@fro.bot/systematic 3.33.0 → 3.33.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/HARNESSES.md +5 -2
- package/dist/lib/connect-ci.d.ts +2 -2
- package/package.json +6 -6
- package/skills/ce-connect/SKILL.md +3 -3
- package/skills/ce-connect/references/fetch-and-import.md +10 -4
- package/skills/ce-connect/references/headless-and-outcomes.md +3 -3
- package/skills/ce-connect/scripts/connect.mjs +18 -14
package/HARNESSES.md
CHANGED
|
@@ -75,7 +75,7 @@ Pi honors Systematic's disable settings. `src/pi.ts` loads the merged config onc
|
|
|
75
75
|
|
|
76
76
|
## Claude Code — Tier 1 shipped adapter
|
|
77
77
|
|
|
78
|
-
Claude Code's profile records name-based subagent dispatch, `AskUserQuestion`, task tracking through `TaskCreate`/`TaskGet`/`TaskList`/`TaskUpdate`, and native Skill/`SKILL.md` discovery [CC-P]. Systematic builds a self-contained plugin bundle in CI from `skills/` and `agents/` via `scripts/build-claude-code-plugin.ts`: it flattens agent personas, composes an output style from the using-systematic body plus the Claude Code profile, emits a declarative `SessionStart` hook, and translates every internal identifier (`ce:<name>`, `systematic:<category>:<name>`) into Claude Code's plugin-namespaced form (`systematic:<skill-dir>`, `systematic:<agent-stem>`), gated by an integrity check that fails the build on any leftover source-namespace or unresolved bare reference [CC-9]. The bundle is never committed to `main` — `claude-code/` is gitignored build staging — and CI publishes the built output to the orphan `claude-code-plugin` branch
|
|
78
|
+
Claude Code's profile records name-based subagent dispatch, `AskUserQuestion`, task tracking through `TaskCreate`/`TaskGet`/`TaskList`/`TaskUpdate`, and native Skill/`SKILL.md` discovery [CC-P]. Systematic builds a self-contained plugin bundle in CI from `skills/` and `agents/` via `scripts/build-claude-code-plugin.ts`: it flattens agent personas, composes an output style from the using-systematic body plus the Claude Code profile, emits a declarative `SessionStart` hook, and translates every internal identifier (`ce:<name>`, `systematic:<category>:<name>`) into Claude Code's plugin-namespaced form (`systematic:<skill-dir>`, `systematic:<agent-stem>`), gated by an integrity check that fails the build on any leftover source-namespace or unresolved bare reference [CC-9]. The bundle is never committed to `main` — `claude-code/` is gitignored build staging — and CI publishes the built output to the orphan `claude-code-plugin` branch when a release is published [CC-11]. Users install it through the marketplace catalog checked into `main` at `.claude-plugin/marketplace.json`, which points the `systematic` plugin entry at the `claude-code-plugin` branch ref [CC-12]: `claude plugin marketplace add marcusrbrown/systematic` then `claude plugin install systematic@systematic`. The plugin has no version field; it is versioned by the source commit SHA baked into each publish commit.
|
|
79
79
|
|
|
80
80
|
Delegation is name-based: a prompt invokes a subagent by name (for example, "Use the systematic-implementer subagent to …") and Claude Code resolves it against the plugin's `agents/` directory; skills may additionally run scoped subagent forks via `context: fork` [CC-1]. `AskUserQuestion` is the blocking-interaction tool [CC-2]. `TodoWrite` is deprecated and disabled by default; `TaskCreate`/`TaskGet`/`TaskList`/`TaskUpdate` are the current task-tracking tools [CC-3][CC-4]. Skills are discovered natively from `SKILL.md` under `~/.claude/skills/`, `.claude/skills/`, and the plugin's own `skills/` directory through the built-in Skill tool; Systematic registers no `systematic_skill` tool on Claude Code, unlike its OpenCode and Pi adapters [CC-5][CC-6][CC-9].
