@basein/runner 0.3.0 → 0.3.1

package/README.md

@@ -417,7 +417,7 @@ what to do when they register, so there is one switch and no second copy of it:
 | `BIR_DERIVE_API_KEY` | **Optional.** Working out what a new request is about — which fleet, which file, which date — is done for you by the service on its own key, as long as you are signed in. Set this (an Anthropic key) only to keep that reading on your machine, on your key. Signed out *and* unset, a scenario whose values change between requests is declined rather than replayed on stale ones. |
 | `ANTHROPIC_API_KEY` | Not used by the background recorder, which has Claude Code's environment and would bill your own key — unless `BIR_USE_ANTHROPIC_API_KEY=1`. A `bir-hooks` run by hand in a terminal uses that terminal's key. |
 | `BIR_DERIVE_MODEL` | Derivation model, when you set a key of your own (default `claude-haiku-4-5-20251001`). |
-| `BIR_MATCH_BUDGET_MS` | How long the prompt hook waits for a match (default `1500`). After a match slower than `BIR_MATCH_SLOW_MS` (default `800`), or one that timed out, prompts stop waiting for 5 min, doubling up to 30 min; a fast match ends that. |
+| `BIR_MATCH_BUDGET_MS` | How long the prompt hook waits for a match (default `3000`). After a match slower than `BIR_MATCH_SLOW_MS` (default `2000`), or one that timed out, prompts stop waiting for 5 min, doubling up to 30 min; a fast match ends that. |
 | `BIR_DERIVE_BUDGET_MS` / `BIR_HOOK_DERIVE_BUDGET_MS` | How long a direct run, and a hook, waits for parameters (default `8000` / `4000`; a hook waits the smaller). |
 | `BIR_PRETOOL_REPLAY_BUDGET_MS` | Everything replay does inside one `PreToolUse` (default `9000`, at most `10000`). |
 | `BIR_REPLAY_BUDGET_MS` / `BIR_STEP_TIMEOUT_MS` | Whole-plan and per-step ceilings for direct execution (default `100000` / `60000`; `BIR_REPLAY_PLAN_BUDGET_MS` also sets the first). A direct run's parameter wait plus its plan are held under 270 s. |

package/dist/bin/bir-hooks.d.ts

@@ -77,7 +77,7 @@
  *                             `bir-hooks` run by hand in a terminal uses that
  *                             terminal's ANTHROPIC_API_KEY as it always did
  *   BIR_DERIVE_MODEL          derivation model (default claude-haiku-4-5-…)
- *   BIR_MATCH_BUDGET_MS       prompt-hook match wait (default 1500)
+ *   BIR_MATCH_BUDGET_MS       prompt-hook match wait (default 3000)
  *   BIR_DERIVE_BUDGET_MS      derivation wait before a direct run (default 8000);
  *                             inside a hook it is at most BIR_HOOK_DERIVE_BUDGET_MS
  *                             (default 4000)

package/dist/bin/bir-hooks.js

@@ -77,7 +77,7 @@
  *                             `bir-hooks` run by hand in a terminal uses that
  *                             terminal's ANTHROPIC_API_KEY as it always did
  *   BIR_DERIVE_MODEL          derivation model (default claude-haiku-4-5-…)
- *   BIR_MATCH_BUDGET_MS       prompt-hook match wait (default 1500)
+ *   BIR_MATCH_BUDGET_MS       prompt-hook match wait (default 3000)
  *   BIR_DERIVE_BUDGET_MS      derivation wait before a direct run (default 8000);
  *                             inside a hook it is at most BIR_HOOK_DERIVE_BUDGET_MS
  *                             (default 4000)

package/dist/control/recorder-main.d.ts

@@ -23,10 +23,10 @@
 import { ControlServer } from "./server.js";
 /**
  * What a prompt waits for its scenario match by default (`BIR_MATCH_BUDGET_MS`).
- * Past it the prompt goes on without one (K5): the service answering in 1-2 s
- * must not add that to every prompt.
+ * Past it the prompt goes on without one (K5): a service slower than 3 s must
+ * not add that to every prompt.
  */
-export declare const DEFAULT_MATCH_BUDGET_MS = 1500;
+export declare const DEFAULT_MATCH_BUDGET_MS = 3000;
 /**
  * `BIR_CORRELATION_DECISION`, passed on only when it was set to `allow` or
  * `ask`. Unset, nothing is passed and the control server decides — and by

package/dist/control/recorder-main.js

@@ -40,10 +40,10 @@ const SHUTDOWN_CLOSE_MS = 3_000;
 const SHUTDOWN_HARD_MS = 5_000;
 /**
  * What a prompt waits for its scenario match by default (`BIR_MATCH_BUDGET_MS`).
- * Past it the prompt goes on without one (K5): the service answering in 1-2 s
- * must not add that to every prompt.
+ * Past it the prompt goes on without one (K5): a service slower than 3 s must
+ * not add that to every prompt.
  */
-export const DEFAULT_MATCH_BUDGET_MS = 1_500;
+export const DEFAULT_MATCH_BUDGET_MS = 3_000;
 /** How often records of dead recorders are swept from the control directory. */
 const SWEEP_EVERY_MS = 24 * 60 * 60 * 1000;
 /**

