier, or grapheme cluster.
+Those defects, width overflow, overlap, hidden focus/cursor, and lost anchors
+are blocking visual-QA failures.
 ### Sticky viewport deterministic visual QA
 
 `test/fixtures/tui/sticky-viewport-showcase.ts` is a fixed-clock, no-network,

package/src/modes/components/irc-sidebar.ts

@@ -82,6 +82,35 @@ export function computeIrcSplitWidths(width: number): {
 		rightWidth: sidebarWidth,
 	};
 }
+/**
+ * Resolves the single shared work-lane geometry. The left lane is used by both
+ * transcript and todo content whenever the IRC lane is effective.
+ */
+export function computeIrcWorkLaneWidths(
+	width: number,
+	sidebarVisible: boolean,
+): { leftWidth: number; separatorWidth: number; rightWidth: number } {
+	const fullWidth = Math.max(0, Math.floor(width));
+	return sidebarVisible
+		? computeIrcSplitWidths(fullWidth)
+		: { leftWidth: fullWidth, separatorWidth: 0, rightWidth: 0 };
+}
+
+export class IrcLeftLaneComponent implements Component {
+	constructor(
+		private readonly content: Component,
+		private readonly isSidebarVisible: (width: number) => boolean,
+	) {}
+
+	render(width: number): string[] {
+		const layout = computeIrcWorkLaneWidths(width, this.isSidebarVisible(width));
+		return this.content.render(layout.leftWidth);
+	}
+
+	invalidate(): void {
+		this.content.invalidate?.();
+	}
+}
 
 type SemanticLine = Readonly<{
 	kind: "header" | "body" | "elision" | "blank";
@@ -288,7 +317,7 @@ export class IrcSplitViewComponent implements ViewportAnchorProvider {
 	renderWithViewportAnchors(width: number): ViewportAnchorRender {
 		if (!this.#visible) return renderComponentWithViewportAnchors(this.leftPane, width);
 		const componentTheme = typeof this.componentTheme === "function" ? this.componentTheme() : this.componentTheme;
-		const { leftWidth, separatorWidth, rightWidth } = computeIrcSplitWidths(width);
+		const { leftWidth, separatorWidth, rightWidth } = computeIrcWorkLaneWidths(width, this.#visible);
 		if (rightWidth === 0) return renderComponentWithViewportAnchors(this.leftPane, width);
 		const separator = separatorWidth > 0 ? componentTheme.fg("dim", ` ${componentTheme.boxSharp.vertical} `) : "";
 		const leftRender = withTerminalGraphicsFallback(

package/src/modes/components/tool-status-header.ts

@@ -206,7 +206,6 @@ export class StatusLineComponent implements Component {
 			separator: settings.get("statusLine.separator"),
 			showHookStatus: settings.get("statusLine.showHookStatus"),
 			showSkillHud: settings.get("statusLine.showSkillHud"),
-			showActionHints: settings.get("statusLine.showActionHints"),
 			segmentOptions: settings.getGroup("statusLine").segmentOptions,
 			sessionAccent: settings.get("statusLine.sessionAccent"),
 			maxRows: settings.get("statusLine.maxRows"),

package/src/modes/controllers/command-controller.ts

@@ -34,7 +34,12 @@ import { BorderedLoader } from "../../modes/components/bordered-loader";
 import { DynamicBorder } from "../../modes/components/dynamic-border";
 import { EvalExecutionComponent } from "../../modes/components/eval-execution";
 import { getMarkdownTheme, getSymbolTheme, theme } from "../../modes/theme/theme";
-import type { InteractiveModeContext } from "../../modes/types";
+import {
+	clearInteractiveActivityLoaders,
+	type InteractiveModeContext,
+	stopInteractiveActivityIndicator,
+	suspendInteractiveActivityIndicator,
+} from "../../modes/types";
 import { computeContextBreakdown, renderContextUsage } from "../../modes/utils/context-usage";
 import { buildHotkeysMarkdown, formatHotkeyMarkdownCode } from "../../modes/utils/hotkeys-markdown";
 import { buildToolsMarkdown } from "../../modes/utils/tools-markdown";
@@ -965,12 +970,10 @@ export class CommandController {
 
 	async #runNewSessionFlow(options?: NewSessionOptions, label: string = "New session started"): Promise<boolean> {
 		if (!(await this.ctx.session.newSession(options))) return false;
+		if (this.ctx.isStopped?.()) return false;
+		clearInteractiveActivityLoaders(this.ctx);
 
