From 8d5223bd1abb78fea95013d94203ce9d783c2a3b Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Tue, 11 Aug 2026 13:58:36 +0800 Subject: [PATCH] test(snapshot): refresh pins after master merge --- .../advanced-toolchain/session.1.jsonl | 2 +- .../advanced-toolchain/session.2.jsonl | 2 +- .../session.1.jsonl | 2 +- .../session.2.jsonl | 2 +- .../snapshots/subagent-mixed/session.1.jsonl | 2 +- .../snapshots/subagent-mixed/session.2.jsonl | 2 +- .../snapshots/subagent-multi/session.1.jsonl | 2 +- .../snapshots/subagent-multi/session.2.jsonl | 2 +- .../subagent-parallel/session.1.jsonl | 8 ++--- .../subagent-parallel/session.2.jsonl | 8 ++--- .../advanced-toolchain/session.1.jsonl | 8 ++--- .../advanced-toolchain/session.2.jsonl | 8 ++--- .../advanced-toolchain/session.jsonl | 26 +++++++-------- .../compaction-recovery/session.jsonl | 12 +++---- .../tests/snapshots/pty-tools/session.jsonl | 32 +++++++++---------- 15 files changed, 59 insertions(+), 59 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index e5fed4e056..34c6e7e85a 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":1786357538308,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Check direct child"}} {"type":"step/start","seq":5,"time":1786357538310,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730458555,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"ebe0cfa0-a909-47e0-8294-28ad84a8fe77"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786357538310,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"d6455b16-1316-4d5c-9dac-9974ec9c0420"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786357538310,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"5448800b-d6bb-42fe-89f2-5c328b6f4e2e"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786357538310,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730458555,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730458555,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 9418ce6bb6..c421ff3a3d 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":1786357538469,"data":{"version":2,"mode":"one-shot","provider":"spawn"}} {"type":"step/start","seq":5,"time":1786357538470,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730458703,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"2ac2cc54-9bce-4cfa-a569-a64f51bc30a7"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786357538471,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"64293dac-d5a9-472f-9f09-e78cf7711c2f"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786357538471,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"2e4f7923-e9ec-4dff-a96f-49bcbb7c3b15"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786357538471,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730458703,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730458703,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl index 295540b267..a1e075ae3f 100644 --- a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":1786357533600,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Start depth one"}} {"type":"step/start","seq":5,"time":1786357533602,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730456014,"data":{"content":[{"type":"text","text":"Call subagent once. Ask that child to attempt one further subagent call, then report the result."}],"source":{"kind":"user"},"role":"user","id":"a8129357-1bde-4cbd-90b4-6b8ad51d52e1"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786357533602,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"fd6ff01e-2162-4b7a-a36d-e67659557c50"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786357533602,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"5957533e-664a-4059-a1e3-55b84d3af1f8"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786357533602,"data":{"title":"Call subagent once. Ask that","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730456014,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730456014,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl index 8cc27b57e7..d19e6e0b0e 100644 --- a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":1786357533628,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Start depth two"}} {"type":"step/start","seq":5,"time":1786357533630,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730456041,"data":{"content":[{"type":"text","text":"Attempt one subagent call beyond the configured cap, then report the rejection."}],"source":{"kind":"user"},"role":"user","id":"d4dc5a16-e542-4dd9-8e82-e6b7829cfc4b"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786357533630,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"b36c8378-9069-48e5-9a6c-d54b0dc89cae"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786357533630,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"6bd22631-731e-43a9-ab2f-3a88b1b14e24"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786357533630,"data":{"title":"Attempt one subagent call beyond","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730456041,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730456042,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl index 0e9acf8a13..1741f24ce8 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":1786357524752,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Reply ALPHA only"}} {"type":"step/start","seq":5,"time":1786357524755,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730450187,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"73ce401a-faaf-408a-879e-7485380d537d"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786357524755,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"0ec19dcd-369e-4632-a29e-96c7ccfb2ed9"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786357524755,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"d516a993-eaae-4083-b5bd-954f2bf5fcdf"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786357524755,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730450187,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730450188,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl index 21d75ee206..d49f1c7fe2 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl @@ -27,7 +27,7 @@ {"type":"subagent/descriptor","seq":41,"time":1786357524800,"data":{"version":2,"mode":"one-shot","provider":"fork","label":"Recall project codeword"}} {"type":"step/start","seq":42,"time":1786357524803,"data":{"turn":2,"step":1}} {"type":"user/message","seq":43,"time":1786357524803,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"},"role":"user","id":"86e9f144-764f-460d-b72b-262cffe43d77"},"surfaceOp":"append"} -{"type":"user/message","seq":44,"time":1786358036899,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"aba1e760-5dcb-4554-9d5e-7c3e75df0d0a"},"surfaceOp":"append"} +{"type":"user/message","seq":44,"time":1786358036899,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"2561783f-44ea-4dce-9c00-86854a71de91"},"surfaceOp":"append"} {"type":"request/header","seq":45,"time":1786358036900,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} {"type":"assistant/chunk","seq":46,"time":1783352148077,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"reasoning-chunks","seq0":47,"time0":1783352148077,"data":{"turn":2,"step":1,"index":0,"dt":[0,0,29,0,0,0,35,0,0,0,0,26,29,31,0,30,0,0,27,1,27,0,1,0,0,31,1,0,0,1790157964],"texts":["The"," user"," is"," asking"," me"," to"," recall"," the"," project"," cod","ew","ord"," that"," was"," mentioned"," earlier"," in"," the"," conversation","."," I"," was"," told"," to"," remember"," it",":"," SA","FF","RON","."]