The open-source app everyone uses to manage agents at work
TypeScript acpxagent-orchestrationagent-skillsagentic-aiai-agentsai-engineeringai-governanceai-toolsautonomous-agentsclaudeclaude-codeclaude-skillscodexhermesllmmcpmulti-agentopenclawproject-managementworkflow-automation
docs: Pi launch repairs and qualification history (4/5) (#14924)
Dottaab8dcab80964
diff --git a/doc/architecture/runner-pi-capabilities.md b/doc/architecture/runner-pi-capabilities.mdindex a392c16033..0172c726fb 100644--- a/doc/architecture/runner-pi-capabilities.md+++ b/doc/architecture/runner-pi-capabilities.md@@ -71,7 +71,41 @@ control, and Daytona results must be established independently.| Supported thinking levels | `get_available_thinking_levels`; ACP available session modes and `thought_level` choices | Pi reasoning-level configuration | Model selection is explicit and unrestricted; historical qualification used the recorded model and level. || Set and verify thinking level | Native `set_thinking_level`, then `get_state`; ACP `session/set_mode` / config option | Saved agent setting, typed runner input, effective-mode admission | Live setting changes during an active turn are not exposed; a new compatible session is required. || Recover selected level | Native restored state plus explicit effective-level verification | Mode-bound durable session identity | Old profiles and missing or mismatched mode identity cannot reuse a warm session. |-| Provider notice severity and pricing provenance | `paperclip/pi_notice` and canonical `provider.notice.recorded` | Retained run event and usage metadata | The activity row currently renders a generic provider-update label and warning icon even for informational pricing estimates. P2: render the safe summary and severity; do not imply an estimated price is a bill. |+| Provider notice severity and pricing provenance | `paperclip/pi_notice` and canonical `provider.notice.recorded` | Retained run event, usage metadata, and safe summary with severity in the activity row | Summary/severity rendering has deterministic coverage; paid visual verification of the rebuilt UI remains pending. Pricing estimates remain distinct from provider billing receipts. |++## Historical profile-13 qualification checkpoint (2026-10-02)++The installed candidate from source `eac50643213d0902a93a5384bae2f1d6c065c9f2`+uses Pi 1.0.0, the explicit OpenRouter DeepSeek model above, and verified `low`+reasoning. Paid local Product E2E passes cover hello, semantic question/answer+continuation, all four native question forms, and human permission denial with+no file side effect. The paid extended Runner `get-task-context` case also+passes through the packaged runner against its authenticated, seeded test+control plane. Runner protocol evidence does not qualify the Product UI.++Three local attempts remain failed: file-edit validation, pending-input+controller restart, and three-turn warm continuation. The first two exposed+assertion gaps: streamed command output supplies the exit receipt, and a+pre-start submission may precede assignment of the native turn ID. Narrow+fixture repairs have positive and negative coverage; neither failed attempt+has been regraded and both require fresh live runs.++The warm attempt completed its first turn and edited files on its second, but+its final semantic tool stayed pending until the existing deadline. OpenRouter+metadata joins the exact native session and records the final response as+cancelled with no finish reason. This supports an unfinished upstream response+at cancellation; it does not establish why the response stopped progressing.+A real pinned SDK/wrapper replay proves both restored-session completion with+the new agent home and completion contract, and safe cancellation when complete+tool JSON arrives without the provider's stream finish marker. The latter+executes no semantic mutation. No timeout or runtime policy was changed to make+that replay pass.++Fresh builds must incorporate the subsequent launch, UI, and fixture fixes.+macOS Intel startup, the remaining local and Runner cases, Linux/Daytona, and+final source-wide checks remain qualification gates. The provider remains+unqualified until that evidence is complete. API-key usage observations cover+the capped qualification campaign; native pricing estimates are not bills.## Historical Pi 1.0 profile-v12 checkpoint (2026-10-02)diff --git a/doc/architecture/runner-rich-acp-capabilities.md b/doc/architecture/runner-rich-acp-capabilities.mdindex c377bafc1a..c1e6e61260 100644--- a/doc/architecture/runner-rich-acp-capabilities.md+++ b/doc/architecture/runner-rich-acp-capabilities.md@@ -30,6 +30,17 @@ for the exact model `openrouter/deepseek/deepseek-v4-flash-0731`. New Piconfiguration and qualification cases select `low`. This candidate is not yetproduction qualified. Cursor v10 and Copilot v13 remain gated.+The installed profile-13 candidate at `eac50643213d0902a93a5384bae2f1d6c065c9f2`+has paid local passes for hello, semantic question continuation, all four native+question forms, and human permission denial without a file side effect. Its+paid extended Runner `get-task-context` case passes against the authenticated+seeded test control plane. That protocol case does not qualify the Product UI.