bullswarm 0.25.3 → 0.25.4

package/CHANGELOG.md

@@ -1,5 +1,58 @@
 # bullswarm changelog
 
+## 0.25.4 — reasoning levels
+
+- A connector now declares how its own CLI expresses a thinking level, and
+  every dispatch resolves exactly one level per attempt. The block is
+  `reasoning: { flag | args, levels, defaults, skipModels? }` — `flag` for a
+  CLI that takes `--effort <level>`, `args` for one whose control is a config
+  override (`-c model_reasoning_effort={level}`). The packaged `claude-code`,
+  `codex`, `grok`, and `command-code` templates carry the block read from
+  their installed CLIs or an official source (Claude Code and Command Code from
+  `--help`, Codex from its config reference, Grok from the binary's own
+  validation message); Command Code's model-dependent set stays marked
+  UNVERIFIED rather than invented. One shared resolver applies the precedence
+  chain — the action's own `reasoning` field, the run-wide override, the
+  configured `strategy.reasoning` level for that pool and tier, the same for
+  the tier globally, then the connector's default for the effort tier — so
+  the first layer that sets a level wins, not the strongest. The level is
+  appended to the spawned command exactly as `--model` is appended today;
+  nothing is appended for a connector with no block, for the literal level
+  `default`, or for a model the connector marks under `skipModels`. A level
+  the connector does not accept is clamped to the nearest one it does, never
+  dropped and never invented. `{ requested, applied, source, clamped }` is
+  recorded on every attempt, in the decision log, in `bullswarm run --json`,
+  in the V2 result envelope, and in the new `bullswarm run --dry-run` command
+  preview — which builds its argv through the same builder that spawns, so
+  preview and dispatch cannot drift.
+
+- `bullswarm setup` asks one reasoning level per effort tier (suggesting
+  high=xhigh, medium=high, low=medium, with `default` always offered to leave
+  a worker CLI's own setting untouched) and stores the answers under
+  `state.strategy.reasoning`. Agents configure the same thing without a
+  terminal: `bullswarm strategy set-reasoning --tier <high|medium|low> --level
+  <low|medium|high|xhigh|max|default> [--pool <name>] --yes`, `bullswarm
+  strategy reset-reasoning [--tier ..] [--pool ..] --yes`, and a `reasoning`
+  section in `strategy configure --file <json> --yes` whose invalidity rejects
+  the whole document. `bullswarm strategy inventory --json` reports the
+  configured levels and, through the resolver dispatch itself uses, the
+  effective level and its source for every pool and tier. Installed home
+  connectors receive the packaged `reasoning` block additively on upgrade, and
+  a block the user has customized is never overwritten.
+
+- A V2 program action accepts an optional `reasoning` field
+  (`low|medium|high|xhigh|max|default`) that the calling agent or the
+  Workflow Planner can set and that outranks every configured level for that
+  one action; `workflow plan contract` documents the field and echoes the
+  run-wide levels a launch would apply. `workflow goal` takes
+  `--worker-reasoning <level>` for every non-planner dispatch and
+  `--planner-reasoning <level>` for a dispatched Workflow Planner, and
+  `bullswarm run` takes `--reasoning <level>`; a level off the scale is a
+  usage error that launches nothing. The applied level appears next to the
+  model in `workflow runs show` (text and `--json`), `workflow runs result
+  --json`, the TUI attempt rows and agent pane, so a run that thought more
+  cheaply than asked is visible rather than inferred.
+
 ## 0.25.3 — usage-limit recovery and headroom-aware routing
 
 - A provider that reports a usage limit is now its own mechanical failure kind,

package/README.md

@@ -149,6 +149,9 @@ bullswarm strategy set-model opencode2 kaihk/gpt-5.6-luna \
   --tiers high,medium,low --yes
 bullswarm strategy configure --file strategy.json --yes  # atomic agent-authored policy
 bullswarm strategy reset-tier low --yes     # restore one tier to automatic
+bullswarm strategy set-reasoning --tier high --level xhigh --yes
+bullswarm strategy set-reasoning --tier high --level high --pool codex --yes
+bullswarm strategy reset-reasoning --tier high --yes  # back to connector defaults
 bullswarm strategy refresh
 bullswarm strategy show --json
 bullswarm strategy apply --yes --refresh-hours 24
@@ -302,6 +305,16 @@ adversarial acceptance judgment. Merely being an analysis/evidence action or
 part of a difficult goal never promotes an action to high. The selected effort
 then resolves through the High/Medium/Low routes configured by `bullswarm setup`.
 