}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl index eb9df14020..43e3166177 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":1786357521754,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Return ALPHA only"}} {"type":"step/start","seq":5,"time":1786357521756,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730447828,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"a287f842-f6f2-4a17-ab4c-820e41f498d5"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786357521756,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"7016faa8-0947-407d-8b73-094b0151b4a9"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786357521756,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"f2a84857-786a-4bb3-ac58-6bcaef1c94af"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786357521756,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730447828,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730447828,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl index 532d32510f..9f278e11a5 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":1786357521799,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Return BETA only"}} {"type":"step/start","seq":5,"time":1786357521801,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730447881,"data":{"content":[{"type":"text","text":"Reply with exactly the word BETA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"53f6419d-8ddc-4eee-8803-5b68411336f9"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786357521802,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"0a941631-7493-4656-ab39-105455bc2821"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786357521802,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"0f892c6d-8e2e-4fb0-a1dd-9438017c606e"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786357521802,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730447881,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730447881,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-parallel/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-parallel/session.1.jsonl index 06938addfc..d5505a1866 100644 --- a/examples/acp-agent/tests/snapshots/subagent-parallel/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-parallel/session.1.jsonl @@ -1,18 +1,18 @@ {"type":"session","version":0,"id":"bbbbbbbb-0000-4000-8000-000000000002","createdAt":1783352127000,"cwd":"{{cwd}}","parentSession":"aaaaaaaa-0000-4000-8000-000000000001","origin":"subagent","delegationDepth":1} {"type":"approval/policy","seq":0,"time":1786373947132,"data":{"policy":"never","source":"delegation"}} -{"type":"agent/inbox/spliced","seq":1,"time":1786373947134,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"7662d815-a3f5-443f-81aa-eab80525df9d"}]}} +{"type":"agent/inbox/spliced","seq":1,"time":1786373947134,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"a4921868-38d9-4bd3-8b1b-6e64fc09d87c"}]}} {"type":"turn/start","seq":2,"time":1786373947134,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":3,"time":1786373947134,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"subagent/descriptor","seq":4,"time":1786373947165,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Say the word ALPHA"}} {"type":"step/start","seq":5,"time":1786373947168,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":6,"time":1786338530759,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"7662d815-a3f5-443f-81aa-eab80525df9d"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786373947168,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"1d0b24b8-7f77-4964-9816-a0a172dc999d"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1786338530759,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"a4921868-38d9-4bd3-8b1b-6e64fc09d87c"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786373947168,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"d3abbbd1-28fb-4f34-94b3-5296d172ab8b"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786373947168,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1786338530759,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1786338530759,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"assistant/chunk","seq":11,"time":1786338530769,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":12,"time":1786338530769,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ALPHA"}}}} {"type":"assistant/chunk","seq":13,"time":1786338530769,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":14,"time":1786338530769,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"1676420f-ce1e-416a-be8c-06862ca6c232"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"} +{"type":"assistant/message","seq":14,"time":1786338530769,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"4e491719-55ea-4f2d-ba02-46ccea23799a"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"} {"type":"step/end","seq":15,"time":1786338530769,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":16,"time":1786338530769,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-parallel/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-parallel/session.2.jsonl index f764b15137..5875110ee5 100644 --- a/examples/acp-agent/tests/snapshots/subagent-parallel/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-parallel/session.2.jsonl @@ -1,18 +1,18 @@ {"type":"session","version":0,"id":"cccccccc-0000-4000-8000-000000000003","createdAt":1783352127001,"cwd":"{{cwd}}","parentSession":"aaaaaaaa-0000-4000-8000-000000000001","origin":"subagent","delegationDepth":1} {"type":"approval/policy","seq":0,"time":1786373947132,"data":{"policy":"never","source":"delegation"}} -{"type":"agent/inbox/spliced","seq":1,"time":1786373947133,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"98991681-6cca-4e88-ade7-c23811390230"}]}} +{"type":"agent/inbox/spliced","seq":1,"time":1786373947133,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"bcfd299a-16a3-47f9-a16f-83164c7c8882"}]}} {"type":"turn/start","seq":2,"time":1786373947133,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":3,"time":1786373947134,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"subagent/descriptor","seq":4,"time":1786373947170,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Say the word ALPHA"}} {"type":"step/start","seq":5,"time":1786373947173,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":6,"time":1786338530749,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"98991681-6cca-4e88-ade7-c23811390230"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1786373947174,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"8ff09265-ea81-4da7-bd07-b8f41ecd375f"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1786338530749,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"bcfd299a-16a3-47f9-a16f-83164c7c8882"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1786373947174,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"72f0af20-7d45-4223-9fb6-01e6503fb72b"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1786373947174,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1786338530749,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1786338530749,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"assistant/chunk","seq":11,"time":1786338530759,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":12,"time":1786338530759,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ALPHA"}}}} {"type":"assistant/chunk","seq":13,"time":1786338530759,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":14,"time":1786338530759,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"3fdfffab-96e9-4de9-a65a-6b5d53ed0f1c"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"} +{"type":"assistant/message","seq":14,"time":1786338530759,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"c4551cb0-5d41-40ba-a425-95281c05ba52"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"} {"type":"step/end","seq":15,"time":1786338530760,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":16,"time":1786338530760,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index cc34734cb7..4c02130cd1 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -1,11 +1,11 @@ {"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"{{cwd}}","parentSession":"11111111-1111-4111-8111-111111111111","origin":"subagent","delegationDepth":1} -{"type":"agent/inbox/spliced","seq":0,"time":1785498583877,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"bc172d06-957b-4318-bba4-8a688104fe3c"}]}} +{"type":"agent/inbox/spliced","seq":0,"time":1785498583877,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"991f0b4e-c00b-4fef-ab74-5c4b91b3ab80"}]}} {"type":"turn/start","seq":1,"time":1785821454445,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":2,"time":1785821454445,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"subagent/descriptor","seq":3,"time":1785821454466,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Check direct