|
|
81
81
|
|
|
@@ -117,6 +117,8 @@ The `ce:connect` skill dispatches `connections-researcher`, an agent that must n
|
|
|
117
117
|
|
|
118
118
|
What the evidence does not show: a scripted model makes the calls, so these proofs show enforcement plumbing, not live model choice. Read tools are not path-scoped on any host and session MCP tools are not denied; the guide documents both as limits. The v1 floor (1.18.29) has no row and is not run against this proof.
|
|
119
119
|
|
|
120
|
+
The scheduled workflow is a separate surface: it runs the skill headless on a CI runner and posts a report issue. Live runs of it, including the report author, the in-place edit on a second same-day run, a hand cancel and an agent-step timeout, are recorded in [CN-6]. That entry also lists what was not observed live.
|
|
121
|
+
|
|
120
122
|
## Worktree placement rule — bootstrap paths
|
|
121
123
|
|
|
122
124
|
One short rule ships in the shared bootstrap: create a worktree at `.worktrees/<branch>` under the main repository root with the `git-worktree` skill's script, and follow a different location or tool when the user or a project instruction names one. The script (`skills/git-worktree/scripts/worktree-manager.sh`) is small and non-interactive: `create`, `list`, `switch`, `copy-env` and `cleanup`, with exit codes 0 ok, 1 error, 2 usage and 3 refused, and no stdin reads. `create` places the worktree at `.worktrees/<branch>` under the main root, writes `.worktrees/.gitignore` and never edits the root `.gitignore`, and fails closed on a bare, separate-git-dir or submodule layout; `cleanup` reports and removes only named clean worktrees [WT-2]. The rule lives in `skills/using-systematic/references/worktree-placement.md` and holds no harness identifiers [WT-1]. Each adapter composes it differently:
|
|
@@ -268,7 +270,7 @@ Migrated-skill discipline is enforced by the [content-integrity gate](scripts/co
|
|
|
268
270
|
- **CC-6** — [Claude Code Agent SDK skills](https://code.claude.com/docs/en/agent-sdk/skills.md).
|
|
269
271
|
- **CC-9** — `scripts/build-claude-code-plugin.ts:5-28,256-368,374-418` (builder, identifier translation, integrity gate); `.gitignore` (`claude-code/` gitignored build staging).
|
|
270
272
|
- **CC-10** — `tests/integration/claude-code.test.ts`.
|
|
271
|
-
- **CC-11** — `.github/workflows/
|
|
273
|
+
- **CC-11** — `.github/workflows/publish-claude-code-plugin.yaml:28-223` (`build` and `push` jobs: on a published non-prerelease release, or a manual dispatch naming an existing tag, the read-only `build` job builds the bundle and guards its required artifacts, and the `push` job, which holds the only write credential and runs no repository code, publishes it to the orphan `claude-code-plugin` branch).
|
|
272
274
|
- **CC-12** — `.claude-plugin/marketplace.json:1-18` (marketplace catalog; `systematic` plugin entry sourced from the `claude-code-plugin` branch ref).
|
|
273
275
|
- **CC-13** — `scripts/build-claude-code-plugin.ts:129-157` (the rule file is read after the using-systematic and profile checks, fails the build when missing, and sits between the body and the profile); `tests/unit/build-claude-code-plugin.test.ts:491-514` and the byte-exact output-style fixture in the same file; `tests/integration/claude-code.test.ts:140-162` (real build: the rule appears exactly once between the body and the profile).
|
|
274
276
|
- **CX-1** — [Codex request_user_input definition](https://github.com/openai/codex/blob/35aaa5d9/codex-rs/tools/src/request_user_input_tool.rs).