+Reasoning depth is a third, independent decision. An action may carry an
+optional `reasoning` field — `low`, `medium`, `high`, `xhigh`, `max`, or
+`default` — that sets how hard the picked model thinks on that one action and
+outranks every configured level for it. `default` passes nothing and lets the
+worker CLI's own setting decide. Omitting the field keeps the configured level.
+It never changes the pool, model, or effort tier, so a `low`-effort mechanical
+step can still be given `xhigh` thinking and a `high`-effort action can be told
+to think cheaply. A connector that does not accept the requested level gets the
+nearest level it supports.
+
 The planner does not author phases or declare success/failure. The kernel
 derives stable presentation stages for the TUI and computes the final V2
 result. Saved V2 runs retain their original execution and workspace policy on
@@ -352,6 +365,30 @@ The worker lock covers scout, work actions, and evidence actions. A pool that ca
 the requested model is ineligible rather than silently substituting another
 model.
 
+Reasoning depth can be pinned for a whole run the same way, without touching
+global strategy:
+
+```bash
+bullswarm workflow goal "Implement and verify the change" --cwd . \
+  --program plan.json --worker-reasoning high --json
+bullswarm run --lane build --reasoning xhigh --prompt '<task>' --json
+```
+
+`--worker-reasoning` covers scout, work actions, and evidence actions;
+`--planner-reasoning` covers a dispatched Workflow Planner and applies only
+with `--orchestrator`. Exactly one level is resolved per attempt, and the
+first layer that sets one wins — not the strongest: the action's own
+`reasoning` field, then the run-wide flag (`--worker-reasoning`,
+`--planner-reasoning`, `bullswarm run --reasoning`), then the configured
+`strategy.reasoning` level for that pool and tier, then the same for the tier
+globally, then the connector's own default for the effort tier, and otherwise
+nothing is appended. So an action asking for `low` beats a run-wide `max`.
+`default` at any layer stops there and passes nothing, letting the worker
+CLI's own setting decide; a connector with no `reasoning` block, or a model it
+marks as skipped, never receives a flag. The applied level is recorded on
+every attempt with the layer that set it and displayed next to the model, so a
+run that thought more cheaply than requested is visible rather than inferred.
+
 The `opencode2` connector itself does not require a KaiHK provider: its base
 spawn command carries no hardcoded model, so a plain OpenCode installation
 dispatches with OpenCode's own configured default. When
@@ -656,8 +693,9 @@ while working. Process exit, a fatal auth/quota signature, explicit operator
 cancellation, or an opt-in timeout remain the terminal signals.
 
 Each attempt records the phase/action, selected pool and model, effort tier,
-routing reason, all eligible candidates with quota surplus, timestamps,
-artifact paths, outcome, and reported-or-estimated token/cost/quota usage.
+the applied reasoning level with the layer that set it, routing reason, all
+eligible candidates with quota surplus, timestamps, artifact paths, outcome,
+and reported-or-estimated token/cost/quota usage.
 `workflow tui <id>` renders this breakdown for completed runs as well as live
 ones; `workflow tui --json <id>` exposes the durable audit document.
 When a provider event stream reports the actual model, Bullswarm records that