child"}} {"type":"step/start","seq":4,"time":1785730501506,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":5,"time":1785730501506,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"bc172d06-957b-4318-bba4-8a688104fe3c"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1786373992181,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"3b96f123-6cad-4c1b-a9d2-93da4bddc369"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730501506,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"991f0b4e-c00b-4fef-ab74-5c4b91b3ab80"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1786373992181,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"4189f795-218b-4908-a78f-9bcebef62a8c"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1786373992181,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785498583897,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement an SDK Plugin or installable profile bundle through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n code: string;\n } & Record;\n /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n cordis_unmount: {\n /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op. */\n interrupt_agent: {\n /** The agent id of the running agent to interrupt. */\n agent_id: string;\n } & Record;\n /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered. */\n send_message: {\n /** The subagent id returned when the background subagent was started. */\n subagent_id: string;\n /** The message to deliver to the subagent. */\n message: string;\n } & Record;\n /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message. */\n run_in_background?: boolean;\n } & Record;\n /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n interrupt_agent: {\n accepted: boolean;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n send_message: {\n messageId: string;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"continuable\";\n subagentId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"continuable\";\n subagentId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement an SDK Plugin or installable profile bundle through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"interrupt_agent","description":"Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op.","parameters":{"type":"object","properties":{"agent_id":{"type":"string","description":"The agent id of the running agent to interrupt."}},"required":["agent_id"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730501507,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -14,6 +14,6 @@ {"type":"assistant/chunk","seq":12,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} {"type":"assistant/chunk","seq":13,"time":1785498583897,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":14,"time":1785730501507,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":15,"time":1785730501507,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"41d01f02-234c-47de-9e75-4598f08aeb9e"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"} +{"type":"assistant/message","seq":15,"time":1785730501507,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"4a0a3a58-e769-4f53-9901-a4572f8a1b08"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"} {"type":"step/end","seq":16,"time":1785730501507,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":17,"time":1785730501507,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index ef0dec8938..d7d757d27d 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -1,11 +1,11 @@ {"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"{{cwd}}","parentSession":"11111111-1111-4111-8111-111111111111","origin":"subagent","delegationDepth":1} -{"type":"agent/inbox/spliced","seq":0,"time":1785498584048,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"82c4000a-4a47-4b62-a645-61e8f6e272bf"}]}} +{"type":"agent/inbox/spliced","seq":0,"time":1785498584048,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"7efb5a24-f331-4cdd-a37c-1651b28a4d45"}]}} {"type":"turn/start","seq":1,"time":1785821454599,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":2,"time":1785821454599,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"subagent/descriptor","seq":3,"time":1785821454618,"data":{"version":2,"mode":"one-shot","provider":"spawn"}} {"type":"step/start","seq":4,"time":1785730501645,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":5,"time":1785730501645,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"82c4000a-4a47-4b62-a645-61e8f6e272bf"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1786373992411,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"61151f36-d0d1-49db-84c7-8c9e01820ce9"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730501645,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"7efb5a24-f331-4cdd-a37c-1651b28a4d45"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1786373992411,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"c4f84380-d91a-4fba-bd69-aac00912a6aa"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1786373992411,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785498584067,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement an SDK Plugin or installable profile bundle through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n code: string;\n } & Record;\n /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n cordis_unmount: {\n /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op. */\n interrupt_agent: {\n /** The agent id of the running agent to interrupt. */\n agent_id: string;\n } & Record;\n /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered. */\n send_message: {\n /** The subagent id returned when the background subagent was started. */\n subagent_id: string;\n /** The message to deliver to the subagent. */\n message: string;\n } & Record;\n /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message. */\n run_in_background?: boolean;\n } & Record;\n /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n interrupt_agent: {\n accepted: boolean;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n send_message: {\n messageId: string;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"continuable\";\n subagentId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"continuable\";\n subagentId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement an SDK Plugin or installable profile bundle through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"interrupt_agent","description":"Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op.","parameters":{"type":"object","properties":{"agent_id":{"type":"string","description":"The agent id of the running agent to interrupt."}},"required":["agent_id"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730501646,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -14,6 +14,6 @@ {"type":"assistant/chunk","seq":12,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} {"type":"assistant/chunk","seq":13,"time":1785498584067,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":14,"time":1785730501646,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":15,"time":1785730501646,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"193aeeff-29df-4b92-99d8-7eba0b0a1b7a"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"} +{"type":"assistant/message","seq":15,"time":1785730501646,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"a9b7df12-66de-4db0-ae53-011abbeeeb74"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"} {"type":"step/end","seq":16,"time":1785730501646,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":17,"time":1785730501646,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl index e416691c5f..3b6f1a8dcc 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -1,9 +1,9 @@ {"type":"session","version":0,"id":"11111111-1111-4111-8111-111111111111","createdAt":1783950000000,"cwd":"{{cwd}}","delegationDepth":0} -{"type":"agent/inbox/spliced","seq":0,"time":1785498583746,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"},"role":"user","id":"b416dba9-a150-472b-b2c7-ba9471907fe2"}]}} +{"type":"agent/inbox/spliced","seq":0,"time":1785498583746,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"},"role":"user","id":"16a5481d-ae3a-4307-96fa-2db41bc2d61b"}]}} {"type":"turn/start","seq":1,"time":1785821454304,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":2,"time":1785821454304,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":4,"time":1785498583779,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"},"role":"user","id":"b416dba9-a150-472b-b2c7-ba9471907fe2"},"surfaceOp":"append"} +{"type":"user/message","seq":4,"time":1785498583779,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"},"role":"user","id":"16a5481d-ae3a-4307-96fa-2db41bc2d61b"},"surfaceOp":"append"} {"type":"session/title","seq":5,"time":1785498583779,"data":{"title":"Run