|
|
@@ -301,3 +303,4 @@ Migrated-skill discipline is enforced by the [content-integrity gate](scripts/co
|
|
|
301
303
|
- **CN-3** — The v2 tool guard. Code: `src/lib/opencode-v2-tool-guard.ts` (`decideToolCall`, the `execute.before` registration, `READ_ONLY_AGENT_NAMES`, `READ_ONLY_TOOL_ALLOWLIST`). Tests: `tests/unit/opencode-v2-tool-guard.test.ts` (the allowlist is exactly read, grep, glob, skill and the two Systematic tools; exact-name matching; every other agent left alone; a refused call throws so the host fails that call alone; a failed hook registration rejects, so `setupOpenCodeV2` can catch it and withhold the guarded agents); `tests/integration/opencode-v2.test.ts` › "the execute.before hook sees each call with the session agent, including Code Mode calls, and a throw fails that call alone" (a plugin hook that throws fails the call without any Systematic guard in play). The reason for the guard, observed on 2.2.5: a session-level allow rule overrides an agent's own deny, and Code Mode `execute` reaches host-native `opencode_*` tools that no frontmatter key can name.
|
|
302
304
|
- **CN-4** — Pi 1.5.0: `tests/unit/pi-delegate-session.test.ts` › "the shipped researcher reaches createAgentSession with read, grep and find and none of bash, write, edit or systematic_delegate" (the `observedBy` for this row; the real session builder runs against a fake runtime and the test asserts the `tools` that reach `createAgentSession`, not the mock); `tests/integration/pi.test.ts` › "a family completes inside the delegate turn cap with read, search and find tools only, and its batch validates" and "a child that never answers stops at the turn cap and the family is degraded, not empty" (the real Pi runtime, run in the v2 host-contract profile). Scope limit: the delegate is capped at 20 turns, and a scripted model drives the integration tests.
|
|
303
305
|
- **CN-5** — Manual evidence, not a CI check. Recorded 2026-11-08 with Claude Code 2.1.319 (`claude --version` prints `2.1.319 (Claude Code)`), run by hand with the plugin bundle built from the rebased branch head and a live model. Verdict PASS. Run A dispatched `systematic:connections-researcher` through the `Agent` tool: the subagent reported its tools as Read, Grep and Glob, read a planted file and returned its marker, skipped Bash, Write, Edit and WebFetch as unavailable, and never called any of them (the checker found no call to Bash, Write, Edit, WebFetch, WebSearch or NotebookEdit). Run B started a session with `claude --agent systematic:connections-researcher`: the session's init message listed Read, Grep and Glob as its tools, none of Bash, Write, Edit, WebFetch, WebSearch or NotebookEdit, and no MCP tools; the read worked and its marker reached the answer. The `HOST_SUPPORT_TABLE` row names this entry as its `observedBy`. Limits: one live model on one Claude Code version; in run A the denial is the subagent's own report, because it never called the tools, and the host's own statement comes from run B's session tool list; the read tools are not path-scoped; whether a dispatched subagent can reach its parent session's MCP tools was not tested. `tests/unit/connect-host-isolation.test.ts` › "claude plugin validate accepts the definition and rejects one that does not parse" remains a parse check only, because an agent whose frontmatter fails to parse loads without its limits. Upstream issue reports 58645 and 94202 (cited from the research behind this feature, not re-checked) describe `disallowedTools` not being enforced for plugin and subagent Bash, so the agent leads with the positive `tools` allowlist.