package/dist/control/server.js

@@ -140,13 +140,14 @@ const DELIVERY_HELLO_TTL_MS = 30 * 60_000;
 /** At most this many `bir-scenario` processes are remembered, newest kept. */
 const DELIVERY_HELLO_MAX = 256;
 /*
- * `slowMs` is 800: a healthy service answers the create-and-match in about
- * 300-450 ms (a cold TLS connection adds ~250 ms), so an answer past 800 ms is
- * a degraded service, and waiting on it would add that much to every prompt.
+ * `slowMs` is 2000: a healthy service answers the create-and-match in about
+ * 300-450 ms (a cold TLS connection adds ~250 ms), but a service that is only
+ * somewhat slow should keep replay on, so only an answer past 2 s counts as a
+ * degraded one, and waiting on it would add that much to every prompt.
  * A false trip costs only replay for one hold, never latency.
  */
 const DEFAULT_MATCH_GATE = {
-    slowMs: 800,
+    slowMs: 2_000,
     holdMs: 5 * 60_000,
     maxHoldMs: 30 * 60_000,
 };

package/dist/replay/controller.js

@@ -57,7 +57,7 @@ export const DEFAULT_BUDGETS = {
     // task; a match that has not answered by then is a turn run normally. The
     // control server stops waiting at all for a while after one that answered
     // slowly (`BIR_MATCH_SLOW_MS`). `BIR_MATCH_BUDGET_MS` in the recorder.
-    matchMs: 1_500,
+    matchMs: 3_000,
     deriveMs: 8_000,
     planMs: 100_000,
     stepMs: 60_000,

package/docs/calculatedReplay.md

@@ -760,7 +760,7 @@ The hook is on the user's critical path. Every await here is a stall the user wa
 
 | Moment | Route | Hook timeout | Answered by | What may be awaited | Budget |
 |---|---|---|---|---|---|
-| `UserPromptSubmit` | `/session/prompt` | 10 s | 7 s | the match; for a scenario with a target, its derivation; a steer plan's argument preview | match `BIR_MATCH_BUDGET_MS` = **1500**; match and arming together ≤ **6 s**; derivation ≤ `BIR_HOOK_DERIVE_BUDGET_MS` = **4000** |
+| `UserPromptSubmit` | `/session/prompt` | 10 s | 7 s | the match; for a scenario with a target, its derivation; a steer plan's argument preview | match `BIR_MATCH_BUDGET_MS` = **3000**; match and arming together ≤ **6 s**; derivation ≤ `BIR_HOOK_DERIVE_BUDGET_MS` = **4000** |
 | `PreToolUse` | `/tool/pre` | 15 s | 12 s | `plan.ready()` (derivation); on a divergence, the remaining steps | derivation ≤ min(`BIR_DERIVE_BUDGET_MS`, `BIR_HOOK_DERIVE_BUDGET_MS`) = **4000**; all replay work ≤ `BIR_PRETOOL_REPLAY_BUDGET_MS` = **9000** (held at ≤ 10 000) |
 | `run_scenario` | `/scenario/run` | `bir-scenario`'s own, **290 s** (`BIR_SCENARIO_RUN_TIMEOUT_MS`) | — | `ready()` + N steps | derivation `BIR_DERIVE_BUDGET_MS` = **8000**; plan `BIR_REPLAY_PLAN_BUDGET_MS` = **100000** (`BIR_REPLAY_BUDGET_MS` overrides it where set); per step `BIR_STEP_TIMEOUT_MS` = **60000**, clipped to what the plan has left |
 | `PostToolUse` | `/tool/post` | 5 s | 2 s | nothing | — |
@@ -794,9 +794,9 @@ minutes, while its steps keep starting. `bir replay` is not held to the ceiling.
 
 **Budget expiry is never an error.** Match budget expired → no plan, ordinary turn, one
 `replay.decision` line (`match_timeout`). **The match gate:** a match that answered slower than
-`BIR_MATCH_SLOW_MS` (**800**), or not at all, also makes prompts stop waiting on the match for 5
+`BIR_MATCH_SLOW_MS` (**2000**), or not at all, also makes prompts stop waiting on the match for 5
 minutes, doubling up to 30 while the service stays slow; a fast match ends the hold
-(`replay.match_gate`). A healthy service answers in 300–450 ms, so past 800 ms waiting would add
+(`replay.match_gate`). A healthy service answers in 300–450 ms, so past 2 s waiting would add
 that much to every prompt. The match is still asked meanwhile, so a hit still stops the recording. Derivation budget expired →
 settings take their recorded `sampleValue`s and targets stay `null`, never `{}`; a plan that needs a
 missing target, or whose `paramsLogic` throws, hands over instead of running (in steer mode the