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-		}
-		this.ctx.statusContainer.clear();
+		stopInteractiveActivityIndicator(this.ctx);
 		this.ctx.resetIrcSidebarSession();
 		this.ctx.resetObserverRegistry();
 		setSessionTerminalTitle(this.ctx.sessionManager.getSessionName(), this.ctx.sessionManager.getCwd());
@@ -991,6 +994,7 @@ export class CommandController {
 
 		this.ctx.chatContainer.addChild(new Text(`${theme.fg("accent", `${theme.status.success} ${label}`)}`, 1, 0));
 		await this.ctx.reloadTodos();
+		if (this.ctx.isStopped?.()) return false;
 		this.ctx.ui.requestRender();
 		return true;
 	}
@@ -1000,19 +1004,18 @@ export class CommandController {
 	}
 
 	async handleContextClearCommand(): Promise<void> {
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-		}
-		this.ctx.statusContainer.clear();
-
+		if (this.ctx.isStopped?.()) return;
+		clearInteractiveActivityLoaders(this.ctx);
+		stopInteractiveActivityIndicator(this.ctx);
 		if (this.ctx.session.isCompacting) {
 			this.ctx.session.abortCompaction();
 			while (this.ctx.session.isCompacting) {
 				await Bun.sleep(10);
 			}
 		}
+		if (this.ctx.isStopped?.()) return;
 		if (!(await this.ctx.session.clearContext())) return;
+		if (this.ctx.isStopped?.()) return;
 		setSessionTerminalTitle(this.ctx.sessionManager.getSessionName(), this.ctx.sessionManager.getCwd());
 
 		this.ctx.statusLine.invalidate();
@@ -1033,6 +1036,7 @@ export class CommandController {
 			new Text(`${theme.fg("accent", `${theme.status.success} Context cleared`)}`, 1, 0),
 		);
 		await this.ctx.reloadTodos();
+		if (this.ctx.isStopped?.()) return;
 		this.ctx.ui.requestRender();
 	}
 
@@ -1049,17 +1053,15 @@ export class CommandController {
 			this.ctx.showWarning("Wait for the current response to finish or abort it before forking.");
 			return;
 		}
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-		}
-		this.ctx.statusContainer.clear();
 
 		const success = await this.ctx.session.fork();
+		if (this.ctx.isStopped?.()) return;
 		if (!success) {
 			this.ctx.showError("Fork failed (session not persisted or cancelled)");
 			return;
 		}
+		clearInteractiveActivityLoaders(this.ctx);
+		stopInteractiveActivityIndicator(this.ctx);
 		this.ctx.resetIrcSidebarSession();
 
 		this.ctx.statusLine.invalidate();
@@ -1256,11 +1258,7 @@ export class CommandController {
 		customInstructionsOrOptions?: string | CompactOptions,
 		isAuto = false,
 	): Promise<CompactionOutcome> {
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-		}
-		this.ctx.statusContainer.clear();
+		const releaseActivityIndicator = suspendInteractiveActivityIndicator(this.ctx);
 
 		const originalOnEscape = this.ctx.editor.onEscape;
 		this.ctx.editor.onEscape = () => {
@@ -1287,24 +1285,28 @@ export class CommandController {
 					? customInstructionsOrOptions
 					: undefined;
 			await this.ctx.session.compact(instructions, options);
+			if (this.ctx.isStopped?.()) return outcome;
 
 			this.ctx.rebuildChatFromMessages("reconcile-same-transcript");
 
 			this.ctx.statusLine.invalidate();
 			this.ctx.updateEditorTopBorder();
 		} catch (error) {
-			if (error instanceof CompactionCancelledError) {
-				outcome = "cancelled";
+			outcome = error instanceof CompactionCancelledError ? "cancelled" : "failed";
+			if (this.ctx.isStopped?.()) return outcome;
+			if (outcome === "cancelled") {
 				this.ctx.showError("Compaction cancelled");
 			} else {
-				outcome = "failed";
 				const message = error instanceof Error ? error.message : String(error);
 				this.ctx.showError(`Compaction failed: ${message}`);
 			}
 		} finally {
 			compactingLoader.stop();
-			this.ctx.statusContainer.clear();
-			this.ctx.editor.onEscape = originalOnEscape;
+			if (!this.ctx.isStopped?.()) {
+				this.ctx.statusContainer.clear();
+				this.ctx.editor.onEscape = originalOnEscape;
+			}
+			releaseActivityIndicator();
 		}
 		await this.ctx.flushCompactionQueue({ willRetry: false });
 		return outcome;
@@ -1323,11 +1325,7 @@ export class CommandController {
 			return;
 		}
 