package/connectors/_schema.json

@@ -74,6 +74,19 @@
     "free": false
   }],
   "modelSelection": {"flag": "--model", "mode": "replace-or-append"},
+  "reasoning": {
+    "$comment": "Optional. How THIS CLI expresses a thinking level. Omit the block entirely when the CLI has no such control: core then appends nothing and reports source 'unsupported'. Declare exactly one of flag/args.",
+    "flag": "--effort",
+    "args": ["-c", "model_reasoning_effort={level}"],
+    "$comment-form": "flag: appended as `<flag> <level>` with replace-or-append semantics, so a level already pinned in spawn.cmd is replaced rather than duplicated. args: appended verbatim with {level} substituted, for CLIs whose control is a config override rather than a flag.",
+    "levels": ["low", "medium", "high", "xhigh", "max"],
+    "$comment-levels": "the subset of the common scale (low, medium, high, xhigh, max — weakest to strongest, src/lib/reasoning.js) that this CLI accepts, weakest first. A requested level outside the subset is clamped to the strongest supported level not above it, or to the weakest supported level when the request is below all of them, and the clamp is recorded.",
+    "defaults": {"high": "xhigh", "medium": "high", "low": "medium"},
+    "$comment-defaults": "the level to use for each effort tier when nothing else asked. Last layer of the precedence chain: action override > run override > strategy per-pool > strategy per-tier > THESE > nothing appended. The literal 'default' at any layer means 'append nothing, let the CLI's own configuration decide'.",
+    "skipModels": ["^model-id-regex-that-rejects-the-flag"],
+    "$comment-skipModels": "Optional connector-owned regexes. A selected model matching one gets no level appended (source 'skipped-model'), for CLIs whose flag is only valid on some models."
+  },
+  "$comment-reasoning": "Optional prose companion. Say which command's output the block was read from, and mark anything the CLI does not actually print as UNVERIFIED — never invent an accepted value.",
   "subscription": {"plan": null, "monthlyPriceUsd": null, "includedValueUsd": null, "quotaWindow": "weekly"},
   "flags": {
     "stealth": false,

package/connectors/claude-code.json

@@ -60,6 +60,13 @@
   "capabilities": ["strong-analysis", "code-reading", "file-editing", "workflow-planning"],
   "knownModels": ["claude-fable-5", "claude-opus-5", "claude-sonnet-5", "claude-haiku-4-5"],
   "modelSelection": { "flag": "--model", "mode": "replace-or-append" },
+  "$comment-reasoning": "verified from `claude --help` (Claude Code 2.1.263): `--effort <level>  Effort level for the current session (low, medium, high, xhigh, max)`. skipModels: `--help` does not state per-model support, so Haiku is excluded conservatively — re-verify before removing the exclusion. With no `reasoning` override anywhere, workers inherit whatever effortLevel the home settings.json sets.",
+  "reasoning": {
+    "flag": "--effort",
+    "levels": ["low", "medium", "high", "xhigh", "max"],
+    "defaults": { "high": "xhigh", "medium": "high", "low": "medium" },
+    "skipModels": ["^claude-haiku-"]
+  },
   "conversation": {
     "newArgs": ["--session-id", "{sessionId}"],
     "resumeArgs": ["--resume", "{sessionId}"]