package/docs/calculatedReplayGuide.md

@@ -345,7 +345,7 @@ so there is exactly one switch and it cannot get out of step with itself.
 | `BIR_MIN_STEER_SIMILARITY` | `0.92` | Below this a match is detected but not replayed (§8) |
 | `BIR_DERIVE_API_KEY` | *(unset)* | **Not required.** Derivation — reading what this request acts on — is done by the service on its key for a signed-in runner. Set this to keep the reading on this machine instead: the prompt then never leaves it, and it is one round trip faster. Signed out *and* unset, only a scenario with nothing to work out replays. A recorder running in the background (started by the SessionStart hook, `bir up` or `bir setup`) ignores `ANTHROPIC_API_KEY` (usually Claude Code's own, and billed) unless `BIR_USE_ANTHROPIC_API_KEY=1`; a `bir-hooks` you run in a terminal uses it |
 | `BIR_DERIVE_MODEL` | `claude-haiku-4-5-20251001` | The derivation model, when this machine does the reading |
-| `BIR_MATCH_BUDGET_MS` | `1500` | How long the prompt hook waits for a match before giving up. After a match slower than `BIR_MATCH_SLOW_MS` (`800`), prompts stop waiting for one for 5 minutes, doubling up to 30 while the service stays slow |
+| `BIR_MATCH_BUDGET_MS` | `3000` | How long the prompt hook waits for a match before giving up. After a match slower than `BIR_MATCH_SLOW_MS` (`2000`), prompts stop waiting for one for 5 minutes, doubling up to 30 while the service stays slow |
 | `BIR_DERIVE_BUDGET_MS` | `8000` | How long `run_scenario` waits for parameters |
 | `BIR_HOOK_DERIVE_BUDGET_MS` | `4000` | How long a hook waits for them: the prompt, for a scenario with a target, and the first `PreToolUse` (never longer than `BIR_DERIVE_BUDGET_MS`) |
 | `BIR_PRETOOL_REPLAY_BUDGET_MS` | `9000` | All replay work inside one `PreToolUse`, a divergence's steps included. At most 10 000 |
@@ -548,7 +548,7 @@ first prompt that states the task plainly.
 |---|---|---|
 | No `run.matched`, ever | Prompt below the server's `SIMILARITY_THRESHOLD` | Rephrase closer, or lower it server-side. Confirm the original run is in the list — a sub-`RECORDING_MIN_ACTIONS` run is never embedded |
 | `run.matched` but no `plan.armed` | A gate declined | Read the `replay.decision` line's `why=`. Ranked by frequency: replay off — `bir replay off`, `BIR_REPLAY=0`, or never switched on here (a `bir install` without `--replay`; `bir replay status` says which) · scenario not `ready` · similarity below threshold · no step is executable |
-| `replay.decision … code=match_timeout` or `code=service_unhealthy` on many prompts | The service answered the match slower than `BIR_MATCH_BUDGET_MS` (1.5 s), or is failing and in its cool-down | Nothing breaks: those turns run normally, and after a slow match prompts stop waiting on it for a while by themselves (`replay.match_gate`). `bir doctor` shows the service's state. Raise `BIR_MATCH_BUDGET_MS` only if the service is reliably just over it — every prompt pays it |
+| `replay.decision … code=match_timeout` or `code=service_unhealthy` on many prompts | The service answered the match slower than `BIR_MATCH_BUDGET_MS` (3 s), or is failing and in its cool-down | Nothing breaks: those turns run normally, and after a slow match prompts stop waiting on it for a while by themselves (`replay.match_gate`). `bir doctor` shows the service's state. Raise `BIR_MATCH_BUDGET_MS` only if the service is reliably just over it — every prompt pays it |
 | `replay.decision … code=no_delivery_tool` | A direct plan, and no running `bir` server has told the recorder it serves `run_scenario`: the server is missing, disabled or failed in `/mcp`, was not added (a subdirectory or worktree of a repository), or the session was started with `BIR_OFF=1` | `/mcp` shows whether `bir` is connected. `bir install --replay` adds it, in the project's own directory; then start a new session |
 | `replay.vetoed … the model's first call was …, not run_scenario` | A direct plan, and the model reached for another tool first — usually because it has no `run_scenario` | As for `no_delivery_tool`. Nothing ran; the model did the task |
 | `replay.pin_declined` on most steered turns | The model's calls to the expected tool are not the step — another command, another file — so nothing is pinned; if it then moves on, `replay.pin_abandoned` retires the plan | Harmless for those calls, which ran as the model wrote them. Persistent declines on one step usually mean its arguments cannot be shown in the directive (they depend on an earlier step's output, or the command runs to several lines), and the model writes its own |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@basein/runner",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "A recording MCP proxy: sits between any MCP client and its MCP servers, executes each call on the client's behalf, and records the run as a reusable BaseIn scenario.",
   "type": "module",
   "license": "MIT",