this advanced flow exactly","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":6,"time":1785498583782,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement an SDK Plugin or installable profile bundle through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n code: string;\n } & Record;\n /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n cordis_unmount: {\n /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op. */\n interrupt_agent: {\n /** The agent id of the running agent to interrupt. */\n agent_id: string;\n } & Record;\n /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered. */\n send_message: {\n /** The subagent id returned when the background subagent was started. */\n subagent_id: string;\n /** The message to deliver to the subagent. */\n message: string;\n } & Record;\n /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message. */\n run_in_background?: boolean;\n } & Record;\n /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n interrupt_agent: {\n accepted: boolean;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n send_message: {\n messageId: string;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"continuable\";\n subagentId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"continuable\";\n subagentId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement an SDK Plugin or installable profile bundle through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"interrupt_agent","description":"Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op.","parameters":{"type":"object","properties":{"agent_id":{"type":"string","description":"The agent id of the running agent to interrupt."}},"required":["agent_id"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"request/context","seq":7,"time":1785730501403,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -12,9 +12,9 @@ {"type":"assistant/chunk","seq":10,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} {"type":"assistant/chunk","seq":11,"time":1785498583784,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":12,"time":1785730501404,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":13,"time":1785730501404,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"87b38c62-f964-4287-9211-0aaaae26a3fd"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[8,9,10,11,12],"surfaceOp":"append"} +{"type":"assistant/message","seq":13,"time":1785730501404,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"f3f6715f-6f97-4249-a4f4-c0b3738c72a9"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[8,9,10,11,12],"surfaceOp":"append"} {"type":"tool/call","seq":14,"time":1785730501404,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}} -{"type":"tool/result","seq":15,"time":1785730501413,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"advanced-mount"},"content":[{"type":"tool-result","toolCallId":"advanced-mount","content":[{"type":"text","text":"Temporary Plugin dyn-1 is running (plugin \"snapshot-marker\"; available until unmounted or DSH restarts)."}],"isError":false}],"role":"user","id":"9ee0c97b-3d15-44b4-8181-4fac2afd3661"}},"sourceEventSeqs":[14],"surfaceOp":"append"} +{"type":"tool/result","seq":15,"time":1785730501413,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"advanced-mount"},"content":[{"type":"tool-result","toolCallId":"advanced-mount","content":[{"type":"text","text":"Temporary Plugin dyn-1 is running (plugin \"snapshot-marker\"; available until unmounted or DSH restarts)."}],"isError":false}],"role":"user","id":"e43f522a-a380-4dd3-ac47-c0d21c8ada51"}},"sourceEventSeqs":[14],"surfaceOp":"append"} {"type":"step/end","seq":16,"time":1785730501413,"data":{"turn":1,"step":1}} {"type":"step/start","seq":17,"time":1785730501423,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":18,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -22,11 +22,11 @@ {"type":"assistant/chunk","seq":20,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}}}} {"type":"assistant/chunk","seq":21,"time":1785498583804,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":22,"time":1785730501424,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":23,"time":1785730501424,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"8224d8e1-aa62-4591-a8a6-9b234162903e"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21,22],"surfaceOp":"append"} +{"type":"assistant/message","seq":23,"time":1785730501424,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"83ba2284-e9d6-472b-b4ae-9822807ebd38"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21,22],"surfaceOp":"append"} {"type":"tool/call","seq":24,"time":1785730501424,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}} {"type":"tool/code-dispatch-start","seq":25,"time":1785730501473,"data":{"rootCallId":"advanced-code","parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"temporary"}}} {"type":"tool/code-dispatch","seq":26,"time":1785730501474,"data":{"rootCallId":"advanced-code","parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"temporary"},"isError":false,"content":[{"type":"text","text":"## Temporary Plugins\n- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: until unmounted or DSH restarts"}]}} -{"type":"tool/result","seq":27,"time":1785730501475,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"advanced-code"},"content":[{"type":"tool-result","toolCallId":"advanced-code","content":[{"type":"text","text":"## Temporary Plugins\n- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: until unmounted or DSH restarts"}],"isError":false}],"role":"user","id":"f01fc48d-0977-49c4-a6f7-03bc92c28b58"}},"sourceEventSeqs":[24],"surfaceOp":"append"} +{"type":"tool/result","seq":27,"time":1785730501475,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"advanced-code"},"content":[{"type":"tool-result","toolCallId":"advanced-code","content":[{"type":"text","text":"## Temporary Plugins\n- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: until unmounted or DSH restarts"}],"isError":false}],"role":"user","id":"f715bd22-6884-433e-bf55-e6397d1747b3"}},"sourceEventSeqs":[24],"surfaceOp":"append"} {"type":"step/end","seq":28,"time":1785730501475,"data":{"turn":1,"step":2}} {"type":"step/start","seq":29,"time":1785730501483,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":30,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -34,9 +34,9 @@ {"type":"assistant/chunk","seq":32,"time":1785037378923,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":33,"time":1785498583869,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":34,"time":1785730501484,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":35,"time":1785730501484,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"b9630434-34f8-43c1-ba56-909745357795"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[30,31,32,33,34],"surfaceOp":"append"} +{"type":"assistant/message","seq":35,"time":1785730501484,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"c1d4ac14-c3c2-4de8-a5cf-3fe6ae9bf377"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[30,31,32,33,34],"surfaceOp":"append"} {"type":"tool/call","seq":36,"time":1785730501484,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}} -{"type":"tool/result","seq":37,"time":1785730501508,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool","callId":"advanced-direct-child"},"content":[{"type":"tool-result","toolCallId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false}],"role":"user","id":"6a2bed14-9dfd-476e-b6e5-1c989fddc4c8"}},"sourceEventSeqs":[36],"surfaceOp":"append"} +{"type":"tool/result","seq":37,"time":1785730501508,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool","callId":"advanced-direct-child"},"content":[{"type":"tool-result","toolCallId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false}],"role":"user","id":"551e942f-400c-4b37-9a2f-0293c71715d2"}},"sourceEventSeqs":[36],"surfaceOp":"append"} {"type":"step/end","seq":38,"time":1785730501508,"data":{"turn":1,"step":3}} {"type":"step/start","seq":39,"time":1785730501521,"data":{"turn":1,"step":4}} {"type":"assistant/chunk","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -44,9 +44,9 @@ {"type":"assistant/chunk","seq":42,"time":1785037378946,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}} {"type":"assistant/chunk","seq":43,"time":1785498583919,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":44,"time":1785730501522,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":45,"time":1785730501522,"data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"ee2f2cbd-6da8-454a-b01a-11817c4d6b7e"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[40,41,42,43,44],"surfaceOp":"append"} +{"type":"assistant/message","seq":45,"time":1785730501522,"data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"dff23c8b-88e2-4821-afe7-be3504e9d0af"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[40,41,42,43,44],"surfaceOp":"append"} {"type":"tool/call","seq":46,"time":1785730501522,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}} -{"type":"tool/result","seq":47,"time":1785730501647,"data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"advanced-workflow"},"content":[{"type":"tool-result","toolCallId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false}],"role":"user","id":"45bbc512-90ea-4fc5-9a93-655eac11db2b"}},"sourceEventSeqs":[46],"surfaceOp":"append"} +{"type":"tool/result","seq":47,"time":1785730501647,"data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"advanced-workflow"},"content":[{"type":"tool-result","toolCallId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false}],"role":"user","id":"225322eb-d697-4209-bb28-a7770e6d664e"}},"sourceEventSeqs":[46],"surfaceOp":"append"} {"type":"step/end","seq":48,"time":1785730501648,"data":{"turn":1,"step":4}} {"type":"step/start","seq":49,"time":1785730501660,"data":{"turn":1,"step":5}} {"type":"assistant/chunk","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -54,9 +54,9 @@ {"type":"assistant/chunk","seq":52,"time":1785037379534,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}} {"type":"assistant/chunk","seq":53,"time":1785498584085,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":54,"time":1785730501661,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":55,"time":1785730501661,"data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"efe91017-9e46-4aff-a2c8-174a68f9f0f0"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[50,51,52,53,54],"surfaceOp":"append"} +{"type":"assistant/message","seq":55,"time":1785730501661,"data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"4d804ba8-e106-4c49-ab40-a9c98e3d9590"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[50,51,52,53,54],"surfaceOp":"append"} {"type":"tool/call","seq":56,"time":1785730501661,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}} -{"type":"tool/result","seq":57,"time":1785730501668,"data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"advanced-unmount"},"content":[{"type":"tool-result","toolCallId":"advanced-unmount","content":[{"type":"text","text":"Temporary Plugin dyn-1 was unmounted and removed."}],"isError":false}],"role":"user","id":"33ae5101-de46-4078-ade4-b8f3c9cf80dc"}},"sourceEventSeqs":[56],"surfaceOp":"append"} +{"type":"tool/result","seq":57,"time":1785730501668,"data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"advanced-unmount"},"content":[{"type":"tool-result","toolCallId":"advanced-unmount","content":[{"type":"text","text":"Temporary Plugin dyn-1 was unmounted and removed."}],"isError":false}],"role":"user","id":"d4f09694-1f4b-4abf-89e2-8926a3fbd48a"}},"sourceEventSeqs":[56],"surfaceOp":"append"} {"type":"step/end","seq":58,"time":1785730501668,"data":{"turn":1,"step":5}} {"type":"step/start","seq":59,"time":1785730501678,"data":{"turn":1,"step":6}} {"type":"assistant/chunk","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} @@ -64,6 +64,6 @@ {"type":"assistant/chunk","seq":62,"time":1785037379541,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_HEADLESS_OK"}}}} {"type":"assistant/chunk","seq":63,"time":1785498584102,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":64,"time":1785730501679,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":65,"time":1785730501679,"data":{"turn":1,"step":6,"message":{"role":"assistant","content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"45ab9bee-3239-4477-9bdd-e7d19010235b"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[60,61,62,63,64],"surfaceOp":"append"} +{"type":"assistant/message","seq":65,"time":1785730501679,"data":{"turn":1,"step":6,"message":{"role":"assistant","content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"6bdd0317-b838-41a4-b3a7-cf0a70dc92cf"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[60,61,62,63,64],"surfaceOp":"append"} {"type":"step/end","seq":66,"time":1785730501679,"data":{"turn":1,"step":6}} {"type":"turn/end","seq":67,"time":1785730501679,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/compaction-recovery/session.jsonl b/examples/headless-agent/tests/snapshots/compaction-recovery/session.jsonl index 2774813a21..1b01e63acf 100644 --- a/examples/headless-agent/tests/snapshots/compaction-recovery/session.jsonl +++ b/examples/headless-agent/tests/snapshots/compaction-recovery/session.jsonl @@ -1,9 +1,9 @@ {"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0} -{"type":"agent/inbox/spliced","seq":0,"time":1786123401613,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Establish a durable compaction premise before continuing. Record every part of this historical evidence: the snapshot uses keyless replay; persistence uses JSONL; the assembled headless application loads its real Cordis composition; model-visible inputs remain logged; tool calls and results remain paired and ordered; context overflow retains the original failure while recovery is attempted; compaction opens with compact/start and closes with compact/end; a successful auxiliary summary records compact/summary provenance; the replacement surface shadows only an older balanced range; the checkpoint remains smaller than the history it replaces; the newest tool result remains verbatim; the retried request sees that checkpoint; the final response proves the same turn continued; deterministic snapshot evidence stays separate from the live-provider smoke; and no external API key is needed. Emit one alpha marker through bash, then finish the task after any required recovery with the exact words COMPACTION RECOVERED."}],"source":{"kind":"user"},"role":"user","id":"d574622b-b9b1-4081-9275-df9cdd84b689"}]}} +{"type":"agent/inbox/spliced","seq":0,"time":1786123401613,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Establish a durable compaction premise before continuing. Record every part of this historical evidence: the snapshot uses keyless replay; persistence uses JSONL; the assembled headless application loads its real Cordis composition; model-visible inputs remain logged; tool calls and results remain paired and ordered; context overflow retains the original failure while recovery is attempted; compaction opens with compact/start and closes with compact/end; a successful auxiliary summary records compact/summary provenance; the replacement surface shadows only an older balanced range; the checkpoint remains smaller than the history it replaces; the newest tool result remains verbatim; the retried request sees that checkpoint; the final response proves the same turn continued; deterministic snapshot evidence stays separate from the live-provider smoke; and no external API key is needed. Emit one alpha marker through bash, then finish the task after any required recovery with the exact words COMPACTION RECOVERED."}],"source":{"kind":"user"},"role":"user","id":"0c1371d2-5d62-4c77-bb7a-b25af4e950c7"}]}} {"type":"turn/start","seq":1,"time":1786123401614,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":2,"time":1786123401614,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1786123401667,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":4,"time":1786123401667,"data":{"content":[{"type":"text","text":"Establish a durable compaction premise before continuing. Record every part of this historical evidence: the snapshot uses keyless replay; persistence uses JSONL; the assembled headless application loads its real Cordis composition; model-visible inputs remain logged; tool calls and results remain paired and ordered; context overflow retains the original failure while recovery is attempted; compaction opens with compact/start and closes with compact/end; a successful auxiliary summary records compact/summary provenance; the replacement surface shadows only an older balanced range; the checkpoint remains smaller than the history it replaces; the newest tool result remains verbatim; the retried request sees that checkpoint; the final response proves the same turn continued; deterministic snapshot evidence stays separate from the live-provider smoke; and no external API key is needed. Emit one alpha marker through bash, then finish the task after any required recovery with the exact words COMPACTION RECOVERED."