|
|
306
|
+
- **CN-6** — Manual evidence from live runs of `.github/workflows/connect.yaml`, not a CI check. Pins: `fro-bot/agent` v0.140.2 at `1ffb6495501f12801f770fa0c0563d16450416e7`, which runs OpenCode v2 2.2.6, and Systematic 3.33.0. Run [43362146039](https://github.com/marcusrbrown/systematic/actions/runs/43362146039) (first dispatch) ended `Connect complete` and posted report issue #1389, authored by `github-actions[bot]`. The ledger cache was empty (a reset). The agent step had no model input, so the parent ran on the action's default model; the step now passes the Fro Bot model. Run [43365759373](https://github.com/marcusrbrown/systematic/actions/runs/43365759373) (second dispatch, the same UTC date): the action log shows `hasModelOverride: true`, and the run ended `Connect complete`. `prepare` logged `Ticks from report #1389: accepted 2, skipped 0, unresolved 0`, and the ledger cache restored (sweep 96 of 435). The `render` visibility recheck passed under `permissions: {}` with the job token. `post` edited #1389 in place and opened no second issue, and the two rejected candidates left the report. Run [43368318366](https://github.com/marcusrbrown/systematic/actions/runs/43368318366) was cancelled by hand about 2.5 minutes into the agent step: the steps after the agent were skipped, `render` and `post` were cancelled, nothing was posted, and the cache and the report were untouched. That is why the agent step has its own timeout below the job's: a cancelled job skips every step after the agent, while a timed-out step lets the record be read, handed on and posted. Run [43475406631](https://github.com/marcusrbrown/systematic/actions/runs/43475406631) (a dispatch with `FRO_BOT_CONNECT_STEP_TIMEOUT` set to 2) ran that path live: the log shows `The action 'Run ce:connect' has timed out after 2 minutes.`, the next step then read the record (`ce:connect ended: no-final-line (agent step: failure).`), `render` logged `Rendered 0 of 0 open candidates, 0 new; outcome no-final-line.`, `post` ran its `Write report` step, and the final `Settle result` step failed red, so the workflow ended `failure`. Not observed live: a busy run, which cannot happen in CI by construction (the lock is never cached or handed off, each run gets a fresh runner, and the concurrency group serializes runs). The workflow tests cover the timeout path against stubbed `gh`, `git` and `npm`.
|
package/dist/lib/connect-ci.d.ts
CHANGED
|
@@ -110,8 +110,8 @@ export type RenderResult = {
|
|
|
110
110
|
readonly hidden: number;
|
|
111
111
|
/** Candidates listed for the first time on this date. */
|
|
112
112
|
readonly fresh: number;
|
|
113
|
-
/** The
|
|
114
|
-
readonly
|
|
113
|
+
/** The `<run>.<attempt>` fetch words of the listed candidates, in the order they appear. */
|
|
114
|
+
readonly fetches: readonly string[];
|
|
115
115
|
readonly outcome: ReportOutcome;
|
|
116
116
|
/** The workflow job turns red after posting. */
|
|
117
117
|
readonly red: boolean;
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@fro.bot/systematic",
|
|
3
|
-
"version": "3.33.
|
|
3
|
+
"version": "3.33.1",
|
|
4
4
|
"description": "Compound-engineering loops for OpenCode, Pi, and Claude Code",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"homepage": "https://fro.bot/systematic",
|
|
@@ -119,12 +119,12 @@
|
|
|
119
119
|
},
|
|
120
120
|
"devDependencies": {
|
|
121
121
|
"@biomejs/biome": "2.6.6",
|
|
122
|
-
"@earendil-works/pi-coding-agent": "1.5.
|
|
122
|
+
"@earendil-works/pi-coding-agent": "1.5.2",
|
|
123
123
|
"@opencode-ai/plugin": "1.19.5",
|
|
124
124
|
"@opencode-ai/sdk": "1.19.5",
|
|
125
|
-
"@opencode/client": "2.2.
|
|
126
|
-
"@opencode/plugin": "2.2.
|
|
127
|
-
"@opencode/sdk": "2.2.
|
|
125
|
+
"@opencode/client": "2.2.7",
|
|
126
|
+
"@opencode/plugin": "2.2.7",
|
|
127
|
+
"@opencode/sdk": "2.2.7",
|
|
128
128
|
"@semantic-release/exec": "7.1.0",
|
|
129
129
|
"@tintinweb/pi-subagents": "0.22.1",
|
|
130
130
|
"@types/bun": "latest",
|
|
@@ -147,7 +147,7 @@
|
|
|
147
147
|
"zod": "4.6.7"
|
|
148
148
|
},
|
|
149
149
|
"overrides": {
|
|
150
|
-
"@earendil-works/pi-ai": "1.5.