+File validation, pending-input controller restart, and three-turn warm+continuation remain failed and unregraded. Assertion repairs and an actual+SDK/wrapper replay now cover the identified boundaries; fresh live proof is+still required. See the [historical Pi checkpoint](runner-pi-capabilities.md#historical-profile-13-qualification-checkpoint-2026-10-02)+for the request-stream diagnosis and remaining platform gates.+Copilot's declaration hashes the shared sidecar, sidecar protocol, direct driver,and generated schema bundle. Pi's reasoning field changed those four files, soCopilot's pending declaration advances to v13 with digest@@ -766,22 +777,22 @@ deterministic evidence are mapped separately after the comparison.| Capability | Codex app-server benchmark | Cursor ACP candidate | Copilot ACP candidate | Pi ACP candidate || --- | --- | --- | --- | --- |-| Exact model | Selected and reported model | Explicit ID required; exact echo, paid semantic protocol and five local semantic product cases passed | Explicit ID required; exact `gpt-5.6-luna` echo, paid semantic protocol and local completion/file/plan/restart passed | Exact `openrouter/deepseek/deepseek-v4-flash-0731`; model echo and v2/v3 paid Product completion/file/question cases passed; v5 native controls passed |+| Exact model | Selected and reported model | Explicit ID required; exact echo, paid semantic protocol and five local semantic product cases passed | Explicit ID required; exact `gpt-5.6-luna` echo, paid semantic protocol and local completion/file/plan/restart passed | Exact `openrouter/deepseek/deepseek-v4-flash-0731`, native-verified `low`; profile-13 paid hello, semantic continuation, native questions and human denial pass; file/restart/warm failures remain open || Text and tools | Typed thread/turn/item events | Standard ACP updates; child activity kept separate | Standard ACP plus opt-in native session events | Wrapper text/tool updates and owned tool gates |-| Active steering | Dedicated `turn/steer` | Concurrent prompt replaces/cancels, so it is not steering | Concurrent prompt replaces/cancels, so it is not steering | Owned `pi/steer` requires handshake, exact active turn and acknowledgment; real active-turn probe passed |-| Queued follow-up | Product continuation controls | Controller can schedule a later prompt; native queue not established | Native pending-message activity exists; no qualified ACP queue responder | Owned `pi/follow_up`, separately named and ordered; real queued marker followed the steered current response |+| Active steering | Dedicated `turn/steer` | Concurrent prompt replaces/cancels, so it is not steering | Concurrent prompt replaces/cancels, so it is not steering | Owned `pi/steer` requires handshake, exact active turn and acknowledgment; historical probe passed, profile-13 paid proof pending |+| Queued follow-up | Product continuation controls | Controller can schedule a later prompt; native queue not established | Native pending-message activity exists; no qualified ACP queue responder | Owned `pi/follow_up`, separately named and ordered; historical marker-order proof, profile-13 paid proof pending || Cancellation | Typed interrupt and process lifecycle | ACP cancel; paid command cleanup pending | ACP cancel; attached async native settlement passes offline. Explicit detached work is rejected before side effects; it is not supported background settlement | Native abort; wrapper waits for `agent_settled` and treats provider errors as failure || Session continuity | Read/load/history/fork and durable identity | Session load/list observed; paid semantic warm continuation passed; native history replay unverified and fork absent in tested methods | Session load plus native history events; semantic pending-question controller recovery passed | Private Pi JSONL mapping/load; native RPC `fork`, `clone`, `get_fork_messages` are not mapped through this ACP wrapper; unresolved UI promises cannot survive provider death || Questions | Typed input requests and response correlation | `cursor/ask_question`, option identity and multiple selection preserved | Native ask-user capability exists, but pinned ACP does not wire its responder; do not display a false answerable form | `select`, `confirm`, `input`, `editor` through typed form elicitation || Permissions | Durable typed approvals | Standard ACP permission options; denied shell write had no observed side effects; separately labeled exact-correlation assessment | Standard ACP; real native reject_once prevented marker creation; session decision scope inspected | Native pre-tool gate; allow once, exact-operation session grant, deny; paths rechecked after wait || Plans | Typed plan and collaboration mode | `cursor/create_plan` includes full plan and revision-bound accept/reject/cancel; todo activity separate | Native plan events displayed; native plan-decision callback not exposed in ACP | No native structured plan event; authenticated Paperclip planning tools available |-| Authenticated tools | Runner bridge and governed operations | ACP HTTP MCP binding; paid context/history reads passed | ACP HTTP MCP binding; paid context read passed | Owned extension registers exact bound MCP tools; four authenticated semantic reads succeeded in a paid partial run; no ambient servers |+| Authenticated tools | Runner bridge and governed operations | ACP HTTP MCP binding; paid context/history reads passed | ACP HTTP MCP binding; paid context read passed | Owned extension registers exact bound MCP tools; profile-13 paid Product completion/questions and seeded Runner context pass; no ambient servers || Delegation | Typed agent roles and lifecycle | Opt-in subagent lifecycle, nested ownership and bounded child activity; never parent transcript flattening | Native session details retain agent/model fields with unknown originating turn; typed turn-owned delegation is not inferred | No built-in ACP delegation protocol; arbitrary extensions are excluded || Files/diffs | Typed file changes and artifact references | Standard tool changes plus validated image references | Correlated ACP tool events remain available; native session file/workspace details are session notices, not attributed task file changes | Wrapper-retained read/write/edit diffs; common typed/UI projection remains partial; semantic artifact tools || Images/artifacts | Typed references and registered work products | Existing contained files only, provenance, `registered:false` | Native session artifact details are bounded notices with no inferred turn ownership or automatic registration | Image/resource tool blocks preserved by wrapper; dedicated artifact channel absent || Image/attachment input | Typed input conversion | ACP advertises images, but the runner turn converter currently forwards text only | ACP advertises images/embedded context, but the runner turn converter currently forwards text only | Native Pi/ACP image input exists, but the runner turn converter currently forwards text only || Usage | Per-request receipt and model context | Pinned ACP omitted receipts on denied and successful turns; account UI confirms included usage separately | ACP/native tokens retained; account UI confirms included credits separately, without a per-run USD receipt | Assistant-message and compaction token receipts; dollar cost is a catalog pricing estimate, never authoritative billing |-| Config/model changes | Typed configurable controls | Agent/Plan/Ask setup is bound to native configuration acknowledgements and recovery; unsolicited mode drift fails admission. Rich parameterized model picker remains unused | Model/reasoning/mode options exist; runtime policy remains authoritative | Exact pinned candidate model; arbitrary slash commands/config/extensions disabled |+| Config/model changes | Typed configurable controls | Agent/Plan/Ask setup is bound to native configuration acknowledgements and recovery; unsolicited mode drift fails admission. Rich parameterized model picker remains unused | Model/reasoning/mode options exist; runtime policy remains authoritative | Exact model; native available levels and set/get-state confirmation map through ACP mode/config to typed `piThinkingLevel`, recovery identity and UI setup. Active-turn mode changes and arbitrary slash commands/extensions remain disabled || Reconnect/restart | Durable controller replay and qualified provider restoration | Semantic pending question survived a real controller restart; exact native callback restoration remains unverified | Semantic pending question survived controller restart with the same interaction and provider session; native callback restoration remains unverified | Wrapper explicitly advertises live-process-only pending-input recovery || Shared capability | User-visible surface | Inspectable implementation / deterministic evidence |@@ -846,7 +857,7 @@ configuration defaults to full auto; it never overrides read-only task policy.## Distribution and isolationCursor pins `2026.09.26-dd393fe`; Copilot pins `1.0.88`; Pi pins wrapper `0.0.33`,-runtime `1.0.0` (Pi profile v12), portable Node and its full npm lock. Native distribution hashes+runtime `1.0.0` (Pi profile v13), portable Node and its full npm lock. Native distribution hashescover macOS ARM64, macOS x64 and Linux x64. Source-owned closure pins remainseparate from profile declaration digests. Native admission reads held files,verifies every admitted byte, creates a private immutable snapshot and retains@@ -875,8 +886,8 @@ qualification gates, not claims that a JavaScript path check confines a shell.| Priority | Exposed but unused, partial, or unverified | Reason and next proof || --- | --- | --- |-| P0 | Remaining paid product cases on local and Daytona | Current Cursor7/Copilot7/Pi9 require authenticated local and Daytona evidence on the exact current runtime. Historical Cursor4 passed hello/question/plan/restart but its latest file marker failed despite correct bytes. Copilot4 passed all five basic local journeys and Daytona hello. Pi7 passed native questions but continuation exposed the final-message bug repaired in8. The semaphore blocker is resolved and Cursor's approved on-demand cap is $25. Native interaction, denial, settlement, platform and complete cost/cleanup gates remain open; no old profile pass qualifies new bytes. |-| P0 | Pi fresh-profile Product verification | Historical v4 plan startup failed with unavailable Postgres semaphores. Historical v6 attempts exposed profile admission and verified-runtime startup faults, repaired without raising deadlines. Preserve every failed attempt and run unchanged canonical cases against the final build; do not remove unrelated IPC objects. |+| P0 | Remaining paid product cases on local and Daytona | Current