}],"source":{"kind":"user"},"role":"user","id":"d574622b-b9b1-4081-9275-df9cdd84b689"},"surfaceOp":"append"} +{"type":"user/message","seq":4,"time":1786123401667,"data":{"content":[{"type":"text","text":"Establish a durable compaction premise before continuing. Record every part of this historical evidence: the snapshot uses keyless replay; persistence uses JSONL; the assembled headless application loads its real Cordis composition; model-visible inputs remain logged; tool calls and results remain paired and ordered; context overflow retains the original failure while recovery is attempted; compaction opens with compact/start and closes with compact/end; a successful auxiliary summary records compact/summary provenance; the replacement surface shadows only an older balanced range; the checkpoint remains smaller than the history it replaces; the newest tool result remains verbatim; the retried request sees that checkpoint; the final response proves the same turn continued; deterministic snapshot evidence stays separate from the live-provider smoke; and no external API key is needed. Emit one alpha marker through bash, then finish the task after any required recovery with the exact words COMPACTION RECOVERED."}],"source":{"kind":"user"},"role":"user","id":"0c1371d2-5d62-4c77-bb7a-b25af4e950c7"},"surfaceOp":"append"} {"type":"session/title","seq":5,"time":1786123401667,"data":{"title":"Establish a durable compaction premise","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":6,"time":1786123401668,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"interrupt_agent","description":"Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op.","parameters":{"type":"object","properties":{"agent_id":{"type":"string","description":"The agent id of the running agent to interrupt."}},"required":["agent_id"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"send_message","description":"Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"request/context","seq":7,"time":1786123401669,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":128000}} @@ -12,21 +12,21 @@ {"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_compaction_marker","name":"bash","arguments":"{\"command\":\"printf 'alpha\\n'\",\"description\":\"Emit compaction premise marker\"}"}}}} {"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":24,"outputTokens":6}}}} {"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":13,"time":1786123401680,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_compaction_marker","name":"bash","arguments":"{\"command\":\"printf 'alpha\\n'\",\"description\":\"Emit compaction premise marker\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"26f5abf0-a8e7-44be-a822-b09a84e567b6"},"usage":{"inputTokens":24,"outputTokens":6}},"sourceEventSeqs":[8,9,10,11,12],"surfaceOp":"append"} +{"type":"assistant/message","seq":13,"time":1786123401680,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_compaction_marker","name":"bash","arguments":"{\"command\":\"printf 'alpha\\n'\",\"description\":\"Emit compaction premise marker\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"ba9c8d97-00b3-41fd-a79e-cfd30ba77980"},"usage":{"inputTokens":24,"outputTokens":6}},"sourceEventSeqs":[8,9,10,11,12],"surfaceOp":"append"} {"type":"tool/call","seq":14,"time":1786123401680,"data":{"turn":1,"step":1,"callId":"call_compaction_marker","name":"bash","arguments":"{\"command\":\"printf 'alpha\\n'\",\"description\":\"Emit compaction premise marker\"}"}} -{"type":"tool/result","seq":15,"time":1786123401700,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_compaction_marker"},"content":[{"type":"tool-result","toolCallId":"call_compaction_marker","content":[{"type":"text","text":"alpha\n"}],"isError":false}],"role":"user","id":"7e240bea-2e93-4a05-b665-5bf5f65347c8"}},"sourceEventSeqs":[14],"surfaceOp":"append"} +{"type":"tool/result","seq":15,"time":1786123401700,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_compaction_marker"},"content":[{"type":"tool-result","toolCallId":"call_compaction_marker","content":[{"type":"text","text":"alpha\n"}],"isError":false}],"role":"user","id":"78c26313-6158-47a1-bdf9-730554c3bfd5"}},"sourceEventSeqs":[14],"surfaceOp":"append"} {"type":"step/end","seq":16,"time":1786123401700,"data":{"turn":1,"step":1}} {"type":"step/start","seq":17,"time":1786123401710,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":18,"time":1786123401715,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"snapshot request exceeded the model context window","code":"CONTEXT_WINDOW_EXCEEDED"}}}}} {"type":"compact/start","seq":19,"time":1786123401715,"data":{"compactionId":"338e88fa-e78b-4d49-bd38-8f919e85f5e1","turn":1}} {"type":"compact/summary","seq":20,"time":1786123401725,"data":{"compactionId":"338e88fa-e78b-4d49-bd38-8f919e85f5e1","summary":[{"type":"text","text":"The request established a durable compaction premise."}],"rawOutput":[{"type":"text","text":"The request established a durable compaction premise."}],"llmStreamCall":true,"shadowedRange":{"start":4,"end":4},"shadowedSeqs":[4],"shadowedTokenCount":264,"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":32,"usage":{"inputTokens":20,"outputTokens":4}}} -{"type":"user/message","seq":21,"time":1786123401725,"data":{"content":[{"type":"text","text":"This is an automatically generated checkpoint condensing an earlier span of the conversation to free up context. Treat the captured context as established background and build on it without restating it. Continue the task directly from the messages that follow, without acknowledging this checkpoint.\n\n"},{"type":"text","text":"The request established a durable compaction premise."},{"type":"text","text":""}],"source":{"kind":"plugin","plugin":"compact","compactionId":"338e88fa-e78b-4d49-bd38-8f919e85f5e1"},"role":"user","id":"b66396e6-ae0c-4c18-acb2-6ce06804dd52"},"sourceEventSeqs":[19,20,4],"surfaceOp":{"op":"replace","start":4,"end":4}} +{"type":"user/message","seq":21,"time":1786123401725,"data":{"content":[{"type":"text","text":"This is an automatically generated checkpoint condensing an earlier span of the conversation to free up context. Treat the captured context as established background and build on it without restating it. Continue the task directly from the messages that follow, without acknowledging this checkpoint.\n\n"},{"type":"text","text":"The request established a durable compaction premise."},{"type":"text","text":""}],"source":{"kind":"plugin","plugin":"compact","compactionId":"338e88fa-e78b-4d49-bd38-8f919e85f5e1"},"role":"user","id":"2fdd7988-558c-469d-8654-2b2a298101e4"},"sourceEventSeqs":[19,20,4],"surfaceOp":{"op":"replace","start":4,"end":4}} {"type":"compact/end","seq":22,"time":1786123401725,"data":{"compactionId":"338e88fa-e78b-4d49-bd38-8f919e85f5e1","turn":1}} {"type":"assistant/chunk","seq":23,"time":1786123401730,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":24,"time":1786123401730,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"COMPACTION RECOVERED"}}} {"type":"assistant/chunk","seq":25,"time":1786123401730,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"COMPACTION RECOVERED"}}}} {"type":"assistant/chunk","seq":26,"time":1786123401730,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":4}}}} {"type":"assistant/chunk","seq":27,"time":1786123401730,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":28,"time":1786123401730,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"COMPACTION RECOVERED"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"b9756633-dd2b-4092-a261-dce0d99405c6"},"usage":{"inputTokens":20,"outputTokens":4}},"sourceEventSeqs":[23,24,25,26,27],"surfaceOp":"append"} +{"type":"assistant/message","seq":28,"time":1786123401730,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"COMPACTION RECOVERED"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"9604108a-6490-4a04-9595-449964fae7e5"},"usage":{"inputTokens":20,"outputTokens":4}},"sourceEventSeqs":[23,24,25,26,27],"surfaceOp":"append"} {"type":"step/end","seq":29,"time":1786123401730,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":30,"time":1786123401730,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl index 6f151cdc3c..04de7f2fbc 100644 --- a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl +++ b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl @@ -1,10 +1,10 @@ {"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0} -{"type":"agent/inbox/spliced","seq":0,"time":1785498587408,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"e8743767-afef-4e92-b6b6-fe15f929be32"}]}} +{"type":"agent/inbox/spliced","seq":0,"time":1785498587408,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"c36f68b3-5f5d-4d34-a7b6-ce5762427e22"}]}} {"type":"turn/start","seq":1,"time":1785821457966,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":2,"time":1785821457966,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":4,"time":1785498587436,"data":{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"e8743767-afef-4e92-b6b6-fe15f929be32"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730504659,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}]},"role":"user","id":"3254c63f-454e-4207-9885-e237090192b4"},"surfaceOp":"append"} +{"type":"user/message","seq":4,"time":1785498587436,"data":{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"c36f68b3-5f5d-4d34-a7b6-ce5762427e22"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730504659,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}]},"role":"user","id":"f2e6350c-ce36-47cc-bc6d-6325b38af2a5"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730504659,"data":{"title":"Exercise the six PTY tools","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498587438,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse a terminal session only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every terminal session id and close sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"interrupt_agent","description":"Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op.","parameters":{"type":"object","properties":{"agent_id":{"type":"string","description":"The agent id of the running agent to interrupt."}},"required":["agent_id"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"send_message","description":"Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: this call returns only its subagent id, and the subagent works on its own from there. You are told when it finishes, so never poll or wait on it; `send_message` sends it more work.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background subagent that keeps its conversation and return only its subagent id. This call does not wait for it; you are told when it finishes. Send it more work with send_message."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730504660,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -13,9 +13,9 @@ {"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-spawn","name":"terminal_open","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}}}} {"type":"assistant/chunk","seq":12,"time":1785498587439,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":13,"time":1785730504661,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":14,"time":1785730504661,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-spawn","name":"terminal_open","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"e784db42-d36c-4886-a006-e99326b48073"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[9,10,11,12,13],"surfaceOp":"append"} +{"type":"assistant/message","seq":14,"time":1785730504661,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-spawn","name":"terminal_open","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"3ea375d3-e467-41f8-8030-dd11d8a4d43a"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[9,10,11,12,13],"surfaceOp":"append"} {"type":"tool/call","seq":15,"time":1785730504662,"data":{"turn":1,"step":1,"callId":"pty-spawn","name":"terminal_open","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}} -{"type":"tool/result","seq":16,"time":1785730504671,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"pty-spawn"},"content":[{"type":"tool-result","toolCallId":"pty-spawn","content":[{"type":"text","text":"started terminal session pty-1 (main) [type: shell]\ndsh> "}],"isError":false}],"role":"user","id":"226c3694-646a-461f-a120-e9f5ef7389aa"}},"sourceEventSeqs":[15],"surfaceOp":"append"} +{"type":"tool/result","seq":16,"time":1785730504671,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"pty-spawn"},"content":[{"type":"tool-result","toolCallId":"pty-spawn","content":[{"type":"text","text":"started terminal session pty-1 (main) [type: shell]\ndsh> "}],"isError":false}],"role":"user","id":"0c3ff7d1-f7c9-4955-bd30-3073c7d099c8"}},"sourceEventSeqs":[15],"surfaceOp":"append"} {"type":"step/end","seq":17,"time":1785730504671,"data":{"turn":1,"step":1}} {"type":"step/start","seq":18,"time":1785730504679,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -23,9 +23,9 @@ {"type":"assistant/chunk","seq":21,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}}}} {"type":"assistant/chunk","seq":22,"time":1785498587457,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":23,"time":1785730504680,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":24,"time":1785730504680,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"8306e63f-497f-44f4-96ca-5f8b22d993fd"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"} +{"type":"assistant/message","seq":24,"time":1785730504680,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"d5f05b46-beb6-40d9-8337-d0e66d37d489"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"} {"type":"tool/call","seq":25,"time":1785730504680,"data":{"turn":1,"step":2,"callId":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}} -{"type":"tool/result","seq":26,"time":1785730504688,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"pty-send"},"content":[{"type":"tool-result","toolCallId":"pty-send","content":[{"type":"text","text":"K\ndsh> \n[wait: stdin_read]\n[session: running]\n[output truncated]"}],"isError":false}],"role":"user","id":"b5e21e31-aef2-411a-885c-7f2b62e8b1fb"},"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[25],"surfaceOp":"append"} +{"type":"tool/result","seq":26,"time":1785730504688,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"pty-send"},"content":[{"type":"tool-result","toolCallId":"pty-send","content":[{"type":"text","text":"K\ndsh> \n[wait: stdin_read]\n[session: running]\n[output truncated]"}],"isError":false}],"role":"user","id":"17e72638-fa1e-4424-85c1-5f81f2a06d13"},"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[25],"surfaceOp":"append"} {"type":"step/end","seq":27,"time":1785730504688,"data":{"turn":1,"step":2}} {"type":"step/start","seq":28,"time":1785730504696,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -33,9 +33,9 @@ {"type":"assistant/chunk","seq":31,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-read","name":"terminal_read","arguments":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}}}} {"type":"assistant/chunk","seq":32,"time":1785498587473,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":33,"time":1785730504697,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":34,"time":1785730504697,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-read","name":"terminal_read","arguments":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"984888f9-6c8d-4928-ac3e-6ae41edc1862"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[29,30,31,32,33],"surfaceOp":"append"} +{"type":"assistant/message","seq":34,"time":1785730504697,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-read","name":"terminal_read","arguments":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"1b2c6eb5-b75e-4f90-9547-2ac2f6733752"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[29,30,31,32,33],"surfaceOp":"append"} {"type":"tool/call","seq":35,"time":1785730504697,"data":{"turn":1,"step":3,"callId":"pty-read","name":"terminal_read","arguments":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}} -{"type":"tool/result","seq":36,"time":1785730504704,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool","callId":"pty-read"},"content":[{"type":"tool-result","toolCallId":"pty-read","content":[{"type":"text","text":"dsh> printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[lines: 0-3 of 