|
|
150
|
+
"@earendil-works/pi-ai": "1.5.2",
|
|
151
151
|
"brace-expansion": "^5.0.8",
|
|
152
152
|
"conventional-changelog-writer": ">=9",
|
|
153
153
|
"devalue": "^5.9.3",
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: ce:connect
|
|
3
3
|
description: "Use when searching the projects the user has allowed for contradictions between their learnings, or for a lesson that one project recorded and a sibling project still needs. Also use when the user asks what their other projects have learned about a failure."
|
|
4
|
-
argument-hint: "[mode:headless | mode:interactive] [group:<name> | projects:<a>,<b> | fetch:<run>]"
|
|
4
|
+
argument-hint: "[mode:headless | mode:interactive] [group:<name> | projects:<a>,<b> | fetch:<run>[.<attempt>]]"
|
|
5
5
|
metadata:
|
|
6
6
|
harness-portability: neutral-v1
|
|
7
7
|
---
|
|
@@ -57,11 +57,11 @@ In the same pass, list every word that starts with `group:` or `projects:`, from
|
|
|
57
57
|
|
|
58
58
|
### Fetch word
|
|
59
59
|
|
|
60
|
-
In the same pass, list every word that starts with `fetch:`. `fetch:<run>` brings the candidates of a scheduled CI run to this machine
|
|
60
|
+
In the same pass, list every word that starts with `fetch:`. `fetch:<run>.<attempt>` brings the candidates of a scheduled CI run to this machine from exactly that attempt of the run. A bare `fetch:<run>` means the newest attempt of that run. A scheduled report prints the `<run>.<attempt>` form. `<run>` is the GitHub run id and `<attempt>` the attempt number; each is a positive integer, digits only, with no sign, no space and no leading zero. A `<run>` has at most 20 digits and an `<attempt>` at most 10. The value must match `^[1-9][0-9]{0,19}(\.[1-9][0-9]{0,9})?$` and nothing else. The same `fetch:` word twice or more counts once. `fetch:<run>` and `fetch:<run>.<attempt>` are different words.
|
|
61
61
|
|
|
62
62
|
- A `fetch:` word together with a `group:` or `projects:` word: stop. The reason is `conflicting-selection: fetch: cannot be combined with group: or projects:`.
|
|
63
63
|
- Two different `fetch:` words: stop. The reason is `conflicting-selection: two different fetch: words`.
|
|
64
|
-
- A `fetch:` value that
|
|
64
|
+
- A `fetch:` value that does not match that pattern, such as an empty one, a zero attempt or a second dot: stop. The reason is `invalid-request: fetch: needs a numeric GitHub run id`. Check this before any value reaches a command.
|
|
65
65
|
- A stop here happens before any command, in the two-line form of Step 1.
|
|
66
66
|
- One valid `fetch:` word: skip Steps 2 to 7 and follow `references/fetch-and-import.md`. A fetch observes no host, dispatches no agent, asks nothing and takes no mode: `mode:` has no effect on it. It ends with the final line that reference names.
|
|
67
67
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Fetch and import
|
|
2
2
|
|
|
3
|
-
`fetch:<run>` brings the candidates of a scheduled CI run to this machine, so a lesson the runner found can be promoted here after the runner is gone. The skill does the part that needs the network, with the user's own `gh`. The helper's `import` operation does the rest and never touches the network.
|
|
3
|
+
`fetch:<run>.<attempt>` brings the candidates of one attempt of a scheduled CI run to this machine, so a lesson the runner found can be promoted here after the runner is gone. A bare `fetch:<run>` does the same for the newest attempt of that run. In every command below, `<run>` and `<attempt>` are the numbers `SKILL.md` already checked: positive integers, nothing else. The skill does the part that needs the network, with the user's own `gh`. The helper's `import` operation does the rest and never touches the network.
|
|
4
4
|
|
|
5
5
|
A fetch dispatches no agent, asks nothing and takes no host observation. It uses neither `begin` nor `publish`. It ends with the `finalLine` that `import` answers, or with `Connect failed` for a stop before `import`.