package/connectors/codex.json

@@ -31,14 +31,61 @@
   },
   "eventStream": {
     "format": "jsonl",
-    "args": ["--json"],
+    "args": [
+      "--json"
+    ],
     "silenceThresholdSec": 600,
     "rules": [
-      { "rootMatch": { "path": "type", "equals": "item.started" }, "idPaths": ["item.id"], "kindPaths": ["item.type"], "kindMap": { "agent_message": "response" }, "summaryPaths": ["item.command", "item.text"], "status": "running" },
-      { "rootMatch": { "path": "type", "equals": "item.completed" }, "idPaths": ["item.id"], "kindPaths": ["item.type"], "kindMap": { "agent_message": "response" }, "summaryPaths": ["item.command", "item.text"], "status": "completed" }
+      {
+        "rootMatch": {
+          "path": "type",
+          "equals": "item.started"
+        },
+        "idPaths": [
+          "item.id"
+        ],
+        "kindPaths": [
+          "item.type"
+        ],
+        "kindMap": {
+          "agent_message": "response"
+        },
+        "summaryPaths": [
+          "item.command",
+          "item.text"
+        ],
+        "status": "running"
+      },
+      {
+        "rootMatch": {
+          "path": "type",
+          "equals": "item.completed"
+        },
+        "idPaths": [
+          "item.id"
+        ],
+        "kindPaths": [
+          "item.type"
+        ],
+        "kindMap": {
+          "agent_message": "response"
+        },
+        "summaryPaths": [
+          "item.command",
+          "item.text"
+        ],
+        "status": "completed"
+      }
     ],
     "output": [
-      { "match": { "path": "type", "equals": "item.completed" }, "path": "item.text", "mode": "last" }
+      {
+        "match": {
+          "path": "type",
+          "equals": "item.completed"
+        },
+        "path": "item.text",
+        "mode": "last"
+      }
     ]
   },
   "meter": {
@@ -51,18 +98,109 @@
     "build",
     "chore"
   ],
-  "capabilities": ["strong-analysis", "code-reading", "file-editing", "workflow-planning"],
-  "knownModels": ["gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna", "gpt-5.5", "gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex"],
-  "modelSelection": { "flag": "--model", "mode": "replace-or-append" },
+  "capabilities": [
+    "strong-analysis",
+    "code-reading",
+    "file-editing",
+    "workflow-planning"
+  ],
+  "knownModels": [
+    "gpt-5.6-sol",
+    "gpt-5.6-terra",
+    "gpt-5.6-luna",
+    "gpt-5.5",
+    "gpt-5.4",
+    "gpt-5.4-mini",
+    "gpt-5.3-codex"
+  ],
+  "modelSelection": {
+    "flag": "--model",
+    "mode": "replace-or-append"
+  },
+  "$comment-reasoning": "Codex has no reasoning flag; the control is the config key `model_reasoning_effort`, overridden per invocation with the escape hatch verified from `codex exec --help` (codex-cli 0.153.4): `-c, --config <key=value>  Override a configuration value that would otherwise be loaded from ~/.codex/config.toml`. Accepted values verified from the official Codex config reference (https://learn.chatgpt.com/docs/config-file/config-reference, read 2026-09-09): `minimal | low | medium | high | xhigh` — \"Adjust reasoning effort for supported models (Responses API only; xhigh is model-dependent)\". `minimal` sits below bullswarm's common scale, so a request below `low` clamps up to `low`. Tier defaults stay at high/medium/low because `xhigh` is model-dependent; an explicit `xhigh` request passes through. Without this block Codex workers think at whatever config.toml sets (this machine: low).",
+  "reasoning": {
+    "args": [
+      "-c",
+      "model_reasoning_effort={level}"
+    ],
+    "levels": [
+      "low",
+      "medium",
+      "high",
+      "xhigh"
+    ],
+    "defaults": {
+      "high": "high",
+      "medium": "medium",
+      "low": "low"
+    }
+  },
   "modelProfiles": [
-    { "match": "^gpt-5\\.6-sol$", "tier": "high", "qualityRank": 6, "pricing": { "inputUsdPerMillion": 4, "cacheReadUsdPerMillion": 0.4, "outputUsdPerMillion": 20 }, "pricingSource": "https://help.openai.com/en/articles/20001415-chatgpt-rate-card-enterprise-token-based-pricing", "pricingUpdatedAt": "2026-08-27" },
-    { "match": "^gpt-5\\.(5|4)$", "tier": "high", "qualityRank": 5 },
-    { "match": "^gpt-5\\.6-terra$", "tier": "medium", "qualityRank": 4, "pricing": { "inputUsdPerMillion": 2, "cacheReadUsdPerMillion": 0.2, "outputUsdPerMillion": 12 }, "pricingSource": "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "pricingUpdatedAt": "2026-08-27" },
-    { "match": "^gpt-5\\.3-codex$", "tier": "medium", "qualityRank": 4, "pricing": { "inputUsdPerMillion": 1.75, "cacheReadUsdPerMillion": 0.175, "outputUsdPerMillion": 14 }, "pricingSource": "https://help.openai.com/en/articles/20001415-chatgpt-rate-card-enterprise-token-based-pricing", "pricingUpdatedAt": "2026-08-27" },
-    { "match": "^gpt-5\\.6-luna$", "tier": "low", "qualityRank": 3, "pricing": { "inputUsdPerMillion": 0.2, "cacheReadUsdPerMillion": 0.02, "outputUsdPerMillion": 1.2 }, "pricingSource": "https://developers.openai.com/api/docs/models", "pricingUpdatedAt": "2026-08-27" },
-    { "match": "mini", "tier": "low", "qualityRank": 2 }
+    {
+      "match": "^gpt-5\\.6-sol$",
+      "tier": "high",
+      "qualityRank": 6,
+      "pricing": {
+        "inputUsdPerMillion": 4,
+        "cacheReadUsdPerMillion": 0.4,
+        "outputUsdPerMillion": 20
+      },
+      "pricingSource": "https://help.openai.com/en/articles/20001415-chatgpt-rate-card-enterprise-token-based-pricing",
+      "pricingUpdatedAt": "2026-08-27"
+    },
+    {
+      "match": "^gpt-5\\.(5|4)$",
+      "tier": "high",
+      "qualityRank": 5
+    },
+    {
+      "match": "^gpt-5\\.6-terra$",
+      "tier": "medium",
+      "qualityRank": 4,
+      "pricing": {
+        "inputUsdPerMillion": 2,
+        "cacheReadUsdPerMillion": 0.2,
+        "outputUsdPerMillion": 12
+      },
+      "pricingSource": "https://developers.openai.com/api/docs/models/gpt-5.6-terra",
+      "pricingUpdatedAt": "2026-08-27"
+    },
+    {
+      "match": "^gpt-5\\.3-codex$",
+      "tier": "medium",
+      "qualityRank": 4,
+      "pricing": {
+        "inputUsdPerMillion": 1.75,
+        "cacheReadUsdPerMillion": 0.175,
+        "outputUsdPerMillion": 14
+      },
+      "pricingSource": "https://help.openai.com/en/articles/20001415-chatgpt-rate-card-enterprise-token-based-pricing",
+      "pricingUpdatedAt": "2026-08-27"
+    },
+    {
+      "match": "^gpt-5\\.6-luna$",
+      "tier": "low",
+      "qualityRank": 3,
+      "pricing": {
+        "inputUsdPerMillion": 0.2,
+        "cacheReadUsdPerMillion": 0.02,
+        "outputUsdPerMillion": 1.2
+      },
+      "pricingSource": "https://developers.openai.com/api/docs/models",
+      "pricingUpdatedAt": "2026-08-27"
+    },
+    {
+      "match": "mini",
+      "tier": "low",
+      "qualityRank": 2
+    }
   ],
-  "subscription": { "plan": null, "monthlyPriceUsd": null, "includedValueUsd": null, "quotaWindow": "weekly" },
+  "subscription": {
+    "plan": null,
+    "monthlyPriceUsd": null,
+    "includedValueUsd": null,
+    "quotaWindow": "weekly"
+  },
   "flags": {
     "stealth": false
   },