3]"}],"isError":false}],"role":"user","id":"f4dfcf94-6cc9-4d88-86de-f08f84678f17"}},"sourceEventSeqs":[35],"surfaceOp":"append"} +{"type":"tool/result","seq":36,"time":1785730504704,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool","callId":"pty-read"},"content":[{"type":"tool-result","toolCallId":"pty-read","content":[{"type":"text","text":"dsh> printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[lines: 0-3 of 3]"}],"isError":false}],"role":"user","id":"f0f5ad30-70c0-4b64-8bfd-562d0d589e57"}},"sourceEventSeqs":[35],"surfaceOp":"append"} {"type":"step/end","seq":37,"time":1785730504704,"data":{"turn":1,"step":3}} {"type":"step/start","seq":38,"time":1785730504712,"data":{"turn":1,"step":4}} {"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -43,9 +43,9 @@ {"type":"assistant/chunk","seq":41,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-signal","name":"terminal_signal","arguments":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}}}} {"type":"assistant/chunk","seq":42,"time":1785498587489,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":43,"time":1785730504713,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":44,"time":1785730504713,"data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-signal","name":"terminal_signal","arguments":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"59d20e41-465e-4275-8635-e71aabd8c264"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[39,40,41,42,43],"surfaceOp":"append"} +{"type":"assistant/message","seq":44,"time":1785730504713,"data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-signal","name":"terminal_signal","arguments":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"eb6ce3ad-7c80-44a5-8946-484f65c07304"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[39,40,41,42,43],"surfaceOp":"append"} {"type":"tool/call","seq":45,"time":1785730504713,"data":{"turn":1,"step":4,"callId":"pty-signal","name":"terminal_signal","arguments":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}} -{"type":"tool/result","seq":46,"time":1785730504721,"data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"pty-signal"},"content":[{"type":"tool-result","toolCallId":"pty-signal","content":[{"type":"text","text":"Error: unknown PTY session pty-missing"}],"isError":true}],"role":"user","id":"889b78af-34e2-4f1f-9c23-91f11beb30c6"}},"sourceEventSeqs":[45],"surfaceOp":"append"} +{"type":"tool/result","seq":46,"time":1785730504721,"data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"pty-signal"},"content":[{"type":"tool-result","toolCallId":"pty-signal","content":[{"type":"text","text":"Error: unknown PTY session pty-missing"}],"isError":true}],"role":"user","id":"ee3ba4da-7d14-423d-97d9-3063c3606084"}},"sourceEventSeqs":[45],"surfaceOp":"append"} {"type":"step/end","seq":47,"time":1785730504721,"data":{"turn":1,"step":4}} {"type":"step/start","seq":48,"time":1785730504730,"data":{"turn":1,"step":5}} {"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -53,9 +53,9 @@ {"type":"assistant/chunk","seq":51,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-kill","name":"terminal_close","arguments":"{\"sessionId\":\"pty-1\"}"}}}} {"type":"assistant/chunk","seq":52,"time":1785498587503,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":53,"time":1785730504731,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":54,"time":1785730504731,"data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-kill","name":"terminal_close","arguments":"{\"sessionId\":\"pty-1\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"169c573c-764e-4b0e-8dc7-e02d403d09a4"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[49,50,51,52,53],"surfaceOp":"append"} +{"type":"assistant/message","seq":54,"time":1785730504731,"data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-kill","name":"terminal_close","arguments":"{\"sessionId\":\"pty-1\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"70af7790-2321-47ad-a1ce-09dadc16c1e9"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[49,50,51,52,53],"surfaceOp":"append"} {"type":"tool/call","seq":55,"time":1785730504731,"data":{"turn":1,"step":5,"callId":"pty-kill","name":"terminal_close","arguments":"{\"sessionId\":\"pty-1\"}"}} -{"type":"tool/result","seq":56,"time":1785730504738,"data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"pty-kill"},"content":[{"type":"tool-result","toolCallId":"pty-kill","content":[{"type":"text","text":"closed terminal session pty-1"}],"isError":false}],"role":"user","id":"2d87ebf4-4dcf-48ec-a06c-c75cf2e5ab27"}},"sourceEventSeqs":[55],"surfaceOp":"append"} +{"type":"tool/result","seq":56,"time":1785730504738,"data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"pty-kill"},"content":[{"type":"tool-result","toolCallId":"pty-kill","content":[{"type":"text","text":"closed terminal session pty-1"}],"isError":false}],"role":"user","id":"bb5e95df-9c10-486d-a6ab-ec690bd5f641"}},"sourceEventSeqs":[55],"surfaceOp":"append"} {"type":"step/end","seq":57,"time":1785730504738,"data":{"turn":1,"step":5}} {"type":"step/start","seq":58,"time":1785730504746,"data":{"turn":1,"step":6}} {"type":"assistant/chunk","seq":59,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -63,9 +63,9 @@ {"type":"assistant/chunk","seq":61,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-list","name":"terminal_list","arguments":"{}"}}}} {"type":"assistant/chunk","seq":62,"time":1785498587517,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":63,"time":1785730504747,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":64,"time":1785730504747,"data":{"turn":1,"step":6,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-list","name":"terminal_list","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"35164590-2ad9-4596-8735-6f568b588c6a"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[59,60,61,62,63],"surfaceOp":"append"} +{"type":"assistant/message","seq":64,"time":1785730504747,"data":{"turn":1,"step":6,"message":{"role":"assistant","content":[{"type":"tool-call","id":"pty-list","name":"terminal_list","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"fb172628-83f2-4f6a-94d8-75d718f630f4"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[59,60,61,62,63],"surfaceOp":"append"} {"type":"tool/call","seq":65,"time":1785730504747,"data":{"turn":1,"step":6,"callId":"pty-list","name":"terminal_list","arguments":"{}"}} -{"type":"tool/result","seq":66,"time":1785730504755,"data":{"turn":1,"step":6,"message":{"source":{"kind":"tool","callId":"pty-list"},"content":[{"type":"tool-result","toolCallId":"pty-list","content":[{"type":"text","text":"(no terminal sessions)"}],"isError":false}],"role":"user","id":"092d93d7-cd79-4b3c-a093-313a54212742"}},"sourceEventSeqs":[65],"surfaceOp":"append"} +{"type":"tool/result","seq":66,"time":1785730504755,"data":{"turn":1,"step":6,"message":{"source":{"kind":"tool","callId":"pty-list"},"content":[{"type":"tool-result","toolCallId":"pty-list","content":[{"type":"text","text":"(no terminal sessions)"}],"isError":false}],"role":"user","id":"f0941936-d174-41c4-b388-1a2169e6dbf9"}},"sourceEventSeqs":[65],"surfaceOp":"append"} {"type":"step/end","seq":67,"time":1785730504755,"data":{"turn":1,"step":6}} {"type":"step/start","seq":68,"time":1785730504763,"data":{"turn":1,"step":7}} {"type":"assistant/chunk","seq":69,"time":0,"data":{"turn":1,"step":7,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} @@ -73,6 +73,6 @@ {"type":"assistant/chunk","seq":71,"time":0,"data":{"turn":1,"step":7,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":72,"time":1785498587531,"data":{"turn":1,"step":7,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":3}}}} {"type":"assistant/chunk","seq":73,"time":1785730504764,"data":{"turn":1,"step":7,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":74,"time":1785730504764,"data":{"turn":1,"step":7,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"27be8e61-4735-4528-acd6-615784da5361"},"usage":{"inputTokens":10,"outputTokens":3}},"sourceEventSeqs":[69,70,71,72,73],"surfaceOp":"append"} +{"type":"assistant/message","seq":74,"time":1785730504764,"data":{"turn":1,"step":7,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"6854d5f7-2802-43da-8f21-b6cf336dff75"},"usage":{"inputTokens":10,"outputTokens":3}},"sourceEventSeqs":[69,70,71,72,73],"surfaceOp":"append"} {"type":"step/end","seq":75,"time":1785730504764,"data":{"turn":1,"step":7}} {"type":"turn/end","seq":76,"time":1785730504764,"data":{"turn":1,"reason":{"kind":"completed"}}}