|
|
6
6
|
|
|
@@ -36,10 +36,16 @@ It prints one JSON array of `{name, expired}` objects. Check the call before you
|
|
|
36
36
|
- The command fails because `gh` is not logged in: stop with `gh-not-authenticated`.
|
|
37
37
|
- The command fails for any other reason (a non-zero exit), or its output is not a JSON array: stop with `artifact-list-failed`. An empty array is an answer; a failed call is not. Never read a failed call as `artifact-not-found`.
|
|
38
38
|
|
|
39
|
-
The record is in an artifact named `connect-run-<run>-<attempt>`, where `<attempt>` is digits only. Take the names that match that pattern for this run id exactly
|
|
39
|
+
The record is in an artifact named `connect-run-<run>-<attempt>`, where `<attempt>` is digits only. Take the names that match that pattern for this run id exactly.
|
|
40
|
+
|
|
41
|
+
- With a bare `fetch:<run>`, pick the one with the highest attempt. A run with attempts 1 and 2 downloads `connect-run-<run>-2`.
|
|
42
|
+
- With `fetch:<run>.<attempt>`, download exactly `connect-run-<run>-<attempt>` with that attempt. Do not pick the highest attempt. A report names the attempt a candidate came from, and a later attempt may not hold it.
|
|
43
|
+
|
|
44
|
+
Then:
|
|
40
45
|
|
|
41
46
|
- The call succeeded and no name matches: stop with `artifact-not-found`.
|
|
42
47
|
- The chosen artifact is expired: stop with `artifact-expired`. The user can tick Rejected in the scheduled run's report, or wait for the candidate to be proposed again.
|
|
48
|
+
- If the named attempt has no artifact, stop with `artifact-not-found`, even when another attempt of the run has one. If the named attempt's artifact is expired, stop with `artifact-expired`. Print the fixed reason and its hint only. Never fall back to another attempt and do not suggest one.
|
|
43
49
|
|
|
44
50
|
### 3. Download into a fresh directory
|
|
45
51
|
|
|
@@ -69,7 +75,7 @@ node "$SKILL_DIR/scripts/connect.mjs" import <<'JSON'
|
|
|
69
75
|
JSON
|
|
70
76
|
```
|
|
71
77
|
|
|
72
|
-
`directory` is the absolute path `mktemp -d` printed. `runId` is the run id from the `fetch:` word. Leave `commit` out when step 1 gave none.
|
|
78
|
+
`directory` is the absolute path `mktemp -d` printed. `runId` is the run id from the `fetch:` word, without the attempt. Leave `commit` out when step 1 gave none. The record carries no attempt, so the request carries none either: the artifact name in step 2 is the only place the attempt is checked.
|
|
73
79
|
|
|
74
80
|
If `node` is missing, the helper file is gone, or `import` prints no JSON answer, the helper is unavailable. Remove `<DEST>`, print `helper-unavailable` and its hint, then `Connect failed`. Nothing was imported.
|
|
75
81
|
|
|
@@ -97,7 +103,7 @@ Print the reason as it is, then the hint.
|
|
|
97
103
|
| `run-not-found` | No run with that id in `marcusrbrown/systematic`. |
|
|
98
104
|
| `gh-not-authenticated` | `gh` is not logged in, or its token cannot read this repository's runs. Run `gh auth login` and try again. |
|
|
99
105
|
| `artifact-list-failed` | `gh` could not list the run's artifacts, or its answer was not a JSON array. Nothing was downloaded. Try again. |
|
|
100
|
-
| `artifact-not-found` | The run has no `connect-run-<run>-<attempt>` artifact. It stopped before it made a record. |
|
|
106
|
+
| `artifact-not-found` | The run has no `connect-run-<run>-<attempt>` artifact for the attempt asked for. It stopped before it made a record. |
|
|
101
107
|
| `artifact-expired` | The record was kept for a limited time and is gone. Tick Rejected in the report, or wait for the candidate to be proposed again. |
|
|
102
108
|
| `download-failed` | `gh run download` failed for another reason. Nothing was imported. |
|
|
103
109
|
| `record-missing`, `record-symlink`, `record-not-regular`, `record-unreadable`, `directory-unreadable` | The downloaded directory does not hold a plain `run.json`. |
|
|
@@ -36,14 +36,14 @@ The digest header and the run record name the selection: `all`, the group, or th
|
|
|
36
36
|
|
|
37
37
|
## Reading a fetch
|
|
38
38
|
|
|
39
|
-
A `fetch:<run>` word is read from the same place as the mode tokens and the selection words. It brings the candidates of a scheduled CI run to this machine and follows `fetch-and-import.md`.