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-		}
-		this.ctx.statusContainer.clear();
+		const releaseActivityIndicator = suspendInteractiveActivityIndicator(this.ctx);
 
 		const originalOnEscape = this.ctx.editor.onEscape;
 		this.ctx.editor.onEscape = () => {
@@ -1347,6 +1345,7 @@ export class CommandController {
 		try {
 			// Handoff generation runs as a oneshot request; the new session is shown after it completes.
 			const result = await this.ctx.session.handoff(customInstructions);
+			if (this.ctx.isStopped?.()) return;
 
 			if (!result) {
 				this.ctx.showError("Handoff cancelled");
@@ -1361,6 +1360,7 @@ export class CommandController {
 			this.ctx.updateEditorTopBorder();
 			this.ctx.updateEditorBorderColor();
 			await this.ctx.reloadTodos();
+			if (this.ctx.isStopped?.()) return;
 
 			this.ctx.chatContainer.addChild(new Spacer(1));
 			this.ctx.chatContainer.addChild(
@@ -1370,6 +1370,7 @@ export class CommandController {
 				this.ctx.showStatus(`Handoff document saved to: ${result.savedPath}`);
 			}
 		} catch (error) {
+			if (this.ctx.isStopped?.()) return;
 			const message = error instanceof Error ? error.message : String(error);
 			if (message === "Handoff cancelled" || (error instanceof Error && error.name === "AbortError")) {
 				this.ctx.showError("Handoff cancelled");
@@ -1389,8 +1390,11 @@ export class CommandController {
 			}
 		} finally {
 			handoffLoader.stop();
-			this.ctx.statusContainer.clear();
-			this.ctx.editor.onEscape = originalOnEscape;
+			if (!this.ctx.isStopped?.()) {
+				this.ctx.statusContainer.clear();
+				this.ctx.editor.onEscape = originalOnEscape;
+			}
+			releaseActivityIndicator();
 		}
 	}
 

package/src/modes/controllers/event-controller.ts

@@ -15,7 +15,12 @@ import { TodoReminderComponent } from "../../modes/components/todo-reminder";
 import { ToolExecutionComponent, type ToolExecutionHandle } from "../../modes/components/tool-execution";
 import { TtsrNotificationComponent } from "../../modes/components/ttsr-notification";
 import { getSymbolTheme, theme } from "../../modes/theme/theme";
-import type { InteractiveModeContext, TodoPhase } from "../../modes/types";
+import {
+	type InteractiveModeContext,
+	stopInteractiveActivityIndicator,
+	syncInteractiveActivityIndicator,
+	type TodoPhase,
+} from "../../modes/types";
 import type { PlanApprovalDetails } from "../../plan-mode/approved-plan";
 import { completionNotifyDisabledByEnv } from "../../sdk/bus/config";
 import { summaryFromMessage } from "../../sdk/bus/helpers";
@@ -166,6 +171,14 @@ export class EventController {
 			this.ctx.retryEscapeHandler = undefined;
 		}
 		this.ctx.retryEscapePrimed = false;
+		if (this.ctx.autoCompactionEscapeHandler) {
+			this.ctx.editor.onEscape = this.ctx.autoCompactionEscapeHandler;
+			this.ctx.autoCompactionEscapeHandler = undefined;
+		}
+		if (this.ctx.autoCompactionLoader) {
+			this.ctx.autoCompactionLoader.stop();
+			this.ctx.autoCompactionLoader = undefined;
+		}
 		if (this.ctx.retryLoader) {
 			this.ctx.retryLoader.stop();
 			this.ctx.retryLoader = undefined;
@@ -266,7 +279,9 @@ export class EventController {
 	}
 