package/connectors/command-code.json

@@ -55,6 +55,12 @@
   "capabilities": ["code-reading", "file-editing", "strong-analysis", "workflow-planning"],
   "modelDiscovery": { "cmd": ["command-code", "--list-models"], "parse": "columns", "ignorePattern": "^(Available|Open Source$|Anthropic$|OpenAI$|Google$|Sakana$|Meta$|xAI$|Pass|cmd|Docs)", "timeoutMs": 20000, "maxModels": 150 },
   "modelSelection": { "flag": "--model", "mode": "replace-or-append" },
+  "$comment-reasoning": "verified from `command-code --help` (1.44.0): `--effort <level>  Set reasoning effort for the session (e.g. low, medium, high) — depends on the model`. UNVERIFIED: the CLI says \"e.g.\" and \"depends on the model\", so the accepted set is neither closed nor uniform across this pool's many providers; low/medium/high is declared conservatively and a stronger request clamps down to high.",
+  "reasoning": {
+    "flag": "--effort",
+    "levels": ["low", "medium", "high"],
+    "defaults": { "high": "high", "medium": "medium", "low": "low" }
+  },
   "modelProfiles": [
     { "match": "^meta/muse-spark-1\\.3-contributor$", "tier": "high", "qualityRank": 5, "pricing": { "inputUsdPerMillion": 0.1, "cacheReadUsdPerMillion": 0.002, "outputUsdPerMillion": 0.2 }, "pricingSource": "https://commandcode.ai/docs/resources/pricing-limits", "pricingUpdatedAt": "2026-09-03" },
     { "match": "^meta/muse-spark-", "tier": "high", "qualityRank": 5, "pricing": { "inputUsdPerMillion": 1.25, "cacheReadUsdPerMillion": 0.15, "outputUsdPerMillion": 4.25 }, "pricingSource": "https://commandcode.ai/docs/resources/pricing-limits", "pricingUpdatedAt": "2026-09-03" },