|
|
39
|
+
A `fetch:<run>.<attempt>` word, or a bare `fetch:<run>` for the newest attempt, is read from the same place as the mode tokens and the selection words. It brings the candidates of a scheduled CI run to this machine and follows `fetch-and-import.md`.
|
|
40
40
|
|
|
41
41
|
| Words found | Result |
|
|
42
42
|
|---|---|
|
|
43
|
-
| One `fetch:<run>`, or the same word twice or more | A fetch of that run. It observes no host, dispatches no agent and asks nothing, so `mode:` has no effect. |
|
|
43
|
+
| One `fetch:<run>.<attempt>` or `fetch:<run>`, or the same word twice or more | A fetch of that attempt, or of the newest attempt of that run. It observes no host, dispatches no agent and asks nothing, so `mode:` has no effect. |
|
|
44
44
|
| `fetch:` with a `group:` or `projects:` word | Stop: `conflicting-selection`. |
|
|
45
45
|
| Two different `fetch:` words | Stop: `conflicting-selection`. |
|
|
46
|
-
| An empty value, or a value that is not
|
|
46
|
+
| An empty value, or a value that is not a positive run id, or a run id and a positive attempt | Stop: `invalid-request`. |
|
|
47
47
|
|
|
48
48
|
A stop here happens before any command. End as for a failed run: the reason on a line of its own, then `Connect failed`.
|
|
49
49
|
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
// biome-ignore-all assist/source/organizeImports: generated bundle
|
|
3
3
|
// Generated by scripts/generate-ce-connect-helper.ts; do not edit by hand.
|
|
4
4
|
// Run `bun run ce-connect-helper:build` to regenerate.
|
|
5
|
-
// source-digest:
|
|
5
|
+
// source-digest: 1dff040830b364bc15183c7ac02704b38be2eeff00e226e50e74817dea36bf40
|
|
6
6
|
// src/ce-connect-helper.ts
|
|
7
7
|
import { spawnSync as spawnSync3 } from 'node:child_process'
|
|
8
8
|
import fs10 from 'node:fs'
|
|
@@ -1473,13 +1473,13 @@ var HOST_SUPPORT_TABLE = [
|
|
|
1473
1473
|
},
|
|
1474
1474
|
{
|
|
1475
1475
|
host: 'opencode-v2',
|
|
1476
|
-
version: '2.2.
|
|
1476
|
+
version: '2.2.7',
|
|
1477
1477
|
observedBy:
|
|
1478
1478
|
'tests/integration/opencode-v2.test.ts > a session-level allow does not lift the guarded researcher when a parent with that rule dispatches it',
|
|
1479
1479
|
},
|
|
1480
1480
|
{
|
|
1481
1481
|
host: 'pi',
|
|
1482
|
-
version: '1.5.