Cursor10/Copilot13/Pi13 require authenticated local and Daytona evidence on the exact current runtime. The current Pi checkpoint above supersedes older profile coverage. Historical Cursor4 passed hello/question/plan/restart but its latest file marker failed despite correct bytes. Copilot4 passed all five basic local journeys and Daytona hello. Pi7 passed native questions but continuation exposed the final-message bug repaired in8. The semaphore blocker is resolved and Cursor's approved on-demand cap is $25. Native interaction, denial, settlement, platform and complete cost/cleanup gates remain open; no old profile pass qualifies new bytes. |+| P0 | Pi profile-13 Product and platform verification | Four paid local cases and one seeded Runner case pass. File validation, pending-input restart and warm continuation remain failed; assertion repairs do not regrade them. Finish the remaining local, Runner/native-control, Intel startup and Linux/Daytona cases on fresh final builds. Earlier semaphore and v6 startup faults remain historical evidence; never remove unrelated IPC objects. || P0 | Copilot native ask-user and plan-decision callbacks | Pinned ACP does not install native responders. Prove no blocking request is exposed, or add a qualified responder/wrapper; never swallow the request. || P0 | Broader Copilot denial and background settlement qualification | Pinned 1.0.88 and isolated 1.0.89 settle attached async commands, but deliberately detached work can finish after end_turn. The earlier paid detached success depended on that model waiting and is not general settlement evidence. Profiles v3/v4 reject explicit detached admission before effects; governed long-lived background work remains unsupported. Denial and process-death recovery pass offline; paid local/Daytona proof remains required. || P0 | Cursor native question availability | Explicit Luna and Composer native-only Plan-mode probes admitted the selected model and trusted instructions but emitted no question callback. The vendor-patch reversal and actual MCP-context constructor proof identify no local native-tool removal. Effective native tool selection is beyond the remote AgentService boundary; seek upstream catalog/availability evidence. No further blind model grid or semantic-question substitution qualifies this feature. |@@ -899,7 +910,7 @@ qualification gates, not claims that a JavaScript path check confines a shell.| P2 | Remaining Copilot native diagnostic/config/account events | The provider inventory records every event and field, its projection or reason for omission. Preserve bounded useful context; avoid credentials, raw environment or unbounded blobs. || P2 | Pi empty or whitespace-only submitted input/editor text | Canonical required text rejects blank responses; optional blank responses are omitted. Defaults can be empty and nonblank text preserves boundary whitespace. Add explicit empty-text semantics across TypeScript, Rust and UI before claiming complete native empty-answer parity. || P2 | Pi native extension surfaces and unsupported slash commands | Arbitrary extensions/templates/themes may execute ambient code. Only reviewed runner-owned capabilities are admitted; structured native plan/goals are not fabricated. Native fork/clone/export are separate unmapped capabilities above. |-| P2 | Pi status/widget/title/editor and session/configuration notifications | `setStatus`, `setWidget`, `setTitle` and `set_editor_text` have no UI projection and are unused by the owned extension. Native session-name and thinking-level events also lack a dedicated projection. Add reviewed bounded notice schemas and governed configuration controls before exposing these fields; `notify` and interactive input already have separate bridges. |+| P2 | Pi status/widget/title/editor and session/configuration notifications | `setStatus`, `setWidget`, `setTitle` and `set_editor_text` have no UI projection and are unused by the owned extension. Native session-name and thinking-level notifications also lack a dedicated projection, although selected thinking level is now handled through ACP mode/config and native confirmation. Provider notice summary/severity has deterministic UI coverage, with rebuilt paid visual proof pending. Add bounded schemas for the remaining fields; `notify` and interactive input already have separate bridges. || P2 | Pi invocation and history provenance metadata | The v4 wrapper retains `nativeToolCallId`, `modelIteration`, `historyMessageIndex` and `identityScope` in private ACP-wire metadata. Closed common tool and permission projections omit them from the UI. Normalized IDs still correlate live tool, MCP and permission events. Add bounded, redacted display-only provenance fields and parity tests before surfacing the native metadata. || P2 | Conditional native-plan follow-up fields | Cursor's optional rejection-reason field also appears for accept/cancel. The current question renderer has no conditional fields; add conditional presentation without changing the revision-bound decision receipt. || P2 | Cursor command exit code projection | The paid file case preserved native `exitCode: 0` inside output text, while the canonical command field remained null. Normalize a typed, correlated exit code without parsing arbitrary prose; current independent file assertions do not prove this field. |