package/connectors/grok.json

@@ -24,15 +24,71 @@
   },
   "eventStream": {
     "format": "jsonl",
-    "args": ["--output-format", "streaming-json"],
+    "args": [
+      "--output-format",
+      "streaming-json"
+    ],
     "silenceThresholdSec": 600,
     "rules": [
-      { "rootMatch": { "path": "type", "equals": "tool_call" }, "idPaths": ["toolCallId"], "kindPaths": ["toolName", "title"], "summaryPaths": ["rawInput.command", "rawInput.file_path", "rawInput.path", "title"], "statusPath": "status" },
-      { "rootMatch": { "path": "type", "equals": "tool_call_update" }, "idPaths": ["toolCallId"], "kindPaths": ["toolName"], "summaryPaths": ["rawOutput.command"], "statusPath": "status" },
-      { "rootMatch": { "path": "type", "equals": "text" }, "kind": "response", "summaryPaths": ["data"], "status": "streaming", "aggregate": "consecutive", "summaryMode": "concat" }
+      {
+        "rootMatch": {
+          "path": "type",
+          "equals": "tool_call"
+        },
+        "idPaths": [
+          "toolCallId"
+        ],
+        "kindPaths": [
+          "toolName",
+          "title"
+        ],
+        "summaryPaths": [
+          "rawInput.command",
+          "rawInput.file_path",
+          "rawInput.path",
+          "title"
+        ],
+        "statusPath": "status"
+      },
+      {
+        "rootMatch": {
+          "path": "type",
+          "equals": "tool_call_update"
+        },
+        "idPaths": [
+          "toolCallId"
+        ],
+        "kindPaths": [
+          "toolName"
+        ],
+        "summaryPaths": [
+          "rawOutput.command"
+        ],
+        "statusPath": "status"
+      },
+      {
+        "rootMatch": {
+          "path": "type",
+          "equals": "text"
+        },
+        "kind": "response",
+        "summaryPaths": [
+          "data"
+        ],
+        "status": "streaming",
+        "aggregate": "consecutive",
+        "summaryMode": "concat"
+      }
     ],
     "output": [
-      { "match": { "path": "type", "equals": "text" }, "path": "data", "mode": "concat" }
+      {
+        "match": {
+          "path": "type",
+          "equals": "text"
+        },
+        "path": "data",
+        "mode": "concat"
+      }
     ]
   },
   "meter": {
@@ -45,20 +101,81 @@
     "build",
     "chore"
   ],
-  "capabilities": ["strong-analysis", "code-reading", "file-editing", "workflow-planning"],
-  "modelDiscovery": { "cmd": ["grok", "models"], "parse": "bullets", "timeoutMs": 20000, "maxModels": 50 },
-  "knownModels": ["grok-4.6", "grok-4.5"],
+  "capabilities": [
+    "strong-analysis",
+    "code-reading",
+    "file-editing",
+    "workflow-planning"
+  ],
+  "modelDiscovery": {
+    "cmd": [
+      "grok",
+      "models"
+    ],
+    "parse": "bullets",
+    "timeoutMs": 20000,
+    "maxModels": 50
+  },
+  "knownModels": [
+    "grok-4.6",
+    "grok-4.5"
+  ],
   "model": "grok-4.6",
-  "modelSelection": { "flag": "--model", "mode": "replace-or-append" },
+  "modelSelection": {
+    "flag": "--model",
+    "mode": "replace-or-append"
+  },
+  "$comment-reasoning": "flag verified from `grok --help` (grok 1.0.13): `--reasoning-effort <EFFORT>  Reasoning effort for reasoning models  [aliases: --effort]`. Accepted values verified from the grok 1.0.13 binary's own validation message (`strings` on the executable): `invalid reasoning effort: (expected one of: none, minimal, low, medium, high, xhigh, max)`. `none` and `minimal` sit below bullswarm's common scale, so a request below `low` clamps up to `low`. Tier defaults mirror claude-code (high=xhigh, medium=high, low=medium).",
+  "reasoning": {
+    "flag": "--reasoning-effort",
+    "levels": [
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max"
+    ],
+    "defaults": {
+      "high": "xhigh",
+      "medium": "high",
+      "low": "medium"
+    }
+  },
   "conversation": {
-    "newArgs": ["--session-id", "{sessionId}"],
-    "resumeArgs": ["--resume", "{sessionId}"]
+    "newArgs": [
+      "--session-id",
+      "{sessionId}"
+    ],
+    "resumeArgs": [
+      "--resume",
+      "{sessionId}"
+    ]
   },
   "modelProfiles": [
-    { "match": "^grok-4\\.6$", "tier": "high", "qualityRank": 5, "pricing": { "inputUsdPerMillion": 2, "cacheReadUsdPerMillion": 0.5, "outputUsdPerMillion": 6 }, "pricingSource": "https://docs.x.ai/developers/models/grok-4.6", "pricingUpdatedAt": "2026-08-27" },
-    { "match": "^grok-4\\.5$", "tier": "medium", "qualityRank": 4 }
+    {
+      "match": "^grok-4\\.6$",
+      "tier": "high",
+      "qualityRank": 5,
+      "pricing": {
+        "inputUsdPerMillion": 2,
+        "cacheReadUsdPerMillion": 0.5,
+        "outputUsdPerMillion": 6
+      },
+      "pricingSource": "https://docs.x.ai/developers/models/grok-4.6",
+      "pricingUpdatedAt": "2026-08-27"
+    },
+    {
+      "match": "^grok-4\\.5$",
+      "tier": "medium",
+      "qualityRank": 4
+    }
   ],
-  "subscription": { "plan": null, "monthlyPriceUsd": null, "includedValueUsd": null, "quotaWindow": "weekly" },
+  "subscription": {
+    "plan": null,
+    "monthlyPriceUsd": null,
+    "includedValueUsd": null,
+    "quotaWindow": "weekly"
+  },
   "flags": {
     "stealth": false
   },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bullswarm",
-  "version": "0.25.3",
+  "version": "0.25.4",
   "description": "Route work across coding-agent CLI subscriptions — paced by live quota meters, verified by content, never trusting exit codes.",
   "type": "module",
   "bin": {