|
|
1482
|
+
version: '1.5.2',
|
|
1483
1483
|
observedBy:
|
|
1484
1484
|
'tests/unit/pi-delegate-session.test.ts > the shipped researcher reaches createAgentSession with read, grep and find and none of bash, write, edit or systematic_delegate',
|
|
1485
1485
|
},
|
|
@@ -9040,13 +9040,16 @@ function factsOf(id, payload) {
|
|
|
9040
9040
|
return lines.join(`
|
|
9041
9041
|
`)
|
|
9042
9042
|
}
|
|
9043
|
+
function fetchWord(payload) {
|
|
9044
|
+
return `${payload.runId}.${payload.attempt}`
|
|
9045
|
+
}
|
|
9043
9046
|
function blockOf(position, id, payload, isNew) {
|
|
9044
9047
|
const lines = [`### Candidate ${position}${isNew ? ' (new)' : ''}`, '']
|
|
9045
9048
|
if (payload === undefined) {
|
|
9046
9049
|
lines.push(`Details unavailable for \`${id}\`.`)
|
|
9047
9050
|
} else {
|
|
9048
9051
|
lines.push(
|
|
9049
|
-
`- Fetch: \`/ce:connect fetch:${payload
|
|
9052
|
+
`- Fetch: \`/ce:connect fetch:${fetchWord(payload)}\` (run ${payload.runId}, attempt ${payload.attempt})`,
|
|
9050
9053
|
'',
|
|
9051
9054
|
fenceText(factsOf(id, payload)),
|
|
9052
9055
|
)
|
|
@@ -9072,18 +9075,19 @@ function ranges(positions) {
|
|
|
9072
9075
|
.join(', ')
|
|
9073
9076
|
}
|
|
9074
9077
|
function fetchLines(rows) {
|
|
9075
|
-
const
|
|
9078
|
+
const byFetch = new Map()
|
|
9076
9079
|
rows.forEach((row, index) => {
|
|
9077
9080
|
if (row.payload === undefined) return
|
|
9078
|
-
const
|
|
9081
|
+
const word = fetchWord(row.payload)
|
|
9082
|
+
const list = byFetch.get(word) ?? []
|
|
9079
9083
|
list.push(index + 1)
|
|
9080
|
-
|
|
9084
|
+
byFetch.set(word, list)
|
|
9081
9085
|
})
|
|
9082
|
-
const lines = [...
|
|
9083
|
-
([
|
|
9084
|
-
`- \`/ce:connect fetch:${
|
|
9086
|
+
const lines = [...byFetch].map(
|
|
9087
|
+
([word, positions]) =>
|
|
9088
|
+
`- \`/ce:connect fetch:${word}\` for candidates ${ranges(positions)}`,
|
|
9085
9089
|
)
|
|
9086
|
-
return {
|
|
9090
|
+
return { fetches: [...byFetch.keys()], lines }
|
|
9087
9091
|
}
|
|
9088
9092
|
var RESET_NOTICE =
|
|
9089
9093
|
'> **Ledger reset.** No cache was restored for this run, so the ledger and the sweep started fresh. Earlier decisions are not remembered, and a tick for a candidate the ledger no longer knows is reported as unresolved.'
|
|
@@ -9144,7 +9148,7 @@ function assemble(input, shown) {
|
|
|
9144
9148
|
`),
|
|
9145
9149
|
ids,
|
|
9146
9150
|
hash,
|
|
9147
|
-
|
|
9151
|
+
fetches: fetch.fetches,
|
|
9148
9152
|
fresh,
|
|
9149
9153
|
}
|
|
9150
9154
|
}
|
|
@@ -9310,7 +9314,7 @@ function renderState(root, request, recordState) {
|
|
|
9310
9314
|
shown,
|
|
9311
9315
|
hidden: open.length - shown,
|
|
9312
9316
|
fresh: result.fresh,
|
|
9313
|
-
|
|
9317
|
+
fetches: result.fetches,
|
|
9314
9318
|
outcome,
|
|
9315
9319
|
red: isRed(outcome),
|
|
9316
9320
|
stateUpdated: recordState,
|
|
@@ -12618,7 +12622,7 @@ function renderReportOp(request, deps) {
|
|
|
12618
12622
|
shown: result.shown,
|
|
12619
12623
|
hidden: result.hidden,
|
|
12620
12624
|
fresh: result.fresh,
|
|
12621
|
-
|
|
12625
|
+
fetches: result.fetches,
|
|
12622
12626
|
outcome: result.outcome,
|
|
12623
12627
|
red: result.red,
|
|
12624
12628
|
stateUpdated: result.stateUpdated,
|