 	async #dispatchEvent(event: AgentSessionEvent): Promise<void> {
+		if (this.ctx.isStopped?.()) return;
 		if (!this.ctx.isInitialized) await this.ctx.init();
+		if (this.ctx.isStopped?.()) return;
 		this.#visibleTranscriptChanged = false;
 		this.#handlingEvent = true;
 		try {
@@ -274,6 +289,7 @@ export class EventController {
 			this.ctx.updateEditorTopBorder();
 			const run = this.#handlers[event.type] as (e: AgentSessionEvent) => Promise<void>;
 			await run(event);
+			if (this.ctx.isStopped?.()) return;
 			if (this.#visibleTranscriptChanged) this.ctx.recordVisibleTranscriptMutation?.();
 			if (this.ctx.isTranscriptViewerOpen?.()) this.ctx.refreshTranscriptViewer?.();
 		} finally {
@@ -878,23 +894,22 @@ export class EventController {
 				const planDetails = details.sourceResultDetails as PlanApprovalDetails | undefined;
 				if (planDetails) {
 					await this.ctx.planModeController.handleApproval(planDetails);
+					if (this.ctx.isStopped?.()) return;
 				}
 			}
 		}
 	}
 
 	async #handleAgentEnd(_event: Extract<AgentSessionEvent, { type: "agent_end" }>): Promise<void> {
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-			this.ctx.statusContainer.clear();
-		}
+		this.ctx.setWorkingMessage(undefined);
+		stopInteractiveActivityIndicator(this.ctx);
 		if (this.ctx.streamingComponent) {
 			this.ctx.chatContainer.removeChild(this.ctx.streamingComponent);
 			this.ctx.streamingComponent = undefined;
 			this.ctx.streamingMessage = undefined;
 		}
 		await this.ctx.planModeController.flushPendingModelSwitch();
+		if (this.ctx.isStopped?.()) return;
 		for (const toolCallId of Array.from(this.ctx.pendingTools.keys())) {
 			if (!this.#backgroundToolCallIds.has(toolCallId)) {
 				this.ctx.pendingTools.delete(toolCallId);
@@ -922,11 +937,7 @@ export class EventController {
 		this.ctx.editor.onEscape = () => {
 			this.ctx.session.abortCompaction();
 		};
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-		}
-		this.ctx.statusContainer.clear();
+		stopInteractiveActivityIndicator(this.ctx, { restoreBackground: false });
 		const reasonText =
 			event.reason === "overflow" ? "Context overflow detected, " : event.reason === "idle" ? "Idle " : "";
 		const actionLabel = event.action === "handoff" ? "Auto-handoff" : "Auto context-full maintenance";
@@ -982,6 +993,7 @@ export class EventController {
 			this.ctx.statusLine.invalidate();
 			this.ctx.updateEditorTopBorder();
 			await this.ctx.reloadTodos();
+			if (this.ctx.isStopped?.()) return;
 			this.ctx.showStatus("Auto-handoff completed");
 		} else if (event.skipped) {
 			// Benign skip: no model selected, no candidate models available, or nothing
@@ -995,6 +1007,8 @@ export class EventController {
 			this.ctx.showWarning("Auto context-full maintenance failed; continuing without maintenance");
 		}
 		await this.ctx.flushCompactionQueue({ willRetry: event.willRetry });
+		if (this.ctx.isStopped?.()) return;
+		syncInteractiveActivityIndicator(this.ctx);
 		this.ctx.ui.requestRender();
 	}
 
@@ -1024,11 +1038,7 @@ export class EventController {
 				this.ctx.session.abortRetry();
 			}
 		};
-		if (this.ctx.loadingAnimation) {
-			this.ctx.loadingAnimation.stop();
-			this.ctx.loadingAnimation = undefined;
-		}
-		this.ctx.statusContainer.clear();
+		stopInteractiveActivityIndicator(this.ctx, { restoreBackground: false });
 		// Stop any prior retry loader/timer before installing a new one.
 		this.ctx.retryLoader?.stop();
 		this.#clearRetryCountdown();
@@ -1071,6 +1081,7 @@ export class EventController {
 		if (!event.success) {
 			this.ctx.showError(`Retry failed after ${event.attempt} attempts: ${event.finalError || "Unknown error"}`);
 		}
+		syncInteractiveActivityIndicator(this.ctx);
 		this.ctx.ui.requestRender();
 	}