package/skill/SKILL.md

@@ -95,6 +95,20 @@ Author the graph around these rules:
   `affects`/`ownedFiles`, and `evidenceFor` requirement IDs. Depend on every
   writer affecting those requirements. Describe the checks; the kernel adds
   the evidence JSON instructions. Evidence is optional for graph completion.
+- **Optional reasoning depth:** `effort` picks the model tier; the optional
+  `reasoning` field picks how hard that model thinks. Values are
+  `low|medium|high|xhigh|max`, or `default` to pass nothing and let the worker
+  CLI's own setting decide. It applies to that one action and outranks every
+  configured level for it — so a `low`-effort integrator can still get `xhigh`
+  thinking. Omit it and the configured level applies; it never changes the
+  pool, model, or effort tier, and a connector that does not accept the exact
+  level gets the nearest level it supports. Set it only when an action needs
+  deeper thinking than its tier implies (a tricky shared-file integrator,
+  ambiguous acceptance judgment) or cheaper thinking for mechanical work.
+  For the whole run instead of one action, pass
+  `--worker-reasoning <level>` (and `--planner-reasoning <level>` with
+  `--orchestrator`) to `workflow goal`; the contract's `reasoning` block
+  echoes what a launch will apply.
 
 Validate, then launch:
 

package/skill/references/operations.md

@@ -167,6 +167,37 @@ and apply validated changes with `strategy set-provider`, `strategy set-model`,
 or one atomic `strategy configure --file <json> --yes`. Never weaken those
 controls in a prompt.
 
+Reasoning depth is a separate axis from routing: the lane and effort tier
+choose the pool and model, and the reasoning level chooses how hard that model
+thinks. The first layer that sets a level wins — not the strongest — in this
+order: an action's own `reasoning` field, then the run-wide
+`--worker-reasoning` / `--planner-reasoning` (`bullswarm run --reasoning`),
+then the configured `strategy.reasoning` level for that pool and tier, then
+the same for the tier globally, then the connector default. An action asking
+for `low` therefore beats a run-wide `max`. `default` at any layer means "pass
+nothing and let the worker CLI's own setting decide", and a connector that does
+not accept the requested level gets the nearest level it supports. The applied
+level is recorded per attempt and shown next to the model in `workflow runs
+show` (text and `--json`), `workflow runs result --json`, the TUI attempt rows,
+and the agent pane, so an unexpectedly cheap or expensive turn is visible
+rather than inferred.
+
+Configure the standing levels the same way as the rest of strategy — no
+interactive UI required:
+
+```bash
+bullswarm strategy set-reasoning --tier high --level xhigh --yes
+bullswarm strategy set-reasoning --tier high --level high --pool codex --yes
+bullswarm strategy reset-reasoning --tier high --yes
+bullswarm strategy inventory --json   # reasoning.tiers, .pools, .effective
+```
+
+`inventory --json` reports `reasoning.effective['<pool>'][tier]` as
+`{ level, source }` through the same resolver dispatch uses, so what it shows
+is what a run will send. `strategy configure --file <json> --yes` takes the
+same values as a `reasoning` section; an invalid section rejects the whole
+document and writes nothing.
+
 ## Recovery and stopping rules
 
 - Auth signatures quarantine the affected pool for a 10-minute re-probe